Phương pháp chẩn đoán hình ảnh (Phần 3)

Phương pháp chẩn đoán hình ảnh (Phần 3)

2089_book.fm Page 51 Tuesday, May 10, 2005 3:38 PM Medical-Image Processing and Analysis for CAD Systems Athanassios N Papadopoulos, Marina E Plissiti, and Dimitrios I Fotiadis CONTENTS 2.1 2.2 Introduction Basics of a CAD System 2.2.1 Computer-Aided Methodologies in Mammography 2.2.2 Historical Overview 2.2.3 CAD Architecture 2.2.4 Preprocessing 2.2.5 Segmentation 2.2.6 Feature Analysis (Extraction, Selection, and Validation) 2.2.7 Classification System (Reduction of False Positives or Characterization of Lesions) 2.2.7.1 Conventional Classifiers 2.2.7.2 Artificial Neural Networks (ANNs) 2.2.7.3 Fuzzy-Logic Systems 2.2.7.4 Support-Vector Machines 2.2.8 Evaluation Methodologies 2.2.9 Integrated CAD Systems 2.3 Computer-Aided Methodologies for Three-Dimensional Reconstruction of an Artery 2.3.1 IVUS Image Interpretation 2.3.2 Automated Methods for IVUS ROI Detection 2.3.2.1 IVUS Image Preprocessing 2.3.2.2 IVUS Image Segmentation 2.3.3 Limitations in Quantitative IVUS Image Analysis 2.3.4 Plaque Characterization in IVUS Images 2.3.5 Three-Dimensional Reconstruction 2.4 Conclusions References Copyright 2005 by Taylor & Francis Group, LLC 2089_book.fm Page 52 Tuesday, May 10, 2005 3:38 PM 52 Medical Image Analysis 2.1 INTRODUCTION Over the last 15 years, several research groups have focused on the development of computerized systems that can analyze different types of medical images and extract useful information for the medical professional Most of the proposed methods use images acquired during a diagnostic procedure Such images are acquired using a variety of techniques and devices, including conventional radiography, computerized tomography, magnetic resonance imaging, ultrasound, and nuclear medicine Computerized schemes have been widely used in the analysis of one-dimensional medical signals such as Electrocardiogram (ECG), Electromyogram (EMG), Electroencephalogram (EEG), etc However, the majority of medical signals are two-dimensional representations Computerized systems designed for the automated detection and characterization of abnormalities in these images can provide medical experts with useful information Such systems are commonly referred to as computer-aided detection/diagnosis systems (CAD) A computer-aided detection procedure does not provide a medical diagnosis Rather, the computerized system is developed to detect signs of pathology in medical images by extracting features that are highly correlated with the type and the characteristics of the abnormality or the disease under investigation If a specific area in a radiological image meets the requirements, the computerized scheme identifies it, and the radiologist can review it to improve the accuracy of the detection procedure On the other hand, computer-aided diagnosis schemes, based on the same or additional features, characterize the identified region according to its pathology A CAD system is defined as a combination of image-processing techniques and intelligent methods that can be used to enhance the medical interpretation process, resulting in the development of more efficient diagnosis The computer outcome assists radiologists in image analysis and diagnostic decision making In addition, a CAD system could direct the radiologist’s attention to regions where the probability of an indication of disease is greatest A CAD system provides reproducible and quite realistic outcomes In this chapter, we review two of the most common procedures in CAD systems The first is related to microcalcification detection and classification in mammograms In this procedure, features of microcalcifications are extracted, and intelligent methods are then used to classify these features The second procedure is based on the fusion of intravascular ultrasound and biplane angiographies aiming at the threedimensional (3-D) reconstruction of an artery 2.2 BASICS OF A CAD SYSTEM Most of the automated CAD approaches include feature-extraction procedures However, several studies of semi-automated approaches have been reported wherein radiologists manually perform feature-mining procedures by employing various feature-extraction modules [1, 2] CAD systems can be classified in two categories according to their objectives: (a) those that are used to detect regions of pathology and (b) those that are used to classify the findings based on their features, which indicate their histological nature Copyright 2005 by Taylor & Francis Group, LLC 2089_book.fm Page 53 Tuesday, May 10, 2005 3:38 PM Medical-Image Processing and Analysis for CAD Systems 53 The role of these computerized systems is to improve the sensitivity of the diagnostic process and not to make decisions about the health status of the patient However, the “D” in CAD should stand for “diagnosis” [3], although several reports in literature utilize the word “detection” [4], which is undoubtedly an essential part of the diagnostic procedure For the design and development of an automated CAD system, several issues must be considered, including the quality of the digitized images, the sequence of the processing steps, and the evaluation methodology Most of the studies use filmscreen images that are digitized using high-performance film digitizers Recent studies employ high-quality medical images obtained directly in digital format using advanced imaging systems (filmless technology) The specific characteristics of the film digitizer significantly influence the quality of the image In the case of filmscreen technology, the maximum optical density of the film is a critical parameter in the quality of the final digitized image In cases where the upper limit of the optical density is low, an estimation of noise is possible during the digitization procedure, especially on the background area (air) of the image Utilization of filmscreen systems with higher optical densities might lead to the reduction of such noise due to digitization 2.2.1 COMPUTER-AIDED METHODOLOGIES IN MAMMOGRAPHY Mammography is one of the radiological fields where CAD systems have been widely applied because the demand for accurate and efficient diagnosis is so high The presence of abnormalities of specific appearance could indicate cancerous circumstances, and their early detection improves the prognosis of the disease, thus contributing to mortality reduction [5] However, diagnostic process is complicated by the superimposed anatomical structures, the multiple tissue background, the low signal-to-noise ratio, and variations in the patterns of pathology Thus, the analysis of medical images is a complicated procedure, and it is not unusual for indications of pathology, such as small or low-contrast microcalcifications, to be missed or misinterpreted by radiologists On the other hand, clinical applications require realtime processing and accuracy in diagnosis Based on these high standards in diagnostic interpretation, numerous intelligent systems have been developed to provide reliable automated CAD systems that can be very helpful, providing a valuable ''second opinion'' to the radiologist [6, 7] 2.2.2 HISTORICAL OVERVIEW Computerized analysis of radiological images first appeared in the early 1960s [8, 9] One of the first studies employing computers in the area of mammography was published by Winsberg et al in 1967 [10] In this approach, the right- and left-breast shapes were compared to detect symmetry differences Computation of local image characteristics from corresponding locations with high variations indicated the presence of a disease Ackerman et al [11] defined four computer-extracted features for the categorization of mammographic lesions as benign or malignant Another study Copyright 2005 by Taylor & Francis Group, LLC 2089_book.fm Page 54 Tuesday, May 10, 2005 3:38 PM 54 Medical Image Analysis by the same research group [12] proposed a computational procedure for the processing of a feature set with 30 characteristics that are obtained by radiologists for the classification of lesions according to their malignancy At the same time, several other works targeting detection and characterization of microcalcification clusters appeared in the literature Wee et al [13] classified microcalcification clusters as benign or malignant using the approximate horizontal length, the average internal gray level, and the contrast of individual microcalcifications The cluster pattern together with features such as size, density, and morphological characteristics of the cluster were also used for microcalcification characterization [14] In the late 1970s, Spiesberger [15] was the first to propose an automated system for the detection of microcalcifications At the end of the 1980s, the literature was enriched by studies reporting several image-processing algorithms and computational processes that provided satisfactory descriptions and efficient procedures for the detection of microcalcifications [16–18] In 1990, Chan et al reported that under controlled circumstances, a CAD system can significantly improve radiologists' accuracy in detecting clustered microcalcifications [19] 2.2.3 CAD ARCHITECTURE CAD systems proposed in the literature are based on techniques from the field of computer vision, image processing, and artificial intelligence The main stages of a typical CAD scheme are: preprocessing, segmentation, feature analysis (extraction, selection, and validation), and classification utilized either to reduce false positives (FPs) or to characterize abnormalities (Figure 2.1) A description of the methods employed in each stage is given in the following sections 2.2.4 PREPROCESSING In this stage, the subtle features of interest are enhanced and the unwanted characteristics of the image are de-emphasized The enhancement procedure results in a better description of the objects of interest, thus improving the sensitivity of the detection system and leading to better characterization in the case of diagnosis The enhancement of the contrast of the regions of interest, the sharpening of the abnormalities’ boundaries, and the suppression of noise is performed in this stage Several methodologies have been reported in the literature based on conventional imageprocessing techniques, region-based algorithms, and enhancement through the transformation of original image into another feature space Global processing can be performed, or local adjusting enhancement parameters can be used to accommodate the particularity of different image areas Morphological, edge-detection, and band-pass filters have been utilized An enhanced representation can be obtained using subtraction procedures on the processed image [18] One of the earliest contrast-enhancement methodologies was the modification of image histogram [20] and its equalization [21] The resulting image contains equally distributed brightness levels over the gray-level scale Because the mammogram contains areas of different intensity, a global modification is poor Copyright 2005 by Taylor & Francis Group, LLC 2089_book.fm Page 55 Tuesday, May 10, 2005 3:38 PM Medical-Image Processing and Analysis for CAD Systems 55 Digital mammogram Preprocessing Computer-aided detection scheme Segmentation Feature extraction - selection Computer-aided diagnosis Classification module - reduction of FP findings Feature extraction - selection Computer-aided characterization scheme Classification module - likelihood of malignancy FIGURE 2.1 CAD architecture Performance can be improved utilizing local adjustments of the processing parameters (adaptive histogram equalization) [22] Another technique restricts the methodology to certain contrast values to increase the effective range of contrast in the specific areas (contrast-limited adaptive histogram equalization) [23] Unsharp masking is a routinely used procedure to enhance the fine-detail structures A high-spatial-frequency component multiplied by a weight factor is added on the original image In the case of linear unsharp filtering, the above parameters are constant throughout the entire image In nonlinear methodologies, the weighting factor depends on the intensity of the examined region (background/foreground), or it can be applied differently in different resolution levels in multiscale approaches [24] Contrast stretch is a rescaling of image gray levels based on linear or nonlinear transformations In linear transformations, the difference between the background and foreground areas is increased to improve the contrast of both areas Introducing a nonlinear transformation, the contrast of the different parts of the image is modified, selectively enhancing the desired gray levels In most medical images, objects of interest have nonstandard intensities, thus the selection of a proper “intensity window” is not sufficient for contrast enhancement The adaptive neighborhood contrast-enhancement method improves the contrast of objects or structures by modifying the gray levels of the neighborhood (contextual region) of each pixel from which the object is composed After the identification of homogeneous areas (using, for example, a growing technique) several conditions are imposed to downgrade unconventional high-contrast areas or low-level noise and to enhance regions surrounded by variable background [25] Techniques that enhance regions of interest by estimating their difference from their background areas are Copyright 2005 by Taylor & Francis Group, LLC 2089_book.fm Page 56 Tuesday, May 10, 2005 3:38 PM 56 Medical Image Analysis called region-based enhancement techniques Typical region growing techniques, which employ contrast and statistical conditions, result in the definition of the extent and the shape of the objects [26] Multiresolution methods, based mainly on wavelet analysis, are used to enhance the features of mammographic images [27] A multiscale analysis of the original mammogram to several subband images provides the advantage of studying each subband independently using scale characteristics Each subband provides information based on different scales resulting in the representation of high- or low-frequency elements on separate images Thus, noise or similar type components of the image can be described in high resolution (small scale), while subtle objects with defined extent or large masses are described in medium-resolution and low-resolution levels (medium and coarse scales), respectively Hence, the significant image features can be selectively enhanced or degraded in different resolution levels [28] Furthermore, adaptive approaches in wavelet enhancement techniques that ensure the avoidance of the utilization of global parameters have been reported [29] Fuzzy-logic techniques are also used for contrast enhancement of microcalcifications [30] Global information (brightness) is employed to transform an image to a fuzzified version using a function, while local information (geometrical statistics) is employed to compute the nonuniformity Methods that are based on deterministic fractal geometry have been used to enhance mammograms [31–33] A fractal-image model was developed to describe mammographic parenchymal and ductal patterns using a set of parameters of affine transformations Microcalcification areas were enhanced by taking the difference between the original image and the modeled image 2.2.5 SEGMENTATION In this stage, the original mammographic image is segregated into separate parts, each of which has similar properties The image background, the tissue area, and the muscle or other areas can be separated because they are characterized using generic features Moreover, apart from the generic classification of image regions, a CAD segmentation procedure can identify regions containing small bright spots that appeared in groups and that correspond to probable microcalcifications and their clusters The complexity of a segmentation procedure depends on the nature of the original image and the characteristics of the objects that have to be identified A mammographic image contains several regions having different attenuation coefficients and optical densities, resulting in intensity variations In addition, because a mammogram is a two-dimensional (2-D) representation of a 3-D object, the overlying areas develop a complex mosaic composed of bright regions that may or may not be a real object Thus, the implementation of a global single threshold or a set of fixed thresholds that defines intensity ranges is not an efficient segmentation procedure Moreover, the employment of a global intensity threshold usually increases the number or the size of the selected regions introducing noise, which makes the procedure inefficient because noise removal requires further treatment In any case, after the first partitioning has been achieved, region-growing techniques, following specific homogeneity and differentiation criteria, can be utilized to define the real extent and the exact borders of the segmented region Copyright 2005 by Taylor & Francis Group, LLC 2089_book.fm Page 57 Tuesday, May 10, 2005 3:38 PM Medical-Image Processing and Analysis for CAD Systems 57 To overcome the limitations of a global thresholding methodology, local thresholding criteria must be utilized from the beginning The definition of the parameters that satisfy the demands of the segmentation algorithm increase the efficiency of the technique The corresponding measures were calculated for a specific window size Some of the local thresholding criteria are: The mean intensity values plus/minus a number of standard deviation (SD) values of intensity [16] The difference of the intensity value of a seed pixel from the maximum and minimum intensity values of pixels that belong to a specific neighborhood around a seed pixel [34] A contrast measure equal to the difference of intensity between object and background region [35] An object is selected only if the feature value belongs to the highest 2% of the values obtained In a similar but more flexible way, adaptive filtering methodologies have been proposed, defining parameters or measures adjusted to a specific area A feature called prediction error (PE) is the difference between the actual pixel value and the weighted sum of the eight nearest-neighbor pixels [36] If PE follows a Gaussian distribution, calcifications are not present Functions using first, second, and third moments of the PE are used to generate a threshold value that reveals the presence of the microcalcifications In another study [37], given a local maximum pixel value x0,y0, an edge pixel is given by the value of x,y that maximizes the difference in pixel values between pixels at x,y and x0,y0, divided by the distance between the two pixels Mathematical morphology filtration has been used to segment the microcalcifications Classical erosion and dilation transformations, as well as their combinations such as open, close, and top-hat transformations, are employed [38] In statistical approaches, several histogram-based analysis and Markov random field models are used [39, 40] Markov random fields have been used to classify pixels to background, calcification, line/edge, and film-emulsion errors [41] Multiscale analysis based on several wavelet transformations has been used to enable the segmentation process to be performed using the different scales-levels [42, 43] Furthermore, as in the preprocessing module, techniques have been applied exploiting fractal [44] and fuzzy-logic methodologies [45] 2.2.6 FEATURE ANALYSIS (EXTRACTION, SELECTION, AND VALIDATION) In this stage, several features from the probable microcalcification candidates are extracted to reduce false positives In any segmentation approach, a considerable number of normal objects are recognized as pathological, which results in reduced efficiency of the detection system To improve the performance of the scheme, several image features are calculated in an effort to describe the specific properties or characteristics of each object The most descriptive of these features are processed by a classification system to make an initial characterization of the segmented samples Copyright 2005 by Taylor & Francis Group, LLC 2089_book.fm Page 58 Tuesday, May 10, 2005 3:38 PM 58 Medical Image Analysis TABLE 2.1 Features for the Detection and Characterization of Microcalcifications and Their Clusters Microcalcification (MC) Cluster Classification Features Radiologists’ Characterization Features Number of MCs in cluster Cluster area Mean MC area SD of MC area Mean MC compactness Mean MC elongation SD of MC elongation SD of MC intensity Mean MC background intensity Mean contrast Cluster eccentricity Mean distance from cluster centroid Neighboring with a larger cluster Cluster entropy Spreading of MCs in cluster Cluster elongation Mean local MC background Mean MC intensity SD of MC compactness SD of distances from cluster centroid Area of the cluster convex hull Length of the cluster convex hull Cluster elements (separable/countable) Cluster size MC size Shape of elements within cluster Shape of elements within cluster Shape of elements within cluster Shape of elements within cluster Density of calcifications Density of calcifications Contrast of calcifications Shape of cluster Calcification distribution Cluster distribution Calcification distribution Calcification distribution Cluster shape Density of calcifications Density of calcifications Shape of elements within cluster Calcification distribution Shape of cluster Shape of cluster Although the number of calculated features derived from different feature spaces is quite large, it is difficult to identify the specific discriminative power of each one Thus, a primary problem is the selection of an effective feature set that has high ability to provide a satisfactory description of the segmented regions Early studies utilized features that were similar to the features that radiologists employ during their diagnosis However, as mentioned previously, additional features not employed by the doctors also have high discrimination power Table 2.1 provides a list of typical morphological features of individual microcalcification and their clusters Specific features could be extracted, such as the surround region dependence matrix (SRDM), gray-level run length (GLRL), and gray-level difference (GLD) [46] Laplacian or Gaussian filtration can be used in the validation of features [47] Using wavelet analysis, features such as energy, entropy, and norms of differences among local orientations can be extracted [48] The use of a large number of features does not improve the classification performance Indeed, the use of features without discriminative power increases the complexity of the characterization process In addition, the probability of misclassification increases with the number of features Moreover, the prediction variability Copyright 2005 by Taylor & Francis Group, LLC 2089_book.fm Page 59 Tuesday, May 10, 2005 3:38 PM Medical-Image Processing and Analysis for CAD Systems 59 is larger, and the classifier is sensitive to outliers Finally, the more features included in a given classifier, the greater is the dimension of a training set needed for the same degree of reliability [49] The selection of the optimal feature subset is a laborious problem Only an exhaustive search over all subsets of features can provide the system with a reliable subset Usually, the criterion of selecting an efficient subset of features is the minimization of misclassification probability (classification error) However, for the testing of a subset, a classifier must be chosen, and it is important to consider that different classifiers and different methods for the estimation of error rate could lead to the selection of a different feature subset One of the most important issues of a mammographic CAD system is the selection of a standard feature set and the classification method that is used to extract regions of pathological interest while minimizing false-positive findings The selection of the appropriate features can be based on “weighting factors” proposed by radiologists [50–53] or on algorithmic procedures that identify the most discriminant features The feature space can be a transformed space that has lower dimension than the original, although its discriminating power could be higher To achieve this, PCA (principal component analysis), which is based on the elimination of features that contribute less, can be used [54, 55] Alternatively, the most discriminative features can be selected, reducing in this way the size of the feature set Several methods have been proposed, such as: Stepwise discriminant analysis [56] Sequential Forward Selection (SFS) and Sequential Backward Selection (SBS) [57] Genetic algorithms [58] Stepwise discriminant analysis is based on the sequential trial of different feature subsets The one that results in the smallest error rate is chosen as the most convenient [59–61] Sequential forward selection is a bottom-up search procedure where one feature at a time is added to the feature set At each stage, the feature to be included in the feature set is selected from among the remaining features [57, 62, 63] Genetic algorithms have been used to select features that could enhance the performance of a classifier (for distinguishing malignant and benign masses) In the same way, genetic algorithms have been used to optimize the feature set for the characterization of microcalcifications [64, 65] 2.2.7 CLASSIFICATION SYSTEM (REDUCTION OF FALSE POSITIVES OR CHARACTERIZATION OF LESIONS) Diagnosis is an integrated medical procedure that is defined as the art or act of recognizing the presence of a disease from its signs or symptoms During the entire process, especially in the case of differential diagnosis, it is obvious that there are several dilemmas for the rejection or acceptance of probable diseases Thus, a classification system is an essential part of a CAD system Classification schemes range from techniques that classify lesions according to their different types (stellate, Copyright 2005 by Taylor & Francis Group, LLC 2089_book.fm Page 60 Tuesday, May 10, 2005 3:38 PM 60 Medical Image Analysis circumscribed masses, or calcifications) [66] to techniques that produce binary diagnosis, characterizing the findings as malignant or benign The classifiers that are utilized in the area of the detection of mammographic microcalcification are those employed in most of the medical image-analysis procedures They could be categorized in the following classes: Conventional classifiers Artificial neural networks Fuzzy-logic systems Support-vector machines 2.2.7.1 Conventional Classifiers 2.2.7.1.1 Rule-Based Systems (Decision Trees) The decision tree is one of the most widely used techniques for the extraction of inductive inference As a learning method, it aims at the definition of an approximating discrete-value target function in which the acquired knowledge is represented as a decision tree The architecture of the classifier includes a set of “if-then” rules A decision-tree scheme includes a main root node, from where the classification procedure starts, and several leaf nodes where the classification of the instance is given Each node in the tree specifies a check of an attribute of the instance, and each branch descending from that node corresponds to one of the possible values for this specific attribute An instance is categorized beginning from the root node and, by checking the attribute specified by this node, moving down to the specific tree branch that is responsible for the value of this attribute A similar procedure is replicated if a new tree is rooted at the new node From the early studies of microcalcification detection and characterization in mammography, rule-based systems provide a remarkable assistance in the simulation of the diagnosis process carried out by a radiologist [67, 68] Although, the conversion of medical rules to “if-then” rules is a feasible task, the development of a highperformance system has not been achieved This is due to the absence of attributevalue pair representations in medical data and the lack of disjunctive descriptions or large data sets for system training that include all the specific disease cases 2.2.7.1.2 Bayesian Quadratic and Linear Classifiers (Statistical) A Bayesian classifier is based on the approximation of the class-conditional probabilistic density functions (PDFs) Each PDF expresses the frequency of occurrence of each sample in the feature space Typically, an unknown sample is classified to a class with the highest value of its PDF The problem is that the precise approximation of the PDFs has to be defined [62] Quadratic and linear classifiers are statistical (parametric) methods that utilize Gaussian distributions for the PDFs The mean vector and the covariance matrix are estimated from the training set of each class In the case of a Bayesian quadratic classifier (BQC), the classification boundary forms a quadratic curve In the case of a Bayesian linear quadratic (BLQ) classifier, instead of using different covariance matrices for the individual classes, one unified covariance matrix is used for all classes, and the classification border is a straight line Copyright 2005 by Taylor & Francis Group, LLC 2089_book.fm Page 72 Tuesday, May 10, 2005 3:38 PM 72 Medical Image Analysis the desired lumen and media/adventitia borders An algorithm based on activecontour models in 2-D and its extension in 3-D is described in the literature [112] The initial contour is placed around the IVUS catheter, and it can be represented by r ≡ r θ , θ ∈ 0, 2π  The contour evolves under the influence of three forces: the internal force, the image force, and the balloon force Thus () Ftotal ( r ) = Fint ( r ) + Fimage + Fbal ( r ) (2.6) The “balloon” force is added in the energy of the active-contour model and causes the contour to inflate until the desired borders are detected The application of the 2-D algorithm results in a set of contours, which are then combined to form a 3-D surface and used as the initial guess for the 3-D algorithm, in which appropriate modifications to the forces and the representation of the contour are introduced A three-dimensional segmentation technique has been developed [101] for the detection of luminal and adventitial borders in IVUS sequences The method is based on the deformation of a template by the features present in the 3-D image This algorithm is a 3-D extension of the digital dynamic contour (DDC) model reported by Lobregt and Viergever [115] The model comprises vertices (which are associated with net force, acceleration, and velocity) connected with edges While the vertices of the model move, the initial contour deforms under the influence of internal and external forces and a third dumping force that helps to bring the model to rest The contour obtains its final shape when the velocity and the acceleration of the vertices become zero Expanding the DDC algorithm in three dimensions, a cylindrical shape is adopted as the initial surface model and it is allowed to deform under the influence of the same three forces The model is composed of vertices, determined in individual contours, and connections between them are then defined The internal force applied to this model depends on transverse and longitudinal curvature vectors Its components are given by: fin,i, j ,trans = fin,i, j ,trans rˆi, j (2.7) fin,i, j ,long = fin,i, j ,long rˆi, j (2.8) and where rˆi, j is a unit radial vector at vertex Vi,j The magnitudes of transverse and longitudinal internal forces are properly defined The external force is the gradient of a 3-D potential field that results from the preprocessing of IVUS images, and it can be decomposed into two tangential and one radial component The damping force is a decelerating force acting at vertex Vi,j and is proportional to and directed opposite to vertex velocity vi,j Copyright 2005 by Taylor & Francis Group, LLC 2089_book.fm Page 73 Tuesday, May 10, 2005 3:38 PM Medical-Image Processing and Analysis for CAD Systems 2.3.3 LIMITATIONS IN 73 QUANTITATIVE IVUS IMAGE ANALYSIS Many restrictions in automated segmentation of IVUS images derive from the quality of the image, such as the lack of homogeneity of regions of interest and the shadowed regions that are produced by the presence of calcium The complicated structure of human vessels and the different components in each part result in an image with high-intensity variations, even in regions corresponding to the same tissue In addition, calcified, hard-plaque regions are typically identified by high-amplitude echo signals with complete distal shadowing Consequently, it is not possible to identify the morphology of the outer layers of the arterial segment, and in the absence of contextual information from image frames adjacent in space and time, single-frame IVUS images are difficult to analyze, even for the most experienced observers It must be reported that systolic–diastolic image artifacts frequently limit the clinical applicability of automated analysis systems A method of limiting cyclic artifacts in IVUS images is based on electrocardiogram-gated (ECG-gated) image acquisition, which is extensively used to overcome the problem of vessel distensibility and cardiac movement The principle of ECG-gated image acquisition is described by von Birgelen et al [109] A workstation is used for the reception of a video input from the IVUS machine and the ECG signal from the patient Upper and lower limits for acceptable RR intervals, i.e., the time duration between two consecutive QRS complexes, are defined (mean value ±50 msec) before image acquisition begins Images are acquired 40 msec after the peak of the R wave, digitized, and stored in the computer If an RR interval is too long or too short, images are rejected, and the transducer does not move until the image can be acquired during a heart cycle with the appropriate RR interval length After an image is acquired, the IVUS transducer is withdrawn in axial 0.2-mm increments through the stationary imaging sheath to acquire the next image at that site In general, ECGgated image acquisition, when combined with an automated boundary detection method results in much smoother vessel boundaries In many cases, images of IVUS sequence are excluded from further analysis because of the problems they exhibit Common problems in IVUS sequences are poor image quality, side branch attachments in the vessel under examination, extensive nonuniform rotational distortion, extensive calcification of the vessel wall, and excessive shadows caused by stent struts The accuracy of the proposed segmentation algorithms would ideally be determined by the comparison of borders extracted automatically with the real borders of the regions of interest However, it is difficult to assess the accuracy and the reliability of the suggested methods because the precise size and shape of the arterial segment is unknown in vivo For that reason, the manual tracing is used as the “gold standard,” and the information that is often used is the location of these borders as given by experienced observers, who generally have different opinions 2.3.4 PLAQUE CHARACTERIZATION IN IVUS IMAGES Plaque composition was shown to correlate with clinical variables in atherosclerotic coronary artery disease [116, 117] The composition of the plaque can be identified in IVUS images, as demonstrated in several studies in comparison with histology Copyright 2005 by Taylor & Francis Group, LLC 2089_book.fm Page 74 Tuesday, May 10, 2005 3:38 PM 74 Medical Image Analysis [118, 119] The classification of plaque in regions of soft (cellular), hard (fibrocalcific), and calcified plaque is based on the characteristic appearance of each one in IVUS images The components of soft plaque (highly cellular areas of intimal hyperplasia, cholesterol, thrombus, and loose connective tissue types) in IVUS images are regions of low contrast and homogeneous texture On the other hand, regions of hard plaque, which may also contain calcium, are characterized by bright echoes (similar to adventitia), heterogeneous texture, and they are often trailed by shadowed areas An automated method for assessing plaque composition in IVUS images has been proposed by Zhang et al [105] The method proposed by Sonka et al [100] was used to detect the borders of the lumen and media/adventitia in the entire IVUS sequence To assess plaque composition, narrow wedges, called elementary regions, were defined in plaque regions, and a classification label was assigned to them, describing a soft or hard plaque To classify elementary regions, several texturefeature measurements were computed Gray-level-based texture descriptors — such as histogram contrast, skewness, kurtosis, dispersion, variance, and the radial profile property — are calculated for each elementary region Co-occurrence matrices were used, and such features as energy, entropy, maximum probability, contrast, and inverse difference moment were computed Two run-length features, such as short primitives emphasis and long primitives emphasis as well as Brownian fractal dimension were also calculated After having calculated these features, correlated ones were removed, and among all features, radial profile, long run emphasis, and the fractal dimension were identified as providing the best features for classifying soft and hard plaques in IVUS images These features were used for the training of a classifier with piecewise linear discrimination functions Afterward, each elementary region was classified as containing soft or hard plaque For the hard-plaque regions, a further classification of hard plaque and shadow subregions was performed When the classification had been applied on the entire IVUS sequence, the plaque type of each pixel was determined as the majority type among the pixels of the same spatial location in a total of seven consecutive frames In the study of Vince et al [120], the efficacy of texture-analysis methods in identifying plaque components was assessed in vitro IVUS images were captured, and regions of interest were identified by microscopic examination of the histological sections Three plaque classes were considered: calcified, fibrous (dense collagenous tissue), and necrotic core (lipidic pool with evident necrosis) Texture-analysis procedures were applied in the region of interest, and the following statistical techniques were evaluated: first-order statistics, Haralick’s method, Laws’s texture energies, neighborhood gray-tone difference matrices (NGTDM), and the texturespectrum method The selection of these methods was based on their ability to differentiate soft tissue and textural patterns in two-dimensional gray-scale images After the implementation of these approaches, classification of texture features was performed The clustering ability of each of the examined texture-analysis techniques was assessed Haralick’s method demonstrated tight clustering of calcified, fibrous, and necrotic regions with no overlap Copyright 2005 by Taylor & Francis Group, LLC 2089_book.fm Page 75 Tuesday, May 10, 2005 3:38 PM Medical-Image Processing and Analysis for CAD Systems z z y x 75 x (a) (b) y FIGURE 2.6 (a) Estimation of the three-dimensional trajectory path from the biplane angiographical data; (b) mapping of IVUS frames along the pullback path in three-dimensional space 2.3.5 THREE-DIMENSIONAL RECONSTRUCTION Three-dimensional reconstruction of the vessel based on IVUS yields more information than two-dimensional IVUS imaging alone in the visualization and assessment of coronary artery disease and the choice of intervention To produce threedimensional renderings of vessel geometry, approaches that rely exclusively on IVUS data perform a straight stacking of adjacent frames [107, 121, 122] However, these approaches not account for the real spatial geometry of the coronary artery, completely neglecting the influence of the vessel curvature, which induces an error in quantitative measurements of the vessel [123] In general, the determination of the position in 3-D space of an object, whose shape and size are unknown, requires more than one view For that reason, techniques have recently been developed [124–127] to reconstruct the true spatial geometry by combining IVUS and biplane angiography These two modalities are well complementary and suitable for fusion, since biplane angiography provides longitudinal projections of the vessel lumen, while IVUS provides transversal cross-sections of the lumen and the wall The main concept of these approaches is illustrated in Figure 2.6 From the angiographical data, a reconstruction of the catheter path during its pullback in 3D space (i.e., the pullback path) is obtained, and IVUS images are placed appropriately along this path The steps of this procedure are depicted in Figure 2.7 Several sources of errors can affect the accuracy of the 3-D vessel model Apart from the problems that each modality is associated with, problems that are closely related to the fusion between both image modalities — such as the determination of the pullback path, the estimation of the catheter twist, and the absolute orientation of IVUS frame sequence — need to be resolved The accurate estimation of the pullback path in 3-D space is important for the correct positioning and orientation of the IVUS images in 3-D space The pullback path in the biplane angiograms can be approximated either by the vessel centerline or by the location of the ultrasound transducer in the vessel In the first case, problems of overshadowed catheters are overcome, but an angular error occurs whenever the catheter centerline is off the Copyright 2005 by Taylor & Francis Group, LLC 2089_book.fm Page 76 Tuesday, May 10, 2005 3:38 PM 76 Medical Image Analysis Acquisition Angiography IVUS Catheter path detection Segmentation Segmentation Specification of 3-D catheter pullback path Estimation of the 3-D geometry ROIs contour extraction Correspondence between IVUS-angiographical data Relative twist Estimation of fusion parameters Absolute orientation Visualization FIGURE 2.7 Basic steps of fusion procedure of IVUS and angiographical data lumen centerline [125] However, in the second case, a sequence of biplane angiograms needs to be recorded over the entire IVUS catheter pullback length Longitudinal catheter twist is an interframe distortion that affects the rotational orientation of the IVUS frames along the pullback path Consequently, the reconstructed plaque may be located incorrectly at the inner side of the vessel bend while it is actually located at the outer bend Finally, it is essential to determine the correct absolute axial orientation of the resulting IVUS frame set The problem is comparable to fitting a sock on a leg [126] While the leg is stable (catheter path), the sock (axial orientation of the IVUS frame set) can freely be rotated around the leg, and it fits optimally only in one axial orientation One of the earliest studies for three-dimensional reconstruction of vessel morphology from X-ray projections and IVUS data was proposed by Pellot et al [124] A well-defined acquisition protocol was used, and couples of X-ray control projections/IVUS images were acquired for each position of the transducer as it was manually withdrawn from small distances in the vessel For the extraction of IVUS transversal contours, a fuzzy classification technique was performed followed by mathematical morphology operators A dynamic tracking algorithm was applied on angiographical images to extract the vessel longitudinal contours A geometric model was adopted for the representation of the acquisitions into a unique reference frame The registered IVUS contours were linearly interpolated to extract a regularly sampled 3-D surface with the same resolution as angiography This 3-D surface constitutes an approximate geometric reconstruction of the vessel using IVUS and X-ray images The 3-D registered data are then combined with the X-ray densitometric Copyright 2005 by Taylor & Francis Group, LLC 2089_book.fm Page 77 Tuesday, May 10, 2005 3:38 PM Medical-Image Processing and Analysis for CAD Systems 77 information to refine the preliminary contours at each slice For that purpose, the researchers used a probabilistic reconstruction process using Markovian modeling associated with a simulated annealing-based optimization algorithm Prause et al [125] focused on the estimation of IVUS catheter twist during pullback They report an algorithm for the calculation of tortuosity-induced catheter twist that is based on sequential triangulation of the three-dimensional pullback path In brief, the method is described as follows Each frame is described by its location at the entire IVUS sequence The consecutive IVUS frames i and i + are located halfway between three sequential points Pi, Pi+1, Pi+2 of the pullback path, at points Si = (Pi + Pi+1)/2 and Si+1 = (Pi+1 + Pi+2)/2 The images are perpendicular to the tangent vectors ti = Pi+1 − Pi and ti+1 = Pi+2 − Pi+1 To determine the orientation of IVUS image i + 1, the already known orientation of image i is used Thus, the orientation of image i + is determined by rotating image i around the normal vector ni = ti × ti+1 at the center of the circumscribed circle of the triangle (Pi, Pi+1, Pi+2) Then, the center of image i + is shifted to point Si+1 If the points Pi, Pi+1, Pi+2 are collinear, the calculation of image i + reduces to a simple translation along the pullback path An important advantage of this approach is that if there are single images in the pullback sequence, rotationally adjusted by anatomic landmarks, the orientation of the remaining frames is fixed or can be interpolated Another method for three-dimensional reconstruction of the vessel based on the fusion of IVUS and angiographical images has been proposed by Wahle et al [126] Angiographical images were processed to estimate the geometry, extract the catheter path, and reconstruct the three-dimensional trajectory The geometry is initially extracted from the parameters as read from the device and refined afterward from a set of given reference points For the extraction of the catheter path in biplane angiograms, the most distal location of the transducer and the location at or proximal to the end of pullback are interactively marked The path of the catheter as well as the two edges of the vessel lumen outline can be extracted with the use of dynamic programming The three-dimensional reconstruction of trajectory is obtained using a well-established and validated three-dimensional reconstruction approach [128] IVUS image-processing includes extraction of regions of interest using the previously described algorithm [100] The fusion process starts with the localization of IVUS frames on the 3-D path, assuming constant pullback speed and a fixed number of images per millimeter of pullback The local behavior of the pullback path in 3-D can be described using the Serret-Frenet formulas, and based on this theory, an analytical model of the catheter is obtained The relative twist is estimated using the method proposed by Prause et al [125] and the amount of twisting, i.e., the presumed error if the torsion is not considered during the reconstruction, is estimated using a reference plane Quantification of the relative twist is estimated, i.e., the presumed error if the torsion is not considered during the reconstruction For the estimation of the absolute orientation in 3-D space, the bending behavior of the catheter is used as a reference The IVUS catheter tends to take a position of minimum bending energy inside a tortuous vessel, resulting in an out-of-center position of the catheter relative to the inner lumen Three-dimensional out-of-center vectors are generated from the contour Copyright 2005 by Taylor & Francis Group, LLC 2089_book.fm Page 78 Tuesday, May 10, 2005 3:38 PM 78 Medical Image Analysis center to the catheter position A single correction angle ϕcorr is determined and applied to all IVUS frames relative to the initial contour After the 3-D mapping of the IVUS data, a surface model of the vessel can be displayed The validation of the method included computer simulation, in which the method showed excellent results, in phantom and in vitro studies, that uncovered influence from several sources of distortion caused mainly by mechanical components of the setup A method for 3-D reconstruction of complex blood-vessel geometries from IVUS images has been proposed by Subramanian et al [127] This technique uses biplane fluoroscopy to image the catheter tip, at a few important points along the length of the vessel, to estimate the curvature of the vessel A reference direction is determined and maintained throughout the acquisition Afterward, the 3-D coordinates of the catheter tip are determined from the X-ray images, the path is estimated, and the IVUS images are located along the path The catheter tip is located manually within each X-ray image A coordinate system (x, y, z) is used, where the vessel’s longitudinal axis is approximately along the z-axis and the two X-ray projection images determine the (x, z) and (y, z) coordinates, respectively After recovering the 3-D points that represent the locations of the catheter tip, they are converted to physical units (mm) and are normalized so that the first point becomes the origin The catheter path is estimated by fitting an interpolating cube spline (Kochanek-Bartels spline) through the points The location of each IVUS frame along the catheter path is determined by uniformly sampling the spline in a number of points that are equal to the number of IVUS images to be used Each IVUS image is positioned so that the catheter tip is on the spline and the image is orthogonal to the tangent vector at this point The orientation of an IVUS image on the catheter path is estimated using two unit vectors ui and vi orthogonal to the catheter path The vectors ui and vi are calculated by ui = ni × vi−1 (2.9) vi = ui × ni (2.10) and where i = 1, …, n − 1, where × indicates vector cross-product, and where the vectors ni , i = 0, 1, …, n − are the tangent vectors at each point The initial vector v0 can be arbitrary, so that it does not coincide with n0 Each of the images is rotated by an amount determined by ni , depending on the path of the catheter tip Finally, the 3-D volume is determined by associating the echo intensity at all lattice points of the volume In vitro validation of the method gave very promising results 2.4 CONCLUSIONS Medical imaging modalities provide useful information about the internal structure and function of the human body Specific modalities are utilized to depict different tissues Identification and characterization of pathological findings require a lot of effort and skill on the part of the radiologist The complexity of the examined images in many cases requires a second opinion or further analysis to avoid misinterpretations CAD systems can provide additional data that can increase the efficiency of Copyright 2005 by Taylor & Francis Group, LLC 2089_book.fm Page 79 Tuesday, May 10, 2005 3:38 PM Medical-Image Processing and Analysis for CAD Systems 79 interpretations Extensive tests and additional research projects aimed at improving CAD’s performance are under evaluation in an effort to increase doctors’ confidence level in CAD systems CAD systems in mammography, and especially microcalcification detection and diagnosis, could provide remarkable support as a “second opinion” tool, improving the effectiveness of the decision-making procedure However, further study is needed to eliminate falsely detected objects An improvement of segmentation and classification algorithms in CAD systems could increase the performance of the schemes in the classification and characterization of pathological findings as malignant or benign Such progress would increase the benefits of these systems by eliminating or minimizing unnecessary biopsies Further testing is needed using the large databases available to researchers as well as the original mammograms that are obtained from the clinical routine and from screening-population projects The contribution of CAD systems is also important in the interpretation of medical data obtained by other imaging modalities In the interpretation of intravascular ultrasound images, CAD systems are beneficial because they can efficiently identify possible abnormalities that might not be recognized by the expert observer Real-time depiction of the arterial wall, determination of plaque composition, and quantitative measurements obtained during clinical routine are considered to be critical components of a CAD system Sophisticated methods for automatically extracting useful information from IVUS images are still under development, and 3-D reconstruction of the vessel has become available The methods described in this chapter provide a more comprehensive understanding and a more circumstantial characterization of coronary artery disease, which could result in better and lessinvasive patient treatment Today, medical-image-processing techniques are used in several CAD systems The processing of images from different modalities must be characterized by high performance if they are to be utilized in clinical environments The use of CAD systems in medical applications addresses a well-recognized clinical weakness of the diagnostic process and also complements the radiologists’ perceptive abilities However, the increased interest and striking expansion of research in the field of CAD systems provides fertile conditions for further development More sophisticated and productive approaches might lead to high-efficiency CAD systems that will be essential components in modern diagnostic practices Those systems will be based on resourceful image-processing techniques followed by intelligent analysis methods Further evaluation of the diagnostic performance of the proposed systems is an important task that should be conducted under clinical conditions REFERENCES Baker, J.A et al., Breast cancer: prediction with artificial neural network based on BI-RADS standardized lexicon, Radiology, 196, 817, 1995 Wu, Y et al., Artificial neural networks in mammography: application to decision making in the diagnosis of breast cancer, Radiology, 187, 81, 1993 Sahiner, B et al., Feature selection and classifier performance in computer-aided diagnosis: the effect of finite sample size, Med Phys., 27, 1509, 2000 Copyright 2005 by Taylor & Francis Group, LLC 2089_book.fm Page 80 Tuesday, May 10, 2005 3:38 PM 80 Medical Image Analysis Roehrig, J and Castellino, R.A., The promise of computer-aided detection in digital mammography, Eur J Radiol., 31, 35, 1999 Smith, R.A., Epidemiology of Breast Cancer in a Categorical Course in Physics: Technical Aspects of Breast Imaging, 2nd ed., RSNA Publication, Oak Brook, IL, 1993, p 21 Nishikawa, R.M et al., Performance of a prototype clinical intelligent mammography workstation, ’96, in Digital Mammography, Doi, K., Giger, M.L., Nishikawa, R.M., and Schmith, R.A., Eds., Elsevier, Amsterdam, 1996, p 93 Roehrig, J et al., Clinical results with R2 ImageChecker system, in Digital Mammography, Karssemeijer, N., Thijssen, M., Hendriks, J., and van Erning, L., Eds., Kluwer Academic Publishers, Dordrecht, Netherlands, 1998, p 395 Becker, H et al., Digital computer determination of a medical diagnostic index directly from chest X-ray images, IEEE Trans Biomed Eng., BME-11, 67, 1964 Meyers, P et al., Automated computer analysis of radiographic images, Radiology, 83, 1029, 1964 10 Winsberg, F et al., Detection of radiographic abnormalities in mammograms by means of optical scanning and computer analysis, Radiology, 89, 211, 1967 11 Ackerman, L.V and Gose, E.E., Breast lesion classification by comport and xerography, Cancer, 30, 1025, 1972 12 Ackerman, L.V et al., Classification of benign and malignant breast tumors on the basis of 36 radiographic properties, Cancer, 31, 342, 1973 13 Wee, W.G et al., Evaluation of mammographic calcifications using a computer program, Radiology, 116, 717, 1975 14 Fox, S.H et al., A computer analysis of mammographic microcalcifications: global approach, in Proc IEEE 5th International Conference on Pattern Recognition, IEEE, New York, 1980, p 624 15 Spiesberger, W., Mammogram inspection by computer, IEEE Trans Biomed Eng., 26, 213, 1979 16 Chan, H.P et al., Image feature analysis and computer-aided diagnosis in digital radiography: automated detection of microcalcifications in mammography, Med Phys., 14, 538, 1987 17 Fam, B.W et al., Algorithm for the detection of fine clustered calcifications on film mammograms, Radiology, 169, 333, 1988 18 Chan, H.P et al., Computer-aided detection of microcalcifications in mammograms: methodology and preliminary clinical study, Invest Radiol., 23, 664, 1988 19 Chan, H.P et al., Improvement in radiologists' detection of clustered microcalcifications on mammograms: the potential of computer-aided diagnosis, Invest Radiol., 25, 1102, 1990 20 Pisano, E.D et al., Image processing algorithms for digital mammography: a pictorial essay, Radiographic, 20, 1479, 2000 21 Bick, U et al., A new single image method for computer-aided detection of small mammographic masses, in Proc CAR: Computer Assisted Radiology, Lemke, H.U., Inamura, K., Jaffe, C.C., and Vannier, M.W., Eds., Springer, Berlin, 1995, p 357 22 Pizer, S.M., Zimmerman, J.B., and Staab, E.V., Adaptive gray-level assignment in CT scan display, J Comput Assist Tomogr., 8, 300, 1984 23 Pizer, S.M et al., Adaptive histogram equalization and its variations, Comp Vision, Graphics, Image Processing, 35, 355, 1987 24 Vuylsteke, P and Schoeters, E., Multiscale image contrast amplification (MUSICA), Proc SPIE, 2167, 551, 1994 Copyright 2005 by Taylor & Francis Group, LLC 2089_book.fm Page 81 Tuesday, May 10, 2005 3:38 PM Medical-Image Processing and Analysis for CAD Systems 81 25 Rangayyan, R.M et al., Improvement of sensitivity of breast cancer diagnosis with adaptive neighborhood contrast enhancement of mammograms, IEEE Trans Inf Technol Biomed., 1, 161, 1997 26 Morrow, W.M et al., Region-based contrast enhancement of mammograms, IEEE Trans Medical Imaging, 11, 392, 1992 27 Mallat, S., A theory for multiresolution signal decomposition: the wavelet representation, IEEE Trans Pattern Analysis Machine Intelligence, 11, 7, 1989 28 Laine, A.F et al., Mammographic feature enhancement by multiscale analysis, IEEE Trans Medical Imaging, 13, 725, 1994 29 Sakellaropoulos, P., Costaridou, L., and Panayiotakis, G., A wavelet-based spatially adaptive method for mammographic contrast enhancement, Phys Med Biol., 48, 787, 2003 30 Cheng, H.D., Yui, M.L., and Freimanis, R.I., A novel approach to microcalcification detection using fuzzy-logic technique, IEEE Trans Medical Imaging, 17, 3, 1998 31 Li, H et al., Fractal modeling of mammogram and enhancement of microcalcifications, IEEE Nucl Sci Symp Medical Imaging Conf., 3, 1850, 1996 32 Li, H., Liu, K.J.R., and Lo, S.C.B., Fractal modelling and segmentation for the enhancement of microcalcifications in digital mammograms, IEEE Trans Medical Imaging, 16, 785, 1997 33 Li, H., Liu, K.J.R., and Lo, S.B., Fractal modeling of mammograms and enhancement of microcalcifications, in Proc IEEE Medical Imaging Conference, Anaheim, 1996, p 1850 34 Shen, L., Rangayyan, R.M., and Desautels, J.E.L., Detection and classification of mammographic calcifications, Int J Pattern Recognition Artif Intelligence, 7, 1403, 1993 35 Zheng, B et al., Computer-aided detection of clustered microcalcifications in digitized mammograms, Acad Radiol., 2, 655, 1995 36 Gurcan, M.N., Yardimci, Y., and Cetin, A.E., Digital Mammography, Kluwer Academic Publishers, Nijmegen, Netherlands, 1998, p 157 37 Bankman, I.N et al., Segmentation algorithms for detecting microcalcifications in mammograms, IEEE Trans Inf Technol Biomed., 1, 141, 1997 38 Betal, D., Roberts, N., and Whitehiuse, G.H., Segmentation and numerical analysis of microcalcifications on mammograms using mathematical morphology, Br J Radiol., 70, 903, 1997 39 Karssemeijer, N., Adaptive noise equalisation and recognition of microcalcification clusters in mammograms, Int J Pattern Recognition Artif Intelligence, 7, 1357, 1993 40 Chen, C.H and Lee, G.G., On digital mammogram segmentation and microcalcification detection using multiresolution wavelet analysis, Graph Mod Image Proc., 59, 349, 1997 41 Veldkamp, W.J.H and Karssemeijer, N., in Digital Mammography Nijmegen 98, Karssemeijer, N., Thijssen, M., Hendriks, J., and van Erning, L., Eds., Kluwer Academic Publications, Amsterdam, 1998, p 160 42 Strickland, R.N and Hahn, H.I., Wavelet transform methods for object detection and recovery, IEEE Trans Image Process., 6, 724, 1997 43 Netsch, T and Peitgen, H.O., Scale-space signatures for the detection of clustered microcalcifications in digital mammograms, IEEE Trans Medical Imaging, 18, 774, 1999 44 Lefebvre, F et al., A fractal approach to the segmentation of microcalcifications in digital mammograms, Med Phys., 22, 381, 1995 Copyright 2005 by Taylor & Francis Group, LLC 2089_book.fm Page 82 Tuesday, May 10, 2005 3:38 PM 82 Medical Image Analysis 45 Cheng, H.D and Xu, H., A novel fuzzy-logic approach to mammogram contrast enhancement, Inf Sci., 148, 167, 2002 46 Kim, J.K et al., Detection of clustered microcalcifications on mammograms using surrounding region dependence method and artificial neural network, J VLSI Signal Process., 18, 251, 1998 47 Te Brake, G.M and Karssemeijer, N., Single and multiscale detection of masses in digital mammograms, IEEE Trans Medical Imaging, 18, 628, 1999 48 Yu, S and Guan, L., A CAD system for the automatic detection of clustered microcalcifications in digitized mammogram films, IEEE Trans Medical Imaging, 19, 115, 2000 49 Kupinski, M.A and Giger, M.L., Feature selection with limited datasets, Med Phys., 26, 2176, 1999 50 Karssemeijer, N., Adaptive noise equalisation and recognition of microcalcification clusters in mammograms, Int J Pattern Recognition Artif Intelligence, 7, 1357, 1993 51 Chan, H.P et al., Improvement in radiologists' detection of clustered microcalcifications on mammograms: the potential of computer-aided diagnosis, Invest Radiol., 25, 1102, 1990 52 Strickland, R.N and Hahn, H.I., Wavelet transforms for detecting microcalcifications in mammograms, IEEE Trans Medical Imaging, 15, 218, 1996 53 Netsch, T., A scale-space approach for the detection of clustered microcalcifications in digital mammograms, in Digital Mammography ’96, Proc 3rd Int Workshop Digital Mammography, Univ of Chicago, Chicago, 1996, p 301 54 Haykin, S., Neural Networks: A Comprehensive Foundation, 2nd ed., Macmillan College Publishing, New York, 1998 55 Papadopoulos, A., Fotiadis, D.I., and Likas, A., An automatic microcalcifications detection system based on a hybrid neural network classifier, Artif Int Med., 25, 149, 2002 56 Sahiner, B et al., Design of a high-sensitivity classifier based on genetic algorithm: application to computer-aided diagnosis, Phys Med Biol., 43, 2853, 1998 57 Yu, S and Guan, L., A CAD system for the automatic detection of clustered microcalcifications in digitized mammogram films, IEEE Trans Medical Imaging, 19, 115, 2000 58 Sahiner, B et al., Image feature selection by a genetic algorithm: application to classification of mass and normal breast tissue, Med Phys., 23, 1671, 1996 59 Sahiner, B et al., Effects of sample size on feature selection in computer-aided diagnosis, in Proc SPIE Medical Imaging, 3661, 499, 1999 60 Gavrielides, M.A., Lo, J.Y., and Floyd, C.E., Parameter optimization of a computeraided diagnosis scheme for the segmentation of microcalcification clusters in mammograms, Med Phys., 29, 475, 2002 61 Chan, H.P et al., Improvement of radiologists’ characterization of mammographic masses by using computer-aided diagnosis: an ROC study, Radiology, 212, 817, 1999 62 Woods, K.S et al., Comparative evaluation of pattern recognition techniques for detection of microcalcifications in mammography, Int J Pattern Recognition Artif Intelligence, 7, 1417, 1993 63 Dhawan, A.P., Analysis of mammographic microcalcifications using gray-level image structure features, IEEE Trans Medical Imaging, 15, 246, 1996 64 Leichter, I et al., Optimizing parameters for computer-aided diagnosis of microcalcifications at mammography, Acad Radiol., 7, 406, 2000 65 Chan, H.P et al., Computerized analysis of mammographic microcalcifications in morphological and texture feature spaces, Med Phys., 25, 2007, 1998 Copyright 2005 by Taylor & Francis Group, LLC 2089_book.fm Page 83 Tuesday, May 10, 2005 3:38 PM Medical-Image Processing and Analysis for CAD Systems 83 66 Qi, H and Snyder, W.E., Lesion detection and characterization in digital mammography by Bezier histograms, J Digital Imaging, 12, 81, 1998 67 Chan, H.P et al., Image feature analysis and computer-aided diagnosis in digital radiography: 1, automated detection of microcalcifications in mammography, Med Phys., 14, 538, 1987 68 Davies, D.H and Dance, D.R., Automated computer detection of clustered calcifications in digital mammograms, Phys Med Biol., 35, 1111, 1990 69 Bhagale, T., Desai, U.B., and Sharma, U., An unsupervised scheme for detection of microcalcifications on mammograms, IEEE Int Conf Image Processing, 2000, p 184 70 Fukunaga, K., Introduction to Statistical Pattern Recognition, 2nd ed., Academic Press, New York, 1990 71 Tsujii, O., Freedman, M.T., and Mun, S.M., Classification of microcalcifications in digital mammograms using trend-oriented radial basis function neural network, Pattern Recognition, 32, 891, 1999 72 Raghu, P.P and Yegnanarayana, B., Multispectral image classification using Gabor filters and stochastic relaxation neural network, Neural Networks, 10, 561, 1997 73 Markey, M.K et al., Self-organizing map for cluster analysis of a breast cancer database, Artif Intel Med., 27, 113, 2003 74 Egmont-Petersen, M., de Ridder, D., and Handels, H., Image processing with neural networks: a review, Pattern Recognition, 35, 2279, 2002 75 Bishop, C.M., Neural Networks for Pattern Recognition, Oxford University Press, Oxford, U.K., 1996 76 Verma, B and Zakos, J., A computer-aided diagnosis system for digital mammograms based on fuzzy-neural and feature-extraction techniques, IEEE Trans Inf Technol Biomed., 5, 46, 2001 77 Burges, C.J.C., A tutorial on support vector machines for pattern recognition, Knowledge Discovery Data Mining, 2, 1, 1998 78 Cristianini, N and Shawe-Taylor, J., An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods, Cambridge University Press, London, 2000 79 Bazzani, A et al., Automated detection of clustered microcalcifications in digital mammograms using an SVM classifier, in Proc 8th Eur Symp Artif Neural Networks, Bruges, Belgium, 2000, p 195 80 El-Naqa, I et al., Support vector machine learning for the detection of microcalcifications in mammograms, IEEE Trans Medical Imaging, 21, 1552, 2002 81 Metz, C.E., ROC methodology in radiologic imaging, Invest Radiol., 21, 720, 1986 82 Chakraborty, D., Maximum likelihood analysis of free-response receiver operating characteristic (FROC) data, Med Phys., 16, 561, 1989 83 Swensson, R.G., Unified measurement of observer performance in detecting and localizing target objects on images, Med Phys., 23, 1709, 1996 84 Chakraborty, D.P and Winter, L., Free-response methodology: alternative analysis and a new observer-performance experiment, Med Phys., 174, 873, 1990 85 Chakraborty, D., Statistical power in observer-performance studies: comparison of the receiver operating characteristic and free-response methods in tasks involving localization, Acad Radiol., 9, 147, 2002 86 Metz, C.E., Evaluation of CAD methods, in Computer-Aided Diagnosis in Medical Imaging, Doi, K., MacMahon, H., Giger, M.L., and Hoffmann, K.R., Eds., Excerpta Medica International Congress Series, Vol 1182, Elsevier Science, Amsterdam, 1999, p 543 87 R2 Technology Co., ImageChecker; available on-line at www.r2tech.com (March 7, 2005) Copyright 2005 by Taylor & Francis Group, LLC 2089_book.fm Page 84 Tuesday, May 10, 2005 3:38 PM 84 Medical Image Analysis 88 CADx Medical Systems, Second Look Digital/AD; available on-line at www cadxmed.com (March 7, 2005) 89 Intelligent Systems Software, MammoReader; available on-line at www.icadmed.com (March 7, 2005) 90 Scanis, Mammex MammoCAD; available on-line at www.scanis.com (March 7, 2005) 91 Williams, L., Prescott, R., and Hartswood, M., Computer-aided cancer detection and the UK national breast screening programme, in Proc 4th Int Workshop on Digital Mammography, Karssemejer, N., Thijssen, M., Hendriks, J., and van Erning, L., Eds., Kluwer Academic Publications, Amsterdam, 1998 92 MedDetect; available on-line at www.meddetectids.com (March 7, 2005) 93 National Health Service Breast Screening Programme (NHSBSP), Computer-Aided Detection In Mammography, Working Party of the Radiologists, Quality Assurance Coordinating Group, NHSBSP publication no 48, NHSBSP, 2001 94 Malich, A et al., Reproducibility: an important factor determining the quality of computer-aided detection (CAD) systems, Eur J Radiol., 36, 170, 2000 95 Burhenne, L.J et al., Potential contribution of computer-aided detection to the sensitivity of screening mammography, Radiology, 215, 554, 2000 96 Malich, A et al., Tumor detection rate of a new commercially available computeraided detection system, Eur Radiol., 11, 2454, 2001 97 Yock, P.G and Fitzgerald, P.J., Intravascular ultrasound imaging, in Cardiac Catheterization, Angiography and Intervention, Baim, D.S and Grossman, W., Eds., Williams & Wilkins, Baltimore, 1996, chap 22 98 Cachard, C et al., Ultrasound contrast agent in intravascular echography: an in vitro study, Ultrasound Med Biol., 23, 705, 1997 99 Meier, D.S et al., Automated morphometry of coronary arteries with digital image analysis of intravascular ultrasound, Am Heart J., 133, 681, 1997 100 Sonka, M et al., Segmentation of intravascular ultrasound images: a knowledgebased approach, IEEE Trans Medical Imaging, 14, 719, 1995 101 Shekhar, R et al., Three-dimensional segmentation of luminal and adventitial borders in serial intravascular ultrasound images, Comput Med Imag Grap., 23, 299, 1999 102 Bouma, C.J et al., Automated lumen definition from 30 MHz intravascular ultrasound images, Med Image Anal., 1, 263, 1997 103 Plissiti, M.E., Fotiadis, D.I., and Michalis, L.K., 3-D reconstruction of stenotic coronary arterial segments using intravascular ultrasound and angiographic images, in XVIIIth ISB Congr Int Soc Biomechanics, ETH, Zurich, 2001, p 224 104 Takagi, A et al., Automated contour detection for high-frequency intravascular ultrasound imaging: a technique with blood noise reduction for edge enhancement, Ultrasound Med Biol., 26, 1033, 2000 105 Zhang, X., McKay, C.R., and Sonka, M., Tissue characterization in intravascular ultrasound images, IEEE Trans Medical Imaging, 17, 889, 1998 106 Li, W et al., Semi-automatic contour detection for volumetric quantification of intracoronary ultrasound, in Proc Comput Cardiol 1994, IEEE Computer Society Press, Washington, DC, 1994, p 277 107 von Birgelen, C et al., Computerized assessment of coronary lumen and atherosclerotic plaque dimensions in three-dimensional intravascular ultrasound correlated with histomorphometry, Am J Cardiol., 78, 1202, 1996 108 Dijkstra, J et al., Automatic border detection in intravascular ultrasound images for quantitative measurements of the vessel, lumen and stent parameters, Int Congr Ser., 1230, 916, 2001 Copyright 2005 by Taylor & Francis Group, LLC 2089_book.fm Page 85 Tuesday, May 10, 2005 3:38 PM Medical-Image Processing and Analysis for CAD Systems 85 109 von Birgelen, C et al., Electrocardiogram-gated intravascular ultrasound image acquisition after coronary stent deployment facilitates on-line three-dimensional reconstruction and automated lumen quantification, JACC, 30, 436, 1997 110 Hagenaars, T et al., Reproducibility of volumetric quantification in intravascular ultrasound images, Ultrasound Med Biol., 26, 367, 2000 111 Mojsilovic, A et al., Automatic segmentation of intravascular ultrasound images: a texture-based approach, Ann Biomed Eng., 25, 1059, 1997 112 Kovalski, G et al., Three-dimensional automatic quantitative analysis of intravascular ultrasound images, Ultrasound Med Biol., 26, 527, 2000 113 Kass, M., Witkin, A., and Terzopoulos, D., Snakes: active contour models, Int J Comput Vision, 1, 321, 1987 114 Zhu, Y and Yan, H., Computerized tumor boundary detection using a Hopfield neural network, IEEE Trans Medical Imaging, 16, 55, 1997 115 Lobregt, S and Viergever, M.A., Discrete dynamic contour model, IEEE Trans Medical Imaging, 14, 12, 1995 116 Mintz, G.S et al., Determinants and correlates of target lesion calcium in coronary artery disease: a clinical, angiographic and intravascular ultrasound study, JACC, 29, 268, 1997 117 Rasheed, Q et al., Correlation of intracoronary ultrasound plaque characteristics in atherosclerotic coronary artery disease patients with clinical variables, Am J Cardiol., 73, 753, 1994 118 Rasheed, Q et al., Intracoronary ultrasound-defined plaque composition: computeraided plaque characterization and correlation with histologic samples obtained during directional coronary atherectomy, Am Heart J., 129, 631, 1995 119 De Feyter, P.J., Mario, C.D., and Serruys, P.W., Quantitative Coronary Imaging, Barjesteh Meeuwes & Co and Thoraxcentre, Erasmus University, Rotterdam, Netherlands, 1995 120 Vince, D.G et al., Comparison of texture analysis methods for the characterization of coronary plaques in intravascular ultrasound images, Comput Med Imag Grap., 24, 221, 2000 121 Shiran, A et al., Serial volumetric intravascular ultrasound assessment of arterial remodeling in left main coronary artery disease, Am J Cardiol., 83, 1427, 1999 122 Weissman, N.J et al., Three-dimensional intravascular ultrasound assessment of plaque after successful atherectomy, Am Heart J., 130, 413, 1995 123 Schuurbiers, J.C.H et al., On the IVUS plaque volume error in coronary arteries when neglecting curvature, Ultrasound Med Biol., 26, 1403, 2000 124 Pellot, C et al., An attempt to 3-D reconstruction vessel morphology from X-ray projections and intravascular ultrasounds modeling and fusion, Comput Med Imag Grap., 20, 141, 1996 125 Prause, G.P.M et al., Towards a geometrically correct 3-D reconstruction of tortuous coronary arteries based on biplane angiography and intravascular ultrasound, Int J Cardiac Imaging, 13, 451, 1997 126 Wahle, A et al., Geometrically correct 3-D reconstruction of intravascular ultrasound images by fusion with biplane angiography: methods and validation, IEEE Trans Medical Imaging, 18, 686, 1999 127 Subramanian, K.R et al., Accurate 3-D reconstruction of complex blood vessel geometries from intravascular ultrasound images: in vitro study, J Med Eng Technol., 24, 131, 2000 Copyright 2005 by Taylor & Francis Group, LLC 2089_book.fm Page 86 Tuesday, May 10, 2005 3:38 PM 86 Medical Image Analysis 128 Wahle, A et al., Assessment of diffuse coronary artery disease by quantitative analysis of coronary morphology based upon 3-D reconstruction from biplane angiograms, IEEE Trans Medical Imaging, 14, 230, 1995 129 Plissiti, M.E et al., An automated method for lumen and media/adventitia border detection in a sequence of IVUS frames, IEEE Trans Inf Technol Biomed., 8, 131, 2004 Copyright 2005 by Taylor & Francis Group, LLC [...]... other classification schemes, an SVM aims to minimize the empirical risk Remp while maximizing the distances (geometric margin) of the data points from the corresponding linear decision boundary (Figure 2 .3) Remp is defined as Remp ( a ) = 1 2l l ∑ y − f ( x , a) i i (2.1) i =1 where xi ∈ RN, i = 1, …, l, is the training vector belonging to one of two classes l is the number of training points yi ∈ {−1,... literature, such as the polynomial type of degree p Copyright 2005 by Taylor & Francis Group, LLC 2089_book.fm Page 64 Tuesday, May 10, 2005 3:38 PM 64 Medical Image Analysis K ( xi , x ) = ( xi ⋅ x + 1) p (2 .3) and the Gaussian kernel K ( xi , x ) = e 2 − xi − x / 2 σ 2 (2.4) where σ is the kernel width 2.2.8 EVALUATION METHODOLOGIES The evaluation of a classification system is one of the major issues in measuring