Research and development of SPECT and SPECT CT images segmentation software for automatic detection and extraction of brain tumors using ITK, VTK, QtResearch and development of SPECT and SPECT CT images segmentation software for automatic detection and extraction of brain tumors using ITK, VTK, QtResearch and development of SPECT and SPECT CT images segmentation software for automatic detection and extraction of brain tumors using ITK, VTK, QtResearch and development of SPECT and SPECT CT images segmentation software for automatic detection and extraction of brain tumors using ITK, VTK, QtResearch and development of SPECT and SPECT CT images segmentation software for automatic detection and extraction of brain tumors using ITK, VTK, QtResearch and development of SPECT and SPECT CT images segmentation software for automatic detection and extraction of brain tumors using ITK, VTK, QtResearch and development of SPECT and SPECT CT images segmentation software for automatic detection and extraction of brain tumors using ITK, VTK, QtResearch and development of SPECT and SPECT CT images segmentation software for automatic detection and extraction of brain tumors using ITK, VTK, QtResearch and development of SPECT and SPECT CT images segmentation software for automatic detection and extraction of brain tumors using ITK, VTK, Qt
MINISTRY OF EDUCATION AND TRAINING VIETNAM ACADEMY OF SCIENCE AND TECHNOLOGY GRADUATE UNIVERSITY OF SCIENCE AND TECHNOLOGY - Ho Thi Thao RESEARCH AND DEVELOPMENT OF SPECT AND SPECT/CT IMAGES SEGMENTATION SOFTWARE FOR AUTOMATIC DETECTION AND EXTRACTION OF BRAIN TUMORS USING ITK, VTK, QT MASTER THESIS: ATOMIC AND NUCLEAR PHYSICS Hanoi - 2019 MINISTRY OF EDUCATION AND TRAINING VIETNAM ACADEMY OF SCIENCE AND TECHNOLOGY GRADUATE UNIVERSITY OF SCIENCE AND TECHNOLOGY - Ho Thi Thao RESEARCH AND DEVELOPMENT OF SPECT AND SPECT/CT IMAGES SEGMENTATION SOFTWARE FOR AUTOMATIC DETECTION AND EXTRACTION OF BRAIN TUMORS USING ITK, VTK, QT Major: Atomic and nuclear physics Code: 60440106 MASTER THESIS: ATOMIC AND NUCLEAR PHYSICS SUPERVISORS: Dr Phan Viet Cuong MSc Le Tuan Anh Hanoi - 2019 i Confirmation This thesis was written on the basic of my research works carries out at Institute of Physics, Vietnam Academy of Science and Technology under the supervision of Dr Phan Viet Cuong and MSc Le Tuan Anh All results of other authors that are used in this thesis are cited correctly April 20, 2018 The author Ho Thi Thao ii Acknowledgements I would like to express my gratitude to all people who have helped and inspired me during my study This thesis would not have been possible without those supports from many people First of all, I would like to thank my teachers, Dr Phan Viet Cuong and MSc Le Tuan Anh, Research and Development Center for Radiation technology, Vietnam Atomic Energy Institute, for giving me the opportunity to within their group, for their guidance, support and constant encouragement during the entire period of preparation of this thesis They had often pointed out the incompleteness of my work and helped me to improve my understandings on each problem They taught me a lot about nuclear physics, nuclear medicine, coding and all academic and non-academic matters I have been extremely lucky to have supervisors who cared so much about my work, my study and who responded to my questions and queries so promptly I have learned a lot of things from them, and more importantly they showed me that everything can be done, just keep hard working, keep big dream, keep big courage, keep going on, day by day In addition, I would also like to thank all the members at Center for Nuclear physics, Institute of Physics, Vietnam Academy of Science and Technology, for providing the best possible environment for us to study and research Finally, I would like to thank Mom, Dad, my brother, for their constant love and support My sister has helped me to diminish the fact of being away from home by the long telephone calls spent laughing I would also like to thank my friends, Luan, Ha, my sister, Tan,… made my time at VAST a lot more fun To everybody else who accompanied me throughout my time as a student: Thank you! Ho Thi Thao iii Abstract Digital Imaging and Communications in Medicine (DICOM) exists as a standard for handling, storing, printing, and transmitting information in medical imaging The DICOM files include not only the information of images, but also contain a lot of medical-related information Reading and Process an image in DICOM format is an important issue for further image processing and visualization In the field of medical image processing, detection of brain tumor from computed tomography (CT), magnetic resonance (MRI), positron emission tomography (PET) or single-photon emission computed tomography (SPECT) is a difficult task due to complexity of the brain hence it is one of the top priority goals In this thesis, the author describes a new method which combines four different steps including smoothing, Sobel edge detection, connected component and finally region growing algorithms for locating and extracting the various lesions in the brain The computational algorithm was implemented by INMOFEVV a new software which combines Insight Toolkit (ITK) to process input image, Visualization Toolkit (VTK) to display and Qt software development framework to build user interface The main function of software includes reading and displaying DICOM images as well as performing advanced image processing It helps to improve quality and efficiency of the diseases diagnosis The analysis results indicate that the proposed method automatically and efficiently detected the tumor region from brain medical images It is very clear for physicians to separate the abnormal from the normal surrounding tissue to get a real identification of related area; improving quality and accuracy of diagnosis, which would help to increase success possibility in treatment by early detection of tumor as well as reducing surgical planning time Key Words: DICOM, Image Processing, ITK, VTK, QT ix x Table of contents Acknowledgements iii Abstract ix Table of contents x Index of figures xii List of acnonyms xvi INTRODUTION CHAPER OVERVIEW 1.1 INTERACTION OF RADIATION WITH MATTER 1.1.1 Interaction of photons with matter 1.1.1.1 Types of photon interactions in matter 1.1.1.2 Attenuation of photons in matter 1.1.2 Interaction of charged particles with matter 1.2 SINGLE PHOTON EMISSION COMPUTED TOMOGRAPHY AND COMPUTED TOMOGRAPHY 1.2.1 Single-photon Emission Computed Tomography 1.2.1.1 Gamma camera 1.2.1.2 Single photon emission computed tomography (SPECT) 15 1.2.2 Computed tomography 18 1.2.3 Hybrid Imaging System: SPECT/CT 23 CHAPTER EXPERIMETAL AND METHODOLOGY 27 2.1 DICOM 27 2.1.1 DICOM image 27 2.1.2 DICOM Information Model 27 2.2 RECONSTRUCTION 28 2.2.1 Iterative Reconstruction Method 29 2.2.2 Filtered Backprojection Method (FBP) 29 2.2.3 Filtering 30 2.3 TECHNOLOGIES 30 2.3.1 Build System - CMake 30 2.3.2 Source Code Libraries 31 2.3.3 Database 31 2.4 INITIAL RESULTS OF INMOFEVV SOFTWARE 32 2.4.1 Fusion images 32 xi 2.4.3 Surface and volume rendering 34 2.4.4 Filters 35 2.5.1 General description of proposed method 38 2.5.2 Preprocessing: Mean filter 41 2.5.2.1 Factors affecting image quality CT, MRI scan 41 2.5.2.2 Mean filter 42 2.5.3 Sobel edge detection 42 2.5.4 Segmentation 43 2.5.4.1 Connected Component Labeling 43 2.5.4.2 Region growing by Confidence Connected 44 3.1 CHOOSING SUITABLE FILTER FILTER FOR PREPROCESSING STEP 47 3.2 CHOOSING SUITABLE METHOD FOR EDGE DETECTION STEP 50 3.3 APPLYING PROPOSED METHOD FOR PHANTOM GAMEX 463 50 3.3.1 Method and test results on phantom 51 3.3.2 Result evaluation 57 3.4 APPLYING PROPOSED METHOD FOR BRAIN IMAGES 59 CONCLUSIONS 67 REFERENCES 69 xii Index of figures Figure 1.1 Predominant types of interaction for a range of incident photon energies and absorber atomic numbers Figure 1.2 Attenuation Figure 1.3 Penetrating and nonpenetraiting radiation Figure 1.4 Components of a standard nuclear medicine imaging system Figure 1.5 Collimator detail 10 Figure 1.6 Scintillation crystal A sodium iodide crystal ―doped‖ with a thallium impurity is used to convert gamma photons into light photons 11 Figure 1.7 Sodium iodide crystal scintillation detector 13 Figure 1.8 Photomultiplier tube and its preamplifer and amplifer 13 Figure 1.9 The positioning algorithm improves image resolution 14 Figure 1.10 Small matrix 16 Figure 1.11 Storing image data in a matrix 16 Figure 1.12 SPECT camera 17 Figure 1.13 Three-headed SPECT camera 17 Figure 1.14 Confgurations of two-headed SPECT camera 17 Figure 1.15 (A.) Slices through the level of the heart from selected projection views are stacked to create a sinogram (B) Complete sinogram 19 Figure 1.16 Basic components of one type of CT scanner, containing a stationary detector ring and rotating inner X-ray tube 20 Figure 1.17 Rotate–stationary configuration A rotating source and collimator generate a fan-shaped X-ray beam that is directed toward a stationary ring of detectors 20 Figure 1.18 Rotate–rotate configuration The opposing source and detector rotate synchronously 20 xiii Figure 1.19 Multislice CT detector array composed of multiple rows of detectors placed side by side along the z-axis 21 Figure 1.120 SPECT-CT (a) Two-gantry system with CT system contained within one gantry and SPECT heads supported on a second gantry; (b) Single-gantry system with one gantry supporting both the SPECT camera heads and an X-ray tube and detector 26 Figure 2.1 DICOM Information Object Definition (IOD) of a patient 28 Figure 2.2 Projection views of a liver are backprojected to create transaxial slices 29 Figure 2.3 Star artifact and backprojection ―blur‖ artifact 30 Figure 2.4 Interface of image processing software 32 Figure 2.5 Fusion result of CT and SPECT image (a,b,c) and SPECT/CT (d) obtained from machine of 108 Central Military Hospital 33 This is the original fusion result of INMOFEVV software The correct SPECT/CT image must be captured at the same time DICOM images obtained from devices must be the same size, recorded time,… Overcoming the disadvantages of fusionimages from any two devices: time, dose projection, shooting angle,… is a big challenge for image reconstrution algorithms 34 Figure 2.6 Multiplanar reconstruction a, brain image; b, abdominal image 34 Figure 2.7 3D visualization results 35 Figure 2.8 Some filters are often used 36 Figure 2.9 The distribution of contour lines 37 Figure 2.10 Flowchart of the proposed method 39 Figure 2.11 Proposed image segmentation algorithm 40 Figure 2.12 Sobel edge detection algorithm 43 Figure 3.1 The graph shows the change of area by threshold 57 Figure 3.2 Three regions are extracted corresponding to the selected seed points of Gamex phantom 58 xiv Figure 3.3 Raw input images 60 Figure 3.4 Preprocessing mean filter 60 Figure 3.5 Sobel edge detection 60 Figure 3.6 Connected component without using Sobel 62 Figure 3.7 Connected component using Sobel 62 Figure 3.8 Segmented images after using region growing 63 Figure 3.9 The results of extracting large and small brain tumors use the proposed segmentation method on MRI images 65 Figure 3.10 The results of extracting large and small brain tumors use the proposed fragmentation method on lung images 65 58 surrounding areas In particular, with a threshold value of 15, the boundary of the soft tissue hole is clear, smooth and unaffected by noise - With threshold value of 31 to 143: only holes corresponding to air and bone are detected - With a threshold value of 144 to 221: only one hole corresponding to air is detected - And with a threshold value of 222 or higher: no holes are detected The objects are completely submerged in the background From the results of Figure 3.1 and Table 3.3 on Gamex phantom, with the threshold value of 15 is the optimal threshold position with all minsize values This is a reliable threshold for extracting results of phantom in accordance with the actual standard area The result of this threshold value is also used for segmentation with clinical images The result of seed point value to determine the range of tumor extract were calculated as Figure 3.2 and Table 3.4 Phantom Gamex (297,145) (328,227) (291,307) Figure 3.2 Three regions are extracted corresponding to the selected seed points of Gamex phantom 59 Table 3.4 Results of seed points, area of round holes extracted within the threshold of 15 Seed point d(mm) R (mm) d(px) S(px2) (297,145) 28.96 14.48 108.72 9284 (328,227) 29.07 14.54 109.87 9480 (291,307) 28.85 14.43 107.91 9146 The results of the three areas on the phantom are 9284 pixels 2, 9480 pixels2, and 9146 pixels2, roughly the same as the area recorded on the phantom 9113 pixels2 Accurate rates are 98.12%, 95.96% and 99.64%, respectively Calculate the area of the extracted object as a round hole with a diameter of 28.5 mm and a index of 122 HU The background object is water with HU index The low HU difference is close to the brain tissue 3.4 APPLYING PROPOSED METHOD FOR BRAIN IMAGES Brain images containing tumors are soft tissues with a small HU index Comparing with the phantom standard model, select the hole with the index is the soft tissue as a reference to perform segmentation and extract the object of interest The procedure is applied to the brain CT, MRI images, with different tumor sites Author collected this experimentation DICOM (Digital Imaging and Communications in Medicine) from hospitals in Vietnam and from the Brain Web dataset [33] The threshold value of 15 (Minsize of 20) is chosen as the optimal index for segmentation for brain images In this thesis, author show typical results from four images corresponding to four patients (Figure 3.3) Firstly, the image eliminates the noise obtained after applying the mean filter as shown in Figure 3.4 As can see from Table 3.5, LoG algorithm uses the second derivative and Laplacian filter detects smooth edges However, it cannot find edge direction and cause deviations in angles of varying intensity This is the reason for losing important structures and features in the image Creating fake 60 borders is the main weakness of finding Canny margins With Sobel edge detection, it is possible to preserve the fine edge details in low contrast areas Use Sobel edge detection to make the edges sharp, smooth and thin The margins are unclear leading to areas that are not distinguished In order to compare these edges, we need to link the components together a b c Figure 3.3 Raw input images d a b c Figure 3.4 Preprocessing mean filter d a, b c Figure 3.5 Sobel edge detection d 61 Table 3.5 Results of evaluation of MSE and PSNR indicators for edge detection methods MSE Images PSNR Canny Sobel LoG Canny Sobel LoG 11444.23 8608.79 11730.91 7.54 8.78 7.44 6972.22 3951.77 8161.47 9.70 12.16 9.01 8223.38 3784.56 9411.21 8.98 12.35 8.39 9811.84 6920.64 7471.96 8.21 9.73 9.40 Mean smoothing increases the quality of the original image Sobel changes the pixel intensity distribution, improving signal-to-noise ratio, and enhancing visibility the ROI‘s edges We can see the edge markers is necessary for each ROI and background in medical image processing The markers computation was done by using the Sobel edge detection operation technique to clean up the image and removing the small blemishes without affecting the overall shape of the segmented objects (Figure 3.5) Making markers for background and ROI by Connected Component filter and output colored segmented image without calculating the gradient magnitude (Figure 3.6) Making markers for background and ROI by Connected Component filter, output colored segmented image, and calculate the gradient magnitude (Figure 3.7) It depends on the change in the gray scale of the area of interest that the threshold value changes accordingly The algorithm determines the number of suspected areas automatically and quantifies them The threshold selection problem is solved by maximizing 62 the number of components connected to that threshold We can see from the results of phantom analysis: the number of connected components is a threshold-dependent function If the threshold is set too low, the objects are over-detected Conversely, if the threshold is too high, the area of interest will be submerged in the background The tumor of the clinical image is clearly visible, shown in white This part has the highest intensity compared to other areas of the image Finally, the location of the tumor area was determined based on the pixel value of the tumor region a b c d Figure 3.6 Connected component without using Sobel a b c Figure 3.7 Connected component using Sobel d 63 a b c d Figure 3.8 Segmented images after using region growing The size of the square region set by the size of smallest tumor The small sub regions are used and the image is divided into small sub regions Therefore it shows all types of nodules (large, small and medium size).The proposed is an automatic method and detected all of the nodules without human interference Median filter can remove noise without corruption of edges and local details of each image However, Sobel mask can be changed and author can use some other mask such as Prewitt or Robert mask Some other methods have high computational complexity and it is not necessary to used them Author used some traditional preprocessing such as our references, especially Sobel method After applying the connected component filter, comparing figures 3.6 and 3.7, corresponding to using and without using Sobel edge detection algorithm The results showed a clear effect in distinguishing lesions and surrounding areas: gray matter, white matter, and background are being completely segmented After connected component, apply confidence connected transform, and author gained the region of interest from brain images in figure 3.8 The tumor portion of the MRI image is visible, shown as white color This section has the highest intensity compared to other areas of the image Finally, the location of the tumor region has been determined based on pixel value of the tumor region 64 A small threshold value is needed to not miss suspicious objects including small tumors From the analysis results for phantom, we can see: - The small threshold value, the greater the level of detailed segmentation, for Gamex phantom image, the objects of interest were clear But for complex medical images, it was necessary to choose the value optimal threshold for extracting objects accurately in size - The tumor in Figure 3.8a, 3.8b, 3.8c, 3.8d with the optimal threshold value is 15 corresponding to the threshold value of the hole (soft tissue) of the phantom The area of the tumor was calculated and compared with the results of the Slicer3D software, the accuracy shown in Table 3.6 Table 3.6 Area of the extracted tumor Images Original size (pixel) Area in pixel Area of tumor Accuracy (%) Image 205 x 246 50430 10174 96.34 Image 409 x 537 219633 32829 95.75 Image 480 x 480 230400 1552 95.32 Image 441 x 521 229761 9257 91.39 The proposed segmentation algorithm is also tested to locate and extract tumors of different sizes, the results shown in Figure 3.9 Another result using the proposed seggmentation algorithm to extract lung tumors is also shown in Figure 3.10 65 a, MRI image with b, extract large tumors tumor c, extract small tumor Figure 3.9 The results of extracting large and small brain tumors use the proposed segmentation method on MRI images a, Lung image with locations b, Extract the first tumor (red) suspected of tumor being marked c, Extract the second tumor (red) d, Extract the third tumor (green) Figure 3.10 The results of extracting large and small brain tumors use the proposed fragmentation method on lung images 66 Table 3.7 Results of brain tumor extraction (1, 2, 3, 4, 5) and lung tumor (6), tumor in liver (7) and extraction of interest area of region growing method No Image Confident connectecd No Image Confident connectecd 238-137 217-427 99-354 196-202 307-391 By experimenting on phantom samples and clinical medical images, the results obtained are highly accurate > 95.96% This is a very useful result to distinguish abnormal areas for brain images with many purposes in surgery or treatment 67 CONCLUSIONS Medical Image Processing plays an important role in diagnosis and it has been useful in many clinical applications The difficulty in brain tumors segmentation lies in their irregularities in terms of shape, size, and location Assisted diagnostic tools need to have high sensitivity with the ability to efficiently detect brain tumors Moreover, computer-assisted or aided diagnostic tools necessarily need to have high-speed processing rate coupled with high level of automation requiring minimal intervention The purpose of this work is to separate the tumor region from the surrounding tissue by defining the boundaries between the regions All that assist the surgeon and physician to diagnose the infected area or remove the tumor from the brain without damaging the surrounded tissue An automated algorithm based on regional development is proposed and verified in this study Experimental results have confirmed its good performance in CT and MRI image segmentation Using ITK and VTK, the author showed the combination of edge and region growing algorithms are effective methods for brain image segmentation development of the software to read DICOM images of planar images and SPECT images Certainly, medical image processing and analysis is a vast field This thesis serves only as a stepping stone or beginning which is more or less like initial exploration and map construction with much details to be further explored later on In the future, we will focus on studying new algorithms more optimally and finishing the INMOFEVV software with featuring enhancement, segmentation, 3D reconstruction obtained from different medical equipment 68 The related publication Ha Quang Thanh, Phan Viet Cuong, Ho Thi Thao, Le Tuan Anh, Nguyen Hong Ha, ―Edge detection technoques for medical image processing using a new tool – INMOFEVV‖, Jounal of Military Science and Technology, No 55, (2018), pp.76-85 Ha Quang Thanh, Phan Viet Cuong, Ho Thi Thao, Le Tuan Anh, Nguyen Hong Ha, ―Brain tumor detection and segmentation using edge and region growing method‖, Jounal of Military Science and Technology, No 56, (2018), pp.115-125 69 REFERENCES [1] Grau V., Mewes A.U.J., Alcasiz M., Improved Watershed Transform for Medical Image Segmentation Using Prior Information, IEEE Transactions On Medical Imaging, 2004, 23, pp 447–458 [2] Biji C.L., Selvathi D., Panicker A., 2011, Tumor detection in brain magnetic resonance images using modified thresholding techniques, Communications in Computer and Information Sicence, 4, pp 300–308 [3] Bhattacharyya D., Kim T.H., 2011, Brain tumor detection using MRI image analysis, Communications in Computer and Information Science, 151, pp 307–314 [4] Anam M., Ali J., Tehseen F., 2012, An Efficient Brain Tumor Detection Algorithm using Watershed and Thresholding Based Segmentation, International Journal Image, Graphics and Signal Processing, 10, pp 34–39 [5] Christ M.C.J., Parvathi R.M.S., 2011, Segmentation of Medical Image using Clustering and Watershed Algorithms, American Journal of Applied Sciences, 8, pp 1349–1352 [6] Ahmed M.M., Mohamad D.B., 2014, Segmentation of Brain MR Images for Tumor Extraction by Combining K-means Clustering and Perona-Malik Anisotropic Diffusion model, International Journal of Image Processing, 2, pp 27–34 [7] Johnson H.J., McCormick M.M., Ibanez L., 2017, The ITK Software Guide, https://itk.org/ItkSoftwareGuide.pdf, Chapter 4, pp 79–82, pp 343–358 [8] Reinhard R Beichel Markus Van Tol Ethan J Ulrich Christian Bauer Tangel Chang Kristin A Plichta Brian J Smith John J Sunderland Michael M Graham Milan Sonka John M Buatti, 2016, Semiautomated segmentation of head and neck cancers in 18F‐FDG PET scans: A just‐enough‐interaction approach, Medical Physics, 43(6), pp.2948-2964 70 [9] Waldo Valenzuel, Peter Vermathen, Chris Boesch, Lutz Nolte1, Mauricio Reyes, (2013), ―iSix - Image Segmentation in Osirix‖, Conference: 30th Annual Scientific Meeting of the European Society for Magnetic Resonance in Medicine and Biology, 30, pp.697 [10] Shapiro J., 2002, Radiation Protection A Guide for Scientists, Regulators, and Physicians, 4th edn Cambridge, MA: Harvard University Press, pp 42, 53 [11] Rachel A Powsner, Matthew R Palmer, and Edward R Powsner, 2013, Essentials of Nuclear Medicine Physics and Instrumentation, 3rd Ed., pp 73100, 119-131, 134-158 [12] Mettler FA, Upton AC., 2008, Medical Effects of Ionizing Radiation, 3rd edn Philadelphia: W.B Saunders, Chapter [13] Soloviev V, Ilyin L, Baranov A, Guskova A, Nadejina NM., 2001, Radiation accidents in the former U.S.S.R In: Gusev IA, Guskova AK, Mettler FA (eds.) Medical Management of Radiation Accidents, 2nd edn Boca Raton, FL: CRC Press, pp 157–165 [14] Wernick MN, Aarsvold JN., 2004, Emission Tomography: The Fundamentals of PET and SPECT London: Elsevier [15] Goldman LW., 2007, Principles of CT and CT technology, J Nucl Med Technol, 35, pp 115–128 [16] Goldman LW., 2008, Principles of CT: Multislice CT, J Nucl Med Technol, 36, pp 57–68 [17] Pianykh OS., 2010, Digital Imaging and Communications in Medicine (DICOM): A Practical Introduction and Survival Guide, Springer [18] NEMA Medical Imaging and Technology Alliance Resource page: http://medical.nema.org/ [19] Maria H L., Hanna P.B., Krzysztof S., Jacek I., Maria L., Maria C., Marek O., Bozena B., Przemyslaw M., 2018, CT–SPECT Analyzer - A Tool for CT and 71 SPECT Data Fusion and Volumetric Visualization, Image Processing and Communications Challenges 9, Advances in Intelligent Systems and Computing 681, Springer [20] S Nagabhushana, 2005, Computer Vision and Image Processing, New Age International Publishers, pp 73–202 [21] C P Behrenbruch, S Petroudi, S Bond, I, D Declerck, F J Leong, J M Brady, 2004, Image filtering techniques for medical image post-processing: an overview, The British Journal of Radiology, 77, pp 126-132 [22] R.Merjulah, Chandra J., 2017, Segmentation Technique for Medical Image Processing: A Survey, Proceedings of the International Conference on Inventive Computing and Informatics, IEEE Xplore Compliant, pp 1055-1061 [23] Lim K.O., Pfefferbaum A, 1989, Segmentation of MR brain images into cerebrospinal fluid spaces, white and gray matter, Journal of Computer Assisted Tomography, 13, pp 588–593 [24] Mokheld, S.A., 2012, Lung Cancer Detection Using Image Processing Techniques, Leonardo Electronic Journal of Practices and Technologies, 20, pp 147-158 [25] Katrien V., Dirk R., Van B., and Zwi N.B, 2003, The cell cycle, a review of regulation, deregulation and therapeutic targets in cancer, Black well Publishing, 36, pp 131-149 [26] M C de Andrade, 2004, An Interactive Algorithm for Image Smoothing and Segmentation‖, Electronic Letters on Computer Vision and Image Analysis, 4(1), pp 32-48 [27] Sharma D., Jindal G., 2011, Computer Aided Diagnosis System for Detection of Lung Cancer in CT Scan Images, International Journal of Computer and Electrical Engineering, 3, pp 714–718 72 [28] Mehena J., 2013, Medical Image edge detection based on mathematical morphology, International Journal of Computer and communication technology, 2, pp 49–53 [29] Xu.P, Miao Q., Shi C., Zhang J., Yang M., 2012, General method for edge detection based on the shear transform, IET Image Processing, 6, pp 839– 853 [30] T Shraddha, K Krishna, B.K.Singh and R P Singh, 2012, Image Segmentation: A Review, International Journal of Computer Science and Management Research, 1(4) [31] W X Kang, Q Q Yang and R R Liang, 2009, The Comparative Research on Image Segmentation Algorithms, IEEE Conference on Education Technology and Computer Science, pp 703-707 [32] Ha Quang Thanh, Ho Thi Thao, Le Tuan Anh, Phan Viet Cuong, Nguyen Hong Ha, 2018, Edge detection techniques for medical image processing using a new tool- INMOFEVV, Journal of Military Science and Technology, 55, pp 76-85 [33] Brain web: http://brainweb.bic.mni.mcgill.ca/cgi/brainweb1 ... SPECT/ CT IMAGES SEGMENTATION SOFTWARE FOR AUTOMATIC DETECTION AND EXTRACTION OF BRAIN TUMORS USING ITK, VTK, QT Major: Atomic and nuclear physics Code: 60440106 MASTER THESIS: ATOMIC AND NUCLEAR...MINISTRY OF EDUCATION AND TRAINING VIETNAM ACADEMY OF SCIENCE AND TECHNOLOGY GRADUATE UNIVERSITY OF SCIENCE AND TECHNOLOGY - Ho Thi Thao RESEARCH AND DEVELOPMENT OF SPECT AND SPECT/ CT IMAGES. .. backprojection ―blur‖ artifact 30 Figure 2.4 Interface of image processing software 32 Figure 2.5 Fusion result of CT and SPECT image (a,b,c) and SPECT/ CT (d) obtained from machine of 108 Central