نوع مقاله: مقاله کامل پژوهشی

نویسندگان

1 دانشجوی دکتری مهندسی پزشکی، آزمایشگاه کنترل و پردازش تصویر هوشمند، دانشکده‌ی مهندسی کامپیوتر و برق، دانشگاه تهران، تهران، ایران

2 استاد، گروه بیوالکتریک، آزمایشگاه کنترل و پردازش تصویر هوشمند، دانشکده‌ی مهندسی کامپیوتر و برق، دانشگاه تهران، تهران، ایران

چکیده

کمی­سازی و مدل­سازی ماهیچه­های اسکلتی می­تواند به بررسی بیماری­های مربوط به ماهیچه، مشکلات حرکتی خاص و شبیه­سازی­های مورد نیاز برای انجام جراحی­های مربوطه کمک نماید. بدین منظور به بخش­بندی ماهیچه­ها در تصاویر پزشکی نیاز است. با توجه به اهمیت ماهیچه­های مقطع ران در حفظ تعادل بدن و راه رفتن، در این پژوهش بخش­بندی این ماهیچه­ها در تصاویر سی­تی­اسکن انجام شده که برای این منظور از روش چنداطلس (بهبود یافته‌ی روش چنداطلس سلسله‌مراتبی در مطالعه‌ی قبلی نویسندگان) استفاده شده است. در این روش پس از پیش­پردازش تصویر، ناحیه‌ی مربوط به ماهیچه از سایر بافت­ها با استفاده از روش FRFCM به صورت اتوماتیک استخراج شده و از ماسک باینری ماهیچه و ماسک ماهیچه‌ی بهبود یافته در روش چنداطلس برای بخش­بندی مجزای ماهیچه­ها استفاده شده است. روش پیشنهادی با استفاده از 20 مجموعه‌ی داده‌ی سی­تی­اسکن شامل 12 نمونه‌ی زن و 8 نمونه‌ی مرد پیاده­سازی شده است. این روش در مقایسه با روش چنداطلس سلسله‌مراتبی هزینه‌ی محاسباتی بسیار کم‌تری دارد. به طور میانگین، زمان مورد نیاز برای بخش­بندی ماهیچه­ها با استفاده از روش پیشنهادی و روش چنداطلس سلسله‌مراتبی به ترتیب برابر با 24 و 71 ثانیه برای یک اسلایس از هر نمونه بوده و بنابراین روش پیشنهادی زمان پیاده­سازی را تقریبا تا یک‌سوم روش قبل کاهش داده است. میانگین ضریب شباهت دایس برای روش پیشنهادی با ماسک ماهیچه‌ی بهبود یافته و روش چنداطلس سلسله‌مراتبی به ترتیب برابر با 69/7±58/86 و 26/8±07/83 بوده و میانگین دقت و حساسیت برای روش پیشنهادی برابر با 6/9±78/89 و 25/9±63/84 و برای روش چنداطلس سلسله‌مراتبی برابر با 04/12±85/88 و 88/10±04/78 می‌باشد. بنابراین بر اساس معیارهای ضریب شباهت دایس، دقت و حساسیت روش پیشنهادی نتایج کمی بهتری نسبت به روش پیشین داشته است. 

کلیدواژه‌ها

عنوان مقاله [English]

Automated Thigh Muscles Segmentation using Hierarchical Multi-Atlas and FRFCM Methods in CT Scan Images

نویسندگان [English]

  • Malihe Molaie 1
  • Reza Aghaeizadeh Zoroofi 2

1 Ph.D. Student, Control and Intelligent Processing Center of Excellence, School of Electrical and Computer Engineering, University of Tehran, Tehran, Iran

2 Professor, Control and Intelligent Processing Center of Excellence, School of Electrical and Computer Engineering, University of Tehran, Tehran, Iran

چکیده [English]

Quantifying and modeling of the skeletal muscles can lead to an easier investigation of muscle diseases, specific mobility problems, and required simulations for the relevant surgeries. To this end, medical images should be segmented, firstly. In this research, thigh muscles segmentation is performed in CT images, since these muscles play a critical role in walking and balancing the body. To this aim, a multi-atlas method is used which is an improvement of the hierarchical multi-atlas method in the previous work. In this method, the muscles region is extracted automatically from the other tissues using FRFCM (Fast and Robust Fuzzy C-Means Clustering) method after the preprocessing stage. This muscle binary mask and the improved mask are used in the multi-atlas method for individual muscle segmentation. The proposed method is implemented using 20 CT data sets consisting of 12 female and 8 male subjects. The results show a less consumed computational time than the hierarchical multi-atlas method. The average computational time required for the muscles segmentation using the proposed method is 24 seconds and for the hierarchical multi-atlas method is 71 seconds per one slice of each case. Therefore, the proposed method reduces the implementation time by a rough factor of three.  The means of the Dice similarity coefficient for the proposed method with improved muscle mask and for the hierarchical multi-atlas method are 86.58±7.69 and 83.07±8.26, respectively.  The means of the precision and sensitivity for our method are 89.78±9.6 and 84.63±9.25, and for the hierarchical multi-atlas method are 88.85±12.04 and 78.04±10.88. Consequently, this method has better results based on the Dice similarity coefficient, precision, and sensitivity metrics.

کلیدواژه‌ها [English]

  • Concurrent segmentation
  • Thigh muscles
  • Multi-atlas method
  • FRFCM
  • CT scan images

[1]   J. Seymour et al., "The prevalence of quadriceps weakness in COPD and the relationship with disease severity," European Respiratory Journal, vol. 36, no. 1, pp. 81-88, 2010.

[2]   M. M. McDermott et al., "Pathophysiological changes in calf muscle predict mobility loss at 2-year follow-up in men and women with peripheral arterial disease," Circulation, vol. 120, no. 12, pp. 1048-1055, 2009.

[3]   A. E. Emery, "The muscular dystrophies," The Lancet, vol. 359, no. 9307, pp. 687-695, 2002.

[4]   K. Uemura, M. Takao, T. Sakai, T. Nishii, and N. Sugano, "Volume increases of the gluteus maximus, gluteus medius, and thigh muscles after hip arthroplasty," The Journal of arthroplasty, vol. 31, no. 4, pp. 906-912. e1, 2016.

[5]   S. Orgiu, C. L. Lafortuna, F. Rastelli, M. Cadioli, A. Falini, and G. Rizzo, "Automatic muscle and fat segmentation in the thigh from T1‐Weighted MRI," Journal of Magnetic Resonance Imaging, vol. 43, no. 3, pp. 601-610, 2016.

[6]   C. Tan et al., "An automated and robust framework for quantification of muscle and fat in the thigh," in Pattern Recognition (ICPR), 2014 22nd International Conference on, 2014, pp. 3173-3178: IEEE.

[7]   E. Ahmad, M. H. Yap, H. Degens, and J. S. McPhee, "Atlas-registration based image segmentation of MRI human thigh muscles in 3D space," in Medical Imaging 2014: Image Perception, Observer Performance, and Technology Assessment, 2014, vol. 9037, p. 90371L: International Society for Optics and Photonics.

[8]   A. Karlsson et al., "Automatic and quantitative assessment of regional muscle volume by multi‐atlas segmentation using whole‐body water–fat MRI," Journal of Magnetic Resonance Imaging, vol. 41, no. 6, pp. 1558-1569, 2015.

[9]   F. Yokota, "Automated muscle segmentation from 3D CT data of the hip using a hierarchical multi-atlas method," in 12th annual meeting of CAOS-international proceedings, 2012, pp. 30-32.

[10]F. Yokota et al., "Automated muscle segmentation from CT images of the hip and thigh using a hierarchical multi-atlas method," International journal of computer assisted radiology and surgery, pp. 1-10, 2018.

[11]S. Andrews and G. Hamarneh, "The generalized log-ratio transformation: learning shape and adjacency priors for simultaneous thigh muscle segmentation," IEEE transactions on medical imaging, vol. 34, no. 9, pp. 1773-1787, 2015.

[12]S. Andrews, G. Hamarneh, A. Yazdanpanah, B. HajGhanbari, and W. D. Reid, "Probabilistic multi-shape segmentation of knee extensor and flexor muscles," in International Conference on Medical Image Computing and Computer-Assisted Intervention, 2011, pp. 651-658: Springer.

[13]E. Jolivet et al., "Skeletal muscle segmentation from MRI dataset using a model-based approach," Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization 2, no. 3, pp. 138-145, 2014.

[14]P.-Y. Baudin, N. Azzabou, P. G. Carlier, and N. Paragios, "Automatic skeletal muscle segmentation through random walks and graph-based seed placement," in Biomedical Imaging (ISBI), 2012 9th IEEE International Symposium on, 2012, pp.   1036-1039: IEEE.

[15]P.-Y. Baudin, N. Azzabou, P. G. Carlier, and N. Paragios, "Prior knowledge, random walks and human skeletal muscle segmentation," In International Conference on Medical Image Computing and Computer-assisted Intervention, pp. 569-576. Springer, Berlin, Heidelberg, 2012.

[16]A. Le Troter et al., "Volume measurements of individual muscles in human quadriceps femoris using atlas-based segmentation approaches," Magnetic Resonance Materials in Physics, Biology and Medicine, vol. 29, no. 2, pp. 245-257, 2016.

[17]J. Kemnitz et al., "Validation of an active shape model-based semi-automated segmentation algorithm for the analysis of thigh muscle and adipose tissue cross-sectional areas," Magnetic Resonance Materials in Physics, Biology and Medicine, vol. 30, no. 5, pp. 489-503, 2017.

[18]J. Kemnitz et al., "Validation of a 3D thigh muscle and adipose tissue segmentation method using statistical shape models," Osteoarthritis and Cartilage, vol. 26, pp. S457-S458, 2018.

[19]J. W. Prescott, T. M. Best, M. S. Swanson, F. Haq, R. D. Jackson, and M. N. Gurcan, "Anatomically anchored template-based level set segmentation: application to quadriceps muscles in MR images from the Osteoarthritis Initiative," Journal of digital imaging, vol. 24, no. 1, pp. 28-43, 2011.

[20]E. Blaak, "Gender differences in fat metabolism," Current Opinion in Clinical Nutrition & Metabolic Care, vol. 4, no. 6, pp. 499-502, 2001.

[21]M. Kistler, S. Bonaretti, M. Pfahrer, R. Niklaus, and P. Büchler, "The virtual skeleton database: an open access repository for biomedical research and collaboration," Journal of medical Internet research, vol. 15, no. 11, p. e245, 2013.

[22]K. Dabov, A. Foi, V. Katkovnik, and K. Egiazarian, "Joint image sharpening and denoising by 3D transform-domain collaborative filtering," in Proc. 2007 Int. TICSP Workshop Spectral Meth. Multirate Signal Process., SMMSP, 2007, vol. 2007.

[23]C. Pérez-Benito, S. Morillas, C. Jordán, and J. A. Conejero, "Smoothing vs. sharpening of colour images: Together or separated," Applied Mathematics and Nonlinear Sciences, vol. 2, no. 1, pp. 299-316, 2017.

[24]V. Katkovnik, A. Foi, and K. Egiazarian, "Advanced Image Processing Based on Spatially Adaptive Nonlocal Image Filtering and Regularization," In Image Processing (ICIP), 2010 17th IEEE International Conference on (pp. 1-296)..

[25]Y. Hou, "Nonlocal Estimation and BM3D Based Face Illumination Normalization," in International Conference on Intelligent and Interactive Systems and Applications, 2018, pp. 115-122: Springer.

[26]J. C. Bezdek, R. Ehrlich, and W. Full, "FCM: The fuzzy c-means clustering algorithm," Computers & Geosciences, vol. 10, no. 2-3, pp. 191-203, 1984.

[27]I. Isgum, M. Staring, A. Rutten, M. Prokop, M. A. Viergever, and B. Van Ginneken, "Multi-atlas-based segmentation with local decision fusion—application to cardiac and aortic segmentation in CT scans," IEEE transactions on medical imaging, vol. 28, no. 7, pp. 1000-1010, 2009.

[28]T. Lei, X. Jia, Y. Zhang, L. He, H. Meng, and A. K. Nandi, "Significantly fast and robust fuzzy c-means clustering algorithm based on morphological reconstruction and membership filtering," IEEE Transactions on Fuzzy Systems, 2018.

[29]B. Glocker, A. Sotiras, N. Komodakis, and N. Paragios, "Deformable medical image registration: setting the state of the art with discrete methods," Annual review of biomedical engineering, vol. 13, pp. 219-244, 2011.

[30]Taha and A. Hanbury, "Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool," BMC medical imaging, vol. 15, no. 1, p. 29, 2015.