MR Kafa Görüntülerinden Otomatik Kafatası, Doku ve Lezyon Bölütlemesi: Olasılıksal ve Kararlı Bir Yaklaşım

Yıl 2018, Cilt: 22 Sayı: 1, 258 - 271, 16.04.2018

Evgin Göçeri , Melih Günay , Utku Şenol

Öz

Nörodegeneratif hastalıkların teşhisinde veya tedavi sürecinde beyin dokularındaki değişim, kapladığı alan, oluşmuş ise lezyonların sayısı, konumu ve büyüklüğü gibi bilgilere ihtiyaç duyulmaktadır. Bu amaçla, kafatası, beyin dokuları ve lezyonlar tıbbi görüntülerden elcil yöntemle bölütlenmekte; bu yapıların kenarlarına, lezyonların sayı ve büyüklük değerlerine kişisel olarak karar verilmektedir. Görüntülerin görsel olarak incelenip analiz edilmesi, doktorlar için zaman alıcı, yorucu ve dikkat gerektiren bir işlemdir. Bununla birlikte, görüntüleme tekniğinden kaynaklanan gürültü ve görüntüdeki gri seviye değişimlerinin düşük olması, bu görsel analizi ve elcil yöntemle görüntü bölütlemeyi daha da zorlaştırmaktadır. Bu durum, kişisel değerlendirme sonuçlarını etkilemekte, farklı doktorların aynı görüntüde farklı kararlar vermesine, hatta aynı doktorun aynı görüntü üzerinde, farklı zamanlarda farklı kararlar vermesine sebep olabilmektedir. Bu nedenle, bu çalışmada, kafa görüntülerinden kafatası, beyin dokusu ve lezyon bölütlemesini otomatik olarak gerçekleştiren bir bilgisayar destekli yaklaşım önerilmektedir. Önerilen bütünleşik yaklaşımda, manyetik rezonans görüntüleri kullanılmış olup, kafatası ve doku bölütlemesi Gauss Karma Modele dayalı olarak olasılıksal bir yöntem ile sağlanırken, lezyon bölütlemesi düzey kümesine dayalı kararsal bir yöntem ile gerçekleştirilmiştir. Geliştirilen yazılım sayesinde, lezyon bölütleme başarıyla (maksimum simetrik yüzey uzaklığı 5.76±3.24 mm) gerçekleştirilebilmektedir.

Anahtar Kelimeler

Doku bölütlemesi, Kafa MR görüntüsü; Kafatası bölütlemesi; Kararsal yaklaşım; Olasılıksal yaklaşım; Lezyon bölütlemesi

Kaynakça

• [1] Konu:Demans,http://www.who.int/mediacentre/factsheets/fs362/en/ (Erişim Tarihi: 30.11.16)
• [2] Konu:Alzheimer,http://www.alz.org/facts/#prevalence (Erişim tarihi:30.11.2016)
• [3] Pringsheim, T., Jette, N., Frolkis, A., Steeves, T.D.L. 2014. The prevalence of Parkinson's disease: A systematic review and meta-analysis, Movement Disorders, 29(13), 1583–1590.
• [4] Filippi, M., Rocca, M.A., Ciccarelli, O., Stefano, N., Evangelou, N., Kappos, L., Rovira, A., Sastre-Garriga, J., Tintorè, M., Frederiksen, J.L., Gasperini, C., Palace, J., Reich, D.S., Banwell, B., Montalban, X., Barkhof, F. 2016. MRI criteria for the diagnosis of multiple sclerosis: MAGNIMS consensus guidelines, Lancet Neurology, 15(3), 292-303.
• [5] Uchiyama, Y., Yokoyama, R., Ando, H., Asano, T., Kato, H., Yamakawa, H., Yamakawa, H., Hara, T., Iwama, T., Hoshi, H., Fujita, H. 2007. Computer-Aided Diagnosis Scheme for Detection of Lacunar Infarcts on MR Images, Acad. Radiology, 14(1):1554–1561.
• [6] Uchiyama, Y., Asano, T., Hara, T., Fujita, H., Hoshi, H., Iwama, T., Kinosada, Y. 2009. CAD Scheme for differential diagnosis of lacunar infarcts and normal Virchow-Robin spaces on brain MR images, In: Dössel O., Schlegel W.C. (eds) World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany. IFMBE Proceedings, Springer, Berlin, Heidelberg, 25(5), 126-128.
• [7] Konu:Cyprus University, eHealth Lab. Datasets:, http://www.medinfo.cs.ucy.ac.cy/index.php/downloads/datasets (Erişim tarihi: 12.03.2016)
• [8] Schmidt, P., Gaser, C., Arsic, M., Buck D., Förschler, A., Berthele A., Hoshi, M., Ilg, R., Schmid, V.J., Zimmer, C., Hemmer, B., Mühlau, M. 2012. An automated tool for detection of FLAIR-hyperintense white-matter lesions in Multiple Sclerosis, NeuroImage, 59(1), 3774–3783
• [9] Klöppel, S., Abdulkadir, A., Hadjidemetriou, S., Issleib, S., Frings, L., Thanh, T.N., Mader, I., Teipel, S.J., Hüll, M., Ronneberger, O. 2011. A comparison of different automated methods for the detection of white matter lesions in MRI data, NeuroImage, 57(1),416–422.
• [10] Muda, A.F., Saad, N.M., Waeleh, N., Abdullah, A.R., Fen, L.Y. 2015. Integration of Fuzzy C-Means with Correlation Template and Active Contour for Brain Lesion Segmentation in Diffusion-Weighted MRI. Third International Conference on Artificial Intelligence, Modelling and Simulation, 2-4 Aralık, Malezya, 268-273.
• [11] Havaei, M., Davy, A., Warde-Farley, D., Biard, A., Courville, A., Bengio, Y., Pal, C., PJodoina, P.M., Larochelle, H. 2017. Brain tumor segmentation with Deep Neural Networks, Medical Image Analysis, 35(1), 18–31
• [12] Rathod, K.U., Kapse, Y.D. 2016. Automated Brain Tumor Detection and Brain MRI Classification Using Artificial Neural Network - A Review, International Journal of Science and Research (IJSR), 5(7), 2319-7064.
• [13] Sweeney, E.M., Vogelstein, J.T., Cuzzocreo, J.L., Calabresi, P.A., Reich, D.S., Crainiceanu, C.M., et al. 2014. A Comparison of Supervised Machine Learning Algorithms and Feature Vectors for MS Lesion Segmentation Using Multimodal Structural MRI, PLoS ONE, 9(4), e95753.
• [14] Goceri, E., Martinez, E., Gunay, M. 2016. Review on Machine Learning Based Lesion Segmentation Methods from Brain MR Images. 15th Int. Conf. on Machine Learning and Applications, 18-21 Aralık, Anaheim, California, 1-6.
• [15] Bal, U. 2012. Dual tree complex wavelet transform based denoising of optical microscopy images. Biomed. Opt. Express., 3(12), 3231–3239.
• [16] Lanza, A., Morigi, S., Sgallari, F., Wen, Y.W. 2014. Image restoration with poisson-gaussian mixed noise. Computer Methods in Biomechanic and Biomedical Engineering: Imaging & Visualization, 2(1), 12–24.
• [17] Yang, J., Fan, J., Ai, D., Wang, X., Zheng, Y., Tang, S., Wang, Y. 2016. Local statistics and non-local mean filter for speckle noise reduction in medical ultrasound image. Neurocomputing, 195(1), 88-95.
• [18] Shafiee, M.J., Haider, S.A., Wong, A., Lui, D., Cameron, A., Modhafar, A., Fieguth, P., Haider, M.A. 2015. Apparent ultra-high b-value diffusion-weighted image reconstruction via hidden conditional random fields. IEEE Trans. Med. Imag. 34(5), 1111–1124.
• [19] Jain, A.K. 1989. Fundamentals of Digital Image Processing. Prentice Hall, Upper Saddle River, NJ, USA, 569s.
• [20] Lim, J.S. 1990. Two Dimensional Signal and Image Processing, Prentice Hall, USA, 680s.
• [21] Coupe, P., Hellier, P., Kervrann, C., Barillot, C. 2009. Nonlocal means-based speckle filtering for ultrasound images. IEEE Trans. on Image Processing. 18(10), 2221-2229.
• [22] Goceri, E., Goksel, B., Elder, J.B., Puduvalli, V.K, Otero, J.J., Gurcan, M.N. 2016. Quantitative Validation of Anti‐PTBP1 Antibody for Diagnostic Neuropathology Use: Image Analysis Approach. International Journal for Numerical Methods in Biomedical Engineering, doi: 10.1002/cnm.2862.
• [23] Lillie, E.M., Urban, J.E., Weaver, A.A., Powers, A.K., Stitzel, J.D. 2015. Estimation of skull table thickness with clinical CT and validation with microCT. J. of Anatomy, 226(1), 73–80.
• [24] Atkins, M.S., Mackiewich, B.T. 1998. Fully automatic segmentation of the brain in MRI. IEEE Trans. On Medical Imaging, 17(1), 98-107.
• [25] Lemieux, L., Hagemann, G., Krakow, K., Woermann, F.G. 1999. Fast, accurate, and reproducible automatic segmentation of the brain in T1-weithed volume MRI data. Magnetic Resonance in Medicine, 42(1),127-35.
• [26] Meegama, R. G. N., Rajapakse, J. C. 2001. Fully automated peeling technique for MR head scans. In 3rd IEEE Int. Conf. on Info., Com. and Signal Proc., 15-18 Ekim, Singapore, 1.
• [27] Horst, K.H., Peitgen, H.O. 2000. The Skull Stripping Problem in MRI Solved by a Single 3D Watershed Transform. MICCAI 2000, 11-14 Ekim, Pittsburgh, Pennsylvania, USA, 134-141.
• [28] Smith, S. M. 2000. BET: brain extraction tool. FMRIB TR00SMS2b, Oxford Centre for Functional Magnetic Resonance Imaging of the Brain, Department of Clinical Neurology, Oxford University, John Radcliffe Hospital, Headington, UK, 23s.
• Dale, A.M., Fischl, B., Sereno, M.I. 1999. Cortical Surface-Based Analysis I:Segmentation and Surface Reconstruction. NeuroImage, 9(2), 179-194.
• [30] Kalavathi, P., Prasath, V.B.S. 2015. Methods on Skull Stripping of MRI Head Scan Images - A Review, Journal of Digital Imaging, 1(1), 1-15.
• [31] Vincent, L. 1993. Morphological grayscale reconstruction in image analysis: Applications and efficient algorithms. IEEE Trans. Image Process., 2 (2), 176–201.
• [32] Grana, C., Borghesani, D., Cucchiara, R. 2010. Op-timized block-based connected components labe-ling with decision trees. IEEE Trans. on Img. Proc., 19(6), 1596–1609.
• [33] McLachlan, G., Peel, D. 2000. Finite Mixture Models. John Wiley & Sons, New York, 407s.
• [34] Fraley, C., Raftery, A. E. 2002. Model-based clustering, discriminant analysis and density estimation. Jour. Am. Statist. Assoc., 1(1), 611–631.
• [35] Goceri, E., Ünlü, M.Z., Dicle, O. 2015. A Comparative Performance Evaluation of Various Approaches for Liver Segmentation from SPIR Images. The Turkish Journal of Electrical Engineering and Computer Sciences (TJEECS), 23(1), 741-768.
• [36] Goceri, E., Unlu, M.Z., Guzelis, C., Dicle, O. 2012. A Liver Segmentation Method Based on Partial Differential Equation and Signed Pressure Force Function, 17th National Biomed. Eng. Meeting Proceedings (BIYOMUT 2012), 3-5 Ekim, İstanbul, 237-240.
• [37] Goceri, E., Gurcan, M.N., Dicle, O. 2014. Fully Automated Liver Segmentation from SPIR Image Series. Computers in Biology and Medicine, 53(1), 265-278.
• [38] Kass, M., Witkin, A., Terzopoulos, D. 1987. Snakes: Active contour models, International Journal of Computer Vision, 1(1), 321–331.
• [39] Kulkarni, S., Chatterji, B.N. 2002. Accurate shape modelling with front propagation using adaptive level sets, Pattern Recognition Letters, 23(13), 1559–1568.
• [40] Osher, S., Sethian, J.A. 1988. Fronts propagating with curvature-dependent speed: Algorithms based on the Hamilton-Jacobi formulation, J.of Comp. Physics, 79(1), 12-49.
• [41] Li, C., Xu, C., Gui C., Fox, M.D. 2010. Distance Regularized Level Set Evolution and Its Application to Image Segmentation, IEEE Trans. on Image Processing, 19(12), 3243-3254.
• [42] Zhang, K., Zhang, L., Song, H., Zhou, W. 2010. Active contours with selective local or global segmentation: A new formulation and level set method, Image and Vision Computing, 28(4), 668–676.
• [43] Caselles, V., Kimmel R., Sapiro, G. 1997. Geodesic active contours, International Journal of Computer Vision, 22(1), 61–79.
• [44] Dennie, C., Thornhill, R., Sethi-Virmani, V., Souza, C. A., Bayanati, H., Gupta, A., Maziak, D. 2016. Role of quantitative computed tomography texture analysis in the differentiation of primary lung cancer and granulomatous nodules. Quantitative Imaging in Medicine and Surgery. 6(1), 6–15.
• [45] Schwier, M., Hahn, H.K., Dahmen, U., Dirsch, O. 2016. Segmentation of vessel structures in serial whole slide sections using region-based context features. Proc. SPIE 9791, Medical Imaging:Digital Pathology, 97910E.
• [46] Huang, Y. 2016. Evaluating and comparing biomarkers with respect to the area under the receiver operating characteristics curve in two-phase case–control studies, Biostatistics, 1(1), 1–24, doi:10.1093/biostatistics/kxw003, 2016