Derin öğrenme ile pencere ayarlı görüntüler kullanılarak beyin inme segmentasyon performansının geliştirilmesi

Yıl 2023, Cilt: 13 Sayı: 4, 1094 - 1109, 15.10.2023

Özlem Polat , Mustafa Said Kartal

https://doi.org/10.17714/gumusfenbil.1319024

Öz

İnme çeşitli nedenlerle beyne kan akışının yavaşladığı veya kesildiği durumlarda ortaya çıkan serebrovasküler bir sağlık sorunudur. Beyin dokusu yeterli besin ve oksijeni alamadığı için beyin hücreleri dakikalar içinde ölmeye başlar ve inmenin oluştuğu bölgedeki fonksiyonlarda geçici ya da kalıcı hasarlar meydana gelir. Beyin inmesi çok ciddi tıbbi bir durumdur ve acil müdahale gerektirmektedir. İnmenin erken tespiti ve inme bölgesinin segmente edilmesi kalıcı hasarların önlenmesi açısından büyük önem arz etmektedir. Bu çalışmada Res2Net omurgalı U-Net derin öğrenme modeli kullanılarak beyin inme segmentasyonu yapılmıştır. Veri seti olarak 1093 hemorajik ve 1130 iskemik inme tipini içeren toplamda 2223 BT görüntüsü kullanılmıştır. Görüntüler pencereleme yöntemi ile ön işlemeden geçirilip sonrasında önerilen model ile eğitilip test edilmişlerdir. Pencereleme ayarı yapılmadan kullanılan görüntülerde ortalama IoU oranı 0.82 olarak elde edilmiş, ön işlemeden sonra bu oran 0.87’ye yükselmiştir; veri çoğaltma yönteminin de uygulanmasından sonra ortalama IoU 0.92’ye ulaşmıştır. Elde edilen test sonuçları görüntülerde uygun pencere ayarlarının kullanılmasının segmentasyon performansını artırdığını göstermiştir.

Anahtar Kelimeler

Beyin inme segmentasyonu, Derin öğrenme, Görüntü pencereleme, U-Net

Improving the performance of brain stroke segmentation using window-adjusted images with deep learning

Öz

Stroke is a cerebrovascular health problem that occurs when blood flow to the brain is slowed or interrupted for various reasons. Since the brain tissue cannot receive enough nutrients and oxygen, brain cells begin to die within minutes and temporary or permanent damage occurs in the functions in the area where the stroke occurred. Brain stroke is a very serious medical condition and requires urgent intervention. Early detection of stroke and segmentation of the stroke site are of great importance in terms of preventing permanent damage. In this study, brain stroke segmentation was performed using U-Net deep learning model with Res2Net backbone. A total of 2223 CT images including 1093 hemorrhagic and 1130 ischemic stroke types were used as dataset. The images were preprocessed with the windowing method and then trained and tested with the proposed model. While the IoU rate was 0.82 in the images used without windowing adjustment, this rate increased to 0.87 after preprocessing, when the data duplication method was added, the average IoU reached 0.92. The test results obtained showed that the use of appropriate window settings in the images increased the segmentation performance.

Anahtar Kelimeler

Brain stroke segmentation, Deep learning, Image windowing, U-Net

Kaynakça

• Aboudi, F., Drissi, C., & Kraiem, T. (2022). Efficient U-Net CNN with data augmentation for MRI ischemic stroke brain segmentation. In 2022 8th IEEE International Conference on Control, Decision and Information Technologies (CoDIT) (ss. 724-728), İstanbul.
• Abuzaid, M.M., Elshami, W., Tekin, H., & Issa, B. (2021). Assessment of the willingness of radiologists and radiographers to accept the integration of artificial intelligence into radiology practice. Academic Radiology, 29(1), 87-94. https://doi.org/10.1016/j.acra.2020.09.014
• Ajam, M., Kanaan, H., Ayache, M., & el Khansa, L. (2019). Segmentation of CT brain stroke image using marker controlled watershed. In 2019 Fifth IEEE International Conference on Advances in Biomedical Engineering (ICABME) (ss. 1-4), Tripoli.
• Alhatemi, R.A.J., & Savaş, S. (2022). Transfer learning-based classification comparison of stroke. Computer Science, IDAP-2022, 192-201. https://doi.org/10.53070/bbd.1172807
• Alquhayz, H., Tufail, H. Z., & Raza, B. (2022). The multi-level classification network (MCN) with modified residual U-Net for ischemic stroke lesions segmentation from ATLAS. Computers in Biology and Medicine, 151, 106332.
• Barros, R.S., Tolhuisen, M.L., Boers, A.M., Jansen, I., Ponomareva, E., Dippel, D.W., van der Lugt, A., van Oostenbrugge, R.J., van Zwam, W.H., Berkhemer, O.A., & Goyal, M. (2020). Automatic segmentation of cerebral infarcts in follow-up computed tomography images with convolutional neural networks. Journal of NeuroInterventional Surgery, 12(9), 848-852. https://doi.org/10.1136/neurintsurg-2019-015471
• Campbell, B.C.V., De Silva, D.A., Macleod, M.R., Coutts, S.B., Schwamm, L.H., Davis, S.M., & Donnan, G.A. (2019a). Ischaemic stroke. Nature Reviews Disease Primers, 5(1), 70. https://doi.org/10.1038/s41572-019-0118-8
• Campbell, B.C.V., & Khatri, P. (2020). Stroke. The Lancet, 396, 129-142. https://doi.org/10.1016/S0140-6736(20)31179-X
• Campbell, B.C.V., Ma, H., Ringleb, P.A., Parsons, M.W., Churilov, L., Bendszus, M., Levi, C.R., Hsu, C., Kleinig, T.J., Fatar, M., Leys, D., Molina, C., Wijeratne, T., Curtze, S., Dewey, H.M., Barber, P.A., Butcher, K.S., De Silva, D.A., Bladin, C.F., Yassi, N., Pfaff, J. A. R., Sharma, G., Bivard, A., Desmond, P.M., Schwab, S., Schellinger, P.D., Yan, B., Mitchell, P.J., Serena, J., Toni, D., Thijs, V., Hacke, W., Davis, S.M., & Donnan, G.A. (2019b). Extending thrombolysis to 4·5-9 h and wake-up stroke using perfusion imaging: a systematic review and meta-analysis of individual patient data. The Lancet, 394(10193), 139-147. https://doi.org/10.1016/S0140-6736(19)31053-0
• Clèrigues, A., Valverde, S., Bernal, J., Freixenet, J., Oliver, A., & Lladó, X. (2019). Acute ischemic stroke lesion core segmentation in CT perfusion images using fully convolutional neural networks. Computers in Biology and Medicine, 115, 103487. https://doi.org/10.1016/j.compbiomed.2019.103487
• DenOtter, T.D., & Schubert, J. (2023). Hounsfield unit. [Updated 2023 Mar 6]. In: StatPearls [Internet]. Treasure Island (FL): StatPearls Publishing; 2023 Jan-. Erişim adresi: https://www.ncbi.nlm.nih.gov/books/NBK547721/
• Gao, S. H., Cheng, M. M., Zhao, K., Zhang, X. Y., Yang, M. H., & Torr, P. (2019). Res2net: A new multi-scale backbone architecture. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(2), 652-662.
• Gautam, A. & Raman, B. (2021). Towards effective classification of brain hemorrhagic and ischemic stroke using CNN. Biomedical Signal Processing and Control, 63, 102178. https://doi.org/10.1016/j.bspc.2020.102178
• GBD (Global Burden of Diseases) 2016 Stroke Collaborators, 2019, Global, regional, and national burden of stroke, 1990-2016: a systematic analysis for the Global Burden of Disease Study 2016. Lancet, Neurology, 18(5), 439–458, https://doi.org/10.1016/S1474-4422(19)30034-1
• He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (ss. 770-778), Las Vegas.
• Hollist, M., Morgan, L., Cabatbat, R., Au, K., Kirmani, M.F., & Kirmani, B.F. (2021). Acute stroke management: Overview and recent updates. Aging and Disease, 12(4), 1000-1009. https://doi.org/10.14336/AD.2021.0311
• Jung, H. (2021). Basic physical principles and clinical applications of computed tomography. Progress in Medical Physics, 32(1), 1-17.
• Karataş, A. F., Doğan, V., & Kılıç, V. (2022). Artificial Intelligence-based Cerebrovascular Disease Detection on Brain Computed Tomography Images. Avrupa Bilim ve Teknoloji Dergisi, (41), 175-182.
• Kaya, B., & Önal, M. (2023). A CNN transfer learning‐based approach for segmentation and classification of brain stroke from noncontrast CT images. International Journal of Imaging Systems and Technology.
• Koç, U., Sezer, E.A., Özkaya, Y.A., Yarbay, Y., Taydaş, O., Ayyıldız, V.A., Kızıloğlu, H.A., Kesimal, U., Çankaya, İ., Beşler, M.S., & Karakaş, E. (2022). Artificial intelligence in healthcare competition (Teknofest-2021): Stroke data set. The Eurasian Journal of Medicine, 54(3), 248. https://doi.org/10.5152/eurasianjmed.2022.22096
• Li, L., Chen, Y., Bao, Y., Jia, X., Wang, Y., Zuo, T., & Zhu, F. (2020). Comparison of the performance between Frontier ASPECTS software and different levels of radiologists on assessing CT examinations of acute ischaemic stroke patients. Clinical Radiology, 75(5), 358-365. https://doi.org/10.1016/j.crad.2019.12.010
• Lo, C.M., Hung, P.H., & Lin, D.T. (2021). Rapid assessment of acute ischemic stroke by computed tomography using deep convolutional neural networks. Journal of Digital Imaging, 34(3), 637-646. https://doi.org/10.1007/s10278-021-00457-y
• Nishio, M., Koyasu, S., Noguchi, S., Kiguchi, T., Nakatsu, K., Akasaka, T., Yamada, H., & Itoh, K. (2020). Automatic detection of acute ischemic stroke using non-contrast computed tomography and two-stage deep learning model. Computer Methods and Programs in Biomedicine, 196, 105711. https://doi.org/10.1016/j.cmpb.2020.105711
• Osborne, T., Tang, C., Sabarwal, K., & Prakash, V. (2016). How to interpret an unenhanced CT brain scan. Part 1: Basic principles of computed tomography and relevant neuroanatomy. South Sudan Medical Journal, 9(3), 67-69.
• Pulli, B., Heit, J.J., & Wintermark, M. (2021). Computed tomography-based ımaging algorithms for patient selection in acute ischemic stroke. Neuroimaging Clinics of North America, 31(2), 235-250. https://doi.org/10.1016/j.nic.2020.12.002
• Ronneberger, O., Fischer, P., & Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18 (s. 234-241). Springer International Publishing.
• Sacco, R.L., Kasner, S.E., Broderick, J.P., Caplan, L.R., Connors, J.J., Culebras, A., Elkind, M.S., George, M.G., Hamdan, A.D., Higashida, R.T., Hoh, B.L., Janis, L.S., Kase, C.S., Kleindorfer, D.O., Lee, J.M., Moseley, M.E., Peterson, E.D., Turan, T.N., Valderrama, A.L., & Vinters, H.V. (2013). An updated definition of stroke for the 21st century: A statement for healthcare professionals from the American Heart Association/American Stroke Association. Stroke, 44(7), 2064-2089. https://doi.org/10.1161/STR.0b013e318296aeca
• Subudhi, A., Dash, M., & Sabut, S. (2020). Automated segmentation and classification of brain stroke using expectation-maximization and random forest classifier. Biocybernetics and Biomedical Engineering, 40(1), 277-289. https://doi.org/10.1016/j.bbe.2019.04.004
• Uçkun, S., Ağarlı, M., & Kılıç, V. (2023). Deep Learning-Based Ischemic Stroke Segmentation on Brain Computed Tomography Images. Avrupa Bilim ve Teknoloji Dergisi, (50), 105-112.
• Vilela, P., & Rowley, H.A. (2017). Brain ischemia: CT and MRI techniques in acute ischemic stroke. European Journal of Radiology, 96, 162-172. https://doi.org/10.1016/j.ejrad.2017.08
• Winzeck, S., Hakim, A., McKinley, R., Pinto, J.A.A.D.S.R., Alves, V., Silva, C., Pisov, M., Krivov, E., Belyaev, M., Monteiro, M., Oliveira, A., Choi, Y., Paik, M.C., Kwon, Y., Lee, H., Kim, B.J., Won, J.H., Islam, M., Ren, H., Robben, D., Suetens, P., Gong, E., Niu, Y., Xu, J., Pauly, J.M., Lucas, C., Heinrich, M.P., Rivera, L.C., Castillo, L.S., Daza, L.A., Beers, A.L., Arbelaezs, P., Maier, O., Chang, K., Brown, J.M., Kalpathy-Cramer, J., Zaharchuk, G., Wiest, R., & Reyes, M. (2018). ISLES 2016 and 2017-Benchmarking ischemic stroke lesion outcome prediction based on multispectral MRI. Frontiers in Neurology, 9, 679. https://doi.org/10.3389/fneur.2018.00679
• Yahiaoui, A. F. Z., & Bessaid, A. (2016). Segmentation of ischemic stroke area from CT brain images. In 2016 IEEE International Symposium on Signal, Image, Video and Communications (ISIVC) (ss. 13-17), Tunus.
• Yalçın, S. & Vural, H. (2022). Brain stroke classification and segmentation using encoder-decoder based deep convolutional neural networks. Computers in Biology and Medicine, 149, 105941. https://doi.org/10.1016/j.compbiomed.2022.105941
• Yang, H., Huang, C., Nie, X., Wang, L., Liu, X., Luo, X., & Liu, L. (2023). IS-Net: Automatic Ischemic Stroke Lesion Segmentation on CT Images. IEEE Transactions on Radiation and Plasma Medical Sciences, 7(5), 483-493.
• Yedavalli, V.S., Tong E., Martin, D., Yeom, K.W., & Forkert, N.D. (2021). Artificial intelligence in stroke imaging: Current and future perspectives. Clinical Imaging, 69, 246-254. https://doi.org/10.1016/j.clinimag.2020.09.005
• Zhou, X. (2020). Automatic segmentation of multiple organs on 3D CT ımages by using deep learning approaches. Advances in Experimental Medicine and Biology, 1213, 135-147. https://doi.org/10.1007/978-3-030-33128-3_9