腦血管疾病，包含腦中風，為台灣十大死因的第4位。急性缺血性腦中風，又佔腦中風人數的8成以上。目前主要治療手段，是在中風後3小時內注射靜脈血栓溶解劑。若超過3小時注射，可能造成腦內出血，導致生命危險，因此治療急性缺血性腦中風是刻不容緩的。臨床醫學上，腦部磁振造影(Magnetic Resonance Imaging, MRI)是診斷急性缺血性腦中風與判定腦部梗塞區域的主要工具，其中擴散權重影像(Diffusion-Weighted Imaging, DWI)對腦梗塞區域有高敏感度。
　　若要量化腦部梗塞體積，目前仍以醫師手動標定為主，但此法既費時又繁瑣。本文提出一種在DWI上快速且自動偵測腦梗塞區域的方法。該方法分成兩個階段，第一階段使用Mask R-CNN對DWI進行腦實質提取，濾除頭骨與背景雜訊；第二階段使用3D Multi-scale CNN對DWI腦實質範圍進行腦梗塞分割，多尺度的網路架構能同時學習梗塞的大致位置和細微的特徵。在訓練兩個網路模型前，皆會進行影像標準化、影像重採樣與資料增量等影像前處理。
　　本論文使用來自台北榮民總醫院218筆DWI，其中200筆執行5-fold交叉驗證，得到平均DSC、Precision、Recall分別為74.2%、77.5%、76.2%，並且剩餘18筆作為內部測試集。最終我們將5-fold交叉驗證得到的五個模型，應用於18筆測試資料上，得到平均DSC、Precision、Recall分別為74.6%、76.7%、74.8%。同時使用來自聯新國際醫院的66筆DWI作為外部測試集，並且在五個模型上得到平均DSC、Precision、Recall分別為68.9%、65.1%、77.8%。

Cerebrovascular diseases including brain strokes are the fourth leading cause of death in Taiwan. Acute ischemic strokes account for more than 80% of brain strokes. To date, the major treatment method is to inject recombinant tissue plasminogen activator (rt-PA). This treatment must be done within 3 hours after brain stroke, because injection of rt-PA later than 3 hours post-stroke may cause life-threatening cerebral hemorrhages. Hence, an accurate diagnosis of acute ischemic stroke and prompt decision for urgent treatment are very important. In clinical medicine, magnetic resonance imaging (MRI) is the most powerful tool for visualizing stroke lesions to diagnose acute ischemic stroke.
To quantify stroke infarction from MRIs, the time-consuming and cumbersome manual labeling is still the main method clinically available. This paper proposes a method for rapidly and automatically detecting infarction on DWI, which is the most sensitive to brain infarct among different MR images. This method can roughly be divided into two stages. The first stage is to use Mask R-CNN to extract brain parenchyma from DWI to eliminate the skull and extracranial noise. The second stage is to use 3D multi-scale CNN to segment brain infarction on DWI brain parenchyma. Multi-scale network architecture can learn both rough infarction positions and detail features. Before training the two neural network models, image preprocessing such as image normalization, image resampling, and data augmentation will be performed.
This study used 218 DWI scans collected from Taipei Veterans General Hospital. Among these scans, 200 were used for a 5-fold cross-validation, which resulted in a 74.2% average Dice similarity coefficient (DSC), a 77.5% average precision, and a 76.2% average recall. The remaining 18 scans were used as the internal test set to test the five generated models. The internal test resulted in a 74.6% average DSC, a 76.7% average precision, and a 76.8% average recall. Furthermore, these models were tested with 66 DWI scans from Landseed International Hospital as an external test set. The average results of DSC, precision, and recall rate were 68.9%, 65.1%, and 77.8%, respectively.

〔1〕衛生福利部:〈109年國人十大死因結果〉，2021年6月18日，取自https://www.mohw.gov.tw/cp-5017-61533-1.html
〔2〕世界衛生組織:〈Top 10 cause of death〉，2020年12月9日，取自https://www.who.int/news-room/fact-sheets/detail/the-top-10-causes-of-death
〔3〕Dirnagl, Ulrich, Costantino Iadecola, and Michael A. Moskowitz. "Pathobiology of ischaemic stroke: an integrated view." Trends in neurosciences 22.9 (1999): 391-397.
〔4〕Van der Worp, H. Bart, and Jan van Gijn. "Acute ischemic stroke." New England Journal of Medicine 357.6 (2007): 572-579.
〔5〕National Institute of Neurological Disorders and Stroke rt-PA Stroke Study Group. "Tissue plasminogen activator for acute ischemic stroke." New England Journal of Medicine 333.24 (1995): 1581-1588.
〔6〕Berkhemer, Olvert A., et al. "A randomized trial of intraarterial treatment for acute ischemic stroke." n Engl J Med 372 (2015): 11-20.
〔7〕Nogueira, Raul G., et al. "Thrombectomy 6 to 24 hours after stroke with a mismatch between deficit and infarct." New England Journal of Medicine 378.1 (2018): 11-21.
〔8〕Baliyan, Vinit, et al. "Diffusion weighted imaging: technique and applications." World journal of radiology 8.9 (2016): 785.
〔9〕Le Bihan, Denis. "Diffusion MRI: what water tells us about the brain." EMBO molecular medicine 6.5 (2014): 569-573.
〔10〕Chalela, Julio A., et al. "Magnetic resonance imaging and computed tomography in emergency assessment of patients with suspected acute stroke: a prospective comparison." The Lancet 369.9558 (2007): 293-298.
〔11〕Le Bihan, Denis, and Heidi Johansen-Berg. "Diffusion MRI at 25: exploring brain tissue structure and function." Neuroimage 61.2 (2012): 324-341.
〔12〕LeCun, Yann, Yoshua Bengio, and Geoffrey Hinton. "Deep learning." nature 521.7553 (2015): 436-444.
〔13〕He, Kaiming, et al. "Mask r-cnn." Proceedings of the IEEE international conference on computer vision. 2017.
〔14〕Girshick, Ross, et al. "Rich feature hierarchies for accurate object detection and semantic segmentation." Proceedings of the IEEE conference on computer vision and pattern recognition. 2014.
〔15〕Girshick, Ross. "Fast r-cnn." Proceedings of the IEEE international conference on computer vision. 2015.
〔16〕Ren, Shaoqing, et al. "Faster r-cnn: Towards real-time object detection with region proposal networks." Advances in neural information processing systems 28 (2015).
〔17〕Uijlings, Jasper RR, et al. "Selective search for object recognition." International journal of computer vision 104.2 (2013): 154-171.
〔18〕Kamnitsas, Konstantinos, et al. "Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation." Medical image analysis 36 (2017): 61-78.
〔19〕Choromanska, Anna, et al. "The loss surfaces of multilayer networks." Artificial intelligence and statistics. PMLR, 2015.
〔20〕Simonyan, Karen, and Andrew Zisserman. "Very deep convolutional networks for large-scale image recognition." arXiv preprint arXiv:1409.1556 (2014).
〔21〕Tsai, Jang-Zern, et al. "Automatic detection and quantification of acute cerebral infarct by fuzzy clustering and histographic characterization on diffusion weighted MR imaging and apparent diffusion coefficient map." BioMed research international 2014 (2014).
〔22〕Li, Wu, et al. "Robust unsupervised segmentation of infarct lesion from diffusion tensor MR images using multiscale statistical classification and partial volume voxel reclassification." NeuroImage 23.4 (2004): 1507-1518.
〔23〕Prakash, KN Bhanu, et al. "Identification, segmentation, and image property study of acute infarcts in diffusion-weighted images by using a probabilistic neural network and adaptive Gaussian mixture model." Academic radiology 13.12 (2006): 1474-1484.
〔24〕Hevia-Montiel, Nidiyare, et al. "Robust nonparametric segmentation of infarct lesion from diffusion-weighted MR images." 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE, 2007.
〔25〕Gupta, Varsha, Bhanu Prakash, and Wieslaw L. Nowinski. "Automatic and rapid identification of infarct slices and hemisphere in DWI scans." Academic Radiology 15.1 (2008): 24-39.
〔26〕Shen, Shan, André J. Szameitat, and Annette Sterr. "Detection of infarct lesions from single MRI modality using inconsistency between voxel intensity and spatial location—a 3-D automatic approach." IEEE Transactions on Information Technology in Biomedicine 12.4 (2008): 532-540.
〔27〕LeCun, Yann, et al. "Gradient-based learning applied to document recognition." Proceedings of the IEEE 86.11 (1998): 2278-2324.
〔28〕Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton. "Imagenet classification with deep convolutional neural networks." Advances in neural information processing systems 25 (2012).
〔29〕Ronneberger, Olaf, Philipp Fischer, and Thomas Brox. "U-net: Convolutional networks for biomedical image segmentation." International Conference on Medical image computing and computer-assisted intervention. Springer, Cham, 2015.
〔30〕Noh, Hyeonwoo, Seunghoon Hong, and Bohyung Han. "Learning deconvolution network for semantic segmentation." Proceedings of the IEEE international conference on computer vision. 2015.
〔31〕Long, Jonathan, Evan Shelhamer, and Trevor Darrell. "Fully convolutional networks for semantic segmentation." Proceedings of the IEEE conference on computer vision and pattern recognition. 2015.
〔32〕Chen, Liang-Chieh, et al. "Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs." IEEE transactions on pattern analysis and machine intelligence 40.4 (2017): 834-848.
〔33〕Qi, Kehan, et al. "X-net: Brain stroke lesion segmentation based on depthwise separable convolution and long-range dependencies." International conference on medical image computing and computer-assisted intervention. Springer, Cham, 2019.
〔34〕Yang, Hao, et al. "CLCI-Net: Cross-level fusion and context inference networks for lesion segmentation of chronic stroke." International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, Cham, 2019.
〔35〕Zhou, Yongjin, et al. "D-UNet: a dimension-fusion U shape network for chronic stroke lesion segmentation." IEEE/ACM transactions on computational biology and bioinformatics 18.3 (2019): 940-950.
〔36〕Tomita, Naofumi, et al. "Automatic post-stroke lesion segmentation on MR images using 3D residual convolutional neural network." NeuroImage: Clinical 27 (2020): 102276.
〔37〕Paing, May Phu, et al. "Automated Segmentation of Infarct Lesions in T1-Weighted MRI Scans Using Variational Mode Decomposition and Deep Learning." Sensors 21.6 (2021): 1952.
〔38〕Chen, Liang, Paul Bentley, and Daniel Rueckert. "Fully automatic acute ischemic lesion segmentation in DWI using convolutional neural networks." NeuroImage: Clinical 15 (2017): 633-643.
〔39〕Abdulla, Waleed. "Mask r-cnn for object detection and instance segmentation on keras and tensorflow." (2017).
〔40〕Smith, Stephen M. "Fast robust automated brain extraction." Human brain mapping 17.3 (2002): 143-155.
〔41〕Refaeilzadeh, Payam, Lei Tang, and Huan Liu. "Cross-validation." Encyclopedia of database systems 5 (2009): 532-538.
〔42〕Fiez, Julie A., Hanna Damasio, and Thomas J. Grabowski. "Lesion segmentation and manual warping to a reference brain: Intra‐and interobserver reliability." Human brain mapping 9.4 (2000): 192-211.
〔43〕Liew, Sook-Lei, et al. "A large, open source dataset of stroke anatomical brain images and manual lesion segmentations." Scientific data 5.1 (2018): 1-11.
〔44〕Neumann, Anders B., et al. "Interrater agreement for final infarct MRI lesion delineation." Stroke 40.12 (2009): 3768-3771.
〔45〕Xue, Yunzhe, et al. "A multi-path 2.5 dimensional convolutional neural network system for segmenting stroke lesions in brain MRI images." NeuroImage: Clinical 25 (2020): 102118.
〔46〕Cirillo, Marco Domenico, David Abramian, and Anders Eklund. "What is the best data augmentation for 3D brain tumor segmentation?." 2021 IEEE International Conference on Image Processing (ICIP). IEEE, 2021.