跳到主要內容

臺灣博碩士論文加值系統

(44.210.149.205) 您好!臺灣時間:2024/04/12 21:56
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:黃裕凱
研究生(外文):Yu-Kai Huang
論文名稱:以三維卷積神經網路探究大腦微出血之偵測與量化
論文名稱(外文):Cerebral Microbleed Detection and Quantification Based on Three-Dimensional Convolutional Neural Networks
指導教授:蔡章仁蔡章仁引用關係
指導教授(外文):Jang-Zern Tsai
學位類別:碩士
校院名稱:國立中央大學
系所名稱:電機工程學系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2022
畢業學年度:110
語文別:中文
論文頁數:82
中文關鍵詞:大腦微出血深度學習人工智慧自動偵測圖形使用者介面
外文關鍵詞:Cerebral microbleedsdeep learningartificial intelligenceautomatic detectiongraphical user interface
相關次數:
  • 被引用被引用:0
  • 點閱點閱:153
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
大腦微出血(Cerebral Microbleeds, CMBs)為小型的慢性腦出血,近期研究中,已逐漸確認其與腦中風、智能障礙等因素有顯著的關係,及早檢測並進行治療成為一個日漸重要的課題。大腦微出血在敏感性加權血管成像(Susceptibility-weighted images, SWI)上表現最為明顯,一般呈現黑色均質圓形。本研究的目的是提出以SWI影像進行分析及自動偵測大腦微出血的方法,以人工智慧模型協助臨床醫師的辨識。
本研究提出的方法主要分為三階段,第一階段為使用運行速度較快並可直接分割的Mask R-CNN,先對SWI影像進行實質腦提取,第二階段在實質腦區域範圍內利用YOLO架構去初步篩選疑似CMBs的部分,接著第三階段以三維卷積神經網路(3D Convolutional Neural Networks)進行最後的CMBs分類,從眾多疑似的CMBs中確認出真正的CMBs。本研究最後將這三階段的功能以圖形使用者介面方式呈現,方便使用者快速操作與觀看結果。
本研究結果顯示SWI影像實質腦提取部份的精準度達98%,敏感度達93%,具95%的Dice係數;以YOLO網路於候選CMBs中篩選CMBs偵測其敏感度為90%,每位病人的平均偽陽數為78.19顆;最終3D CNN模型顯示大部分病人的CMB與非CMB都可被辨識分類,其敏感度為85%,每位病人平均偽陽數為2.41顆CMBs。
總而言之,本研究利用神經網路進行自動檢測與標記,在大腦微出血的偵測獲得良好的結果,能將大部分的大腦微出血篩選出來,並排除疑似區域。在實質腦提取方面亦達到相當高的成果,能有效地將實質腦給提取出來。本研究將上述結果整合起來成功開發圖形使用者介面讓使用者可以簡單操作。
Cerebral Microbleed (CMB) is a small chronic cerebral hemorrhage. Recent studies have gradually confirmed that it has a significant relationship with factors such as stroke and intellectual disability. Early detection and treatment have become an increasingly important issue. Cerebral microbleeds are most evident on Susceptibility-Weighted Images (SWI) and usually appear as black homogeneous circles. The purpose of this study is to develop a method for automatically detecting cerebral microbleeds by analyzing SWI images and assisting clinicians to identify them with an artificial intelligence model.
The method proposed in this study is mainly divided into three stages. The first stage is to use Mask R-CNN, which runs faster and can perform segmentation directly, to extract the parenchymal brain from the SWI image. The second stage uses YOLO to screen for candidate CMBs within the scope of the parenchymal brain area. The third stage uses a 3D convolutional neural network to classify the candidate CMBs to find the real CMBs. Finally, the functions of the three stages are integrated and presented through a graphical user interface to provide convenience and efficiency for the users.
The results of the study showed that the accuracy of SWI image parenchymal brain extraction was 98%, the sensitivity was 93%, and the Dice coefficient was 95%; the sensitivity of detecting candidate CMBs on the YOLO network was 90%, and the average number of false positives per patient was 78.19 CMBs. The final 3D CNN model showed that CMB and non-CMB in most patients could be identified and classified, with a sensitivity of 85% and an average false positive average of 3.73 CMBs per patient.
In summary, this research used three types of neural networks in series for automatic detection of CMBs. This method can largely reduce the burden of the clinicians in detecting CMBs. The output quality rendered by this method is good and clinically useful.
摘要 i
Abstract iv
致謝 vi
目錄 vii
圖目錄 x
表目錄 xii
第一章 緒論 1
1.1 研究動機與背景 1
1.2 研究架構 2
1.3 大腦微出血 3
1.4 磁敏感性加權影像 4
1.5 相關研究 6
第二章 研究方法 10
2.1 資料集 10
2.2 影像前處理 11
2.2.1 正規化 11
2.2.2 腦提取前處理 12
2.2.3 資料處理並排 14
2.3 Mask R-CNN介紹 15
2.3.1 R-CNN 16
2.3.2 Fast R-CNN 17
2.3.3 Faster R-CNN 18
2.3.4 Mask R-CNN 19
2.4 YOLO介紹 21
2.4.1 YOLOv1 22
3.4.2 YOLOv2 24
2.4.3 YOLOv3 26
2.5 3D CNN介紹 29
2.6 評估指標 30
第三章 研究結果 33
3.1 交叉驗證 33
3.2 Mask R-CNN 階段結果 34
3.3 YOLO 階段結果 35
3.4 3D CNN 階段結果 37
第四章 討論 41
第五章 結論與未來展望 45
5.1 結論 45
5.2 未來展望 45
參考文獻 48
附錄 1
[1] 陳右緯, 大腦微出血(Cerebral Microbleeds)之診斷及臨床意義, 台灣腦中風學會會訊‧第15卷第3期, 2008
[2] E診斷醫學社區, 2017取自 https://kknews.cc/zh-tw/health/nmzllv8.html
[3] Yakushiji, Yusuke, et al. "Distributional impact of brain microbleeds on global cognitive function in adults without neurological disorder." Stroke 43.7 (2012): 1800-1805.
[4] Werring, David J., et al. "Cognitive dysfunction in patients with cerebral microbleeds on T2*-weighted gradient-echo MRI." Brain 127.10 (2004): 2265-2275.
[5] Charidimou, Andreas, et al. "Cerebral microbleeds: a guide to detection and clinical relevance in different disease settings." Neuroradiology 55.6 (2013): 655-674.
[6] Azad, Rajiv, et al. "Detection and differentiation of focal intracranial calcifications and chronic microbleeds using MRI." Journal of Clinical and Diagnostic Research: JCDR 11.5 (2017): TC19.
[7] Wu, Zhen, et al. "Identification of calcification with MRI using susceptibility‐weighted imaging: a case study." Journal of Magnetic Resonance Imaging: An Official Journal of the International Society for Magnetic Resonance in Medicine 29.1 (2009): 177-182.
[8] Docampo, Jorge, et al. "Susceptibility-weighted angiography of intracranial blood products and calcifications compared to gradient echo sequence." The neuroradiology journal 26.5 (2013): 493-500.
[9] Nandigam, R. N. K., et al. "MR imaging detection of cerebral microbleeds: effect of susceptibility-weighted imaging, section thickness, and field strength." American Journal of Neuroradiology 30.2 (2009): 338-343.
[10] Kuijf, Hugo J., et al. "Semi-automated detection of cerebral microbleeds on 3.0 T MR images." PLoS One 8.6 (2013): e66610.
[11] Dou, Qi, et al. "Automatic detection of cerebral microbleeds from MR images via 3D convolutional neural networks." IEEE transactions on medical imaging 35.5 (2016): 1182-1195.
[12] Al-Masni, Mohammed A., et al. "Automated detection of cerebral microbleeds in MR images: A two-stage deep learning approach." NeuroImage: Clinical 28 (2020): 102464.
[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] Uijlings, Jasper RR, et al. "Selective search for object recognition." International journal of computer vision 104.2 (2013): 154-171.
[16] Girshick, Ross. "Fast r-cnn." Proceedings of the IEEE international conference on computer vision. 2015.
[17] Ren, Shaoqing, et al. "Faster r-cnn: Towards real-time object detection with region proposal networks." Advances in neural information processing systems 28 (2015).
[18] Understanding Region of Interest — (RoI Pooling) 2020 取自https://towardsdatascience.com/understanding-region-of-interest-part-1-roi-pooling-e4f5dd65bb44
[19] Redmon, Joseph, et al. "You only look once: Unified, real-time object detection." Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.
[20] Redmon, Joseph, and Ali Farhadi. "YOLO9000: better, faster, stronger." Proceedings of the IEEE conference on computer vision and pattern recognition. 2017.
[21] Redmon, Joseph, and Ali Farhadi. "Yolov3: An incremental improvement." arXiv preprint arXiv:1804.02767 (2018).
[22] Bochkovskiy, Alexey, Chien-Yao Wang, and Hong-Yuan Mark Liao. "Yolov4: Optimal speed and accuracy of object detection." arXiv preprint arXiv:2004.10934 (2020).
[23] Ji, Shuiwang, et al. "3D convolutional neural networks for human action recognition." IEEE transactions on pattern analysis and machine intelligence 35.1 (2012): 221-231.
[24] Chesebro, Anthony G., et al. "Automated detection of cerebral microbleeds on T2*-weighted MRI." Scientific reports 11.1 (2021): 1-13.
[25] Chen, Hao, et al. "Automatic detection of cerebral microbleeds via deep learning based 3D feature representation." 2015 IEEE 12th international symposium on biomedical imaging (ISBI). IEEE, 2015.
[26] Lu, Siyuan, et al. "Cerebral Microbleed Detection via Convolutional Neural Network and Extreme Learning Machine." Frontiers in Computational Neuroscience (2021): 81.
[27] Dou, Qi, et al. "Automatic detection of cerebral microbleeds from MR images via 3D convolutional neural networks." IEEE transactions on medical imaging 35.5 (2016): 1182-1195.
電子全文 電子全文(網際網路公開日期:20240801)
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊