跳到主要內容

臺灣博碩士論文加值系統

(44.220.44.148) 您好!臺灣時間:2024/06/14 09:48
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:璩文威
研究生(外文):Wen-Wei Chu
論文名稱:使用深度學習進行腦部腫瘤核磁共振影像分割與分類
論文名稱(外文):MRI Brain Tumor Segmentation and Classification with Deep Learning
指導教授:邱泓文邱泓文引用關係
指導教授(外文):Hung-Wen Chiu
口試委員:徐建業陳俊璋
口試委員(外文):Chien-Yeh HsuChun-Chang Chen
口試日期:2020-07-02
學位類別:碩士
校院名稱:臺北醫學大學
系所名稱:醫學資訊研究所
學門:醫藥衛生學門
學類:醫學技術及檢驗學類
論文種類:學術論文
論文出版年:2020
畢業學年度:108
語文別:中文
論文頁數:66
中文關鍵詞:深度學習膠質瘤腦部腫瘤影像分割腦部腫瘤分類U-net
外文關鍵詞:Deep learningGliomasBrain tumor SegmentationBrain tumor classificationU-net
相關次數:
  • 被引用被引用:0
  • 點閱點閱:238
  • 評分評分:
  • 下載下載:1
  • 收藏至我的研究室書目清單書目收藏:0
論文名稱:使用深度學習進行腦部腫瘤核磁共振影像分割與分類
臺北醫學大學醫學資訊研究所
研究生姓名: 璩文威
指導教授:邱泓文 臺北醫學大學醫學資訊研究所 教授
深度學習的應用在近年於諸多領域獲得了高度的成功與關注,醫學影像分割便是一例;其中,腦部腫瘤的探測與分析領域特別受到關注,原因在於其病患的生存率深受診斷精確度與即時性所影響。本實驗便是使用深度學習模組對膠質瘤(gliomas)患者的腦部影像進行全自動腫瘤影像分割與腫瘤分類,旨在快速且準確地進行完整腫瘤、腫瘤核心以及顯影腫瘤區域的影像分割,同時預測該腫瘤屬於惡性或良性腫瘤。本實驗使用在醫學影像分割表現不俗的U-net作為腫瘤分割模組,並採用串接式架構進一步提升效能;腫瘤分類上,採用深度卷積神經網路模組借助腫瘤分割成果進行分類預測。本實驗使用2019年度Brain Tumor Segmentation Challenge (BRATS 2019)所提供的MRI影像組作為訓練與測試資料。在腫瘤分割上,本實驗自完整腫瘤、腫瘤核心與顯影腫瘤區域得到Dice相似系數分別為89.92、84.91及74.38;在腫瘤分類上,本實驗精確度、靈敏度及特異度依序為94.12%、96.68%及93.38%。
Title of Thesis:MRI Brain Tumor Segmentation and Classification with Deep Learning
Author:Wen-Wei Chu
Thesis advised by : Hung-Wen Chiu
Taipei Medical University,
Graduate Institute of Biomedical Informatics
In last decade, applications of using deep learning for automatic brain tumor segmentation gains significantly great awareness, thanks to the critical demand on timely and precise diagnosis, which largely affects the survival of patients. Gliomas are one of the most common brain tumors. They are hard to detect due to the big variety of their size and boundary. To diagnosis tumors like Gliomas, brain tumor segmentation plays as an essential step. However, manual tumor segmentation is time-consuming and has individual variability. We developed a deep learning application for brain tumor segmentation, providing fully automatic, timely, and precise segmentation for brain magnetic resonance image. Along with the segmentation, the application also provides accurate classification prediction of the tumor. We cascaded two U-net models for segmentation, and a CNN model for classification. All models are trained and validated by dataset obtained from Brain Tumor Segmentation Challenge (BRATS) held in 2019. Our application achieved Dice Similarity Coefficient of 89.92, 84.91, and 74.38 for whole tumor, tumor core, and enhancing tumor, respectively. It also achieved accuracy of 94.12%, sensitivity of 96.68%, and specificity of 93.38% for tumor classification.
目錄

考試委員審定書 i
臺北醫學大學暨國家圖書館電子暨紙本學位論文延後公開申請書 ii
誌謝 iii
目錄 iv
表目錄 vii
圖目錄 viii
摘要 ix
Abstract x
緒論 1
1-1 研究背景 1
1-1-1膠質瘤簡介 1
1-1-2膠質瘤診斷方式 2
1-1-3膠質瘤分級 4
1-1-4 腦部腫瘤影像分割 4
1-1-5深度學習 5
1-2 研究動機 6
1-3研究目的 6
文獻探討 7
2-1 自動化腦部腫瘤影像分割之文獻探討 7
2-2 自動化腫瘤分類之文獻探討 18
研究材料與方法 21
3-1 深度學習原理與模組架構 22
3-1-1 深度學習 22
3-1-2 卷積神經網路模組 22
3-1-3 U-net 23
3-2 實驗資料與前處理程序 26
3-2-1 MRI影像 27
3-2-2 BRATS腦部MRI資料組 29
3-2-3資料前處理程序 29
3-3 實驗流程與模組設計 31
3-3-1 實驗流程 32
3-3-2 邊界分割模組設計 36
3-3-3 腫瘤分割模組設計 40
3-3-4 腫瘤分類模組設計 40
3-3-5 實驗環境 41
3-4 實驗結果評估方式 41
實驗結果 45
4-1 預期成果 45
4-2 邊界分割模組訓練成果 45
4-3 腫瘤分割模組訓練成果 48
4-4 腫瘤分類模組訓練成果 50
討論 53
5-1 邊界分割模組討論 53
5-2 腫瘤分割模組討論 54
5-3 腫瘤分類模組討論 56
結論與建議 58
6-1 實驗結論 58
6-2 研究限制 59
6-3 建議 59
參考文獻 61


表目錄

表 1. 腦部影像分割方法學的分類方式 9
表 2. 較具代表性的半自動與全自動化腦部影像分割模組整理 12
表 3. 較具代表性的半自動與全自動化腦部影像分類模組整理 20
表 4. 邊界分割模組架構圖 38
表 5. 腫瘤分割模組架構圖 39
表 6. 腫瘤分類模組架構圖 41
表 7. 邊界分割模組效能 46
表 8. 腫瘤分割模組效能 49
表 9. 腫瘤分類模組效能 51
表 10. 邊界分割模組與其他深度學習模組的完整腫瘤分割效能比較 53
表 11.腫瘤分割模組與其他深度學習模組的腫瘤核心與顯影腫瘤區域分割效能比較 55
表 12. 腫瘤分類模組與其他深度學習模組的腫瘤分類精確度比較 56


圖目錄

圖 1. 研究架構圖 21
圖 2. 殘差學習法 25
圖 3. U-NET模組架構 26
圖 4. MRI序列生成影像範例 28
圖 5. 訓練階段資料處理流程 31
圖 6. 測試階段資料處理流程 32
圖 7. 邊界分割模組標籤範例 33
圖 8. 邊界分割模組流程圖 34
圖 9. 腫瘤分割模組流程圖 35
圖 10. 腫瘤分類模組流程圖 36
圖 11. 邊界分割模組使用大切片資料增量時的預測輸出範例 47
圖 12. 腫瘤分割模組訓練資料組 49
圖 13.腫瘤分割模組預測輸出範例 50
Adams, R., Bischof, L. J. I. T. o. p. a., & intelligence, m. (1994). Seeded region growing. 16(6), 641-647.
Akkus, Z., Galimzianova, A., Hoogi, A., Rubin, D. L., & Erickson, B. J. J. J. o. d. i. (2017). Deep learning for brain MRI segmentation: state of the art and future directions. 30(4), 449-459.
Bahadure, N. B., Ray, A. K., & Thethi, H. P. J. I. j. o. b. i. (2017). Image analysis for MRI based brain tumor detection and feature extraction using biologically inspired BWT and SVM. 2017.
Bajwa, I. S., Asghar, M. N., & Naeem, M. A. Learning-based Improved Seeded Region Growing Algorithm for Brain Tumor Identification.
Bauer, S., Nolte, L.-P., & Reyes, M. (2011). Fully automatic segmentation of brain tumor images using support vector machine classification in combination with hierarchical conditional random field regularization. Paper presented at the International Conference on Medical Image Computing and Computer-Assisted Intervention.
Bauer, S., Wiest, R., Nolte, L.-P., Reyes, M. J. P. i. M., & Biology. (2013). A survey of MRI-based medical image analysis for brain tumor studies. 58(13), R97.
Birare, G., & Chakkarwar, V. (2018). Automated Detection of Brain Tumor Cells Using Support Vector Machine. Paper presented at the 2018 9th International Conference on Computing, Communication and Networking Technologies (ICCCNT).
Chaddad, A. J. I. J. o. B. I. (2015). Automated feature extraction in brain tumor by magnetic resonance imaging using gaussian mixture models. 2015.
DeAngelis, L. M. J. N. E. j. o. m. (2001). Brain tumors. 344(2), 114-123.
Deng, W., Xiao, W., Deng, H., & Liu, J. (2010). MRI brain tumor segmentation with region growing method based on the gradients and variances along and inside of the boundary curve. Paper presented at the 2010 3rd International Conference on Biomedical Engineering and Informatics.
Dong, H., Yang, G., Liu, F., Mo, Y., & Guo, Y. (2017). Automatic brain tumor detection and segmentation using U-Net based fully convolutional networks. Paper presented at the annual conference on medical image understanding and analysis.
El-Dahshan, E.-S. A., Mohsen, H. M., Revett, K., & Salem, A.-B. M. J. E. s. w. A. (2014). Computer-aided diagnosis of human brain tumor through MRI: A survey and a new algorithm. 41(11), 5526-5545.
Ertosun, M. G., & Rubin, D. L. (2015). Automated grading of gliomas using deep learning in digital pathology images: A modular approach with ensemble of convolutional neural networks. Paper presented at the AMIA Annual Symposium Proceedings.
Georgiadis, P., Cavouras, D., Kalatzis, I., Daskalakis, A., Kagadis, G. C., Sifaki, K., . . . biomedicine, p. i. (2008). Improving brain tumor characterization on MRI by probabilistic neural networks and non-linear transformation of textural features. 89(1), 24-32.
Gordillo, N., Montseny, E., & Sobrevilla, P. J. M. r. i. (2013). State of the art survey on MRI brain tumor segmentation. 31(8), 1426-1438.
Havaei, M., Davy, A., Warde-Farley, D., Biard, A., Courville, A., Bengio, Y., . . . Larochelle, H. J. M. i. a. (2017). Brain tumor segmentation with deep neural networks. 35, 18-31.
Havaei, M., Jodoin, P.-M., & Larochelle, H. (2014). Efficient interactive brain tumor segmentation as within-brain kNN classification. Paper presented at the 2014 22nd International Conference on Pattern Recognition.
He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. Paper presented at the Proceedings of the IEEE conference on computer vision and pattern recognition.
Hinton, G., Deng, L., Yu, D., Dahl, G. E., Mohamed, A.-r., Jaitly, N., . . . Sainath, T. N. J. I. S. p. m. (2012). Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. 29(6), 82-97.
Isensee, F., Kickingereder, P., Wick, W., Bendszus, M., & Maier-Hein, K. H. (2017). Brain tumor segmentation and radiomics survival prediction: Contribution to the brats 2017 challenge. Paper presented at the International MICCAI Brainlesion Workshop.
Isensee, F., Kickingereder, P., Wick, W., Bendszus, M., & Maier-Hein, K. H. (2018). No new-net. Paper presented at the International MICCAI Brainlesion Workshop.
Işın, A., Direkoğlu, C., & Şah, M. J. P. C. S. (2016). Review of MRI-based brain tumor image segmentation using deep learning methods. 102, 317-324.
Joshi, D. M., Rana, N., & Misra, V. (2010). Classification of brain cancer using artificial neural network. Paper presented at the 2010 2nd International Conference on Electronic Computer Technology.
Kamnitsas, K., Ledig, C., Newcombe, V. F., Simpson, J. P., Kane, A. D., Menon, D. K., . . . Glocker, B. J. M. i. a. (2017). Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation. 36, 61-78.
Kharrat, A., Gasmi, K., Messaoud, M. B., Benamrane, N., & Abid, M. J. L. j. o. s. (2010). A hybrid approach for automatic classification of brain MRI using genetic algorithm and support vector machine. 17(1), 71-82.
Kim, S.-S., Harford, J. B., Pirollo, K. F., Chang, E. H. J. B., & communications, b. r. (2015). Effective treatment of glioblastoma requires crossing the blood–brain barrier and targeting tumors including cancer stem cells: the promise of nanomedicine. 468(3), 485-489.
Kleesiek, J., Urban, G., Hubert, A., Schwarz, D., Maier-Hein, K., Bendszus, M., & Biller, A. J. N. (2016). Deep MRI brain extraction: A 3D convolutional neural network for skull stripping. 129, 460-469.
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. Paper presented at the Advances in neural information processing systems.
Kumar, T. S., Rashmi, K., Ramadoss, S., Sandhya, L., & Sangeetha, T. (2017). Brain tumor detection using SVM classifier. Paper presented at the 2017 Third International Conference on Sensing, Signal Processing and Security (ICSSS).
LeCun, Y., Bengio, Y., & Hinton, G. J. n. (2015). Deep learning. 521(7553), 436-444.
Liaw, A., & Wiener, M. J. R. n. (2002). Classification and regression by randomForest. 2(3), 18-22.
Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., . . . Sánchez, C. I. J. M. i. a. (2017). A survey on deep learning in medical image analysis. 42, 60-88.
Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. Paper presented at the Proceedings of the IEEE conference on computer vision and pattern recognition.
Louis, D. N., Ohgaki, H., Wiestler, O. D., Cavenee, W. K., Burger, P. C., Jouvet, A., . . . Kleihues, P. J. A. n. (2007). The 2007 WHO classification of tumours of the central nervous system. 114(2), 97-109.
Ma, C., Luo, G., & Wang, K. J. I. t. o. m. i. (2018). Concatenated and connected random forests with multiscale patch driven active contour model for automated brain tumor segmentation of MR images. 37(8), 1943-1954.
Menze, B. H., Jakab, A., Bauer, S., Kalpathy-Cramer, J., Farahani, K., Kirby, J., . . . Wiest, R. J. I. t. o. m. i. (2014). The multimodal brain tumor image segmentation benchmark (BRATS). 34(10), 1993-2024.
Mohsen, H., El-Dahshan, E.-S. A., El-Horbaty, E.-S. M., Salem, A.-B. M. J. F. C., & Journal, I. (2018). Classification using deep learning neural networks for brain tumors. 3(1), 68-71.
Nayak, D. R., Dash, R., & Majhi, B. J. N. (2016). Brain MR image classification using two-dimensional discrete wavelet transform and AdaBoost with random forests. 177, 188-197.
Noguchi, T., Higa, D., Asada, T., Kawata, Y., Machitori, A., Shida, Y., . . . Tajima, T. J. J. J. o. R. (2018). Artificial intelligence using neural network architecture for radiology (AINNAR): classification of MR imaging sequences. 36(12), 691-697.
Nyúl, L. G., Udupa, J. K., & Zhang, X. J. I. t. o. m. i. (2000). New variants of a method of MRI scale standardization. 19(2), 143-150.
Ostrom, Q. T., Bauchet, L., Davis, F. G., Deltour, I., Fisher, J. L., Langer, C. E., . . . Walsh, K. M. J. N.-o. (2014). The epidemiology of glioma in adults: a “state of the science” review. 16(7), 896-913.
Otsu, N. J. I. t. o. s., man,, & cybernetics. (1979). A threshold selection method from gray-level histograms. 9(1), 62-66.
Pan, Y., Huang, W., Lin, Z., Zhu, W., Zhou, J., Wong, J., & Ding, Z. (2015). Brain tumor grading based on neural networks and convolutional neural networks. Paper presented at the 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).
Pereira, S., Pinto, A., Alves, V., & Silva, C. A. J. I. t. o. m. i. (2016). Brain tumor segmentation using convolutional neural networks in MRI images. 35(5), 1240-1251.
Ronneberger, O., Fischer, P., & Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. Paper presented at the International Conference on Medical image computing and computer-assisted intervention.
Shen, D., Wu, G., & Suk, H.-I. J. A. r. o. b. e. (2017). Deep learning in medical image analysis. 19, 221-248.
Shih, F. Y., Cheng, S. J. I., & computing, v. (2005). Automatic seeded region growing for color image segmentation. 23(10), 877-886.
Shree, N. V., & Kumar, T. J. B. i. (2018). Identification and classification of brain tumor MRI images with feature extraction using DWT and probabilistic neural network. 5(1), 23-30.
Steenwijk, M. D., Pouwels, P. J., Daams, M., van Dalen, J. W., Caan, M. W., Richard, E., . . . Vrenken, H. J. N. C. (2013). Accurate white matter lesion segmentation by k nearest neighbor classification with tissue type priors (kNN-TTPs). 3, 462-469.
Sujan, M., Alam, N., Noman, S. A., & Islam, M. J. J. I. J. o. C. A. (2016). A Segmentation based Automated System for Brain Tumor Detection. 153(10), 41-49.
Tustison, N. J., Shrinidhi, K., Wintermark, M., Durst, C. R., Kandel, B. M., Gee, J. C., . . . Avants, B. B. J. N. (2015). Optimal symmetric multimodal templates and concatenated random forests for supervised brain tumor segmentation (simplified) with ANTsR. 13(2), 209-225.
Vaishnavee, K., & Amshakala, K. (2015). An automated MRI brain image segmentation and tumor detection using SOM-clustering and Proximal Support Vector Machine classifier. Paper presented at the 2015 IEEE International Conference on Engineering and Technology (ICETECH).
Wadhwa, A., Bhardwaj, A., & Verma, V. S. J. M. r. i. (2019). A review on brain tumor segmentation of MRI images. 61, 247-259.
Wang, G., Li, W., Ourselin, S., & Vercauteren, T. (2017). Automatic brain tumor segmentation using cascaded anisotropic convolutional neural networks. Paper presented at the International MICCAI brainlesion workshop.
Wang, S., Zhang, Y., Dong, Z., Du, S., Ji, G., Yan, J., . . . Technology. (2015). Feed‐forward neural network optimized by hybridization of PSO and ABC for abnormal brain detection. 25(2), 153-164.
Wasule, V., & Sonar, P. (2017). Classification of brain MRI using SVM and KNN classifier. Paper presented at the 2017 Third International Conference on Sensing, Signal Processing and Security (ICSSS).
Wu, W., Chen, A. Y., Zhao, L., Corso, J. J. J. I. j. o. c. a. r., & surgery. (2014). Brain tumor detection and segmentation in a CRF (conditional random fields) framework with pixel-pairwise affinity and superpixel-level features. 9(2), 241-253.
Zacharaki, E. I., Wang, S., Chawla, S., Soo Yoo, D., Wolf, R., Melhem, E. R., & Davatzikos, C. J. M. R. i. M. A. O. J. o. t. I. S. f. M. R. i. M. (2009). Classification of brain tumor type and grade using MRI texture and shape in a machine learning scheme. 62(6), 1609-1618.
Zhang, N., Ruan, S., Lebonvallet, S., Liao, Q., Zhu, Y. J. C. V., & Understanding, I. (2011). Kernel feature selection to fuse multi-spectral MRI images for brain tumor segmentation. 115(2), 256-269.
Zhang, W., Li, R., Deng, H., Wang, L., Lin, W., Ji, S., & Shen, D. J. N. (2015). Deep convolutional neural networks for multi-modality isointense infant brain image segmentation. 108, 214-224.
電子全文 電子全文(本篇電子全文限研究生所屬學校校內系統及IP範圍內開放)
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊