臺灣博碩士論文加值系統

轉移性腦瘤是由其他部位的原發性腫瘤細胞轉移至腦部而形成的。轉移性腦瘤的存在也往往會導致腦水腫的形成。腦水腫是在細胞層級之下，細胞內或是細胞間液體累積，在巨觀之下造成腦組織腫脹並且功能異常。準確評估轉移性腦瘤及其引起腦水腫的位置、大小對於制定有效的治療策略至關重要。目前轉移性腦瘤及其引起腦水腫的評估通常依賴醫師的肉眼觀察，分別使用對比劑增強T1權重影像和T2權重影像。然而，這種主觀判定的方法不僅耗時還導致結果的不一致性。
本研究提出了一種基於深度學習的自動化分割模型，以實現轉移性腦瘤及其引起的腦水腫的準確辨識和量化。我們使用了Mask-region convolutional neural network (mask R-CNN)進行腦遮罩的提取，接著經由前處理和三維卷積神經網路DeepMedic進行轉移性腦瘤及其引起腦水腫的自動分割。
經過46位病患共90筆資料的五摺交叉驗證，我們的腦遮罩提取模型獲得平均Dice係數為96.4%，而轉移性腦瘤及其引起腦水腫分割模型平均Dice係數分別為71.6%與85.1%。我們亦開發一個友善的圖形使用者介面，使臨床醫師方便使用這些模型進行影像分析。
研究結果顯示，我們提出的基於深度學習自動化分割模型為轉移性腦瘤及其引起的腦水腫的準確辨識和量化提供了一個有前景的解決方案。模型的準確性和開發的使用者介面為臨床醫師提供了一個可靠且直觀的工具，有助於更準確地評估轉移性腦瘤和腦水腫的位置、大小提供治療策略的規劃。

Metastatic brain tumors are formed when cancer cells from primary tumors in other parts of the body spread to the brain. The presence of brain metastases often leads to the development of brain edema. Brain edema refers to the excessive accumulation of fluid in the brain tissue. Accurate assessment of the location and size of metastatic tumors and brain edema is crucial for effective treatment strategies. Currently, the evaluation of brain metastases and brain edema heavily relies on visual observation by physicians using T1C-weighted and T2-weighted images. However, this subjective approach is not only time-consuming but also prone to inconsistencies in results.
In this study, we propose a deep learning-based automated segmentation model for the accurate identification and quantification of metastatic tumors and the associated brain edema. We employ Mask R-CNN for brain mask extraction, followed by preprocessing and the utilization of a 3D convolutional neural network called DeepMedic for automatic segmentation of metastatic tumors and brain edema.
Through five-fold cross-validation on a dataset comprising 90 records from 46 patients, our brain mask extraction model achieves excellent results with an average Dice coefficient of 96.4%. The segmentation models for metastatic tumors and brain edema attain Dice coefficients of 71.6% and 85.1%, respectively. Additionally, we have developed an intuitive graphical user interface that enables clinical physicians to conveniently utilize these models for image analysis.
The research findings demonstrate that our proposed deep learning-based automated segmentation model provides a promising solution for the accurate identification and quantification of metastatic tumors and associated brain edema. The accuracy of the models and the developed user interface offer a reliable and intuitive tool for clinical physicians, facilitating a more precise evaluation of the location and size of brain metastases and brain edema, ultimately aiding in the selection of appropriate treatment strategies.

摘要 v
Abstract vii
目錄 ix
圖目錄 xi
表目錄 xiii
第一章 緒論 1
1.1 研究動機 1
1.2 轉移性腦瘤及其引起腦水腫 2
1.3 相關研究 3
第二章 研究方法 9
2.1 磁振造影 10
2.2 資料集 11
2.3 影像前處理 13
2.3.1 提取腦遮罩 13
2.3.2 影像對位 17
2.3.3 影像體素尺寸重採樣 18
2.3.4 影像標準化 22
2.4 資料增量 22
2.5 分割水腫及腫瘤模型 24
2.6 交叉驗證 25
2.7 評估指標 27
第三章 研究結果 32
3.1 提取腦遮罩結果 32
3.2 對位結果 35
3.3 腦水腫分割結果 38
3.4 轉移性腦瘤分割結果 42
第四章 討論 47
4.1 排除之數據集 47
4.2 分割表現不佳案例之探討 48
4.2.1分割腦水腫 49
4.2.2分割轉移性腦瘤 50
4.3 與現有方法之比較 52
4.4 圖形使用者介面的使用限制 55
4.5 臨床應用 56
第五章 結論 57
參考文獻 58
附錄 65

[1] I. J. Fidler, "The Biology of Brain Metastasis: Challenges for Therapy," (in eng), Cancer J, vol. 21, no. 4, pp. 284-93, Jul-Aug 2015, doi: 10.1097/ppo.0000000000000126.
[2] A. Niranjan, L. D. Lunsford, and M. S. Ahluwalia, "Targeted Therapies for Brain Metastases," (in eng), Prog Neurol Surg, vol. 34, pp. 125-137, 2019, doi: 10.1159/000493057.
[3] D. Kondziolka et al., "Long-term survivors after gamma knife radiosurgery for brain metastases," (in eng), Cancer, vol. 104, no. 12, pp. 2784-91, Dec 15 2005, doi: 10.1002/cncr.21545.
[4] N. Fravi, "[Brain edema]," (in ger), Ther Umsch, vol. 61, no. 11, pp. 679-86, Nov 2004, doi: 10.1024/0040-5930.61.11.679. Das Hirnödem.
[5] P. Roth, L. Regli, M. Tonder, and M. Weller, "Tumor-associated edema in brain cancer patients: pathogenesis and management," (in eng), Expert Rev Anticancer Ther, vol. 13, no. 11, pp. 1319-25, Nov 2013, doi: 10.1586/14737140.2013.852473.
[6] W. Wick and W. Küker, "Brain edema in neurooncology: radiological assessment and management," (in eng), Onkologie, vol. 27, no. 3, pp. 261-6, Jun 2004, doi: 10.1159/000077976.
[7] E. R. Gerstner et al., "VEGF inhibitors in the treatment of cerebral edema in patients with brain cancer," (in eng), Nat Rev Clin Oncol, vol. 6, no. 4, pp. 229-36, Apr 2009, doi: 10.1038/nrclinonc.2009.14.
[8] W. Stummer, "Mechanisms of tumor-related brain edema," (in eng), Neurosurg Focus, vol. 22, no. 5, p. E8, May 15 2007, doi: 10.3171/foc.2007.22.5.9.
[9] J. Jośko and K. Knefel, "The role of vascular endothelial growth factor in cerebral oedema formation," (in eng), Folia Neuropathol, vol. 41, no. 3, pp. 161-6, 2003.
[10] I. Njeh et al., "3D multimodal MRI brain glioma tumor and edema segmentation: a graph cut distribution matching approach," (in eng), Comput Med Imaging Graph, vol. 40, pp. 108-19, Mar 2015, doi: 10.1016/j.compmedimag.2014.10.009.
[11] B. N. Saha, N. Ray, R. Greiner, A. Murtha, and H. Zhang, "Quick detection of brain tumors and edemas: a bounding box method using symmetry," (in eng), Comput Med Imaging Graph, vol. 36, no. 2, pp. 95-107, Mar 2012, doi: 10.1016/j.compmedimag.2011.06.001.
[12] C. Zhang, X. Shen, H. Cheng, and Q. Qian, "Brain Tumor Segmentation Based on Hybrid Clustering and Morphological Operations," (in eng), Int J Biomed Imaging, vol. 2019, p. 7305832, 2019, doi: 10.1155/2019/7305832.
[13] A. Demirhan, M. Törü, and I. Güler, "Segmentation of tumor and edema along with healthy tissues of brain using wavelets and neural networks," IEEE journal of biomedical and health informatics, vol. 19, no. 4, pp. 1451-1458, 2014.
[14] T. Kohonen, "The self-organizing map," Proceedings of the IEEE, vol. 78, no. 9, pp. 1464-1480, 1990.
[15] M. I. Razzak, M. Imran, and G. Xu, "Efficient brain tumor segmentation with multiscale two-pathway-group conventional neural networks," IEEE journal of biomedical and health informatics, vol. 23, no. 5, pp. 1911-1919, 2018.
[16] K. Kamnitsas et al., "Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation," Medical image analysis, vol. 36, pp. 61-78, 2017.
[17] K. Kamnitsas et al., "DeepMedic for brain tumor segmentation," in Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries: Second International Workshop, BrainLes 2016, with the Challenges on BRATS, ISLES and mTOP 2016, Held in Conjunction with MICCAI 2016, Athens, Greece, October 17, 2016, Revised Selected Papers 2, 2016: Springer, pp. 138-149.
[18] K. He, G. Gkioxari, P. Dollar, and R. Girshick, "Mask R-CNN," (in eng), IEEE Trans Pattern Anal Mach Intell, vol. 42, no. 2, pp. 386-397, Feb 2020, doi: 10.1109/tpami.2018.2844175.
[19] R. Girshick, J. Donahue, T. Darrell, and J. Malik, "Rich feature hierarchies for accurate object detection and semantic segmentation," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2014, pp. 580-587.
[20] R. Girshick, "Fast R-CNN. Proceedings of the IEEE International Conference on Computer Vision (ICCV)," 2015.
[21] S. Ren, K. He, R. Girshick, and J. Sun, "Faster r-cnn: Towards real-time object detection with region proposal networks," Advances in neural information processing systems, vol. 28, 2015.
[22] J. R. Uijlings, K. E. Van De Sande, T. Gevers, and A. W. Smeulders, "Selective search for object recognition," International journal of computer vision, vol. 104, pp. 154-171, 2013.
[23] Han D (2013) Comparison of commonly used image interpolation methods. In: Proceedings of the 2nd international conference on computer science and electronic engineering (ICCSEE 2013), pp 1556–1559.
[24] T. M. Lehmann, C. Gonner, and K. Spitzer, "Addendum: B-spline interpolation in medical image processing," IEEE Transactions on Medical Imaging, vol. 20, pp. 660-665, 2001.
[25] J. Nalepa, M. Marcinkiewicz, and M. Kawulok, "Data augmentation for brain-tumor segmentation: a review," Frontiers in computational neuroscience, vol. 13, p. 83, 2019.
[26] S. S. M. Salehi, D. Erdogmus, and A. Gholipour, "Auto-Context Convolutional Neural Network (Auto-Net) for Brain Extraction in Magnetic Resonance Imaging," IEEE Transactions on Medical Imaging, vol. 36, no. 11, pp. 2319-2330, 2017, doi: 10.1109/TMI.2017.2721362.
[27] Isensee, F.Schell, M.Pflueger, I.Brugnara, G.Bonekamp, D.Neuberger, U.Wick, A.Schlemmer, H. P.Heiland, S.Wick, W.Bendszus, M.Maier-Hein, K. H.Kickingereder, P., "Automated brain extraction of multisequence MRI using artificial neural networks," (in eng), Hum Brain Mapp, vol. 40, no. 17, pp. 4952-4964, Dec 1 2019, doi: 10.1002/hbm.24750.
[28] S. Karuppanagounder, P. Kalaividya, and K. Thiruvenkadam, "Brain Extraction Algorithm for T1 of Human Head Scans Brain Extraction Algorithm for T1-W and T2-W of Human Head Scans," International Journal of Computational Intelligence and Informatics, vol. 5, pp. 47-57, 07/01 2015.
[29] Kleesiek, Jens Urban, Gregor Hubert, Alexander Schwarz, Daniel Maier-Hein, Klaus Bendszus, Martin Biller, Armin., "Deep MRI brain extraction: A 3D convolutional neural network for skull stripping," NeuroImage, vol. 129, pp. 460-469, 2016/04/01/ 2016, doi:DOI: 10.1016/j.neuroimage.2016.01.024.
[30] Ranjbar, Sara Singleton, Kyle Curtin, Lee Rickertsen, Cassandra Paulson, Lisa Hu, Leland Mitchell, Joseph Swanson, Kristin, Robust Automatic Whole Brain Extraction on Magnetic Resonance Imaging of Brain Tumor Patients using Dense-Vnet. 2020.
[31] M. Laha, P. C. Tripathi, and S. Bag, "A skull stripping from brain MRI using adaptive iterative thresholding and mathematical morphology," in 2018 4th International Conference on Recent Advances in Information Technology (RAIT), 2018: IEEE, pp. 1-6.
[32] Q. Jiaqing and C. Wenqiang, "Brain tissues extraction based on improved Brain Extraction Tool algorithm," in 2016 2nd IEEE International Conference on Computer and Communications (ICCC), 14-17 Oct. 2016 2016, pp. 553-556, doi: 10.1109/CompComm.2016.7924762.
[33] A. Chaddad and C. Tanougast, "Quantitative evaluation of robust skull stripping and tumor detection applied to axial MR images," Brain Informatics, vol. 3, no. 1, pp. 53-61, 2016/03/01 2016, doi: 10.1007/s40708-016-0033-7.
[34] K. Xie, J. Yang, Z. G. Zhang, and Y. M. Zhu, "Semi-automated brain tumor and edema segmentation using MRI," (in eng), Eur J Radiol, vol. 56, no. 1, pp. 12-9, Oct 2005, doi: 10.1016/j.ejrad.2005.03.028.
[35] Chen, Yasheng Dhar, Rajat Heitsch, Laura Ford, Andria Fernandez Cadenas, Israel Carrera, Caty Montaner, Joan Lin, Weili Shen, Dinggang An, Hongyu, "Automated quantification of cerebral edema following hemispheric infarction: application of a machine-learning algorithm to evaluate CSF shifts on serial head CTs," NeuroImage: Clinical, vol. 12, pp. 673-680, 2016.
[36] Zhao, Xianjing Chen, Kaixing Wu, Ge Zhang, Guyue Zhou, Xin Lv, Chuanfeng Wu, Shiman Chen, Yun Xie, Guotong Yao, Zhenwei, "Deep learning shows good reliability for automatic segmentation and volume measurement of brain hemorrhage, intraventricular extension, and peripheral edema," European Radiology, vol. 31, no. 7, pp. 5012-5020, 2021/07/01 2021, doi: 10.1007/s00330-020-07558-2.
[37] Yong En Kok Stefan Pszczolkowski Zhe Kang Law Azlinawati Ali Kailash Krishnan Philip M. Bath Nikola Sprigg Robert A. Dineen Andrew P. French, "Semantic Segmentation of Spontaneous Intracerebral Hemorrhage, Intraventricular Hemorrhage, and Associated Edema on CT Images Using Deep Learning," Radiology: Artificial Intelligence, vol. 4, no. 6, p. e220096, 2022, doi: 10.1148/ryai.220096.
[38] W. Tu, L. Kong, R. Karunamuni, K. Butcher, L. Zheng, and R. McCourt, "Nonlocal spatial clustering in automated brain hematoma and edema segmentation," Applied Stochastic Models in Business and Industry, vol. 35, no. 2, pp. 321-329, 2019.
[39] Dhar, R.Falcone, G. J.Chen, Y.Hamzehloo, A.Kirsch, E. P.Noche, R. B.Roth, K.Acosta, J.Ruiz, A.Phuah, C. L.Woo, D.Gill, T. M.Sheth, K. N.Lee, J. M., "Deep Learning for Automated Measurement of Hemorrhage and Perihematomal Edema in Supratentorial Intracerebral Hemorrhage," (in eng), Stroke, vol. 51, no. 2, pp. 648-651, Feb 2020, doi: 10.1161/strokeaha.119.027657.
[40] S. Reza and K. M. Iftekharuddin, "Multi-fractal texture features for brain tumor and edema segmentation," in Medical Imaging 2014: Computer-Aided Diagnosis, 2014, vol. 9035: SPIE, pp. 11-20.
[41] C. Sun, A. Shrivastava, S. Singh, and A. Gupta, "Revisiting unreasonable effectiveness of data in deep learning era," in Proceedings of the IEEE international conference on computer vision, 2017, pp. 843-852.
[42] M. H. Hesamian, W. Jia, X. He, and P. Kennedy, "Deep Learning Techniques for Medical Image Segmentation: Achievements and Challenges," Journal of Digital Imaging, vol. 32, no. 4, pp. 582-596, 2019/08/01 2019, doi: 10.1007/s10278-019-00227-x.
[43] J. G. A. Barbedo, "Impact of dataset size and variety on the effectiveness of deep learning and transfer learning for plant disease classification," Computers and Electronics in Agriculture, vol. 153, pp. 46-53, 2018/10/01/ 2018, doi: https://doi.org/10.1016/j.compag.2018.08.013.
[44] H. Abu Alhaija, S. K. Mustikovela, L. Mescheder, A. Geiger, and C. Rother, "Augmented Reality Meets Computer Vision: Efficient Data Generation for Urban Driving Scenes," International Journal of Computer Vision, vol. 126, no. 9, pp. 961-972, 2018/09/01 2018, doi: 10.1007/s11263-018-1070-x.
[45] Bauknecht, Hans-Christian Romano, Valentina C. Rogalla, Patrik Klingebiel, Randolf Wolf, Claudia Bornemann, Lars Hamm, Bernd Hein, Patrick A., "Intra- and Interobserver Variability of Linear and Volumetric Measurements of Brain Metastases Using Contrast-Enhanced Magnetic Resonance Imaging," Investigative Radiology, vol. 45, no. 1, 2010. [Online]. Available: https://journals.lww.com/investigativeradiology/Fulltext/2010/01000/Intra__and_Interobserver_Variability_of_Linear_and.8.aspx.
[46] Bertels, Jeroen Eelbode, Tom Berman, Maxim Vandermeulen, Dirk Maes, Frederik Bisschops, Raf Blaschko, Matthew B., "Optimizing the dice score and jaccard index for medical image segmentation: Theory and practice," in Medical Image Computing and Computer Assisted Intervention–MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13–17, 2019, Proceedings, Part II 22, 2019: Springer, pp. 92-100.
[47] S. K. Yoo et al., "Deep-Learning-Based Automatic Detection and Segmentation of Brain Metastases with Small Volume for Stereotactic Ablative Radiotherapy," (in eng), Cancers (Basel), vol. 14, no. 10, May 23 2022, doi: 10.3390/cancers14102555.
[48] Li, C. C.Wu, M. Y.Sun, Y. C.Chen, H. H.Wu, H. M.Fang, S. T.Chung, W. Y.Guo, W. Y.Lu, H. H., "Ensemble classification and segmentation for intracranial metastatic tumors on MRI images based on 2D U-nets," (in eng), Sci Rep, vol. 11, no. 1, p. 20634, Oct 19 2021, doi: 10.1038/s41598-021-99984-5.
[49] Ziyaee, H.Cardenas, C. E.Yeboa, D. N.Li, J.Ferguson, S. D.Johnson, J.Zhou, Z.Sanders, J.Mumme, R.Court, L.Briere, T.Yang, J., "Automated Brain Metastases Segmentation With a Deep Dive Into False-positive Detection," (in eng), Adv Radiat Oncol, vol. 8, no. 1, p. 101085, Jan-Feb 2023, doi: 10.1016/j.adro.2022.101085.
[50] Huang, Y.Bert, C.Sommer, P.Frey, B.Gaipl, U.Distel, L. V.Weissmann, T.Uder, M.Schmidt, M. A.Dörfler, A.Maier, A.Fietkau, R.Putz, F., "Deep learning for brain metastasis detection and segmentation in longitudinal MRI data," (in eng), Med Phys, vol. 49, no. 9, pp. 5773-5786, Sep 2022, doi: 10.1002/mp.15863.
[51] Wang, Jen-Yeu Qu, Vera Hui, Caressa Sandhu, Navjot Mendoza, Maria G.Panjwani, Neil Chang, Yu-Cheng Liang, Chih-Hung Lu, Jen Tang Wang, Lei Kovalchuk, Nataliya Gensheimer, Michael F.Soltys,Scott G.Pollom, Erqi L., "Stratified assessment of an FDA-cleared deep learning algorithm for automated detection and contouring of metastatic brain tumors in stereotactic radiosurgery," Radiation Oncology, vol. 18, no. 1, p. 61, 2023/04/04 2023, doi: 10.1186/s13014-023-02246-z.
[52] Wang, Jen-Yeu Sandhu, Navjot Mendoza, Maria Lin, Jhih-Yuan Cheng, Yueh-Hung Chang, Yu-Cheng Liang, Chih-Hung Lu, Jen-Tang Soltys, Scott Pollom, Erqi., "RADI-12. Deep learning for automatic detection and contouring of metastatic brain tumors in stereotactic radiosurgery: a retrospective analysis with an FDA-cleared software algorithm," Neuro-Oncology Advances, vol. 3, no. Supplement_3, pp. iii20-iii20, 2021, doi: 10.1093/noajnl/vdab071.082.
[53] N. Chitphakdithai, V. L. Chiang, and J. S. Duncan, "Tracking Metastatic Brain Tumors in Longitudinal Scans via Joint Image Registration and Labeling," (in eng), Spatiotemporal Image Anal Longitud Time Ser Image Data (2012), vol. 7570, pp. 124-136, Oct 2012, doi: 10.1007/978-3-642-33555-6_11.