近年來隨著生醫影像大量的數位化，人們可開發出不同的演算法對它們進行分析以解決對應的問題。本研究旨在建立一套自動化的硼中子捕獲治療(Boron Neutron Capture Therapy，BNCT)劑量分析系統，先藉著卷積神經網路(Convolutional Neural Networks，CNNs)自動且快速地進行電腦斷層掃描(Computed Tomography，CT)影像之腫瘤偵測，接著使用蒙地卡羅方法(Monte Carlo Method)進行劑量分析，用以評估病患接受BNCT之治療前最佳的照射時間，避免正常組織接收到過多的劑量。
系統的建構分成兩階段，第一階段對原始CT影像進行前處理，並訓練輸入串接(Input Cascaded)多尺度分析模型對小細胞肺癌小鼠CT影像進行腫瘤辨識，建立一個高準確率的辨識系統，第二階段藉由腫瘤辨識模型所預測出的腫瘤區域建置均質化小鼠肺癌體素模型，並使用蒙地卡羅計算程式(Monte Carlo N-particle transport code，MCNP)計算經由清華水池式反應器(Tsing Hua Open Pool Reactor，THOR)照射，小鼠體內器官組織在不同T/N Ratio下之劑量分佈。在腫瘤辨識的部分，經過訓練的腫瘤辨識模型對腫瘤區域有超過90%的成功率，預測整筆3D影像(512張2D切片)只需約1小時的時間，能夠正確且迅速地找出影像中之腫瘤組織。在劑量分析的部分，我們對MCNP的輸出檔進行分析，發現在T/N Ratio大於2時，可以在不超過正常組織的耐受劑量的情況下殺死腫瘤細胞，且治療可在1小時內完成。

With the increasing digitization of a large number of biomedical images, people can develop different algorithms to analyze them for different purposes. This study aims to establish a treatment planning system for Boron Neutron Capture Therapy (BNCT). The system first uses the proposed convolutional neural networks (CNNs) to automatically detect tumors from computed tomography (CT) images, followed by Monte Carlo Method for dose analysis for best irradiation time to prevent normal tissues from receiving too much dose.
The construction of the system is divided into two stages. In the first stage, the original CT images are pre-processed, and the Input Cascaded multi-scale analysis model is trained to perform tumor delineation on CT images of mice with small cell lung cancer to establish a high-accuracy delineation system. The second stage is to build a homogenized mouse lung cancer voxel model based on the tumor areas delineated by the delineation system and use Monte Carlo N-particle transport code (MCNP) to calculate the dose distribution of organs and tissues in mice under different T/N Ratio through Tsing Hua Open Pool Reactor (THOR) irradiation. For tumor delineation, the obtained model achieved a success rate of more than 90%. Moreover, It took approximately 1 hour to process the entire image stack (512 2D slices). As for dose analysis, we analyzed the output file of MCNP and found that when T/N Ratio was more than 2, tumor cells could be effectively dealt with without exceeding the tolerated dose of normal tissues.

摘要 i
Abstract ii
誌謝 iii
目錄 iv
圖目錄 vii
表目錄 ix
第一章 緒論 1
1.1研究動機 1
1.2文獻回顧 2
1.3研究架構 4
第二章 深度學習 5
2.1神經網路介紹 5
2.1.1類神經網路 6
2.1.2活化函數 6
2.2最佳化方法 7
2.2.1損失函數 8
2.2.2梯度下降法 8
2.2.3反向傳播法 8
2.3卷積神經網路 9
2.3.1卷積層 9
2.3.2池化層 11
2.3.3全連接層 13
第三章 蒙地卡羅方法 14
3.1幾何描述建立 14
3.1.1曲面卡 14
3.1.2柵元卡 15
3.2資料卡 15
3.2.1材料卡 15
3.2.2射源描述 15
3.2.3計數卡 17
第四章 實驗數據 19
4.1數據來源 19
4.2數據格式 19
4.3數據標注 20
4.4數據分配 20
第五章 實驗方法 21
5.1數據前處理 21
5.1.1直方圖均化(Histogram equalization) 22
5.1.2數據切割 23
5.1.3數據增強 24
5.2 Input Cascaded神經網路架構 25
5.3劑量分析 27
5.3.1均質化濃縮 27
5.3.2組織分類 28
5.3.3組織合併 30
5.3.4定義射源卡與計數卡 31
5.3.5輸出檔分析 32
第六章 實驗結果與討論 33
6.1腫瘤分割 33
6.1.1評估指標 33
6.1.2結果呈現 34
6.1.3結果討論 38
6.2劑量分析 39
6.2.1評估指標 39
6.2.2結果呈現 39
6.2.3結果討論 41
第七章 總結 42
參考資料 43

[1] R. F. Barth, A. H. Soloway, and R. G. Fairchild, "Boron neutron capture therapy for cancer," Scientific American, vol. 263, no. 4, pp. 100-107, 1990.
[2] R. F. Barth, A. H. Soloway, R. G. Fairchild, and R. M. Brugger, "Boron neutron capture therapy for cancer. Realities and prospects," Cancer, vol. 70, no. 12, pp. 2995-3007, 1992.
[3] R. F. Barth, J. A. Coderre, M. G. H. Vicente, and T. E. Blue, "Boron neutron capture therapy of cancer: current status and future prospects," Clinical Cancer Research, vol. 11, no. 11, pp. 3987-4002, 2005.
[4] H. R. Withers, J. M. Taylor, and B. Maciejewski, "Treatment volume and tissue tolerance," International Journal of Radiation Oncology* Biology* Physics, vol. 14, no. 4, pp. 751-759, 1988.
[5] T. Aihara and N. Morita, "BNCT for advanced or recurrent head and neck cancer," in Neutron Capture Therapy: Springer, 2012, pp. 417-424.
[6] K. Hideghéty et al., "Postoperative treatment of glioblastoma with BNCT at the Petten irradiation facility (EORTC Protocol 11961)," Strahlentherapie und onkologie, vol. 175, no. 2, p. 111, 1999.
[7] S. S. Raab et al., "Clinical impact and frequency of anatomic pathology errors in cancer diagnoses," Cancer: Interdisciplinary International Journal of the American Cancer Society, vol. 104, no. 10, pp. 2205-2213, 2005.
[8] J. Chadwick, "The existence of a neutron," Proceedings of the Royal Society of London. Series A, Containing Papers of a Mathematical and Physical Character, vol. 136, no. 830, pp. 692-708, 1932.
[9] G. Locher, "A-BNCT," Am. J. Roentgenol, vol. 36, pp. 1-13, 1936.
[10] F. Le, S. WH, L. HB, and R. JS, "Neutron capture therapy of gliomas using boron," Transactions of the American Neurological Association, vol. 13, no. 79th Meeting, pp. 110-113, 1954.
[11] J. Archambeau, " The effect of increasing exposures of the 10B(n,a)7Li reaction on the skin of man," Meadowbrook Hospital, East Meadow, NY Brookhaven National Lab., Upton, NY, 1970.
[12] D. N. Slatkin, "A history of boron neutron capture therapy of brain tumours: postulation of a brain radiation dose tolerance limit," Brain, vol. 114, no. 4, pp. 1609-1629, 1991.
[13] W. Sweet, A. Soloway, and G. Brownell, "Boron-slow neutron capture therapy of gliomas," Acta Radiologica: Therapy, Physics, Biology, vol. 1, no. 2, pp. 114-121, 1963.
[14] A. K. Asbury, R. G. Ojemann, S. L. Nielsen, and W. H. Sweet, "Neuropathologic study of fourteen cases of malignant brain tumor treated by boron-10 slow neutron capture radiation," Journal of Neuropathology & Experimental Neurology, vol. 31, no. 2, pp. 278-303, 1972.
[15] H. Hatanaka, "Boron-neutron capture therapy for tumors," in Glioma: Springer, 1991, pp. 233-249.
[16] H. Hatanaka, K. Sano, and H. Yasukochi, "Clinical results of boron neutron capture therapy," in Progress in neutron capture therapy for cancer: Springer, 1992, pp. 561-568.
[17] H. Hatanaka, W. Sweet, K. Sano, and F. Ellis, "The present status of boron-neutron capture therapy for tumors," Pure and applied chemistry, vol. 63, no. 3, pp. 373-374, 1991.
[18] Y. Mishima et al., "First human clinical trial of melanoma neutron capture. Diagnosis and therapy," Strahlentherapie und Onkologie, vol. 165, no. 2/3, pp. 251-254, 1989.
[19] R. L. Moss, "Critical review, with an optimistic outlook, on Boron Neutron Capture Therapy (BNCT)," Applied Radiation and Isotopes, vol. 88, pp. 2-11, 2014.
[20] K. Nedunchezhian, N. Aswath, M. Thiruppathy, and S. Thirugnanamurthy, "Boron neutron capture therapy-a literature review," Journal of clinical and diagnostic research: JCDR, vol. 10, no. 12, p. ZE01, 2016.
[21] S. I. Haginomori et al., "Planned fractionated boron neutron capture therapy using epithermal neutrons for a patient with recurrent squamous cell carcinoma in the temporal bone: a case report," Head & neck, vol. 31, no. 3, pp. 412-418, 2009.
[22] T. Aihara et al., "First clinical case of boron neutron capture therapy for head and neck malignancies using 18F‐BPA PET," Head & Neck: Journal for the Sciences and Specialties of the Head and Neck, vol. 28, no. 9, pp. 850-855, 2006.
[23] L.-W. Wang et al., "Fractionated boron neutron capture therapy in locally recurrent head and neck cancer: a prospective phase I/II trial," International Journal of Radiation Oncology* Biology* Physics, vol. 95, no. 1, pp. 396-403, 2016.
[24] M. Suzuki et al., "Reirradiation for locally recurrent lung cancer in the chest wall with boron neutron capture therapy (BNCT)," in International Cancer Conference Journal, 2012, vol. 1, no. 4: Springer, pp. 235-238.
[25] C. Cortes and V. Vapnik, "Support-vector networks," Machine learning, vol. 20, no. 3, pp. 273-297, 1995.
[26] D. Pregibon, "Logistic regression diagnostics," The annals of statistics, vol. 9, no. 4, pp. 705-724, 1981.
[27] J. Dehmeshki, J. Chen, M. V. Casique, and M. Karakoy, "Classification of lung data by sampling and support vector machine," in The 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2004, vol. 2: IEEE, pp. 3194-3197.
[28] C. Lombardi, G. Tassi, G. Pizzocolo, and F. Donato, "Clinical significance of a multiple biomarker assay in patients with lung cancer: a study with logistic regression analysis," Chest, vol. 97, no. 3, pp. 639-644, 1990.
[29] Y. LeCun and Y. Bengio, "Convolutional networks for images, speech, and time series," The handbook of brain theory and neural networks, vol. 3361, no. 10, p. 1995, 1995.
[30] A. Krizhevsky, I. Sutskever, and G. E. Hinton, "Imagenet classification with deep convolutional neural networks," Advances in neural information processing systems, vol. 25, pp. 1097-1105, 2012.
[31] O. Russakovsky et al., "Imagenet large scale visual recognition challenge," International journal of computer vision, vol. 115, no. 3, pp. 211-252, 2015.
[32] K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale image recognition," arXiv preprint arXiv:1409.1556, 2014.
[33] C. Szegedy et al., "Going deeper with convolutions," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp. 1-9.
[34] R. Hecht-Nielsen, "Theory of the backpropagation neural network," in Neural networks for perception: Elsevier, 1992, pp. 65-93.
[35] S.-C. Wang, "Artificial neural network," in Interdisciplinary computing in java programming: Springer, 2003, pp. 81-100.
[36] B. Xu, N. Wang, T. Chen, and M. Li, "Empirical evaluation of rectified activations in convolutional network," arXiv preprint arXiv:1505.00853, 2015.
[37] F. Schorfheide, "Loss function‐based evaluation of DSGE models," Journal of Applied Econometrics, vol. 15, no. 6, pp. 645-670, 2000.
[38] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, 1998.
[39] R. Nevatia and K. R. Babu, "Linear feature extraction and description," Computer Graphics and Image Processing, vol. 13, no. 3, pp. 257-269, 1980.
[40] N. Metropolis and S. Ulam, "The monte carlo method," Journal of the American statistical association, vol. 44, no. 247, pp. 335-341, 1949.
[41] A. L. Reed, "Medical physics calculations with MCNP: a primer," Boston, MA: Los Alamos National Laboratory, X-3 MCC, LA-UR-07-4133, 2007.
[42] P. Mildenberger, M. Eichelberg, and E. Martin, "Introduction to the DICOM standard," European radiology, vol. 12, no. 4, pp. 920-927, 2002.
[43] S. Pieper, M. Halle, and R. Kikinis, "3D Slicer," in 2004 2nd IEEE international symposium on biomedical imaging: nano to macro (IEEE Cat No. 04EX821), 2004: IEEE, pp. 632-635.
[44] S. B. Kotsiantis, D. Kanellopoulos, and P. E. Pintelas, "Data preprocessing for supervised leaning," International journal of computer science, vol. 1, no. 2, pp. 111-117, 2006.
[45] S. M. Pizer et al., "Adaptive histogram equalization and its variations," Computer vision, graphics, and image processing, vol. 39, no. 3, pp. 355-368, 1987.
[46] J. Wang and L. Perez, "The effectiveness of data augmentation in image classification using deep learning," Convolutional Neural Networks Vis. Recognit, vol. 11, pp. 1-8, 2017.
[47] J. Long, E. Shelhamer, and T. Darrell, "Fully convolutional networks for semantic segmentation," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp. 3431-3440.
[48] M. Havaei et al., "Brain tumor segmentation with deep neural networks," Medical image analysis, vol. 35, pp. 18-31, 2017.
[49] U. Schneider, E. Pedroni, and A. Lomax, "The calibration of CT Hounsfield units for radiotherapy treatment planning," Physics in Medicine & Biology, vol. 41, no. 1, p. 111, 1996.
[50] Y.-W. Liu, T. Huang, S. Jiang, and H. Liu, "Renovation of epithermal neutron beam for BNCT at THOR," Applied radiation and isotopes, vol. 61, no. 5, pp. 1039-1043, 2004.
[51] B. Emami et al., "Tolerance of normal tissue to therapeutic irradiation," International Journal of Radiation Oncology* Biology* Physics, vol. 21, no. 1, pp. 109-122, 1991.