深度學習應用在牙科X光影像自動診斷牙周病已成為一種有用的技術。本論文提出利用影像前處理和卷積神經網路自動診斷牙周病，牙科X光影像先透過數據增強、對比限制自適應直方圖均化與非銳化遮罩的影像處理技術進行前處理，再利用改良之sVGGNet卷積神經網路進行診斷。所提出的方法在準確度、敏感度、特異度、精確度、F1分數和接收者操作特徵曲線下面積的效能評估皆優於參考文獻的效果。

Deep learning of dental X-ray image has been a useful technique for automatic diagnosis of periodontitis. This thesis proposes the automatic diagnosis of periodontitis using image preprocessing and the convolutional neural network (CNN). The dental X-ray images are processed by data augmentation and the image processing techniques of contrast limit adaptive histogram equalization and unsharp masking. The diagnosis of periodontitis is then implemented by the proposed sVGGNet. The detection performances of our proposed method in terms of accuracy, sensitivity, specificity, precision, F1 score and the area under the receiver-operating characteristic curve outperform those of previous works.

摘要 i
ABSTRACT iii
目錄 v
表目錄 viii
圖目錄 ix
第一章 緒論 1
1.1 人工智慧與醫療的應用 1
1.2研究動機 3
1.3論文架構 6
第二章 相關文獻回顧 7
2.1 深度學習與牙周病診斷 7
2.2 卷積神經網路 10
2.3 影像處理方法 16
2.3.1對比限制自適應直方圖均化 16
2.3.2非銳化遮罩 17
第三章 所提出的方法 19
3.1資料前處理 19
3.2 改良之卷積神經網路 27
3.3 實驗流程 30
第四章 實驗結果 33
4.1 模型評估方法 33
4.2影像前處理參數選擇 38
4.3整體實驗結果 44
第五章 結論 45
參考文獻 47

[1]M. I. Razzak, S. Naz, and A. Zaib, “Deep learning for medical image processing: overview, challenges and the future,” Classification in BioApps, Vol.26, Nov. 2017, pp. 323-350.
[2]K. Suzuki, “Overview of deep learning in medical imaging,” Radiological Physics and Technology, Vol.10, July 2017, pp.257-273.
[3]S. M. Anwar, M. Majid, A. Qayyum, M. Awais, M. Alnowami, and M. K. Khan, “Medical image analysis using convolutional neural networks: a review,” Journal of Medical Systems, Vol.42, October 2018, pp.226.
[4]M. Jagr, A. Eckhardt, S. Pataridis, Z. Broukal, J. Duskova, and I. Miksik, “Proteomics of human teeth and saliva,” Physiological Research, Vol. 63, Feb. 2014, pp.141-154.
[5]A. Falcao and P. Bullon, “A review of the influence of periodontal treatment in systemic diseases,” Periodontology 2000, Vol.79, Mar. 2019, pp.117-128.
[6]P. M. Preshaw, A. L. Alba, D. Herrera, S. Jepsen, A. Konstantinidis, K. Makrilakis, and R. Taylor, “Periodontitis and diabetes: a two-way relationship,” Diabetologia, Vol.55, Jan. 2012, pp.21-31.
[7]T. E. Van Dyke and S. Dave, “Risk Factors for Periodontitis,” International Academy of Periodontology, Vol.7, Jan. 2005, pp.3-7.
[8]M. A. Nazir, “Prevalence of periodontal disease, its association with systemic diseases and prevention,” International Journal of Health Sciences, Vol.11, June 2017, pp.72-80.
[9]GBD 2016 Disease and Injury Incidence and Prevalence Collaborators, “Global, regional, and national incidence, prevalence, and years lived with disability for 328 diseases and injuries for 195 countries, 1990-2016: a systematic analysis for the Global Burden of Disease Study 2016,” Lancet, vol.390, Sep. 2016, pp.1211-1259.
[10]R.G. Watt, A. Heilmann, S. Listl, and M.A. Peres, “London charter on oral health inequalities,” Journal of Dental Research, Vol.95, Mar. 2016, pp.7-245.
[11]D. F. Kinane, P. G. Stathopoulou, and P. N. Papapanou, “Periodontal diseases,” Nature Reviews Disease Primers, Vol. 3, June 2017.
[12]J. H. Lee, D. H. Kim, S. N. Jeong, and S. H. Choi, “Diagnosis and prediction of periodontally compromised teeth using a deep learning-based convolutional neural network algorithm,” Journal of Periodontal and Implant Science, Vol.48, Apr. 2018, pp.114-123.
[13]A. Gulli, and S. Pal, “Deep Learning with Keras,” Packt Publishing Ltd, 2017.
[14]K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” in Proceedings of International Conference on Learning Representations, Apr. 2015.
[15]J. Krois, T. Ekert, L. Meinhold, T. Golla, B. Kharbot, A. Wittemeier, C. Dörfer, and F. Schwendicke, “Deep learning for the radiographic detection of periodontal bone loss,” Scientific Reports, Vol.9, June 2019, pp.8495.
[16]J. Joo, S. Jeong, H. Jin, U. Lee, J. Y. Yoon, and S. C. Kim, “Periodontal disease detection using convolutional neural networks,” in Proceedings of 2019 International Conference on Artificial Intelligence in Information and Communication, Feb. 2019.
[17]W. Li, X. Jiang, W. Sun, S.H. Wang, C. Liu, X. Zhang, Y. D. Zhang, W. Zhou, and L. Miao, “Gingivitis identification via multichannel gray-level co-occurrence matrix and particle swarm optimization neural network,” International Journal of Imaging Systems and Technology, Vol.30, Dec. 2019, pp.401-411.
[18]M. Jogin, Mohana, M. S. Madhulika, G. D. Divya, R. K. Meghana, and S. Apoorva, “Feature extraction using convolution neural networks (CNN) and deep learning,” in Proceedings of 2018 3rd IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology, May 2018.
[19]S. Zubair, F.Yan, and W.Wang, “Dictionary learning based sparse coefficients for audio classification with max and average pooling,” Digital Signal Processing, Vol.23, May 2013, pp.960-970.
[20]N. Cui, “Applying gradient descent in convolutional neural networks,” Journal of Physics, Vol.1004, Feb. 2018, pp.23-25.
[21]D. Sun, Y. Chen, J. Liu, Y. Li, and R. Ma, “Digital signal modulation recognition algorithm based on VGGNet model,” in Proceedings of 2019 IEEE 5th International Conference on Computer and Communications, Dec. 2019.
[22]S. M. Pizer, E. P. Amburn, J. D. Austin, R. Cromartie, A. Geselowitz,T. Greer, B. H. Romeny, J. B. Zimmerman, and K. Zuiderveld, “Adaptive histogram equalization and its variations,” Computer Vision, Graphics, and Image Processing, Vol.39, Sep. 1987, pp.355-368.
[23]K. Zuiderveld, “Contrast limited adaptive histogram equalization,” Graphics gems IV, Academic Press, 1994.
[24]S. Chen and Y. Cai, “Enhancement of chest radiograph in emergency intensive care unit by means of reverse anisotropic diffusion-based unsharp masking model,” Diagnostics, Vol.9, Apr. 2019, pp.45.
[25]V. Bhateja, M. Misra, and S. Urooj, “Unsharp masking approaches for HVS based enhancement of mammographic masses: a comparative evaluation,” Future Generation Computer Systems, Vol.82, May 2018, pp. 176-189.
[26]K. Panetta, Y. Zhou, S. Agaian, and H. Jia, “Nonlinear unsharp masking for mammogram enhancement,” IEEE Transactions on Information Technology in Biomedicine, Vol.15, Nov. 2011, pp. 918-928.
[27]Y. Sano, T. Mori, T. Goto, S. Hirano, and K. Funahashi, “Super-resolution method and its application to medical image processing,” in Proceedings of 2017 IEEE 6th Global Conference on Consumer Electronics, Oct. 2017.
[28]X. Glorot, A. Bordes, and Y. Bengio, “Deep sparse rectifier neural networks,” in Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, Jan. 2011.