請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/51254
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 林文澧(Win-Li Lin) | |
dc.contributor.author | Yen-Ning Hsu | en |
dc.contributor.author | 許晏寧 | zh_TW |
dc.date.accessioned | 2021-06-15T13:28:39Z | - |
dc.date.available | 2020-08-20 | |
dc.date.copyright | 2020-08-20 | |
dc.date.issued | 2020 | |
dc.date.submitted | 2020-08-11 | |
dc.identifier.citation | 1. Dorr W and Hendry JH. (2001) Consequential late effects in normal tissues. Radiotherapy and Oncology, 61(3), 223-231. 2. 劉子維. (2014) 應用於放射線所造成肌肉組織傷害之超音波影像分析方法. 國立臺灣大學醫學工程學研究所學位論文. 3. Zhao Y, Haginoya K, and Sun G, et al. (2003) Platelet‐derived growth factor and its receptors are related to the progression of human muscular dystrophy: an immunohistochemical study. The Journal of Pathology, 201(1), 149-159. 4. Hall EJ and Giaccia AJ. (2012) Radiobiology for the Radiologist 7th. Lippincott Williams Wilkins. 5. Hobbie RK and Roth BJ. (2007) Intermediate Physics for Medicine and Biology 4th. Springer. 6. Citrin D, Cotrim AP, and Hyodo F, et al. (2010) Radioprotectors and mitigators of radiation-induced normal tissue injury. Oncologist, 15(4), 360-371. 7. Johansson S, Svensson H, and Denekamp J. (2000) Timescale of evolution of late radiation injury after postoperative radiotherapy of breast cancer patients. International Journal of Radiation Oncology Biology Physics, 48(3), 745-750. 8. Furby A, Behin A, and Lefaucheur JP, et al. (2010) Late-onset cervicoscapular muscle atrophy and weakness after radiotherapy for Hodgkin disease: a case series. Journal of Neurology, Neurosurg and Psychiatry, 81(1), 101-104. 9. van Leeuwen-Segarceanu EM, Dorresteijn LD, and Pillen S, et al. (2012) Progressive muscle atrophy and weakness after treatment by mantle field radiotherapy in Hodgkin lymphoma survivors. International Journal of Radiation Oncology Biology Physics, 82(2), 612-618. 10. Hughes S. (2001) Medical ultrasound imaging. Electronic Journals of Physics Education, 36, 468-475. 11. O’Mahony N, Campbell S, and Carvalho A, et al. (2019) Deep Learning vs. Traditional Computer Vision. In Science and Information Conference, 128-144. 12. Lin Y, Xu X, and Ou J, et al. (2017) Machine learning for mask/water hotspot detection and mask synthesis. Photomask Technology, 10451. 13. LeCun Y, Bengio Y, and Hinton G. (2015) Deep learning. Nature, 521, 436-444. 14. Delanian S and Lefaix JL. (2007) Current management for late normal tissue injury: radiation-induced fibrosis and necrosis. Seminars in Radiation Oncology, 17(2), 99-107. 15. Maurits NM, Bollen AE, and Windhausen A, et al. (2003) Muscle ultrasound analysis: normal values and differentiation between myopathies and neuropathies. Ultrasound in Medicine and Biology, 29(2), 215-225. 16. Pillen S, Tak RO, and Zwarts MJ, et al. (2009) Skeletal muscle ultrasound: correlation between fibrous tissue and echo intensity. Ultrasound in Medicine and Biology, 35(3), 443-446. 17. 郭哲源. (2017) 利用超音波影像評估經放射線治療後頭頸部癌症病患肌肉纖維化之量化研究. 國立臺灣大學醫學工程學研究所學位論文. 18. Liu S, Wang Y, and Yang X, et al. (2019) Deep Learning in Medical Ultrasound Analysis: A Review. Engineering, 5(2), 261-275. 19. Brattain LJ, Telfer BA, and Dhyani M, et al. (2019) Machine Learning for Medical Ultrasound: Status, Methods, and Future Opportunities. Abdominal Radiology, 43(4), 786-799. 20. Cruz-Aceves I, Oloumi F, and Rangayyan RM, et al. (2016) Automatic segmentation of coronary arteries using Gabor filters and thresholding based on multiobjective optimization. Biomedical Signal Processing and Control, 25, 76-85. 21. Hadjerci O, Hafiane A, and Conte D, et al. (2016) Computer-aided detection system for nerve identification using ultrasound images: A comparative study. Informatics in Medicine Unlocked, 3, 29-43. 22. Long J, Shelhamer E, and Darrell T. (2015) Fully Convolutional Networks for Semantic Segmentation. In Computer Vision and Pattern Recognition (CVPR). 23. Ronneberger O, Fischer P, and Brox T. (2015) U-Net: Convolutional Networks for Biomedical Image Segmentation. MICCAI, 935, 234-241. 24. Kakade A and Dumbali J. (2018) Identification of Nerve in Ultrasound Images Using U-net Architecture. In Communication information and Computing Technology (ICCICT). 25. Yasaka K, Akai H, and Kunimatsu A, et al. (2018) Deep Learning with Convolutional Neural Network in Radiology. Japanese Journal of Radiology, 36(4), 257-272. 26. Milletari F, Navab N, and Ahmadi SA. (2016) V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation. arXiv:1606.04797. 27. Dice LR. (1945) Measures of the Amount of Ecologic Association Between Species. Ecology, 26(3), 297-302. 28. Visa S, Ramsay B, and Ralescu A, et al. (2011) Confusion Matrix-based Feature Selection. The 22nd Midwest Artificial Intelligence and Cognitive Science Conference, 1-8. 29. Tharwat A. (2018) Classification assessment methods. Applied Computing and Informatics, 1-13. 30. Liu SL, Niu ZD, and Sun G, et al. (2014) Gabor filter-based edge detection: A note. Optik, 125(15), 4120-4123. 31. Zainudin MSN, Said MM, and Ismail MM. (2011) Feature Extraction on Medical Image Using 2D Gabor Filter. Applied Mechanics and Materials, 52-54, 2128-2132. 32. Bosnjak A, Montilla G, and Torrealba V. (1998) Medical images segmentation using Gabor filters applied to echocardiographic images. Computers in Cardiology, 25, 457-460. 33. Jain AK, Ratha NK, and Lakshmanan S. (1997) Object detection using Gabor filters. Pattern Recognition, 30(2), 295-309. 34. Kamarainen JK, Kyrki V, and Kalviainen H. (2006) Invariance Properties of Gabor Filter Based Features-Overview and Applications. IEEE Transactions on Image Processing, 15(5), 1088-1099. 35. Horvath A, Spindler S, and Szalai M. (2016) Preprocessing Endoscopic Images of Colorectal Polyps. Acta Technica Jaurinensis, 9(1), 65-82. 36. Boser BE, Guyon IM, and Vapnik V. (1992) A training algorithm for optimal margin classifiers. In Proceedings of the 5th Annual ACM Workshop on Computational Learning Theory, 144-152. 37. Cortes C and Vapnik V. (1995) Support-Vector Networks. Machine Learning, 20, 273-297. 38. Chang CC and Lin CJ. (2011) LIBSVM: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 2(3), 1-27. 39. Tax David MJ and Duin Robert PW. (1999) Support vector domain description. Pattern Recognition Letters, 20, 1191-1199. 40. Manevitz LM and Yousef M. (2001) One-Class SVMs for Document Classification. Journal of Machine Learning Research, 2, 139-154. 41. Xiao Y, Wang H, and Zhang L, et al. (2014) Two methods of selecting Gaussian kernel parameters for one-class SVM and their application to fault detection. Knowledge-Based Systems, 59, 75-84. 42. Huang Q, Zhang F, and Li X. (2018) Machine Learning in Ultrasound Computer-Aided Diagnostic Systems: A Survey. BioMed Research International, 1-10. 43. D’Souza JC, Sultan LR, and Hunt SJ, et al. (2019) B-mode ultrasound for the assessment of hepatic fibrosis: a quantitative multiparametric analysis for a radiomics approach. Scientific Reports 9, 1-10. 44. Goodman ZD. (2007) Grading and staging systems for inflammation and fibrosis in chronic liver diseases. Journal of Hepatology, 47, 598–607. 45. Lin YS. (2017) Ultrasound Evaluation of Liver Fibrosis. Journal of Medical Ultrasound, 25(3), 127-129. 46. Guermazi A, Roemer FW, and Robinson P, et al. (2017) Imaging of Muscle Injuries in Sports Medicine: Sports Imaging Series. Radiology, 282(3), 646-636. 47. Draghi F, Zacchino M, and Canepari M, et al. (2013) Muscle injuries: ultrasound evaluation in the acute phase. Journal of Ultrasound, 16(4), 209-214. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/51254 | - |
dc.description.abstract | 研究背景與目的 頭頸癌患者經放射線治療後,通常會發生肌肉纖維化的副作用,造成該肌肉僵硬與緊繃,使脖子無法轉動,嚴重地影響病患的生活品質,因此他們會定期且長期回醫院追蹤與檢查。在臨床診斷上,醫師通常利用觸診及肉眼判斷放射線治療前與後的肌肉超音波影像之變化情形,屬於主觀和定性的診斷方式。因此,本研究提出自動分割超音波影像上之肌肉與纖維分析的方法,輔助醫師以客觀和定量的角度評估肌肉受傷情形,進而預測放射線治療後的情況,藉此優化其治療策略與復健療程,改善病患往後的生活品質。 材料與方法 本研究共完整收案28位經66~70 Gy放射線治療的頭頸癌患者,包括20位男性和8位女性,年齡座落於28~69歲,採用其放射線治療前與後追蹤一年內的B型超音波影像。在影像分析方法上,主要分為肌肉分割與纖維量化這兩部分。首先,訓練U-Net深度神經網路來自動分割超音波影像上之胸鎖乳突肌,接著,將其肌肉進行Gabor濾波器和條件型自適應閾值演算法來概略分割纖維組織,此外,再利用單類別支持向量機涉及空間分布與表現,以提取更精確的纖維組織,最後,計算纖維比與其變化量以客觀評估該肌肉纖維化的嚴重程度。 結果 本研究結果顯示基於U-Net所分割超音波影像上之胸鎖乳突肌的評估指標,包括準確率達99%,Dice coefficient達96%,而精確率及召回率也達96%。在纖維分析方面,本研究發現放射線治療後3個月及6個月相較於放射線治療前的纖維比變化量有明顯增加,而1年後則有緩降趨勢。 結論 本研究提供一個客觀與量化的方式來分割超音波影像上之胸鎖乳突肌及分析其纖維比趨勢,而此方法可用於預測肌肉纖維化的預後情形,並輔助醫師找出最佳治療策略。 | zh_TW |
dc.description.abstract | Background and Objective Patients with head/neck cancer after receiving radiation therapy (RT) usually suffer from the side effects of muscle fibrosis, causing muscle stiffness and tightness and restricting the neck movement, and these deeply affect their life quality. Clinically, these patients need long-term follow-ups routinely with palpation and ultrasonography, which are subjective and qualitative diagnosis. In this study, we proposed automatic segmentation for muscle/fibers ultrasound images to help doctors objectively and quantitatively evaluate the damage condition of muscle, optimize treatment strategies and rehabilitation courses, and predict prognosis after RT. Materials and Methods In this study, 28 patients with head/neck cancer, 20 males and 8 females ranging from 28 to 69 years old, received 66~70 Gy during radiation treatment, and their B-mode ultrasound images were acquired before the treatment and during one year follow-ups. The proposed method was mainly divided into two parts: muscle segmentation and fiber quantification. It was firstly to train a U-Net to segment the sternocleidomastoid muscle (SCM) as ROI input for the next step, and secondly Gabor filter and Conditional adaptive thresholding methods were applied to segment the fibrotic tissue from the predicted SCM ROIs. In addition, we refined the segmentation of fibrotic tissue using One-Class Support vector machine (SVM) accounting for both spatial coherence and appearance. Finally, the ratio of fiber to muscle and its variations were calculated to objectively evaluate the severity of muscle fibrosis. Results Our results show that U-Net based SCM segmentation can achieve an Accuracy over 99% with a Dice coefficient of over 96%. The Precision and Recall are above 96%. The fiber analysis indicates that the variations of fiber/muscle ratio increase at 3 and 6 months after RT and decrease at 1 year after RT. Conclusion The proposed method is an objective and quantitative to segment SCM of the ultrasound image and analyze the condition of its fiber/muscle ratio. It can be used for forecasting the prognosis of muscle fibrosis and may support doctors’ decision-making in treating this symptom. | en |
dc.description.provenance | Made available in DSpace on 2021-06-15T13:28:39Z (GMT). No. of bitstreams: 1 U0001-1008202013302900.pdf: 3142013 bytes, checksum: 59f2f60cae6fbde1e5e94768df4fef4a (MD5) Previous issue date: 2020 | en |
dc.description.tableofcontents | 目錄 誌謝 i 中文摘要 ii Abstract iv 圖目錄 viii 表目錄 x 第一章、 緒論 1 1.1 頸部肌肉組織之生理構造 1 1.2 放射線治療(Radiation therapy, RT) 4 1.3 放射線治療對頭頸癌患者之影響 7 1.4 醫用診斷超音波 9 1.5 人工智慧(Artificial intelligence, AI) 12 1.6 研究動機與目的 14 第二章、 材料與方法 15 2.1 臨床收案分析 15 2.1.1 收案資訊與影像來源 15 2.1.2 資料集處理 18 2.2 影像分析架構 19 2.3 影像分析方法 21 2.3.1 U-Net 21 2.3.2 Gabor濾波器 27 2.3.3 條件型自適應閾值演算法 29 2.3.4 單類別支持向量機 31 第三章、 結果與討論 34 3.1 U-Net預測結果與討論 34 3.2 纖維分析與討論 40 3.3 臨床收案分析與討論 43 第四章、 結論與未來展望 49 參考文獻 50 | |
dc.language.iso | zh-TW | |
dc.title | 利用機器學習量化評估經放射線治療後頭頸癌患者之肌肉超音波影像 | zh_TW |
dc.title | Quantitative Evaluation of Muscle Ultrasound Images Using Machine Learning for Head/Neck Cancer Patients with Radiation Therapy | en |
dc.type | Thesis | |
dc.date.schoolyear | 108-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 陳永耀(Yung-Yaw Chen),陳景欣(Gin-Shin Chen) | |
dc.subject.keyword | B型超音波影像,頭頸部癌症,肌肉纖維化,U-Net,Gabor濾波器,條件型自適應閾值演算法,單類別支持向量機, | zh_TW |
dc.subject.keyword | B-mode ultrasound image,head/neck cancer,muscle fibrosis,U-Net,Gabor filter,Conditional adaptive thresholding,One-Class SVM, | en |
dc.relation.page | 54 | |
dc.identifier.doi | 10.6342/NTU202002794 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2020-08-12 | |
dc.contributor.author-college | 工學院 | zh_TW |
dc.contributor.author-dept | 醫學工程學研究所 | zh_TW |
顯示於系所單位: | 醫學工程學研究所 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
U0001-1008202013302900.pdf 目前未授權公開取用 | 3.07 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。