請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/70971完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 張書瑋(Shu-Wei Chang) | |
| dc.contributor.author | Pei-Hsin Chiu | en |
| dc.contributor.author | 邱霈欣 | zh_TW |
| dc.date.accessioned | 2021-06-17T04:46:24Z | - |
| dc.date.available | 2021-12-07 | |
| dc.date.copyright | 2020-08-24 | |
| dc.date.issued | 2020 | |
| dc.date.submitted | 2020-08-20 | |
| dc.identifier.citation | Feleus A, Bierma-Zeinstra S, Miedema H, Bernsen R, Verhaar J, Koes B: Incidence of non-traumatic complaints of arm, neck and shoulder in general practice. Manual Therapy 2008, 13(5):426-433. Ottenheijm RP, van’t Klooster IG, Starmans LM, Vanderdood K, de Bie RA, Dinant G-J, Cals JW: Ultrasound-diagnosed disorders in shoulder patients in daily general practice: a retrospective observational study. BMC family practice 2014, 15(1):115. Louwerens JK, Sierevelt IN, van Hove RP, van den Bekerom MP, van Noort A: Prevalence of calcific deposits within the rotator cuff tendons in adults with and without subacromial pain syndrome: clinical and radiologic analysis of 1219 patients. Journal of shoulder and elbow surgery 2015, 24(10):1588-1593. Serafini G, Sconfienza LM, Lacelli F, Silvestri E, Aliprandi A, Sardanelli F: Rotator cuff calcific tendonitis: short-term and 10-year outcomes after two-needle US-guided percutaneous treatment—nonrandomized controlled trial. Radiology 2009, 252(1):157-164. Gimblett PA, Saville J, Ebrall P: A conservative management protocol for calcific tendinitis of the shoulder. Journal of manipulative and physiological therapeutics 1999, 22(9):622-627. Fusaro I, Orsini S, Diani S, Saffioti G, Zaccarelli L, Galletti S: Functional results in calcific tendinitis of the shoulder treated with rehabilitation after ultrasonic-guided approach. Musculoskeletal surgery 2011, 95(1):31-36. Farin PU, Jaroma H: Sonographic findings of rotator cuff calcifications. Journal of ultrasound in medicine 1995, 14(1):7-14. Papatheodorou A, Ellinas P, Takis F, Tsanis A, Maris I, Batakis N: US of the shoulder: rotator cuff and non–rotator cuff disorders. Radiographics 2006, 26(1):e23-e23. Churchill SR, Fehringer EV, Dubinsky TJ, Matsen III FA: Rotator cuff ultrasonography: diagnostic capabilities. JAAOS-Journal of the American Academy of Orthopaedic Surgeons 2004, 12(1):6-11. Al-Shawi A, Badge R, Bunker T: The detection of full thickness rotator cuff tears using ultrasound. The Journal of bone and joint surgery British volume 2008, 90(7):889-892. De Jesus JO, Parker L, Frangos AJ, Nazarian LN: Accuracy of MRI, MR arthrography, and ultrasound in the diagnosis of rotator cuff tears: a meta-analysis. American Journal of Roentgenology 2009, 192(6):1701-1707. Iannotti JP, Ciccone J, Buss DD, Visotsky JL, Mascha E, Cotman K, Rawool NM: Accuracy of office-based ultrasonography of the shoulder for the diagnosis of rotator cuff tears. JBJS 2005, 87(6):1305-1311. Jacobson JA, Lancaster S, Prasad A, van Holsbeeck MT, Craig JG, Kolowich P: Full-thickness and partial-thickness supraspinatus tendon tears: value of US signs in diagnosis. Radiology 2004, 230(1):234-242. Rutten MJ, Jager GJ, Kiemeney LA: Ultrasound detection of rotator cuff tears: observer agreement related to increasing experience. American Journal of Roentgenology 2010, 195(6):W440-W446. Sansone V, Consonni O, Maiorano E, Meroni R, Goddi A: Calcific tendinopathy of the rotator cuff: the correlation between pain and imaging features in symptomatic and asymptomatic female shoulders. Skeletal radiology 2016, 45(1):49-55. Iossifidis A, Ibrahim EF, Petrou C: Ultrasound for the detection of full-thickness rotator cuff tears: the learning curve for an orthopaedic surgeon using a novel training method. Shoulder elbow 2015, 7(3):158-162. McCormack RA, Nayyar S, Jazrawi L: Physician training: ultrasound and accuracy of diagnosis in rotator cuff tears. Bulletin of the NYU Hospital for Joint Diseases 2016, 74(3):207. O'Connor PJ, Rankine J, Gibbon W, Richardson A, Winter F, Miller JH: Interobserver variation in sonography of the painful shoulder. Journal of Clinical Ultrasound 2005, 33(2):53-56. Ohrndorf S, Naumann L, Grundey J, Scheel T, Scheel AK, Werner C, Backhaus M: Is musculoskeletal ultrasonography an operator-dependent method or a fast and reliably teachable diagnostic tool? Interreader agreements of three ultrasonographers with different training levels. International journal of rheumatology 2010, 2010. Radiology ACo: ACR practice guideline for performing and interpreting diagnostic ultrasound examinations. American College of Radiology 2006. Hertzberg BS, Kliewer MA, Bowie JD, Carroll BA, DeLong DH, Gray L, Nelson RC: Physician training requirements in sonography: how many cases are needed for competence? American Journal of Roentgenology 2000, 174(5):1221-1227. Hawkins J: Addressing the shortage of radiologists. Radiology Management 2001, 23(4):26-29. Yawn B, Krein S, Christianson J, Hartley D, Moscovice I: Rural radiology: who is producing images and who is reading them? The Journal of Rural Health 1997, 13(2):136-144. Soni K: Has the Radiologist Shortage Been Resolved? Recent Findings Using an Improved Survey Based Measurement. 2009. Shanafelt TD, Boone S, Tan L, Dyrbye LN, Sotile W, Satele D, West CP, Sloan J, Oreskovich MR: Burnout and satisfaction with work-life balance among US physicians relative to the general US population. Archives of internal medicine 2012, 172(18):1377-1385. Kaplan A, Haenlein M: Siri, Siri, in my hand: Who’s the fairest in the land? On the interpretations, illustrations, and implications of artificial intelligence. Business Horizons 2019, 62(1):15-25. Mitchell TM: Machine learning. 1997. Burr Ridge, IL: McGraw Hill 1997, 45(37):870-877. Russell S, Norvig P: Artificial intelligence: a modern approach. 2002. Deng L, Yu D: Deep learning: methods and applications. Foundations and trends in signal processing 2014, 7(3–4):197-387. Bengio Y, Courville A, Vincent P: Representation learning: A review and new perspectives. IEEE transactions on pattern analysis and machine intelligence 2013, 35(8):1798-1828. Schmidhuber J: Deep learning in neural networks: An overview. Neural networks 2015, 61:85-117. LeCun Y, Bengio Y, Hinton G: Deep learning. nature 2015, 521(7553):436-444. Carin L, Pencina MJ: On deep learning for medical image analysis. Jama 2018, 320(11):1192-1193. Hubel DH, Wiesel TN: Receptive fields, binocular interaction and functional architecture in the cat's visual cortex. The Journal of physiology 1962, 160(1):106. LeCun Y, Bottou L, Bengio Y, Haffner P: Gradient-based learning applied to document recognition. Proceedings of the IEEE 1998, 86(11):2278-2324. Krizhevsky A, Sutskever I, Hinton GE: Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems: 2012; 2012: 1097-1105. Simonyan K, Zisserman A: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:14091556 2014. Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A: Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition: 2015; 2015: 1-9. He K, Zhang X, Ren S, Sun J: Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition: 2016; 2016: 770-778. Huang G, Liu Z, Van Der Maaten L, Weinberger KQ: Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition: 2017; 2017: 4700-4708. Brattain LJ, Telfer BA, Dhyani M, Grajo JR, Samir AE: Machine learning for medical ultrasound: status, methods, and future opportunities. Abdominal radiology 2018, 43(4):786-799. Hinton GE, Srivastava N, Krizhevsky A, Sutskever I, Salakhutdinov RR: Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:12070580 2012. West JV, Dan; Warnick, Sean: 'Spring Research Presentation: A Theoretical Foundation for Inductive Transfer'. Brigham Young University, College of Physical and Mathematical Sciences 2007. Loua T: Atlas statistique de la population de Paris: J. Dejey cie; 1873. Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D: Grad-cam: Visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE international conference on computer vision: 2017; 2017: 618-626. Zhou B, Khosla A, Lapedriza A, Oliva A, Torralba A: Learning deep features for discriminative localization. In: Proceedings of the IEEE conference on computer vision and pattern recognition: 2016; 2016: 2921-2929. Mollura DJ, Azene EM, Starikovsky A, Thelwell A, Iosifescu S, Kimble C, Polin A, Garra BS, DeStigter KK, Short B: White paper report of the RAD-AID Conference on International Radiology for Developing Countries: identifying challenges, opportunities, and strategies for imaging services in the developing world. Journal of the American College of Radiology 2010, 7(7):495-500. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/70971 | - |
| dc.description.abstract | 以超音波檢查進行棘上肌鈣化性肌腱炎診斷時，常受限於其對操作者的經驗依賴性、放射科醫師人手不足以及城鄉之間民眾對於放射科服務可及性的差異，為了減緩以上之限制，本研究應用卷積神經網路建立人工智慧之機器學習模型，透過此模型建立電腦輔助系統以協助放射科醫師在超音波檢查中判斷長軸以及短軸的棘上肌鈣化性肌腱炎的存在。 本研究提出三個基於不同訓練集的機器學習模型，分別是僅基於長軸的長軸模型、僅基於短軸的短軸模型以及同時基於長、短軸的長短軸模型，以卷積神經網路之DenseNet121預訓練模型進行模型之建立與訓練，比較三者之間對於棘上肌鈣化性肌腱炎的判斷準確度以及其餘相關評估指標可知：同時基於長、短軸訓練之長短軸模型，其準確度為91.32%、靈敏度為87.89%、特異度為94.74%，是三種模型中最適合向放射科醫師提供超音波檢查中判斷長軸以及短軸的棘上肌鈣化性肌腱炎的存在的協助之模型。 | zh_TW |
| dc.description.abstract | Diagnosing supraspinatus calcific tendinopathy with ultrasound examination is usually limited by the dependence of ultrasound examination on experience of operators, the shortage of physicians, and the difference of the radiology service accessibility between urban and rural community. To eliminate these limitations, convolutional neural network was applied to build the machine learning models in this study. It was expected to build the computer aided system in order to assist physicians with diagnosing the existence of longitudinal view and transverse view of supraspinatus calcific tendinopathy in ultrasound examinations. Three models trained on different training dataset were proposed in this study, which were the longitudinal model trained on only longitudinal view of supraspinatus calcific tendinopathy, the transverse model trained on only transverse view of supraspinatus calcific tendinopathy, and the longi-trans model trained on both longitudinal view and transverse view of supraspinatus calcific tendinopathy. These models were built and trained by DenseNet121, which is a pre-trained model in convolutional neural network. Compared the accuracy and other evaluation index of these three models against the longitudinal view and transverse view of supraspinatus calcific tendinopathy, it was found that the accuracy of the longi-trans model was 94.74%, which was the highest among the three models, and its sensitivity and specificity were 87.89% and 94.74% respectively. In conclusion, the longi-trans model is the most suitable model to provide physicians assistance of diagnosing the existence of longitudinal view and transverse view of supraspinatus calcific tendinopathy in ultrasound examinations. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-17T04:46:24Z (GMT). No. of bitstreams: 1 U0001-2008202000084400.pdf: 3327083 bytes, checksum: 059a72fdeb8bdaad5bc4477de01be81f (MD5) Previous issue date: 2020 | en |
| dc.description.tableofcontents | 誌謝……………………………………………………………………………………………………………………iv 中文摘要……………………………………………………………………………………………………………v 英文摘要…………………………………………………………………………………………………………vi Chapter 1 Introduction………………………………………………………………………1 1.1 Background……………………………………………………………………………………………1 1.2 Machine learning……………………………………………………………………………4 1.2.1 Artificial intelligence……………………………………………………4 1.2.2 Machine learning………………………………………………………………………5 1.2.3 Deep learning………………………………………………………………………………6 1.2.4 Convolutional neural networks……………………………………6 1.3 Statement of purpose…………………………………………………………………8 Chapter 2 Data description……………………………………………………………9 2.1 Data collection………………………………………………………………………………9 2.2 Data distribution………………………………………………………………………10 2.2.1 Longitudinal view of supraspinatus tendon…10 2.2.2 Transverse view of supraspinatus tendon………10 2.3 Data preprocessing……………………………………………………………………11 2.3.1 De-identification…………………………………………………………………11 2.3.2 Labeled ultrasound images……………………………………………11 2.3.3 Data distribution…………………………………………………………………14 Chapter 3 Methodology………………………………………………………………………19 3.1 DenseNet-121……………………………………………………………………………………19 3.2 Data augmentation………………………………………………………………………20 3.2.1 Rotation range…………………………………………………………………………21 3.2.2 Width shift range…………………………………………………………………22 3.2.3 Height shift range………………………………………………………………22 3.2.4 Shear range…………………………………………………………………………………22 3.2.5 Zoom range……………………………………………………………………………………22 3.2.6 Channel shift range……………………………………………………………23 3.2.7 Horizontal flip………………………………………………………………………23 3.2.8 Fill mode………………………………………………………………………………………23 3.2.9 Data flow………………………………………………………………………………………24 3.3 Dropout layer…………………………………………………………………………………25 3.4 Activation…………………………………………………………………………………………25 3.5 Optimizer……………………………………………………………………………………………26 3.5.1 Adam……………………………………………………………………………………………………26 3.5.2 Learning rate……………………………………………………………………………27 3.6 Loss function…………………………………………………………………………………27 3.7 Class weight……………………………………………………………………………………28 3.8 Transfer learning………………………………………………………………………29 3.9 Heatmap…………………………………………………………………………………………………29 3.10 Evaluation index………………………………………………………………………31 3.10.1 Accuracy………………………………………………………………………………………32 3.10.2 Loss…………………………………………………………………………………………………32 3.10.3 Confusion matrix…………………………………………………………………33 3.10.4 Testing accuracy…………………………………………………………………34 3.10.5 Sensitivity………………………………………………………………………………34 3.10.6 Specificity………………………………………………………………………………35 3.10.7 Positive predictive value (PPV)…………………………35 3.10.8 Negative predictive value (NPV)…………………………35 3.10.9 False positive value (FPR)………………………………………35 3.10.10 False negative value (FNR)……………………………………36 3.10.11 Positive likelihood ratio (+LR)………………………36 3.10.12 Negative likelihood ratio (-LR)………………………37 3.10.13 Receiver operating characteristic curve (ROC curve)…………………………………………………………………………………………………37 3.10.14 Area under the Curve (AUC)……………………………………39 Chapter 4 Results…………………………………………………………………………………41 4.1 The longitudinal model…………………………………………………………41 4.1.1 Evaluation index……………………………………………………………………41 4.1.1.1 Testing dataset with longitudinal view of supraspinatus tendon…………………………………………………………………………41 4.1.1.2 Testing dataset with transverse view of supraspinatus tendon…………………………………………………………………………44 4.1.1.3 Testing dataset with both longitudinal and transverse view of supraspinatus tendon………………………47 4.1.2 Heatmap……………………………………………………………………………………………50 4.1.2.1 Testing dataset with longitudinal view of supraspinatus tendon…………………………………………………………………………50 4.1.2.2 Testing dataset with transverse view of supraspinatus tendon…………………………………………………………………………51 4.2 The transverse model………………………………………………………………52 4.2.1 Evaluation index……………………………………………………………………52 4.2.1.1 Testing dataset with longitudinal view of supraspinatus tendon…………………………………………………………………………52 4.2.1.2 Testing dataset with transverse view of supraspinatus tendon…………………………………………………………………………55 4.2.1.3 Testing dataset with both longitudinal and transverse view of supraspinatus tendon………………………58 4.2.2 Heatmap……………………………………………………………………………………………61 4.2.2.1 Testing dataset with longitudinal view of supraspinatus tendon…………………………………………………………………………61 4.2.2.2 Testing dataset with transverse view of supraspinatus tendon…………………………………………………………………………62 4.3 The longi-trans model……………………………………………………………63 4.3.1 Evaluation index……………………………………………………………………63 4.3.1.1 Testing dataset with longitudinal view of supraspinatus tendon…………………………………………………………………………63 4.3.1.2 Testing dataset with transverse view of supraspinatus tendon…………………………………………………………………………66 4.3.1.3 Testing dataset with both longitudinal and transverse view of supraspinatus tendon………………………69 4.3.2 Heatmap……………………………………………………………………………………………72 4.3.2.1 Testing dataset with longitudinal view of supraspinatus tendon…………………………………………………………………………72 4.3.2.2 Testing dataset with transverse view of supraspinatus tendon…………………………………………………………………………73 Chapter 5 Discussion…………………………………………………………………………74 5.1 Evaluation index…………………………………………………………………………74 5.2 Heatmap…………………………………………………………………………………………………80 Chapter 6 Conclusion…………………………………………………………………………86 Reference………………………………………………………………………………………………………88 | |
| dc.language.iso | en | |
| dc.title | 以卷積神經網路實現棘上肌鈣化性肌腱炎之診斷 | zh_TW |
| dc.title | Diagnosis of Supraspinatus Calcific Tendinopathy using Convolutional Neural Networks | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 108-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 吳爵宏(Chueh-Hung Wu),周佳靚(Chia-Ching Chou) | |
| dc.subject.keyword | 棘上肌鈣化性肌腱炎,超音波,深度學習,機器學習,卷積神經網路,DenseNet121,醫療影像辨識, | zh_TW |
| dc.subject.keyword | Supraspinatus calcific tendinopathy,Ultrasound,Deep learning,Machine learning,Convolutional Neural Network,DenseNet121,Medical images identification, | en |
| dc.relation.page | 91 | |
| dc.identifier.doi | 10.6342/NTU202004111 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2020-08-20 | |
| dc.contributor.author-college | 工學院 | zh_TW |
| dc.contributor.author-dept | 土木工程學研究所 | zh_TW |
| 顯示於系所單位： | 土木工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-2008202000084400.pdf 目前未授權公開取用 | 3.25 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。