請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/99469完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 周承復 | zh_TW |
| dc.contributor.advisor | Cheng-Fu Chou | en |
| dc.contributor.author | 陳冠伊 | zh_TW |
| dc.contributor.author | Kuan-Yi Chen | en |
| dc.date.accessioned | 2025-09-10T16:23:04Z | - |
| dc.date.available | 2025-09-11 | - |
| dc.date.copyright | 2025-09-10 | - |
| dc.date.issued | 2025 | - |
| dc.date.submitted | 2025-07-28 | - |
| dc.identifier.citation | [1] Seung Min Ryu, Soyoung Lee, Miso Jang, Jung-Min Koh, Sung Jin Bae, Seong Gyu Jegal, Keewon Shin, and Namkug Kim. Diagnosis of osteoporotic vertebral compression fractures and fracture level detection using multitask learning with u-net in lumbar spine lateral radiographs. Computational and Structural Biotechnology Journal, 21:3452–3458, 2023.
[2] SL Silverman. The clinical consequences of vertebral compression fracture. Bone, 13:S27–S31, 1992. [3] E Kanterewicz, E Puigoriol, JR Rodriguez Cros, and P Peris. Prevalent vertebral fractures and minor vertebral deformities analyzed by vertebral fracture assessment (vfa) increases the risk of incident fractures in postmenopausal women: the frodos study. Osteoporosis International, 30:2141–2149, 2019. [4] Peder Wiklund, David Buchebner, and Mats Geijer. Vertebral compression fractures at abdominal ct: underdiagnosis, undertreatment, and evaluation of an ai algorithm. Journal of Bone and Mineral Research, 39(8):1113–1119, 2024. [5] Pierre D Delmas, Lex van de Langerijt, Nelson B Watts, Richard Eastell, Harry Genant, Andreas Grauer, and David L Cahall. Underdiagnosis of vertebral fractures is a worldwide problem: the impact study. Journal of bone and mineral research, 20(4):557–563, 2005. [6] Qianyi Qiu, Junzhang Huang, Yi Yang, Yinxia Zhao, Xiongfeng Zhu, Jiayou Peng, Cuiling Zhu, Shuxue Liu, Weiqing Peng, Junqi Sun, et al. Automatic ai tool for opportunistic screening of vertebral compression fractures on chest frontal radiographs: A multicenter study. Bone, 191:117330, 2025. [7] Li-Wei Cheng, Hsin-Hung Chou, Yu-Xuan Cai, Kuo-Yuan Huang, Chin-Chiang Hsieh, Po-Lun Chu, I-Szu Cheng, and Sun-Yuan Hsieh. Automated detection of vertebral fractures from x-ray images: A novel machine learning model and survey of the field. Neurocomputing, 566:126946, 2024. [8] Chulho Kim, Minjae Kang, Woon Tak Yuh, Seung-Lee Lee, Jae Jun Lee, Jong-Uk Hou, and Suk Hyung Kang. Comparative efficacy of anteroposterior and lateral x-ray based deep learning in the detection of osteoporotic vertebral compression fracture. Scientific Reports, 14(1):28388, 2024. [9] Olaf Ronneberger, Philipp Fischer, and Thomas Brox. U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention–MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18, pages 234–241. Springer, 2015. [10] Jieneng Chen, Yongyi Lu, Qihang Yu, Xiangde Luo, Ehsan Adeli, Yan Wang, Le Lu, Alan L Yuille, and Yuyin Zhou. Transunet: Transformers make strong encoders for medical image segmentation. arXiv preprint arXiv:2102.04306, 2021. [11] Hu Cao, Yueyue Wang, Joy Chen, Dongsheng Jiang, Xiaopeng Zhang, Qi Tian, and Manning Wang. Swin-unet: Unet-like pure transformer for medical image segmentation. In European conference on computer vision, pages 205–218. Springer, 2022. [12] Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, and Baining Guo. Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE/CVF international conference on computer vision, pages 10012–10022, 2021. [13] Sheng Hung Liao. Quality control of spinal x-ray images based on deep learning. Master’s thesis, National Taiwan University, Taipei, 2024. [14] Geert Litjens, Thijs Kooi, Babak Ehteshami Bejnordi, Arnaud Arindra Adiyoso Setio, Francesco Ciompi, Mohsen Ghafoorian, Jeroen Awm Van Der Laak, Bram Van Ginneken, and Clara I Sánchez. A survey on deep learning in medical image analysis. Medical image analysis, 42:60–88, 2017. [15] Mohammed Kutbi. Artificial intelligence-based applications for bone fracture detection using medical images: a systematic review. Diagnostics, 14(17):1879, 2024. [16] Saad I Nafisah and Ghulam Muhammad. Tuberculosis detection in chest radiograph using convolutional neural network architecture and explainable artificial intelligence. Neural Computing and Applications, 36(1):111–131, 2024. [17] Nattaphon Twinprai, Artit Boonrod, Arunnit Boonrod, Jarin Chindaprasirt, Wichien Sirithanaphol, Prinya Chindaprasirt, and Prin Twinprai. Artificial intelligence (ai) vs. human in hip fracture detection. Heliyon, 8(11), 2022. [18] Lee-Ren Yeh, Yang Zhang, Jeon-Hor Chen, Yan-Lin Liu, An-Chi Wang, Jie-Yu Yang, Wei-Cheng Yeh, Chiu-Shih Cheng, Li-Kuang Chen, and Min-Ying Su. A deep learning-based method for the diagnosis of vertebral fractures on spine mri: retrospective training and validation of resnet. European Spine Journal, 31(8):2022–2030, 2022. [19] Seok Won Chung, Seung Seog Han, Ji Whan Lee, Kyung-Soo Oh, Na Ra Kim, Jong Pil Yoon, Joon Yub Kim, Sung Hoon Moon, Jieun Kwon, Hyo-Jin Lee, et al. Automated detection and classification of the proximal humerus fracture by using deep learning algorithm. Acta orthopaedica, 89(4):468–473, 2018. [20] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016. [21] Hua Wang, Jichong Ying, Jianlei Liu, Tianming Yu, and Dichao Huang. Harnessing resnet50 and senet for enhanced ankle fracture identification. BMC Musculoskeletal Disorders, 25(1):250, 2024. [22] Mingxing Tan and Quoc Le. Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning, pages 6105–6114. PMLR, 2019. [23] Subhan Ali, Ali Shariq Imran, Zenun Kastrati, Sher Muhammad Daudpota, Faouzi Alaya Cheikh, and Mohib Ullah. Enhancing wrist fracture detection and classification through deep learning and xai. In 2024 12th European Workshop on Visual Information Processing (EUVIP), pages 1–6. IEEE, 2024. [24] Wojciech Samek, Thomas Wiegand, and Klaus-Robert Müller. Explainable artificial intelligence: Understanding, visualizing and interpreting deep learning models. arXiv preprint arXiv:1708.08296, 2017. [25] Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. ” why should i trust you?” explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pages 1135–1144, 2016. [26] Scott M Lundberg and Su-In Lee. A unified approach to interpreting model predictions. Advances in neural information processing systems, 30, 2017. [27] Ramprasaath R Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, and Dhruv Batra. Grad-cam: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE international conference on computer vision, pages 618–626, 2017. [28] Kentaro Wada. Labelme: Image Polygonal Annotation with Python. [29] Ozan Oktay, Jo Schlemper, Loic Le Folgoc, Matthew Lee, Mattias Heinrich, Kazunari Misawa, Kensaku Mori, Steven McDonagh, Nils Y Hammerla, Bernhard Kainz, et al. Attention u-net: Learning where to look for the pancreas. arXiv preprint arXiv:1804.03999, 2018. [30] Hieu Huy Pham, H Nguyen Trung, and Ha Quy Nguyen. Vindr-spinexr: A large annotated medical image dataset for spinal lesions detection and classification from radiographs. PhysioNet, pages RRID–SCR_007345, 2021. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/99469 | - |
| dc.description.abstract | 脊椎壓迫性骨折（Vertebral Compression Fractures, VCFs）是骨質疏鬆常見的併發症，且在臨床診斷中經常被低估，可能導致延誤治療並加重病患預後。雖然以椎體為單位的分類模型在自動化 VCF 偵測上展現潛力，但若直接應用於以病人為單位的診斷，常會導致較高的假陽性率。為了解決此問題，本研究提出一個兩階段的深度學習框架，專門用於偵測腰椎 X 光影像中的 VCF。第一階段進行影像層級的分類，用以過濾正常個案，有效降低假陽性數量，並減少不必要的椎體分析。第二階段針對分割後的單節椎體，結合影像特徵與根據放射科醫師經驗而設計的特徵進行椎體層級的 VCF 診斷，同時使用 Grad-CAM 達到模型預測的可解釋性。我們使用來自台大醫院（NTUH）的大型腰椎 X 光資料集進行評估，該資料集包含數千張的 X 光脊椎影像。我們提出的兩階段系統在病人層級達到 87.0% 準確率、 87.3% 特異度以及85.7% 靈敏度；在椎體層級則達到 97.1% 準確率、97.9% 特異度與 77.3% 靈敏度。實驗結果顯示，兩階段設計不僅提升診斷準確性，亦能提供臨床可解釋的預測結果，有助於放射科醫師進行早期 VCF 偵測。 | zh_TW |
| dc.description.abstract | Vertebral compression fractures (VCFs) are a common consequence of osteoporosis and are often underdiagnosed in clinical settings, potentially leading to delayed treatment and worsened patient outcomes. While vertebra-level classification models have shown effectiveness in automated VCF detection, they often suffer from high false positive rates when applied directly to patient-level diagnosis. To address this issue, we propose a two-stage deep learning–based framework for detecting VCFs in lumbar spine X-ray images. The first stage performs image-level classification to filter out normal cases, effectively reducing the number of false positives and minimizing unnecessary vertebra-level evaluations. The second stage focuses on vertebra-level diagnosis by analyzing segmented vertebral bodies using both image and features based on radiologist insights. Grad-CAM is employed to enhance the interpretability of model predictions. We evaluated our method using a dataset from National Taiwan University Hospital (NTUH), which contains thousands of lumbar spine X-rays. The proposed two-stage system achieved 87.0% accuracy, 87.3% specificity, and 85.7% sensitivity at the patient level and 97.1% accuracy, 97.9% specificity, and 77.3% sensitivity at the vertebra level. These results demonstrate that our two-stage design not only improves diagnostic precision but also offers clinically interpretable predictions, making it a valuable tool for aiding radiologists in early VCF detection. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2025-09-10T16:23:04Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2025-09-10T16:23:04Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | Verification Letter from the Oral Examination Committee i
Acknowledgements iii 摘要 v Abstract vii Contents ix List of Figures xiii List of Tables xv Chapter 1 Introduction 1 Chapter 2 Related Work 5 2.1 Deep Learning in Compression Detection . . . . . . . . . . . . . . . 5 2.2 U-Net Based Architecture for Image Segmentation . . . . . . . . . . 7 2.3 CNN for Medical Image Classification . . . . . . . . . . . . . . . . 9 2.4 Explainable AI . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10 Chapter 3 Dataset 13 3.1 Landmark Identification in Lumbar Spine . . . . . . . . . . . . . . . 13 3.2 Approaches to Dataset Collection . . . . . . . . . . . . . . . . . . . 14 Chapter 4 Methods 17 4.1 Segmentation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18 4.1.1 Data Augmentation . . . . . . . . . . . . . . . . . . . . . . . . . . 18 4.1.2 Segmentation Model Selection . . . . . . . . . . . . . . . . . . . . 20 4.1.3 Loss function . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20 4.2 Global View Classification . . . . . . . . . . . . . . . . . . . . . . . 21 4.2.1 VCF Classification from LAT and AP Views . . . . . . . . . . . . . 21 4.2.2 Prediction Fusion Strategy . . . . . . . . . . . . . . . . . . . . . . 21 4.3 Vertebral Feature Engineering . . . . . . . . . . . . . . . . . . . . . 22 4.3.1 Landmark Point Definition . . . . . . . . . . . . . . . . . . . . . . 23 4.3.1.1 Corner Point Extraction . . . . . . . . . . . . . . . . . 23 4.3.1.2 Midpoint Calculation on Boundary Edges . . . . . . . 23 4.3.2 Feature Definition . . . . . . . . . . . . . . . . . . . . . . . . . . . 24 4.3.2.1 Box-Based Normalized Ratios . . . . . . . . . . . . . 24 4.3.2.2 Edge Height and Length Ratios . . . . . . . . . . . . . 25 4.3.2.3 Symmetry Ratios . . . . . . . . . . . . . . . . . . . . 26 4.3.2.4 Corner Angles . . . . . . . . . . . . . . . . . . . . . . 27 4.4 Local Vertebra Classification . . . . . . . . . . . . . . . . . . . . . . 29 Chapter 5 Experiments 31 5.1 Setting . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 31 5.2 Evaluation Metrics . . . . . . . . . . . . . . . . . . . . . . . . . . . 33 5.2.1 Segmentation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33 5.2.2 Classifier . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 34 5.2.2.1 Confusion Matrix . . . . . . . . . . . . . . . . . . . . 34 5.2.2.2 Performance Metrics . . . . . . . . . . . . . . . . . . 35 5.3 Result . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37 5.3.1 Segmentation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37 5.3.2 Global View Classifier . . . . . . . . . . . . . . . . . . . . . . . . 38 5.3.2.1 Prediction Fusion . . . . . . . . . . . . . . . . . . . . 40 5.3.3 Local Vertebra Classifier . . . . . . . . . . . . . . . . . . . . . . . 41 5.3.4 Analysis of the Two-Stage Pipeline . . . . . . . . . . . . . . . . . . 42 Chapter 6 Discussion 45 6.1 Comparison with Related Work . . . . . . . . . . . . . . . . . . . . 45 6.2 Execution Time in the Application . . . . . . . . . . . . . . . . . . . 47 6.3 Limitations . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 47 Chapter 7 Conclusion 49 Chapter 8 Future Work 51 References 53 | - |
| dc.language.iso | en | - |
| dc.subject | 脊椎壓迫性骨折 | zh_TW |
| dc.subject | 脊椎X光片 | zh_TW |
| dc.subject | 深度學習 | zh_TW |
| dc.subject | 可解釋AI | zh_TW |
| dc.subject | Lumbar Spine X-ray | en |
| dc.subject | Deep Learning | en |
| dc.subject | Vertebral Compression Fracture(VCF) | en |
| dc.subject | Explainable AI | en |
| dc.title | 基於深度學習之雙視角脊椎X光片壓迫性骨折診斷 | zh_TW |
| dc.title | Detection of Vertebral Compression Fractures in Dual-View Spinal X-ray Images Based on Deep Learning | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 113-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 吳曉光;蔡子傑;李明穗;張志豪 | zh_TW |
| dc.contributor.oralexamcommittee | Hsiao-Kuang Wu;Tzu-Chieh Tsai;Ming-Sui Lee;Chih-Hao Chang | en |
| dc.subject.keyword | 脊椎壓迫性骨折,脊椎X光片,深度學習,可解釋AI, | zh_TW |
| dc.subject.keyword | Vertebral Compression Fracture(VCF),Lumbar Spine X-ray,Deep Learning,Explainable AI, | en |
| dc.relation.page | 57 | - |
| dc.identifier.doi | 10.6342/NTU202502241 | - |
| dc.rights.note | 同意授權(限校園內公開) | - |
| dc.date.accepted | 2025-07-30 | - |
| dc.contributor.author-college | 電機資訊學院 | - |
| dc.contributor.author-dept | 資訊工程學系 | - |
| dc.date.embargo-lift | 2030-08-04 | - |
| 顯示於系所單位： | 資訊工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-113-2.pdf 未授權公開取用 | 17.4 MB | Adobe PDF | 檢視/開啟 |
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。