請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/85945完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 周呈霙(Cheng-Ying Chou) | |
| dc.contributor.author | Jeng-En Wu | en |
| dc.contributor.author | 吳証恩 | zh_TW |
| dc.date.accessioned | 2023-03-19T23:29:57Z | - |
| dc.date.copyright | 2022-09-23 | |
| dc.date.issued | 2022 | |
| dc.date.submitted | 2022-09-21 | |
| dc.identifier.citation | [1] Mihai Gheorghiade, Faiez Zannad, George Sopko, Liviu Klein, Ileana L Piña, Mar- vin A Konstam, Barry M Massie, Edmond Roland, Shari Targum, Sean P Collins, et al. Acute heart failure syndromes: current state and framework for future research. Circulation, 112(25):3958–3968, 2005. [2] AlanBStorrow,CathyAJenkins,WesleyHSelf,PaulineTAlexander,TylerWBar- rett, Jin H Han, Candace D McNaughton, Benjamin S Heavrin, Mihai Gheorghiade, and Sean P Collins. The burden of acute heart failure on us emergency departments. JACC: Heart Failure, 2(3):269–277, 2014. [3] Jennifer L Martindale, Abel Wakai, Sean P Collins, Phillip D Levy, Deborah Dier- cks, Brian C Hiestand, Gregory J Fermann, Ian Desouza, and Richard Sinert. Di- agnosing acute heart failure in the emergency department: a systematic review and meta-analysis. Academic Emergency Medicine, 23(3):223–242, 2016. [4] Emmert Roberts, Andrew J Ludman, Katharina Dworzynski, Abdallah Al- Mohammad, Martin R Cowie, John JV McMurray, and Jonathan Mant. The di- agnostic accuracy of the natriuretic peptides in heart failure: systematic review and diagnostic meta-analysis in the acute care setting. BMJ, 350, 2015. [5] Paul A Heidenreich, Biykem Bozkurt, David Aguilar, Larry A Allen, Joni J Byun, Monica M Colvin, Anita Deswal, Mark H Drazner, Shannon M Dunlay, Linda R Evers, et al. 2022 aha/acc/hfsa guideline for the management of heart failure: a re- port of the american college of cardiology/american heart association joint commit- tee on clinical practice guidelines. Journal of the American College of Cardiology, 79(17):e263–e421, 2022. [6] Jarrel CY Seah, Jennifer SN Tang, Andy Kitchen, Frank Gaillard, and Andrew F Dixon. Chest radiographs in congestive heart failure: visualizing neural network learning. Radiology, 290(2):514–522, 2019. [7] Takuya Matsumoto, Satoshi Kodera, Hiroki Shinohara, Hirotaka Ieki, Toshihiro Ya- maguchi, Yasutomi Higashikuni, Arihiro Kiyosue, Kaoru Ito, Jiro Ando, Eiki Taki- moto, et al. Diagnosing heart failure from chest x-ray images using deep learning. International Heart Journal, 61(4):781–786, 2020. [8] Sarah Jabbour, David Fouhey, Ella Kazerooni, Jenna Wiens, and Michael W Sjod- ing. Combining chest x-rays and electronic health record (ehr) data using machine learning to diagnose acute respiratory failure. Journal of the American Medical Informatics Association, 29(6):1060–1068, 2022. [9] Pranav Rajpurkar, Jeremy Irvin, Kaylie Zhu, Brandon Yang, Hershel Mehta, Tony Duan, Daisy Ding, Aarti Bagul, Curtis Langlotz, Katie Shpanskaya, et al. Chexnet: Radiologist-level pneumonia detection on chest x-rays with deep learning. arXiv preprint arXiv:1711.05225, 2017. [10] Han Liu, Lei Wang, Yandong Nan, Faguang Jin, Qi Wang, and Jiantao Pu. Sdfn: Segmentation-based deep fusion network for thoracic disease classification in chest x-ray images. Computerized Medical Imaging and Graphics, 75:66–73, 2019. [11] Qingji Guan, Yaping Huang, Zhun Zhong, Zhedong Zheng, Liang Zheng, and Yi Yang. Diagnose like a radiologist: Attention guided convolutional neural net- work for thorax disease classification. arXiv preprint arXiv:1801.09927, 2018. [12] Jeremy Kawahara, Sara Daneshvar, Giuseppe Argenziano, and Ghassan Hamarneh. Seven-point checklist and skin lesion classification using multitask multimodal neu- ral nets. IEEE Journal of Biomedical and Health Informatics, 23(2):538–546, 2018. [13] Jordan Yap, William Yolland, and Philipp Tschandl. Multimodal skin lesion classi- fication using deep learning. Experimental Dermatology, 27(11):1261–1267, 2018. [14] Alistair Johnson, Lucas Bulgarelli, Tom Pollard, Steven Horng, Leo Anthony Celi, and Roger Mark. MIMIC-IV. PhysioNet. Available online at: https://physionet. org/content/mimiciv/1.0/(accessed August 23, 2021), 2020. [15] Ary L Goldberger, Luis AN Amaral, Leon Glass, Jeffrey M Hausdorff, Plamen Ch Ivanov, Roger G Mark, Joseph E Mietus, George B Moody, Chung-Kang Peng, and H Eugene Stanley. Physiobank, physiotoolkit, and physionet: components of a new research resource for complex physiologic signals. Circulation, 101(23):e215–e220, 2000. [16] Alistair EW Johnson, Tom J Pollard, Nathaniel R Greenbaum, Matthew P Lungren, Chih-ying Deng, Yifan Peng, Zhiyong Lu, Roger G Mark, Seth J Berkowitz, and Steven Horng. MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs. arXiv preprint arXiv:1901.07042, 2019. [17] Junji Shiraishi, Shigehiko Katsuragawa, Junpei Ikezoe, Tsuneo Matsumoto, Takeshi Kobayashi, Ken-ichi Komatsu, Mitate Matsui, Hiroshi Fujita, Yoshie Kodera, and Kunio Doi. Development of a digital image database for chest radiographs with and without a lung nodule: receiver operating characteristic analysis of radiologists’ detection of pulmonary nodules. American Journal of Roentgenology, 174(1):71– 74, 2000. [18] Boris Sekachev, M Nikita, and Z Andrey. Computer vision annotation tool: a uni- versal approach to data annotation (2019). Available at: https://github.com/ openvinotoolkit/cvat. [19] Stephen M Pizer, E Philip Amburn, John D Austin, Robert Cromartie, Ari Geselowitz, Trey Greer, Bart ter Haar Romeny, John B Zimmerman, and Karel Zuiderveld. Adaptive histogram equalization and its variations. Computer Vision, Graphics, and Image Processing, 39(3):355–368, 1987. [20] Gao Huang, Zhuang Liu, Laurens Van Der Maaten, and Kilian Q Weinberger. Densely connected convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 4700–4708, 2017. [21] Olaf Ronneberger, Philipp Fischer, and Thomas Brox. U-net: Convolutional net- works for biomedical image segmentation. In International Conference on Medical Image Computing and Computer-assisted Intervention, pages 234–241. Springer, 2015. [22] Liang-Chieh Chen, Yukun Zhu, George Papandreou, Florian Schroff, and Hartwig Adam. Encoder-decoder with atrous separable convolution for semantic image seg- mentation. In Proceedings of the European Conference on Computer Vision (ECCV), pages 801–818, 2018. [23] 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. [24] Joost JM Van Griethuysen, Andriy Fedorov, Chintan Parmar, Ahmed Hosny, Nicole Aucoin, Vivek Narayan, Regina GH Beets-Tan, Jean-Christophe Fillion-Robin, Steve Pieper, and Hugo JWL Aerts. Computational radiomics system to decode the radiographic phenotype. Cancer Research, 77(21):e104–e107, 2017. [25] Diederik P Kingma and Jimmy Ba. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014. [26] Shih-Cheng Huang, Anuj Pareek, Saeed Seyyedi, Imon Banerjee, and Matthew P Lungren. Fusion of medical imaging and electronic health records using deep learn- ing: a systematic review and implementation guidelines. NPJ Digital Medicine, 3(1):1–9, 2020. [27] Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, and Antonio Torralba. Learning deep features for discriminative localization. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 2921–2929, 2016. [28] Tianqi Chen and Carlos Guestrin. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 785–794, 2016. [29] Scott M Lundberg and Su-In Lee. A unified approach to interpreting model predic- tions. Advances in Neural Information Processing Systems, 30, 2017. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/85945 | - |
| dc.description.abstract | 本研究旨在使用結合患者胸腔 X 光片和電子健康紀錄的多模態深度學習模型 於急診室進行急性心臟衰竭之篩檢。如果病人 N 端前腦利鈉肽的血液濃度高於 300ng/L，則被定義為陽性。對於每張胸腔 X 光片，肺心遮罩生成器最初通過肺心 分割模型識別肺和心臟區域。然後通過預定義的演算法手動提取三個估計心臟大 小的比例值和 306 個放射組學特徵。最終，多模態深度學習模型融合來自電子健 康紀錄和胸腔 X 光片的資訊並輸出最終預測。研究群體是從公開資料集 Medical Information Mart for Intensive Care (MIMIC) IV 中所提取。研究群體包括 1,432 名患 者和 1,833 對胸腔 X 光片和電子健康紀錄。其中，71% 的樣本為陽性。53% 的患 者為男性，47% 為女性。研究群體的年齡分佈最小為 20 歲最大為 91 歲，年齡平 均為 65 歲。此回溯性實驗在此資料集上顯示，當多模態深度學習模型整合來自每 個單模態模型的預測結果時，模型預測表性最高可達 AUROC 值 0.89。 | zh_TW |
| dc.description.abstract | This study aims to screen suspected acute heart failure (AHF) in the emergency department using a multimodal deep learning model combining patients'chest X-rays (CXRs) and electronic health records (EHRs). The binary label for AHF is defined as positive if a patient’s value of N terminal pro B type natriuretic peptide (NT-proBNP) is higher than 300 ng/L. For each CXR, the lung-heart mask generator initially identified the lung and heart region by the lung-heart segmentation model. Then three heart-size ratios and 306 radiomic features were extracted manually by predefined formulas. Eventually, the information from EHRs and CXRs was fused to output the final prediction. The study population was extracted from the Medical Information Mart for Intensive Care (MIMIC) IV open-source dataset. The study population includes 1,432 patients and 1,833 pairs of CXR and EHR. 71% of the samples are positive. 53% of the patient are male, and 47% are female. The age of the study population range from 20 to 91, with a mean of 65. The retrospective experiments illustrated that the proposed method achieved the highest AUROC of 0.89 when fusing all predictions from every single-modality model. | en |
| dc.description.provenance | Made available in DSpace on 2023-03-19T23:29:57Z (GMT). No. of bitstreams: 1 U0001-0508202217164600.pdf: 20809797 bytes, checksum: add91fecc587e8428804a2349a1fda73 (MD5) Previous issue date: 2022 | en |
| dc.description.tableofcontents | Acknowledgements i 摘要 iii Abstract v Contents vii List of Figures xi List of Tables xiii List of Algorithms xiv Chapter 1: Introduction 1 1.1 Background............................... 1 1.1.1 Choosing NT-proBNP as an acute heart failure indicator . . . . . . . 3 1.2 Contributions.............................. 4 Chapter 2: Literature Review 7 2.1 Predicting Thoracic Diseases Using DL and CXR . . . . . . . . . . . 7 2.2 Predicting HF Using DL and CXR................... 8 2.3 Multimodal DL Combining Medical Imaging and EHR . . . . . . . . 9 Chapter 3: Materials and Methods 13 3.1 Data Description ............................ 13 3.1.1 MIMIC-IV............................... 13 3.1.2 MIMIC-CXR ............................. 14 3.1.3 JSRT.................................. 15 3.1.4 Manually labeled lung-heart masks for images in MIMIC-CXR . . . 15 3.2 Data Pre-processing .......................... 17 3.2.1 EHR from MIMIC-IV......................... 17 3.2.2 CXR from MIMIC-CXR ....................... 18 3.2.3 CXR from JSRT............................ 19 3.3 Frontal-lateral Classifier ........................ 20 3.4 Lung-heart Mask Generator ...................... 21 3.4.1 Segmentation models ......................... 22 3.4.2 Mask post-processing......................... 23 3.5 Feature Extraction from Lung-Heart Masks . . . . . . . . . . . . . . 26 3.5.1 Heart-size ratios............................ 26 3.5.2 Radiomic features........................... 27 3.5.3 Thoracic region of interest ...................... 28 3.6 NT-proBNP Prediction Models..................... 28 3.6.1 Numerical models........................... 30 3.6.2 Image models ............................. 30 3.6.3 Multimodal models .......................... 31 3.6.4 Fusion strategy ............................ 31 Chapter 4: Results and Discussions 37 4.1 Demographics of Study Population .................. 37 4.2 PA, AP, and Frontal Views....................... 37 4.3 Evaluation of Mask Post-processing.................. 39 4.4 Performance Based on Input Combination . . . . . . . . . . . . . . . 40 4.5 Performance Based on Fusion Strategy ................ 42 4.6 Analysis of Image Data......................... 43 4.7 Analysis of Numerical Data ...................... 44 4.8 Analysis of Heart-size Ratios...................... 48 4.9 Analysis of Radiomic Features..................... 49 Chapter 5: Limitations 55 5.1 Label Uncertainty............................ 55 5.2 Segmentation Models.......................... 56 5.3 Mask Post-processing Algorithms ................... 58 5.4 Generalization ............................. 59 Conclusion 61 References 63 Appendix A — Figures 69 A.1 FlowchartofInclusionandExclusion ................. 69 Appendix B — Tables 71 B.1 RadiomicFeatures ........................... 71 | |
| dc.language.iso | en | |
| dc.title | 利用多模態深度學習模型結合胸部 X 光 和電子健康紀錄以篩檢急性心臟衰竭 | zh_TW |
| dc.title | Multimodal Deep Learning Model for Screening Acute Heart Failure in Emergency Department Using Chest X-rays and Electronic Health Records | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 110-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 王偉仲(Wei-Chung Wang),李志國(Chih-Kuo Lee),陳定立(Ting-Li Chen) | |
| dc.subject.keyword | 多模態,深度學習,急性心臟衰竭,胸腔 X 光,電子健康紀錄, | zh_TW |
| dc.subject.keyword | acute heart failure,chest X-ray,deep learning,electronic health record,multimodality, | en |
| dc.relation.page | 72 | |
| dc.identifier.doi | 10.6342/NTU202202103 | |
| dc.rights.note | 同意授權(全球公開) | |
| dc.date.accepted | 2022-09-22 | |
| dc.contributor.author-college | 共同教育中心 | zh_TW |
| dc.contributor.author-dept | 統計碩士學位學程 | zh_TW |
| dc.date.embargo-lift | 2022-09-23 | - |
| 顯示於系所單位： | 統計碩士學位學程 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-0508202217164600.pdf | 20.32 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。