簡易檢索 / 詳目顯示

研究生: 吳秉宸
Ping-Chen Wu
論文名稱: 微型資料集之人工智慧應用:以肺腔放射影像為例
Artificial intelligence methods for a limited amount of datasets:chest x-ray images
指導教授: 黃騰毅
Teng-Yi Huang
口試委員: 林益如
Yi-Ru Lin
蔡尚岳
Shang-Yueh Tsai
吳文超
Wen-Chau Wu
學位類別: 碩士
Master
系所名稱: 電資學院 - 電機工程系
Department of Electrical Engineering
論文出版年: 2020
畢業學年度: 108
語文別: 中文
論文頁數: 44
中文關鍵詞: 人工智慧機器學習深度學習胸腔X光影像微型資料集
外文關鍵詞: Artificial intelligence, Machine learning, Deep learning, Chest x-ray images, a linited amount of datasets
相關次數: 點閱:312下載:0
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報
  • 現代醫療影像中,胸腔X光影像為臨床使用上,能夠快速取得病患胸腔內部資訊的醫療影像,並可經由此影像來對病人做初步診斷。本研究以人工智慧的方式,訓練模型來自動判別該病患是否為肺部渾濁。然而人工智慧也有其受限之處,在臨床上可能會遇到資料不足的狀況,這樣的情況下可能會造成訓練的模型預測結果不佳,因此本研究使用不同訓練方法,讓模型可以在資料受限的情形下也能有一定判別效果,且探討不同網路架構訓練出的模型準確度差異,提出較好方案。此外醫生在診斷時,會根據病患年齡性別、過去診斷紀錄或是其它檢查結果來同時判讀,因此使用特徵結合法來模擬此情境,了解在擁有多種資訊時,模型預測結果的差異。本研究最後提出以機器學習模型預測結果回推計算的方式,產生出模型對於影像關注區域圖的熱力圖。


    In the applications of medical imaging, chest x-ray is a useful tool for the diagnosis of lung diseases. In this study, we implemented a classification system to automatically determine if the patient has lung opacities. We studied various classification models based on machine and deep learning and evaluated the performance of these models to identify a suitable model for datasets with limited sample sizes and applied it on the pneumonia datasets. We also investigated on how to combine various features obtained from chest x-ray. Finally, this study proposes a method to interpret results by generating heat-maps to locate the chest regions that could be associated with the lung opacities.

    中文摘要 I Abstract II 目錄 III 圖目錄 V 表目錄 VI 第一章 簡介 1 1.1 研究動機 1 1.2 肺部渾濁 3 1.3 影像辨識架構 4 1.3.1 VGG16 4 1.3.2 ResNet50 5 1.3.3 MobileNet 6 1.3.4 ImageNet 8 1.3.5 LGBM 9 第二章 方法與材料 12 2.1 資料來源 12 2.1.1 RSNA資料集 12 2.1.2 Stanford資料集 13 2.1.3 COVID-19資料集 14 2.2 資料前處理 15 2.3 模型訓練 16 2.4 評估方式 17 2.5 研究目標 18 2.5.1 任務一:模型訓練之資料量差異 18 2.5.2 任務二:模型訓練之特徵量差異 19 2.5.3 任務三:選擇方法之通用性 20 2.6 熱力圖 21 第三章 實驗結果 23 3.1 任務一 23 3.2 任務二 26 3.3 任務三 27 3.4 熱力圖 28 第四章 討論與結論 29 參考文獻 33

    [1] Parveen NR, Sathik MM. Detection of Pneumonia in chest X-ray images. J Xray Sci Technol 2011;19(4):423-8.
    [2] Qin C, Yao D, Shi Y, Song Z. Computer-aided detection in chest radiography based on artificial intelligence: a survey. Biomed Eng Online 2018;17(1):113.
    [3] Hwang EJ, Nam JG, Lim WH, Park SJ, Jeong YS, Kang JH, et al. Deep Learning for Chest Radiograph Diagnosis in the Emergency Department. Radiology 2019;293(3):573-80.
    [4] Dunnmon JA, Yi D, Langlotz CP, Re C, Rubin DL, Lungren MP. Assessment of Convolutional Neural Networks for Automated Classification of Chest Radiographs. Radiology 2019;290(2):537-44.
    [5] Rajpurkar P, Irvin J, Zhu K, Yang B, Mehta H, Duan T, et al. Chexnet: Radiologist-level pneumonia detection on chest x-rays with deep learning. 2017.
    [6] Rajpurkar P, Irvin J, Ball RL, Zhu K, Yang B, Mehta H, et al. Deep learning for chest radiograph diagnosis: A retrospective comparison of the CheXNeXt algorithm to practicing radiologists. PLoS Med 2018;15(11):e1002686.
    [7] Salehinejad H, Colak E, Dowdell T, Barfett J, Valaee S. Synthesizing Chest X-Ray Pathology for Training Deep Convolutional Neural Networks. IEEE Trans Med Imaging 2019;38(5):1197-206.
    [8] 羅時燕, 王聖帆, 朱大成, 江倪全, 吳芳姿, 吳俊忠, et al. 醫學分子檢驗. 2 ed.: 五南圖書出版股份有限公司; 2009.
    [9] 莊克士. 醫學影像物理學. 1 ed.: 合記圖書出版社; 2006.
    [10] Simonyan K, Zisserman AJapa. Very deep convolutional networks for large-scale image recognition. 2014.
    [11] He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition. 2016:770-8.
    [12] Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, et al. Mobilenets: Efficient convolutional neural networks for mobile vision applications. 2017.
    [13] Deng J, Dong W, Socher R, Li L, Kai L, Li F-F. ImageNet: A large-scale hierarchical image database. 2009 IEEE Conference on Computer Vision and Pattern Recognition. 2009:248-55.
    [14] Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, et al. ImageNet Large Scale Visual Recognition Challenge. Int J Comput Vision 2015;115(3):211-52.
    [15] Quinlan JR. Induction of Decision Trees. Machine Learning 1986;1(1):81-106.
    [16] Ke G, Meng Q, Finley T, Wang T, Chen W, Ma W, et al. LightGBM: a highly efficient gradient boosting decision tree. Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach, California, USA: Curran Associates Inc.; 2017:3149–57.
    [17] Irvin J, Rajpurkar P, Ko M, Yu Y, Ciurea-Ilcus S, Chute C, et al. CheXpert-A Large Chest Radiograph Dataset. 2019.
    [18] Cohen JP. covid-chestxray-dataset; 2020. Available from: https://github.com/ieee8023/covid-chestxray-dataset.
    [19] Zhou B, Khosla A, Lapedriza A, Oliva A, Torralba A. Learning deep features for discriminative localization. Proceedings of the IEEE conference on computer vision and pattern recognition. 2016:2921-9.
    [20] Xie S, Girshick R, Dollár P, Tu Z, He K. Aggregated residual transformations for deep neural networks. Proceedings of the IEEE conference on computer vision and pattern recognition. 2017:1492-500.

    無法下載圖示 全文公開日期 2025/07/16 (校內網路)
    全文公開日期 2025/07/16 (校外網路)
    全文公開日期 2025/07/16 (國家圖書館:臺灣博碩士論文系統)
    QR CODE