https://scholars.lib.ntu.edu.tw/handle/123456789/607504
標題: | Data Homogeneity Effect in Deep Learning-Based Prediction of Type 1 Diabetic Retinopathy | 作者: | YUN-NUNG CHEN YI-TING HSIEH TA-CHING CHEN |
關鍵字: | adult;Article;controlled study;convolutional neural network;deep learning;diabetic patient;diabetic retinopathy;eye fundus;human;image artifact;image quality;insulin dependent diabetes mellitus;microaneurysm;middle aged;non insulin dependent diabetes mellitus;optic disk;prediction;retina blood vessel;retina hemorrhage;retina macula lutea;sensitivity and specificity;Taiwan;transfer of learning | 公開日期: | 2021 | 卷: | 2021 | 來源出版物: | Journal of Diabetes Research | 摘要: | This study is aimed at evaluating a deep transfer learning-based model for identifying diabetic retinopathy (DR) that was trained using a dataset with high variability and predominant type 2 diabetes (T2D) and comparing model performance with that in patients with type 1 diabetes (T1D). The Kaggle dataset, which is a publicly available dataset, was divided into training and testing Kaggle datasets. In the comparison dataset, we collected retinal fundus images of T1D patients at Chang Gung Memorial Hospital in Taiwan from 2013 to 2020, and the images were divided into training and testing T1D datasets. The model was developed using 4 different convolutional neural networks (Inception-V3, DenseNet-121, VGG1, and Xception). The model performance in predicting DR was evaluated using testing images from each dataset, and area under the curve (AUC), sensitivity, and specificity were calculated. The model trained using the Kaggle dataset had an average (range) AUC of 0.74 (0.03) and 0.87 (0.01) in the testing Kaggle and T1D datasets, respectively. The model trained using the T1D dataset had an AUC of 0.88 (0.03), which decreased to 0.57 (0.02) in the testing Kaggle dataset. Heatmaps showed that the model focused on retinal hemorrhage, vessels, and exudation to predict DR. In wrong prediction images, artifacts and low-image quality affected model performance. The model developed with the high variability and T2D predominant dataset could be applied to T1D patients. Dataset homogeneity could affect the performance, trainability, and generalization of the model. ? 2021 Jui-En Lo et al. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85123746952&doi=10.1155%2f2021%2f2751695&partnerID=40&md5=631dd629ef5f048caec8cfd849d3421b https://scholars.lib.ntu.edu.tw/handle/123456789/607504 |
ISSN: | 23146745 | DOI: | 10.1155/2021/2751695 |
顯示於: | 資訊工程學系 |
在 IR 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。