Identifying the Key Components in ResNet-50 for Diabetic Retinopathy Grading from Fundus Images: A Systematic Investigation

Huang，Yijin1,2; Lin，Li1,3; Cheng，Pujin1; Lyu，Junyan1,4; Tam，Roger2; Tang，Xiaoying1

2023-05-01

10.3390/diagnostics13101664

Diagnostics   影响因子和分区

2075-4418

Although deep learning-based diabetic retinopathy (DR) classification methods typically benefit from well-designed architectures of convolutional neural networks, the training setting also has a non-negligible impact on prediction performance. The training setting includes various interdependent components, such as an objective function, a data sampling strategy, and a data augmentation approach. To identify the key components in a standard deep learning framework (ResNet-50) for DR grading, we systematically analyze the impact of several major components. Extensive experiments are conducted on a publicly available dataset EyePACS. We demonstrate that (1) the DR grading framework is sensitive to input resolution, objective function, and composition of data augmentation; (2) using mean square error as the loss function can effectively improve the performance with respect to a task-specific evaluation metric, namely the quadratically weighted Kappa; (3) utilizing eye pairs boosts the performance of DR grading and; (4) using data resampling to address the problem of imbalanced data distribution in EyePACS hurts the performance. Based on these observations and an optimal combination of the investigated components, our framework, without any specialized network design, achieves a state-of-the-art result (0.8631 for Kappa) on the EyePACS test set (a total of 42,670 fundus images) with only image-level labels. We also examine the proposed training practices on other fundus datasets and other network architectures to evaluate their generalizability. Our codes and pre-trained model are available online.

classification diabetic retinopathy training setting

SCI

英语

第一 ; 通讯

National Natural Science Foundation of China[62071210];Shenzhen Science and Technology Innovation Program[RCYX20210609103056042];

General & Internal Medicine

Medicine, General & Internal

WOS:000997274100001

MDPI

2-s2.0-85160530116

Scopus

1.Department of Electronic and Electrical Engineering,Southern University of Science and Technology,Shenzhen,518055,China
2.School of Biomedical Engineering,The University of British Columbia,Vancouver,V6T 1Z4,Canada
3.Department of Electrical and Electronic Engineering,The University of Hong Kong,Hong Kong
4.Queensland Brain Institute,The University of Queensland,Brisbane,4072,Australia

Huang，Yijin,Lin，Li,Cheng，Pujin,et al. Identifying the Key Components in ResNet-50 for Diabetic Retinopathy Grading from Fundus Images: A Systematic Investigation[J]. Diagnostics,2023,13(10).

Huang，Yijin,Lin，Li,Cheng，Pujin,Lyu，Junyan,Tam，Roger,&Tang，Xiaoying.(2023).Identifying the Key Components in ResNet-50 for Diabetic Retinopathy Grading from Fundus Images: A Systematic Investigation.Diagnostics,13(10).

Huang，Yijin,et al."Identifying the Key Components in ResNet-50 for Diabetic Retinopathy Grading from Fundus Images: A Systematic Investigation".Diagnostics 13.10(2023).