Unsupervised Lesion-Aware Transfer Learning for Diabetic Retinopathy Grading in Ultra-Wide-Field Fundus Photography

Bai，Yanmiao1; Hao，Jinkui1; Fu，Huazhu3; Hu，Yan4; Ge，Xinting5; Liu，Jiang4; Zhao，Yitian1,2; Zhang，Jiong1,2

10.1007/978-3-031-16434-7_54

2022

25th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)

0302-9743

1611-3349

978-3-031-16433-0

LECT NOTES ARTIF INT

13432 LNCS

560-570

SEP 18-22, 2022

null,Singapore,SINGAPORE

GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND

SPRINGER INTERNATIONAL PUBLISHING AG

Ultra-wide-field (UWF) fundus photography is a new imaging technique with providing a broader field of view images, and it has become a popular and effective tool for the screening and diagnosis for many eye diseases, such as diabetic retinopathy (DR). However, it is practically challenging to train a robust deep learning model for DR grading in UWF images, due to the limited scale of data and manual annotations. By contrast, we may find large-scale high-quality regular color fundus photography datasets in the research community, with either image-level or pixel-level annotation. In consequence, we propose an Unsupervised Lesion-aware TRAnsfer learning framework (ULTRA) for DR grading in UWF images, by leveraging a large amount of publicly well-annotated regular color fundus images. Inspired by the clinical identification of DR severity, i.e., the decision making process of ophthalmologists based on the type and number of associated lesions, we design an adversarial lesion map generator to provide the auxiliary lesion information for DR grading. A Lesion External Attention Module (LEAM) is introduced to integrate the lesion feature into the model, allowing a relative explainable DR grading. Extensive experimental results show the proposed method is superior to the state-of-the-art methods.

Diabetic retinopathy Unsupervised UWF imaging

Others

English

CPCI-S

National Science Foundation Program of China[62103398]

Computer Science ; Radiology, Nuclear Medicine & Medical Imaging

Computer Science, Artificial Intelligence ; Computer Science, Interdisciplinary Applications ; Radiology, Nuclear Medicine & Medical Imaging

WOS:000867288800054

2-s2.0-85139043607

Scopus

1.Cixi Institute of Biomedical Engineering,Ningbo Institute of Materials Technology and Engineering,Chinese Academy of Sciences,Ningbo,China
2.Affiliated Ningbo Eye Hospital of Wenzhou Medical University,Ningbo,China
3.Institute of High Performance Computing,A*STAR,Singapore,Singapore
4.Southern University of Science and Technology,Shenzhen,China
5.School of Information Science and Engineering,Shandong Normal University,Jinan,China

Bai，Yanmiao,Hao，Jinkui,Fu，Huazhu,et al. Unsupervised Lesion-Aware Transfer Learning for Diabetic Retinopathy Grading in Ultra-Wide-Field Fundus Photography[C]. GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND:SPRINGER INTERNATIONAL PUBLISHING AG,2022:560-570.