Enhancing semi‐supervised contrastive learning through saliency map for diabetic retinopathy grading

Abstract

Abstract Diabetic retinopathy (DR) is a severe ophthalmic condition that can lead to blindness if not diagnosed and provided timely treatment. Hence, the development of efficient automated DR grading systems is crucial for early screening and treatment. Although progress has been made in DR detection using deep learning techniques, these methods still face challenges in handling the complexity of DR lesion characteristics and the nuances in grading criteria. Moreover, the performance of these algorithms is hampered by the scarcity of large‐scale, high‐quality annotated data. An innovative semi‐supervised fundus image DR grading framework is proposed, employing a saliency estimation map to bolster the model's perception of fundus structures, thereby improving the differentiation between lesions and healthy regions. By integrating semi‐supervised and contrastive learning, the model's ability to recognise inter‐class and intra‐class variations in DR grading is enhanced, allowing for precise discrimination of various lesion features. Experiments conducted on publicly available DR grading datasets, such as EyePACS and Messidor, have validated the effectiveness of our proposed method. Specifically, our approach outperforms the state of the art on the kappa metric by 0.8% on the full EyePACS dataset and by 3.2% on a 10% subset of EyePACS, demonstrating its superiority over previous methodologies. The authors’ code is publicly available at https://github.com/500ZhangJC/SCL‐SEM‐framework‐for‐DR‐Grading.

Keywords

• computer vision
• convolutional neural nets
• learning (artificial intelligence)
• medical image processing