What question did this study set out to answer?

This study aims to enhance the accuracy of diabetic retinopathy lesion segmentation using a novel architecture.

May 10, 2026Open Access

Dynamic multi-scale fusion and dual-process convolution for improved retinal lesion segmentation

Key Points

This study aims to enhance the accuracy of diabetic retinopathy lesion segmentation using a novel architecture.
Introduced the DP-UNet architecture combining ConvNeXt and U-Net frameworks.
Implemented Dynamic Multi-Scale Fusion for context aggregation and Dual-Process Convolution for feature enhancement.
Evaluated on IDRiD and DDR datasets, achieving state-of-the-art performance in lesion segmentation.
Achieved a mean PR-AUC of 63.32% on IDRiD and 58.78% on DDR datasets.
Demonstrated superior performance in hemorrhage segmentation compared to existing methods.
Ablation studies revealed significant contributions from each component, particularly enhancing the segmentation of microaneurysms.

Abstract

Accurate segmentation of diabetic retinopathy lesions from fundus images remains a significant challenge due to their diverse scales and subtle visual characteristics. To tackle this issue, a new architecture called DP-UNet is introduced, combining a contemporary ConvNeXt backbone with a U-Net framework. The framework is enhanced through the synergistic incorporation of a Dynamic Multi-Scale Fusion (DMSF) module for adaptive context aggregation, the Dual-Process Convolution (DPConv) block for feature enhancement, and a wavelet-based dual-path downsampling mechanism to preserve high-frequency edge details. Comprehensive evaluations on the IDRiD (Porwal et al., Med Image Anal 59:101561, 2020) and DDR (Li et al., Inf Sci 501:511–522, 2019) datasets demonstrate that the proposed method achieves state-of-the-art performance. It attains a mean PR-AUC of 63.32% on IDRiD and 58.78% on DDR, with superior results specifically in hemorrhage segmentation. Ablation studies confirm the individual contributions of each component, particularly in improving the segmentation of microaneurysms, a critical yet challenging lesion type. The architecture effectively reconciles the extraction of global semantic information with the preservation of local fine-grained details, advancing the task from pixel-wise classification to multi-scale feature synergy. While the model exhibits strong overall performance, qualitative analysis identifies minor boundary inaccuracies, highlighting an avenue for future refinement. This work provides a robust and generalizable solution for automated lesion segmentation, offering considerable potential to assist in clinical diagnosis and management.

KI fragen

Bookmark

View Full Paper