DPN: Detail-Preserving Network with High Resolution Representation for Efficient Segmentation of Retinal Vessels

TL;DR

This paper introduces DPN, a high-resolution, detail-preserving network for retinal vessel segmentation that outperforms existing methods in speed and efficiency by avoiding encoder-decoder architecture and maintaining full resolution.

Contribution

The paper proposes a novel DPN architecture with DP-Blocks that preserves high-resolution details without down-sampling, improving segmentation accuracy and efficiency.

Findings

Achieves comparable segmentation accuracy on three datasets.

Over 20-160 times faster segmentation speed than existing methods.

Uses significantly fewer parameters (~120k) than other models.

Abstract

Retinal vessels are important biomarkers for many ophthalmological and cardiovascular diseases. Hence, it is of great significance to develop automatic models for computer-aided diagnosis. Existing methods, such as U-Net follow the encoder-decoder pipeline, where detailed information is lost in the encoder in order to achieve a large field of view. Although spatial detailed information could be recovered partly in the decoder, while there is noise in the high-resolution feature maps of the encoder. And, we argue this encoder-decoder architecture is inefficient for vessel segmentation. In this paper, we present the detail-preserving network (DPN), which avoids the encoder-decoder pipeline. To preserve detailed information and learn structural information simultaneously, we designed the detail-preserving block (DP-Block). Further, we stacked eight DP-Blocks together to form the DPN. More importantly, there are no down-sampling operations among these blocks. Therefore, the DPN could maintain a high/full resolution during processing, avoiding the loss of detailed information. To illustrate the effectiveness of DPN, we conducted experiments over three public datasets. Experimental results show, compared to state-of-the-art methods, DPN shows competitive/better performance in terms of segmentation accuracy, segmentation speed, and model size. Specifically, 1) Our method achieves comparable segmentation performance on the DRIVE, CHASE_DB1, and HRF datasets. 2) The segmentation speed of DPN is over 20-160 times faster than other methods on the DRIVE dataset. 3) The number of parameters of DPN is1 around 120k, far less than all comparison methods.