PraNet-V2: Dual-Supervised Reverse Attention for Medical Image Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hu, Bo-Cheng, Ji, Ge-Peng, Shao, Dian, Fan, Deng-Ping
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909993731620864
author Hu, Bo-Cheng
Ji, Ge-Peng
Shao, Dian
Fan, Deng-Ping
author_facet Hu, Bo-Cheng
Ji, Ge-Peng
Shao, Dian
Fan, Deng-Ping
contents Accurate medical image segmentation is essential for effective diagnosis and treatment. Previously, PraNet-V1 was proposed to enhance polyp segmentation by introducing a reverse attention (RA) module that utilizes background information. However, PraNet-V1 struggles with multi-class segmentation tasks. To address this limitation, we propose PraNet-V2, which, compared to PraNet-V1, effectively performs a broader range of tasks including multi-class segmentation. At the core of PraNet-V2 is the Dual-Supervised Reverse Attention (DSRA) module, which incorporates explicit background supervision, independent background modeling, and semantically enriched attention fusion. Our PraNet-V2 framework demonstrates strong performance on four polyp segmentation datasets. Additionally, by integrating DSRA to iteratively enhance foreground segmentation results in three state-of-the-art semantic segmentation models, we achieve up to a 1.36% improvement in mean Dice score. Code is available at: https://github.com/ai4colonoscopy/PraNet-V2/tree/main/binary_seg/jittor.
format Preprint
id arxiv_https___arxiv_org_abs_2504_10986
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PraNet-V2: Dual-Supervised Reverse Attention for Medical Image Segmentation
Hu, Bo-Cheng
Ji, Ge-Peng
Shao, Dian
Fan, Deng-Ping
Computer Vision and Pattern Recognition
Accurate medical image segmentation is essential for effective diagnosis and treatment. Previously, PraNet-V1 was proposed to enhance polyp segmentation by introducing a reverse attention (RA) module that utilizes background information. However, PraNet-V1 struggles with multi-class segmentation tasks. To address this limitation, we propose PraNet-V2, which, compared to PraNet-V1, effectively performs a broader range of tasks including multi-class segmentation. At the core of PraNet-V2 is the Dual-Supervised Reverse Attention (DSRA) module, which incorporates explicit background supervision, independent background modeling, and semantically enriched attention fusion. Our PraNet-V2 framework demonstrates strong performance on four polyp segmentation datasets. Additionally, by integrating DSRA to iteratively enhance foreground segmentation results in three state-of-the-art semantic segmentation models, we achieve up to a 1.36% improvement in mean Dice score. Code is available at: https://github.com/ai4colonoscopy/PraNet-V2/tree/main/binary_seg/jittor.
title PraNet-V2: Dual-Supervised Reverse Attention for Medical Image Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.10986