Skip to main navigation Skip to search Skip to main content

RWKVFUSE: PARALLEL ENCODERS NETWORK FOR MEDICAL IMAGE SEGMENTATION

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Medical image segmentation is essential for accurate lesion identification and disease diagnosis. Conventional CNN-based methods are limited by their restricted receptive fields, whereas Transformer models effectively capture global dependencies but incur quadratic computational costs. Recently, sequence modeling approaches with linear attention mechanisms, such as the RWKV, have demonstrated the ability to model long-range dependencies with linear complexity. To address this, we propose a dual-encoder architecture, RWKVFuse, which integrates VRWKV and CNNs to extract fine-grained spatial features and long-range dependencies. Extensive experiments across four imaging modalities show that the proposed RWKVFuse model outperforms state-of-the-art methods in metrics such as DSC and HD95. Our code is available at: https://github.com/alqurri/rwkv.

Original languageEnglish (US)
Title of host publicationISBI 2026 - 23rd IEEE International Symposium on Biomedical Imaging
PublisherIEEE Computer Society
ISBN (Electronic)9798331577636
DOIs
StatePublished - 2026
Event23rd IEEE International Symposium on Biomedical Imaging, ISBI 2026 - London, United Kingdom
Duration: Apr 8 2026 → Apr 11 2026

Publication series

NameProceedings - International Symposium on Biomedical Imaging
Volume2026-April
ISSN (Print)1945-7928
ISSN (Electronic)1945-8452

Conference

Conference23rd IEEE International Symposium on Biomedical Imaging, ISBI 2026
Country/TerritoryUnited Kingdom
CityLondon
Period4/8/26 → 4/11/26

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Fingerprint

Dive into the research topics of 'RWKVFUSE: PARALLEL ENCODERS NETWORK FOR MEDICAL IMAGE SEGMENTATION'. Together they form a unique fingerprint.

Cite this