U-Net V2: Rethinking the Skip Connections of U-Net for Medical Image Segmentation

Yaopeng Peng; Danny Z. Chen; Milan Sonka

doi:10.1109/ISBI60581.2025.10980742

Back

Conference proceeding

U-Net V2: Rethinking the Skip Connections of U-Net for Medical Image Segmentation

Yaopeng Peng, Danny Z. Chen and Milan Sonka

Proceedings (International Symposium on Biomedical Imaging), pp.1-5

04/14/2025

DOI: 10.1109/ISBI60581.2025.10980742

View Online

Abstract

In this paper, we introduce U-Net v2, a new robust and efficient U-Net variant for medical image segmentation. It aims to augment the infusion of semantic information into low-level features while simultaneously refining high-level features with finer details. For an input image, we begin by extracting multilevel features with a deep neural network encoder. Next, we enhance the feature map of each level by infusing semantic information from higher-level features and integrating finer details from lower-level features through Hadamard product. Our novel skip connections empower features of all the levels with enriched semantic characteristics and intricate details. The improved features are subsequently transmitted to the decoder for further processing and segmentation. Our method can be seamlessly integrated into any Encoder-Decoder network. We evaluate our method on several public medical image segmentation datasets for skin lesion segmentation and polyp segmentation, and the experimental results demonstrate the segmentation accuracy of our new method over state-of-the-art methods, while preserving memory and computational efficiency. Code is available at: https://github.com/yaoppeng/U-Net_v2.

Semantics

Biomedical imaging

Decoding

Feature extraction

Graphics processing units

Image segmentation

Lesions

Medical image segmentation

Memory management

Refining

Semantics and detail infusion

Skin

Skip connections

U-Net

Details

Title: Subtitle: U-Net V2: Rethinking the Skip Connections of U-Net for Medical Image Segmentation
Creators: Yaopeng Peng - University of Notre Dame
Danny Z. Chen - University of Notre Dame
Milan Sonka - University of Iowa
Resource Type: Conference proceeding
Publication Details: Proceedings (International Symposium on Biomedical Imaging), pp.1-5
DOI: 10.1109/ISBI60581.2025.10980742
ISSN: 1945-7928
eISSN: 1945-8452
Publisher: IEEE
Number of pages: 5
Language: English
Date published: 04/14/2025
Academic Unit: Roy J. Carver Department of Biomedical Engineering; Electrical and Computer Engineering; Radiation Oncology; Fraternal Order of Eagles Diabetes Research Center; Injury Prevention Research Center; Ophthalmology and Visual Sciences
Record Identifier: 9984824169802771

Metrics

53 Record Views