Improved Vessel Segmentation with Symmetric Rotation-Equivariant U-Net

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Jiazhen, Du, Yuexi, Dvornek, Nicha C., Onofrey, John A.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916581853888512
author Zhang, Jiazhen
Du, Yuexi
Dvornek, Nicha C.
Onofrey, John A.
author_facet Zhang, Jiazhen
Du, Yuexi
Dvornek, Nicha C.
Onofrey, John A.
contents Automated segmentation plays a pivotal role in medical image analysis and computer-assisted interventions. Despite the promising performance of existing methods based on convolutional neural networks (CNNs), they neglect useful equivariant properties for images, such as rotational and reflection equivariance. This limitation can decrease performance and lead to inconsistent predictions, especially in applications like vessel segmentation where explicit orientation is absent. While existing equivariant learning approaches attempt to mitigate these issues, they substantially increase learning cost, model size, or both. To overcome these challenges, we propose a novel application of an efficient symmetric rotation-equivariant (SRE) convolutional (SRE-Conv) kernel implementation to the U-Net architecture, to learn rotation and reflection-equivariant features, while also reducing the model size dramatically. We validate the effectiveness of our method through improved segmentation performance on retina vessel fundus imaging. Our proposed SRE U-Net not only significantly surpasses standard U-Net in handling rotated images, but also outperforms existing equivariant learning methods and does so with a reduced number of trainable parameters and smaller memory cost. The code is available at https://github.com/OnofreyLab/sre_conv_segm_isbi2025.
format Preprint
id arxiv_https___arxiv_org_abs_2501_14592
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Improved Vessel Segmentation with Symmetric Rotation-Equivariant U-Net
Zhang, Jiazhen
Du, Yuexi
Dvornek, Nicha C.
Onofrey, John A.
Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
Automated segmentation plays a pivotal role in medical image analysis and computer-assisted interventions. Despite the promising performance of existing methods based on convolutional neural networks (CNNs), they neglect useful equivariant properties for images, such as rotational and reflection equivariance. This limitation can decrease performance and lead to inconsistent predictions, especially in applications like vessel segmentation where explicit orientation is absent. While existing equivariant learning approaches attempt to mitigate these issues, they substantially increase learning cost, model size, or both. To overcome these challenges, we propose a novel application of an efficient symmetric rotation-equivariant (SRE) convolutional (SRE-Conv) kernel implementation to the U-Net architecture, to learn rotation and reflection-equivariant features, while also reducing the model size dramatically. We validate the effectiveness of our method through improved segmentation performance on retina vessel fundus imaging. Our proposed SRE U-Net not only significantly surpasses standard U-Net in handling rotated images, but also outperforms existing equivariant learning methods and does so with a reduced number of trainable parameters and smaller memory cost. The code is available at https://github.com/OnofreyLab/sre_conv_segm_isbi2025.
title Improved Vessel Segmentation with Symmetric Rotation-Equivariant U-Net
topic Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2501.14592