P3Net: Progressive and Periodic Perturbation for Semi-Supervised Medical Image Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yao, Zhenyan, Zhang, Miao, Wu, Lanhu, Piao, Yongri, Tian, Feng, Sun, Weibing, Lu, Huchuan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909619516866560
author Yao, Zhenyan
Zhang, Miao
Wu, Lanhu
Piao, Yongri
Tian, Feng
Sun, Weibing
Lu, Huchuan
author_facet Yao, Zhenyan
Zhang, Miao
Wu, Lanhu
Piao, Yongri
Tian, Feng
Sun, Weibing
Lu, Huchuan
contents Perturbation with diverse unlabeled data has proven beneficial for semi-supervised medical image segmentation (SSMIS). While many works have successfully used various perturbation techniques, a deeper understanding of learning perturbations is needed. Excessive or inappropriate perturbation can have negative effects, so we aim to address two challenges: how to use perturbation mechanisms to guide the learning of unlabeled data through labeled data, and how to ensure accurate predictions in boundary regions. Inspired by human progressive and periodic learning, we propose a progressive and periodic perturbation mechanism (P3M) and a boundary-focused loss. P3M enables dynamic adjustment of perturbations, allowing the model to gradually learn them. Our boundary-focused loss encourages the model to concentrate on boundary regions, enhancing sensitivity to intricate details and ensuring accurate predictions. Experimental results demonstrate that our method achieves state-of-the-art performance on two 2D and 3D datasets. Moreover, P3M is extendable to other methods, and the proposed loss serves as a universal tool for improving existing methods, highlighting the scalability and applicability of our approach.
format Preprint
id arxiv_https___arxiv_org_abs_2505_15861
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle P3Net: Progressive and Periodic Perturbation for Semi-Supervised Medical Image Segmentation
Yao, Zhenyan
Zhang, Miao
Wu, Lanhu
Piao, Yongri
Tian, Feng
Sun, Weibing
Lu, Huchuan
Image and Video Processing
Computer Vision and Pattern Recognition
Perturbation with diverse unlabeled data has proven beneficial for semi-supervised medical image segmentation (SSMIS). While many works have successfully used various perturbation techniques, a deeper understanding of learning perturbations is needed. Excessive or inappropriate perturbation can have negative effects, so we aim to address two challenges: how to use perturbation mechanisms to guide the learning of unlabeled data through labeled data, and how to ensure accurate predictions in boundary regions. Inspired by human progressive and periodic learning, we propose a progressive and periodic perturbation mechanism (P3M) and a boundary-focused loss. P3M enables dynamic adjustment of perturbations, allowing the model to gradually learn them. Our boundary-focused loss encourages the model to concentrate on boundary regions, enhancing sensitivity to intricate details and ensuring accurate predictions. Experimental results demonstrate that our method achieves state-of-the-art performance on two 2D and 3D datasets. Moreover, P3M is extendable to other methods, and the proposed loss serves as a universal tool for improving existing methods, highlighting the scalability and applicability of our approach.
title P3Net: Progressive and Periodic Perturbation for Semi-Supervised Medical Image Segmentation
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.15861