ISSD-NET: Intra-student Self-distillation with Adaptive q-vMF Loss for Enhanced Semi-supervised Medical Segmentation

  • Haowen Li
  • , Guoheng Huang
  • , Xiaochen Yuan
  • , Yan Li
  • , Chi Man Pun
  • , Baiying Lei
  • , Zhixin Huang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Medical image segmentation heavily depends on labeled data, but its acquisition is costly and time-consuming. Semi-supervised learning (SSL) utilizes unlabeled data to relieve this burden, yet existing methods suffer from inaccurate pseudo-labels caused by distribution mismatch, hard label information loss, and inter-class size imbalance. To address these issues, we propose an advanced semi-supervised framework for medical image segmentation (ISSD-NET). ISSD-NET incorporates three key components: First, the Grad-CAM Splicing Module (GCSM) leverages Grad-CAM to locate semantically rich regions and splice them into augmented samples, aligning labeled and unlabeled data distributions for more reliable pseudo-labels. Second, the Self-Distillation Consistency Regularization Module (SCRM) generates soft pseudo-labels as supplementary supervision, preserving uncertainty and fine-grained details to overcome hard label limitations. Additionally, the Adaptive q-vMF Dice Loss dynamically adjusts similarity metrics to address class imbalance, further refining pseudo-label quality. Experiments on ACDC and LA datasets show that ISSD-NET outperforms state-of-the-art methods in semi-supervised medical segmentation, enhancing accuracy and offering a robust solution for reliable medical image analysis.

Original languageEnglish
Title of host publicationNeural Information Processing - 32nd International Conference, ICONIP 2025, Proceedings
EditorsTadahiro Taniguchi, Chi Sing Andrew Leung, Tadashi Kozuno, Junichiro Yoshimoto, Mufti Mahmud, Maryam Doborjeh, Kenji Doya
PublisherSpringer Science and Business Media Deutschland GmbH
Pages486-500
Number of pages15
ISBN (Print)9789819543779
DOIs
Publication statusPublished - 2026
Event32nd International Conference on Neural Information Processing, ICONIP 2025 - Okinawa, Japan
Duration: 20 Nov 202524 Nov 2025

Publication series

NameLecture Notes in Computer Science
Volume16310 LNCS
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference32nd International Conference on Neural Information Processing, ICONIP 2025
Country/TerritoryJapan
CityOkinawa
Period20/11/2524/11/25

Keywords

  • dice loss
  • medical image segmentation
  • self knowledge distillation
  • Semi-supervised learning

Fingerprint

Dive into the research topics of 'ISSD-NET: Intra-student Self-distillation with Adaptive q-vMF Loss for Enhanced Semi-supervised Medical Segmentation'. Together they form a unique fingerprint.

Cite this