• Home
  • Search
  • HiImp-SMI: an implicit transformer framework with high-frequency adapter for medical image segmentation
  • Cite Icon1
  • https://doi.org/10.3389/fphy.2025.1614983Copy DOI Icon

HiImp-SMI: an implicit transformer framework with high-frequency adapter for medical image segmentation

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Accurate and generalizable segmentation of medical images remains a challenging task due to boundary ambiguity and variations across domains. In this paper, an implicit transformer framework with a high-frequency adapter for medical image segmentation (HiImp-SMI) is proposed. A new dual-branch architecture is designed to simultaneously process spatial and frequency information, enhancing both boundary refinement and domain adaptability. Specifically, a Channel Attention Block selectively amplifies high-frequency boundary cues, improving contour delineation. A Multi-Branch Cross-Attention Block facilitates efficient hierarchical feature fusion, addressing challenges in multi-scale representation.Additionally, a ViT-Conv Fusion Block adaptively integrates global contextual awareness from Transformer features with local structural details, thereby significantly boosting cross-domain generalization. The entire network is trained in a supervised end-to-end manner, with frequency-adaptive modules integrated into the encoding stages of the Transformer backbone. Experimental evaluations show that HiImp-SMI consistently outperforms mainstream models on the Kvasir-Sessile and BCV datasets, including state-of-the-art implicit methods. For example, on the Kvasir-Sessile dataset, HiImp-SMI achieves a Dice score of 92.39%, outperforming I-MedSAM by 1%. On BCV, it demonstrates robust multi-class segmentation with consistent superiority across organs. These quantitative results demonstrate the framework’s effectiveness in refining boundary precision, optimizing multi-scale feature representation, and improving cross-dataset generalization. This improvement is largely attributed to the dual-branch design and the integration of frequency-aware attention mechanisms, which enable the model to capture both anatomical details and domain-robust features. The proposed framework may serve as a flexible baseline for future work involving implicit modeling and multi-modal representation learning in medical image analysis.

Similar Papers
  • Research Article
  • Citations2

MM-HiFuse: multi-modal multi-task hierarchical feature fusion for esophagus cancer staging and differentiation classification

  • Jan 01, 2025
  • Complex & Intelligent Systems
  • Xiangzuo Huo +6
  • Research Article
  • Citations9

Continual learning in medical image analysis: A comprehensive review of recent advancements and future prospects.

  • Dec 01, 2025
  • Medical image analysis
  • Pratibha Kumari +5
  • Research Article
  • Citations995

Not-so-supervised: A survey of semi-supervised, multi-instance, and transfer learning in medical image analysis.

  • Mar 29, 2019
  • Medical Image Analysis
  • Veronika Cheplygina +2
  • Research Article
  • Citations225

Deep learning models in medical image analysis

  • Mar 17, 2022
  • Journal of Oral Biosciences
  • Masayuki Tsuneki
  • Research Article
  • Citations100

Federated Learning for Medical Image Analysis with Deep Neural Networks.

  • Apr 24, 2023
  • Diagnostics
  • Sajid Nazir +1
  • Research Article
  • Citations1

Deep Learning for Medical Image Analysis: Advances, Challenges and Future Prospects

  • Apr 30, 2025
  • Journal of Artificial Intelligence & Cloud Computing
  • Suman Mehta +1
  • Research Article
  • Citations1

Abstract 1937: DIME-CT: Self-supervised learning for medical image analysis using patch-based embeddings

  • Jun 15, 2022
  • Cancer Research
  • Leon Fedden +4
  • Conference Article
  • Citations18

A Systematic Literature Review of Medical Image Analysis Using Deep Learning

  • Jul 01, 2020
  • Ricardo Buettner +3
  • Research Article
  • Citations2

Multimodal Federated Learning for Healthcare: Adaptive and Private Fusion

  • Jul 04, 2025
  • Applied and Computational Engineering
  • Yiheng Wang
  • Conference Article
  • Citations5

A Comprehensive Review on the Significance and Impact of Deep Learning in Medical Image Analysis

  • Nov 10, 2021
  • Shubhajit Panda +2
  • Research Article
  • Citations873

Domain Adaptation for Medical Image Analysis: A Survey.

  • Mar 01, 2022
  • IEEE transactions on bio-medical engineering
  • Hao Guan +1
  • Book Chapter
  • Citations6

Application of Particle Swarm Optimization in Accurate Segmentation of Brain MR Images

  • Jan 01, 2009
  • Nosratallah Forghani +4
  • Research Article
  • Citations2

Physics-informed Machine Learning for Medical Image Analysis

  • Sep 15, 2025
  • ACM Computing Surveys
  • Chayan Banerjee +4
  • Research Article
  • Citations257

Challenges of Deep Learning in Medical Image Analysis—Improving Explainability and Trust

  • Mar 01, 2023
  • IEEE Transactions on Technology and Society
  • Tribikram Dhar +3
  • Research Article

Applications and future perspectives of deep learning in medical image analysis

  • Jan 01, 2018
  • Iryou kikigaku (The Japanese journal of medical instrumentation)
  • 菅野 伸彦 +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.