TRiST (Topology‑Reinforced Swin Transformer) augments hierarchical Vision Transformers with explicit topological information for medical image analysis. It computes 2D persistent homology (H0 and H1) at four Swin stages, refines persistence bands with gated residual networks, and injects learned key‑saliency scores into shifted‑window attention. The resulting Topo‑SwinV2‑B and Topo‑Swin‑UNet models outperform Swin baselines across five medical datasets.
By Pengfei Gu, Huimin Li, Guangyu Meng, Hao Zheng, Haoteng Tang, Bin Fu, Danny Z. Chen
Medical images contain topological patterns, such as connected components and loops, at scales ranging from small lesions to organ boundaries. Although hierarchical Vision Transformers have advanced m...
arXiv:2606. 29763v1 Announce Type: cross Abstract: Topological data analysis (TDA), particularly persistent homology (PH), captures geometric structural properties in medical images (e.
By Guangyu Meng, Pengfei Gu, Xueyang Li, Yiyu Shi, Erin Wolf Chambers, Danny Z. Chen
The paper introduces DPIF, a plug‑and‑play dual‑path interaction framework that can be integrated with any encoder‑decoder segmentation network. DPIF aligns cross‑view distributions using Sinkhorn optimal transport, decouples features via conditional mutual information to transfer knowledge within shared semantic spaces, and applies persistent homology‑based topological regularization to encode anatomical invariants. Experiments on a private echocardiography dataset and two public datasets show that DPIF‑enhanced models outperform single‑view baselines and achieve comparable performance to full‑data single‑view models while using only 40–60% of the data.
By Shuhuan Wang, Yuanyuan Cui, Pengju Wang, Huimin Guo, Ling Yue, Yin Gu, Yanchao Zhang, Wei Feng, Yunhe Liu, Wei Qian, Mingjun Xu, Shuang Liu, He Ma
The growing number of medical vision foundation models highlights the need for effective model selection. However, mainstream selection methods rely on exhaustive fine-tuning, which is computationally expensive.
The paper introduces FreNet, a feature reconfiguration framework that incorporates visual priors for medical lesion segmentation. FreNet performs pixel‑level reconfiguration before encoding using an Implicit Prior Neural Network (IPNN) that leverages SAM, and feature‑level reconfiguration during encoding via a Dual‑domain Feature Reconfiguration (DFR) module, which includes a Frequency Decoupling Module (FDM) and a Spatial Localization Module (SLM). Experiments on nine benchmarks across three imaging modalities show that FreNet outperforms state‑of‑the‑art methods, achieving a 5.0% Dice improvement over the best baseline on the ETIS dataset and a 7.2% improvement over SAM.
By Yinan Liu, Jiankang Hong, Zhen Gao, Ye Lu
The paper introduces SSS, a semi‑supervised framework that builds on the Vision Foundation Model SAM‑2 to improve medical image segmentation. It combines a weak‑to‑strong consistency regularization with a Discriminative Feature Enhancement mechanism and a prompt generator that uses Physical Constraints with a Sliding Window to supply prompts for unlabeled data. Experiments on the ACDC and BHSD datasets show that SSS outperforms prior methods, achieving a 53.15 Dice score on BHSD, a +3.65 improvement over the state of the art.
By Hongjie Zhu, Xiwei Liu, Rundong Xue, Zeyu Zhang, Yong Xu, Daji Ergu, Ying Cai, Yang Zhao
Feature Reconfiguration With Visual Prior for Medical Lesion Segmentation proposes FreNet, a framework that reconfigures images and features before and during encoding to improve lesion segmentation. It introduces an Implicit Prior Neural Network that uses a visual prior from SAM to suppress background responses, and a Dual-domain Feature Reconfiguration module that decouples features in frequency and spatial domains to better handle diverse lesion morphology. Experiments on nine benchmarks across three imaging modalities show FreNet outperforms state‑of‑the‑art methods, achieving a 5.0% Dice improvement over the best prior method on the ETIS dataset.
The paper introduces CoLeTra, a data augmentation technique designed to enhance topology accuracy in image segmentation of thin, tubular structures such as blood vessels. By artificially breaking these structures in training images while preserving the original labels, CoLeTra teaches models that continuous structures can appear disconnected, improving segmentation quality even when training labels are topologically inaccurate. Experiments across various architectures, loss functions, and datasets show that CoLeTra yields more topologically accurate segmentations and often boosts Dice and clDice scores, and the authors also release a dedicated dataset for topology-focused segmentation.
By Juan Miguel Valverde, Maja {\O}stergaard, Adrian Rodriguez-Palomo, Peter Alling Strange Vibe, Nina K{\o}lln Wittig, Henrik Birkedal, Anders Bjorholm Dahl
arXiv:2608.24364v1 Announce Type: new
Abstract: Self-supervised pretraining enables transferable representations for medical imaging, yet most CT encoders remain biased toward coarse semantic underst...
By Sebasti\'an Gonz\'alez, Karen Sanchez, Jos\'e M. Saavedra, Marcelo Pizarro, Bernard Ghanem
arXiv:2609.36648v1 Announce Type: new
Abstract: Vision-language pre-training has reshaped image clustering, giving rise to language-assisted image clustering (LaIC), which leverages textual semantics...
By Yuanwei Hu, Bo Peng, Yuheng Jia, Xinting Hu, Yadan Luo, Wenjie Zhu
arXiv:2607.10851v2 Announce Type: replace
Abstract: Medical image classification models are ideally expected to identify diagnostically relevant regions while making predictions, yet standard classif...
By Tonmoy Hossain, Atiqur Rahman, Farhana Hossain Swarnali, Miaomiao Zhang