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.
arXiv:2609.15669v1 Announce Type: cross Abstract: Multimodal image registration is a key component of many clinical workflows, yet it remains challenging because corresponding anatomical structures o...
Self-supervised pretraining enables transferable representations for medical imaging, yet most CT encoders remain biased toward coarse semantic understanding, limiting their sensitivity to fine-graine...
Multimodal image registration is a key component of many clinical workflows, yet it remains challenging because corresponding anatomical structures often exhibit substantially different image intensit...
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...
arXiv:2606. 06342v1 Announce Type: cross Abstract: Topological Data Analysis (TDA) offers a principled, intrinsic lens for comparing neural representations.
The paper introduces a geometry‑guided sampling operator that directs feature sampling rather than altering convolution kernels in 3D encoder‑decoder networks. By predicting local orientations and bounded step sizes, the operator samples symmetrically around each voxel, generating compact geometric and boundary cues that improve fine‑structure segmentation. Replacing stride‑1 and stride‑2 operations in a 3D U‑Net yields consistent gains on BraTS, MSD Hepatic Vessel, and TDSC‑ABUS datasets, with better boundary metrics and fewer parameters, and the operator can be integrated into other backbones without architectural changes.
arXiv:2603. 04024v2 Announce Type: replace-cross Abstract: Ambiguous 3D medical image segmentation often involves boundaries where different expert delineations are non-identical yet clinically plausible.
Accurate medical image interpolation and anatomical structure segmentation are fundamental for computer-aided diagnosis and treatment planning. Anisotropic medical volumes with sparse through-plane sampling often suffer from structural discontinuity and boundary blur, hindering reliable clinical image analysis.
arXiv:2608. 05960v1 Announce Type: cross Abstract: Routine CT interpretation is inherently comprehensive, capturing incidental findings across the entire scan volume.
arXiv:2606. 17340v1 Announce Type: cross Abstract: Accurate vision-based navigation in monocular endoscopy is difficult due to limited depth cues, weak tissue texture, non-rigid deformation, and substantial appearance variation across domains, all of which complicate pose estimation, depth prediction, and image-to-anatomy alignment.
Domain Elastic Transform (DET) is a grid‑free, probabilistic framework that jointly aligns geometry and high‑dimensional vector‑valued functions on irregular sparse manifolds, such as those found in spatial transcriptomics. By treating data as functions rather than voxelized images, DET performs unsupervised, scalable registration through sampled point alignment and displacement interpolation, guided by a joint spatial‑functional Bayesian likelihood. Evaluations on MERFISH mouse‑brain slices and Stereo‑seq mouse‑embryo atlases show DET achieving superior spatial overlap and topology compared to existing pipelines, with an accelerated variant delivering high label‑transfer accuracy.
arXiv:2608. 19965v1 Announce Type: cross Abstract: Segmentation of curvilinear anatomical structures in 3D medical images remains challenging due to complex topology, severe class imbalance, weak contrast, and large variations in structure morphology.