SSFMamba is a Mamba-based framework that fuses spatial and frequency-domain modeling for 3D medical image segmentation. It uses a dual-branch design, with a spatial branch preserving voxel-level textures and a frequency branch capturing global context through spectral components. The core 3D Multi-Directional Scanning Mechanism incorporates Hermitian symmetry and State Space Models to enable direction-aware global modeling, leading to superior performance on MRI and CT datasets, especially for low-contrast organs like the pancreas.
arXiv:2605.30972v2 Announce Type: replace Abstract: Accurate 3D medical image segmentation requires both fine spatial detail and long-range volumetric context. Although Mamba provides efficient long-...
arXiv:2610.24858v2 Announce Type: replace Abstract: Reducing MRI acquisition time improves patient comfort, reduces motion artefacts, and increases scanner throughput. Clinical protocols often shorte...
Foundation models such as Segment Anything Model 2 (SAM2) have transformed natural-image and video segmentation, and recent work has begun adapting them to medical imaging. These adaptations, however, are largely general-purpose models that treat MRI as one modality among many; large-scale, MRI-specific modelling and benchmarking remain limited, even though MRI's low soft-tissue contrast leaves many boundaries effectively invisible on individual slices.
The paper presents a scale‑aware 3D deep‑learning framework for detecting brain metastases in multimodal MRI. It trains separate 3D U‑Nets on two spatial fields of view (96³ and 64³ voxels) and fuses their probability maps via weighted late fusion. On a 97‑patient cohort, this cross‑FOV fusion improved lesion‑level precision and F1 while markedly reducing false positives compared to individual models, demonstrating that complementary spatial context enhances detection performance.
arXiv:2505. 17338v3 Announce Type: replace-cross Abstract: Photorealistic volumetric rendering of CT scans greatly benefits clinical workflows, yet neural approaches such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) require prohibitive per-scan optimization (hours for NeRF, about 30 minutes for 3DGS), making them impractical in clinical settings.
arXiv:2606. 03888v1 Announce Type: cross Abstract: Self-supervised learning has enabled large-scale pre-training on 2D natural images, producing general-purpose visual representations that transfer effectively across tasks.
The paper introduces DB‑SUiT, a surface‑based diffusion bridge that translates cortical MRI to PET images directly on the cortical manifold. It employs a conditional spherical U‑shaped vision Transformer to capture multi‑scale surface features and long‑range dependencies while incorporating demographic and subcortical information. Evaluations on two dementia datasets show that the synthesized PET surfaces outperform MRI and PET volumes in automated classification and achieve high diagnostic accuracy in a blinded reader study.
arXiv:2609.14312v1 Announce Type: new Abstract: Multi-shell diffusion MRI (dMRI) unlocks more expressive microstructural modeling than single-shell scans, yet its longer acquisition time hinders depl...
The paper presents an anatomy‑aligned surface learning framework for reconstructing patient‑specific 4D myocardial surfaces from sparsely sampled short‑axis cine MRI. By parameterizing epicardial and endocardial surfaces on a shared circumferential‑longitudinal UV domain, the method transforms irregular 3D reconstruction into structured coordinate‑field completion, enabling explicit correspondence across subjects and cardiac phases. Experiments on three public datasets show the approach outperforms mesh‑based and implicit methods, achieving Chamfer distances around 2.6–2.9 mm and preserving ventricular function with small errors in volume and ejection fraction.
arXiv:2602.20773v2 Announce Type: replace Abstract: Purpose: Developing generalizable medical image segmentation models is challenging because imaging data are distributed across institutions and dif...
arXiv:2603.23295v2 Announce Type: replace Abstract: Radiotherapy workflows for oncological patients increasingly rely on multi-modal medical imaging, commonly involving both Magnetic Resonance Imagin...
arXiv:2610. 13915v1 Announce Type: new Abstract: Self-supervised learning on 3D medical images commonly relies on random sub-volume sampling during pretraining.