arXiv AI

Toward Foundation Detection Models via Example-Based Grounding in EM-DETR

The paper proposes a new method for creating a multi‑domain foundation model for medical lesion detection by combining diverse datasets annotated for anatomical structures and abnormalities. It introduces a student‑teacher training strategy to merge heterogeneous label spaces, reducing catastrophic forgetting and improving feature learning. Using an adapted example‑based EM‑DETR framework, the model achieves state‑of‑the‑art performance, surpassing previous benchmarks by 1–3 percentage points on key chest X‑ray and mammography metrics.

arXiv Computer Vision
Aug 26

Example-based Robust Abnormality Detection with Minimal Annotations using Exemplar Med-DETR

arXiv:2608.24281v1 Announce Type: new Abstract: Reducing annotation requirements remains a key challenge in developing robust medical object detectors. To address this, Vision-Language (VL) object de...

By Sheethal Bhat, Bogdan Georgescu, Awais Mansoor, Mathias Zinnen, Pranjal Sahu, Florin C. Ghesu, Sasa Grbic, Andreas Maier
arXiv Computer Vision
Sep 15

Designing UNICORN: a Unified Benchmark for Imaging in Computational Pathology, Radiology, and Natural Language

arXiv:2603.02790v2 Announce Type: replace Abstract: Foundation models are changing the way we develop medical artificial intelligence. By learning broadly generalizable features across diverse data m...

By Michelle Stegeman (and on behalf of the UNICORN consortium), Lena Philipp (and on behalf of the UNICORN consortium), Fennie van der Graaf (and on behalf of the UNICORN consortium), Marina D'Amato (and on behalf of the UNICORN consortium), Cl\'ement Grisi (and on behalf of the UNICORN consortium), Luc Builtjes (and on behalf of the UNICORN consortium), Joeran S. Bosma (and on behalf of the UNICORN consortium), Judith Lefkes (and on behalf of the UNICORN consortium), Rianne A. Weber (and on behalf of the UNICORN consortium), James A. Meakin (and on behalf of the UNICORN consortium), Thomas Koopman (and on behalf of the UNICORN consortium), Anne Mickan (and on behalf of the UNICORN consortium), Mathias Prokop (and on behalf of the UNICORN consortium), Ewoud J. Smit (and on behalf of the UNICORN consortium), Fr\'ed\'erique Meeuwsen (and on behalf of the UNICORN consortium), Geert Litjens (and on behalf of the UNICORN consortium), Jeroen van der Laak (and on behalf of the UNICORN consortium), Bram van Ginneken (and on behalf of the UNICORN consortium), Maarten de Rooij (and on behalf of the UNICORN consortium), Henkjan Huisman (and on behalf of the UNICORN consortium), Colin Jacobs (and on behalf of the UNICORN consortium), Francesco Ciompi (and on behalf of the UNICORN consortium), Alessa Hering (and on behalf of the UNICORN consortium)
arXiv AI
Jun 30

Towards Modality-Agnostic Medical Image Anomaly Detection: A Training-Free Manifold Refinement Approach

arXiv:2604. 19191v2 Announce Type: replace-cross Abstract: Deploying AI-based anomaly detection across diverse clinical imaging settings remains challenging because most existing methods rely on modality-specific architectures, anatomical priors, or extensive retraining, limiting their use as general-purpose screening tools.

By Pritam Kar, Gouri Lakshmi S, Saptarshi Bej
arXiv Machine Learning
Aug 31

EXPOSE: Explainable and Domain-Robust Embeddings from Pathology Vision Foundation Models using Sparse Autoencoders

EXPOSE is a framework that applies Sparse Autoencoders to Vision Foundation Model embeddings in computational pathology, aiming to separate biological signals from domain‑specific noise. By training a sparse representation of VFM features and using a linear classifier to flag domain‑specific latent dimensions, the method masks these components before downstream relapse prediction, avoiding the need to retrain the backbone model. Experiments on a large prostate cancer dataset demonstrate that removing domain‑specific features improves cross‑domain performance and raises the Domain Robustness Index (DoRI).

By Anja Witte, Maximilian Lennartz, Jan Baumbach, Guido Sauter, Stefan Bonn, Patrick Fuhlert, Marina Zimmermann
arXiv Computer Vision
Sep 18

UniReg: Conditional Unified Model for Medical Image Registration

UniReg is a conditional unified model for medical image registration that adapts deformation field estimation based on anatomical priors, registration type constraints, and instance-specific features. It combines the precision of task‑specific learning with the generalization of traditional optimization, enabling effective alignment across diverse CT and MR scenarios within a single framework. Experiments show UniReg outperforms state‑of‑the‑art learning‑based methods in accuracy while providing strong cross‑scenario generalization and reducing training cost and model redundancy.

By Zi Li, Jianpeng Zhang, Tai Ma, Tony C. W. Mok, Yan-Jie Zhou, Zeli Chen, Xianghua Ye, Le Lu, Cheng Chen, Dakai Jin
arXiv AI
Sep 18

Optimal Transport Metric Learning for Feature Alignment in Partially Supervised Segmentation

The paper proposes a two‑stage learning framework for multi‑organ segmentation that handles partially annotated datasets and domain shifts. First, the model learns accurate segmentations from available annotations to build robust feature representations. Second, it introduces learnable organ prototypes and a Sinkhorn‑triplet loss to enforce organ‑wise feature consistency across datasets, keeping embeddings of the same organ close while separating different organs, even when annotations are missing.

By Dakini Mallam Garba, Salim Abdou Daoura
arXiv Machine Learning
Sep 16

A deep dictionary network-based foundation model for ultra-low-dose CT denoising

The paper introduces a deep dictionary network (DDN) foundation model designed for ultra‑low‑dose CT (ULDCT) denoising across multiple organs. By cascading convolutional sparse coding layers with iterative soft‑thresholding, the architecture offers inherent interpretability, while dynamic dictionary and threshold modules enhance representation. The model is pre‑trained on over one million normal‑dose CT images and fine‑tuned on multi‑organ ULDCT datasets, achieving state‑of‑the‑art performance that consistently outperforms existing methods.

By Baoshun Shi, Shuangyi Yang, Ke Jiang, Bin Zhu, Zhanli Hu, Huazhu Fu