← Back to all news
arXiv Machine Learning By Naren Akash, Neeraja Ramanan

Do Medical Vision Models Reason About Anatomy? Probing the Spatial Inductive Biases of Learned Visual Representations

Read the original on arXiv Machine Learning →

The paper introduces SPAR‑Bench, a set of eight probes designed to test whether medical vision models can reason about anatomy in abdominal CT scans. Experiments across five architectures and three foundation models—both frozen and fine‑tuned—show that while models can recall canonical organ locations, they fail to perform relational reasoning or spatial comparisons within a patient, even under zero‑shot transfer. The study also demonstrates that pooled probing underestimates a model’s relational capabilities and that open‑weight multimodal large language models perform poorly on these tasks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Jul 24

Sparse Concept Channels in Frozen 3D CT Vision Encoders

arXiv:2607. 20993v1 Announce Type: cross Abstract: Large vision-language models are becoming increasingly dominant in 3D medical image interpretation, but we rarely know which internal units encode clinical findings or where that information lives in the representation.

By Farhad Nooralahzadeh, Lea Bogensperger, Christian Bluethgen, Michael Krauthammer
llmsragmultimodal
More like this →
arXiv Computer Vision
Aug 28

DALE-CT: Depth-Aware 2D Slice Encoders Learn an Anatomical World Model of Chest CT

DALE-CT introduces depth‑aware 2D slice encoders that learn an anatomical world model of chest CT scans without 3D or positional supervision. By sampling self‑supervised views across a physical $z$‑axis slab, the encoder captures how anatomy changes between neighboring slices, enabling it to recover slice ordering and distinguish slices by anatomy alone. The model, trained on a large 287k‑scan corpus, achieves state‑of‑the‑art performance on CT‑RATE and is released with full code and evaluation tools.

By Evan W. Damron, Mahmut S. Gokmen, Mitchell A. Klusty, Caroline N. Leach, Emily B. Collier, V. K. Cody Bumgardner
llms
More like this →