The Flow has not summarised this story yet — read it at arXiv Computer Vision.
XGLASS is a method that transfers expertise from 2D X‑ray vision‑language models to 3D CT volumes by using disease‑conditioned importance maps derived from radiologist gaze on X‑rays. By aligning these gaze priors with coronal CT projections, XGLASS predicts a disease‑specific ordering of axial slices, prioritizing diagnostically relevant slices. The approach achieves a top‑10 hit rate of up to 75.9% on a 240‑slice scan and reduces downstream model calls by 87.5% while improving F1 scores, making it a lightweight preselector for volumetric CT analysis.
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.
arXiv:2610.06938v1 Announce Type: new Abstract: Medical image segmentation remains fragmented along two axes: segmentation paradigms and data dimensionality. Existing methods are typically developed...
The study investigates how few expert-annotated cases are needed to fine‑tune MedSAM3 for abdominal organ segmentation using Low‑Rank Adaptation (LoRA). With only 10 annotated CT or MRI cases, the LoRA‑adapted models achieve performance comparable to specialist systems that require orders of magnitude more data, including reliable gallbladder segmentation and near‑state‑of‑the‑art results for liver, kidneys, and spleen. The approach also generalizes to cardiac segmentation on the Whole Heart dataset, and training takes only 3–5 hours per organ on a single GPU, roughly twice as fast as nnU-Net.
arXiv:2609.01554v1 Announce Type: cross Abstract: Automated lesion segmentation in whole-body PET/CT is complicated by the variety of physiological tracer uptake patterns and by the differing appeara...
arXiv:2608.30844v1 Announce Type: cross Abstract: Interactive lesion segmentation in whole-body PET/CT requires a model to provide a strong initial prediction while also responding efficiently to spa...