TriALS introduces a 150-case four-phase CT dataset and challenge showing top segmentation methods reach 0.754 Dice on venous phase but only 0.57 on non-contrast CT, with external validation gains up to 28%.
Data13, 10.1038/ s41597-025-06343-4 (2025)
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
VERITAS is a multi-agent system for verifiable hypothesis testing on multimodal clinical MRI datasets that achieves 81.4% verdict accuracy with frontier models and introduces an epistemic evidence labeling framework.
SAM 3 outperforms SAM 2 under click prompting for zero-shot 3D medical segmentation across 16 datasets and 54 structures, with fewer failure modes in prompt-frame over-segmentation and prediction retention.
CT-IDP derives over 900 quantitative phenotypes from multi-organ CT segmentations and uses sparse logistic regression to classify diseases, achieving macro-AUCs of 0.897/0.877/0.780 on MERLIN/Duke-Abdomen/AMOS datasets and outperforming a DINOv3 vision transformer baseline.
Anatomical location dominates prompt alignment in zero-shot VLM segmentation of NSCLC tumors, with VoxTell achieving DSC 0.613 comparable to fine-tuned baselines.
citing papers explorer
-
TriALS: Triphasic-Aided Liver Lesion Segmentation Benchmark in Non-Contrast CT
TriALS introduces a 150-case four-phase CT dataset and challenge showing top segmentation methods reach 0.754 Dice on venous phase but only 0.57 on non-contrast CT, with external validation gains up to 28%.
-
VERITAS: Verifiable Epistemic Reasoning for Image-Derived Hypothesis Testing via Agentic Systems
VERITAS is a multi-agent system for verifiable hypothesis testing on multimodal clinical MRI datasets that achieves 81.4% verdict accuracy with frontier models and introduces an epistemic evidence labeling framework.
-
Comparing SAM 2 and SAM 3 for Zero-Shot Segmentation of 3D Medical Data
SAM 3 outperforms SAM 2 under click prompting for zero-shot 3D medical segmentation across 16 datasets and 54 structures, with fewer failure modes in prompt-frame over-segmentation and prediction retention.
-
CT-IDP: Segmentation-Derived Quantitative Phenotypes for Interpretable Abdominal CT Disease Classification
CT-IDP derives over 900 quantitative phenotypes from multi-organ CT segmentations and uses sparse logistic regression to classify diseases, achieving macro-AUCs of 0.897/0.877/0.780 on MERLIN/Duke-Abdomen/AMOS datasets and outperforming a DINOv3 vision transformer baseline.
-
Exploring Prompt Alignment with Clinical Factors in Zero-Shot Segmentation VLMs for NSCLC Tumor Segmentation
Anatomical location dominates prompt alignment in zero-shot VLM segmentation of NSCLC tumors, with VoxTell achieving DSC 0.613 comparable to fine-tuned baselines.