[KongchangAI]
ModelAnatomy-guided Reasoning with Interleaved Visual Evidence

ARIVE

An anatomy-guided radiology report generation framework that generates a traceable multimodal chain of thought by interleaving visual inspection of anatomical regions with diagnostic reasoning, improving report interpretability and clinical validity.

Timeline (last 90 days)

Nov 11

ARIVE (Anatomy-guided Reasoning with Interleaved Visual Evidence) is a radiology report generation framework that interleaves anatomical region inspection with diagnostic reasoning.

Unverified50%
Nov 11

The research team constructed 159,416 multimodal chain-of-thought trajectories from the MIMIC-CXR dataset, each trajectory containing visual evidence of the inspected anatomical region and its corresponding clinical interpretation.

Unverified50%
Nov 11

The ARIVE model is trained on the constructed multimodal chain-of-thought trajectories and further optimized with an anatomy reward and a clinical content reward.

Unverified50%
Nov 11

On both the MIMIC-CXR and MIMIC-ABN datasets, ARIVE's clinical efficacy metrics outperform strong baseline models.

Unverified50%
Nov 11

Expert blind evaluation results show that the reports generated by ARIVE are competitive with those of leading models.

Unverified50%
Nov 11

ARIVE's multimodal chain-of-thought trajectories received high scores for diagnostic traceability, with reviewers able to trace back along the reasoning chain to the sources of the report's conclusions.

Unverified50%
Nov 11

A paired-review evaluation showed that when reviewers had access to MCoT, they more easily identified errors in generated reports.

Unverified50%
Nov 11

Current evaluations of ARIVE remain concentrated on the MIMIC series of datasets, and the diversity and noise levels in real clinical settings may bring new challenges.

Unverified50%

All Facts (8)

Source Articles