---
title: "Interleaving anatomical inspection and... | SI Paper Desk"
url: https://thesimind.si/papers/2611.14018/
description: "ARIVE writes chest X-ray reports by first inspecting body regions and reasoning about them, so reviewers can trace each finding and may catch errors more..."
---

Number 8 of 12 · November 13, 2026

# Interleaving anatomical inspection and diagnostic reasoning for explainable radiology report generation

ARIVE writes chest X-ray reports by first inspecting body regions and reasoning about them, so reviewers can trace each finding and may catch errors more easily.

Chentao Huang, Runlong Lin, Zhijun Wang and 5 more · Submitted November 10, 2026 · arXiv 2611.14018v1 · cs.CV

[Read the paper on arXiv](https://arxiv.org/abs/2611.14018) · [The PDF](https://arxiv.org/pdf/2611.14018) · [The day's 12](https://thesimind.si/papers/day/2026-11-13/)

## What they found

The authors built ARIVE, a system that drafts radiology reports in steps. It looks at anatomical regions, reasons about what it sees, and only then writes the final report. To train it, they built 159,416 step-by-step reasoning trajectories that mix images and text, using MIMIC-CXR. They then tuned it further with rewards for anatomical accuracy and clinical content. The abstract says ARIVE beat strong baselines on clinical-efficacy measures on MIMIC-CXR and on MIMIC-ABN, which focuses on abnormal cases. In blinded expert grading its reports were competitive with leading models, and its reasoning trails got high ratings for diagnostic traceability. A paired review test suggests that seeing the reasoning can help reviewers spot errors in reports.

## Why it matters

Current SI systems can draft plausible radiology reports, but it is hard to see why they wrote what they did. That makes reports hard to check or fix. Showing the evidence trail behind each finding could make SI drafts easier for doctors to review. The abstract gives no figures for the gains, so the size of the improvement is unclear.

## How it changes the race

This is a focused step for medical SI, not a change in frontier capability. It points to a way to make specialist models easier to audit by training them to show their visual evidence before they answer.

## Safety and control

Showing the reasoning behind each finding helps human reviewers check and correct SI output in a high-stakes setting. The abstract only says the reasoning "can aid" error spotting. It does not say whether the shown reasoning always matches what the model actually did.

### The abstract, by the authors

Automated radiology report generation can draft clinically plausible reports, yet the pathway from visual evidence to reported findings remains opaque, leaving the diagnostic basis of these reports unexplained and the generated reports difficult to review or revise. We introduce ARIVE (Anatomy-guided Reasoning with Interleaved Visual Evidence), an explainable report generation framework that interleaves anatomical inspection with diagnostic reasoning prior to final report composition. To support this process, we constructed 159,416 multimodal chain-of-thought (MCoT) trajectories from MIMIC-CXR, wherein visual evidence from inspected anatomical regions informs subsequent clinical interpretation. Trained on these trajectories and further optimized using anatomical and clinical-content rewards, ARIVE achieved superior clinical-efficacy performance compared with strong baselines on MIMIC-CXR and the abnormality-centered MIMIC-ABN. ARIVE's reports were competitive with those of leading models in blinded expert grading, and its MCoT trajectories earned high ratings for diagnostic traceability. Furthermore, a paired review evaluation suggests that access to MCoT can aid in identifying errors within generated reports.

Quoted from arXiv:2611.14018. The research and its words belong to its authors.

Desk score **72** out of 100

Why it was picked

- Interpretability (in the title)
- Reasoning (in the title)
- Evals
- Cross-listed in 2 fields

Topics

- [Health](https://thesimind.si/papers/?tag=health)
- [Multimodal](https://thesimind.si/papers/?tag=multimodal)
- [Interpretability](https://thesimind.si/papers/?tag=interpretability)
- [Reasoning](https://thesimind.si/papers/?tag=reasoning)
- [Vision](https://thesimind.si/papers/?tag=vision)
- [Reinforcement learning](https://thesimind.si/papers/?tag=reinforcement-learning)

**arXiv ID:** 2611.14018v1
**Submitted:** November 10, 2026
**Fields:** cs.CV (Computer Vision), cs.AI (Artificial Intelligence)
**Level:** Intermediate

Fingerprint, SHA-256

`662206d5b4c4550ca167f9f35420354f925125277c80b5bc9fb0ef258c146ba7`

On Solana: [Proof of Mind seal, 5PD2kk...Cqj6](https://solscan.io/tx/5PD2kk3Z7ogxetzRzWzdkmJzSKCEFyURumqF5Erz8h6F6E3GNRvEQuqS2rQBDr2mCmbjXczUupWfuuFsbFZhCqj6)

### The exact text fingerprinted

{"arxiv":"2611.14018","version":1,"title":"Interleaving anatomical inspection and diagnostic reasoning for explainable radiology report generation","authors":["Chentao Huang","Runlong Lin","Zhijun Wang","Yunxiang Li","Yuanyuan Sun","Jian Wang","Hongfei Lin","Ling Luo"],"day":"2026-11-13","rank":8,"score":72,"status":"written","summary":{"takeaway":"ARIVE writes chest X-ray reports by first inspecting body regions and reasoning about them, so reviewers can trace each finding and may catch errors more easily.","found":"The authors built ARIVE, a system that drafts radiology reports in steps. It looks at anatomical regions, reasons about what it sees, and only then writes the final report. To train it, they built 159,416 step-by-step reasoning trajectories that mix images and text, using MIMIC-CXR. They then tuned it further with rewards for anatomical accuracy and clinical content. The abstract says ARIVE beat strong baselines on clinical-efficacy measures on MIMIC-CXR and on MIMIC-ABN, which focuses on abnormal cases. In blinded expert grading its reports were competitive with leading models, and its reasoning trails got high ratings for diagnostic traceability. A paired review test suggests that seeing the reasoning can help reviewers spot errors in reports.","matters":"Current SI systems can draft plausible radiology reports, but it is hard to see why they wrote what they did. That makes reports hard to check or fix. Showing the evidence trail behind each finding could make SI drafts easier for doctors to review. The abstract gives no figures for the gains, so the size of the improvement is unclear.","race":"This is a focused step for medical SI, not a change in frontier capability. It points to a way to make specialist models easier to audit by training them to show their visual evidence before they answer.","safety":"Showing the reasoning behind each finding helps human reviewers check and correct SI output in a high-stakes setting. The abstract only says the reasoning \"can aid\" error spotting. It does not say whether the shown reasoning always matches what the model actually did.","level":"intermediate","tags":["health","multimodal","interpretability","reasoning","vision","reinforcement-learning"]}}

[Check it on Verify a thought](https://thesimind.si/proof-of-mind/)

## The authors

Chentao Huang, Runlong Lin, Zhijun Wang, Yunxiang Li, Yuanyuan Sun, Jian Wang, Hongfei Lin, Ling Luo

Credit for this research belongs to its authors. SI MIND's page is a plain-English reading of their abstract on arXiv, not a review of the full paper.

Related on the desk

## More papers on these topics

[Nov 10, 2026 · Number 9Mental Imagery That Matters: Curing Latent Collapse in Multimodal ReasoningSome SI models that reason with internal visual states barely use them. The authors call this Mental Simulation Collapse and fix it with AnchorSim, a training method that makes those states matter.MultimodalReasoningInterpretability](https://thesimind.si/papers/2611.10423/) · [Nov 15, 2026 · Number 12Asymmetric Multimodal Learning with Decomposed JEPAsTraining SI models only to align text and images throws away information that each side holds alone. Splitting the latent space into a shared core and private parts recovers it.MultimodalTrainingTheory](https://thesimind.si/papers/2611.16639/) · [Nov 20, 2026 · Number 5SixthView: A Benchmark for Hidden-View Reconstruction and 3D Assembly ReasoningOn SixthView, a new test of 3D assembly reasoning, three vision-language models did far better with exact text descriptions than with images alone, and images added almost nothing once the text was given.BenchmarksVisionMultimodal](https://thesimind.si/papers/2611.23891/)

[Number 7](https://thesimind.si/papers/2611.14760/) · [All 12 for Nov 13, 2026](https://thesimind.si/papers/day/2026-11-13/) · [Number 9](https://thesimind.si/papers/2611.13850/)
