# How Well Do Multi-modal LLMs Interpret CT Scans? An Auto-Evaluation Framework for Analyses

arXiv: https://arxiv.org/abs/2403.05680 · HTML: https://mlsanity.com/paper/2403.05680/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 29 references that are in the map.
- First posted on arXiv 8 Mar 2024.

## Builds on (most cited first, 14 of 14)

- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases](https://mlsanity.com/paper/1705.02315/) (2017)
- [Capabilities of GPT-4 on Medical Challenge Problems](https://mlsanity.com/paper/2303.13375/) (2023)
- [Generating Radiology Reports via Memory-driven Transformer](https://mlsanity.com/paper/2010.16056/) (2020)
- [Cross-modal Memory Networks for Radiology Report Generation](https://mlsanity.com/paper/2204.13258/) (2022)
- [Towards Generalist Foundation Model for Radiology by Leveraging Web-scale 2D&3D Medical Data](https://mlsanity.com/paper/2308.02463/) (2023)
- [Opportunities and Challenges for ChatGPT and Large Language Models in Biomedicine and Health](https://mlsanity.com/paper/2306.10070/) (2023)
- [The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning](https://mlsanity.com/paper/2305.14045/) (2023)
- [NegBio: a high-performance tool for negation and uncertainty detection in radiology reports](https://mlsanity.com/paper/1712.05898/) (2017)
- [Utilizing Longitudinal Chest X-Rays and Reports to Pre-Fill Radiology Reports](https://mlsanity.com/paper/2306.08749/) (2023)
- [Holistic and Comprehensive Annotation of Clinically Significant Findings on Diverse CT Images: Learning from Radiology Reports and Label Ontology](https://mlsanity.com/paper/1904.04661/) (2019)
- [Path to Medical AGI: Unify Domain-specific Medical LLMs with the Lowest Cost](https://mlsanity.com/paper/2306.10765/) (2023)
- [Leveraging Professional Radiologists' Expertise to Enhance LLMs' Evaluation for Radiology Reports](https://mlsanity.com/paper/2401.16578/) (2024)

## Built on by (most cited first, 1 of 1)

- [PET2Rep: Towards Vision-Language Model-Drived Automated Radiology Report Generation for Positron Emission Tomography](https://mlsanity.com/paper/2508.04062/) (2025)

## Abstract (arXiv)

Automatically interpreting CT scans can ease the workload of radiologists. However, this is challenging mainly due to the scarcity of adequate datasets and reference standards for evaluation. This study aims to bridge this gap by introducing a novel evaluation framework, named ``GPTRadScore''. This framework assesses the capabilities of multi-modal LLMs, such as GPT-4 with Vision (GPT-4V), Gemini Pro Vision, LLaVA-Med, and RadFM, in generating descriptions for prospectively-identified findings. By employing a decomposition technique based on GPT-4, GPTRadScore compares these generated descriptions with gold-standard report sentences, analyzing their accuracy in terms of body part, location, and type of finding. Evaluations demonstrated a high correlation with clinician assessments and highlighted its potential over traditional metrics, such as BLEU, METEOR, and ROUGE. Furthermore, to contribute to future studies, we plan to release a benchmark dataset annotated by clinicians. Using GPTRadScore, we found that while GPT-4V and Gemini Pro Vision fare better, their performance revealed significant areas for improvement, primarily due to limitations in the dataset used for training these models. To demonstrate this potential, RadFM was fine-tuned and it resulted in significant accuracy improvements: location accuracy rose from 3.41% to 12.8%, body part accuracy from 29.12% to 53%, and type accuracy from 9.24% to 30%, thereby validating our hypothesis.