# Inspecting state of the art performance and NLP metrics in image-based medical report generation

arXiv: https://arxiv.org/abs/2011.09257 · HTML: https://mlsanity.com/paper/2011.09257/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Nov 2020.

## Built on by (most cited first, 3 of 3)

- [Interactive and Explainable Region-guided Radiology Report Generation](https://mlsanity.com/paper/2304.08295/) (2023)
- [Extracting and Encoding: Leveraging Large Language Models and Medical Knowledge to Enhance Radiological Text Representation](https://mlsanity.com/paper/2407.01948/) (2024)
- [Regulating Anatomy-Aware Rewards via Trajectory-Integral Feedback for Volumetric Computed Tomography Analysis](https://mlsanity.com/paper/2605.20277/) (2026)

## Abstract (arXiv)

Several deep learning architectures have been proposed over the last years to deal with the problem of generating a written report given an imaging exam as input. Most works evaluate the generated reports using standard Natural Language Processing (NLP) metrics (e.g. BLEU, ROUGE), reporting significant progress. In this article, we contrast this progress by comparing state of the art (SOTA) models against weak baselines. We show that simple and even naive approaches yield near SOTA performance on most traditional NLP metrics. We conclude that evaluation methods in this task should be further studied towards correctly measuring clinical accuracy, ideally involving physicians to contribute to this end.