# RetSTA: An LLM-Based Approach for Standardizing Clinical Fundus Image Reports

Source: [RetSTA: An LLM-Based Approach for Standardizing Clinical Fundus Image Reports](<https://www.sota2.com/research/paper/68fa77681e209131cea7314b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-02T09:01:30.836Z

Authors: Jiushen Cai, Weihang Zhang, Hanruo Liu, Ningli Wang, Huiqi Li

Published: 2025-03-12T13:00:57.000Z

## Abstract

Standardization of clinical reports is crucial for improving the quality of healthcare and facilitating data integration. The lack of unified standards, including format, terminology, and style, is a great challenge in clinical fundus diagnostic reports, which increases the difficulty for large language models (LLMs) to understand the data. To address this, we construct a bilingual standard terminology, containing fundus clinical terms and commonly used descriptions in clinical diagnosis. Then, we establish two models, RetSTA-7B-Zero and RetSTA-7B. RetSTA-7B-Zero, fine-tuned on an augmented dataset simulating clinical scenarios, demonstrates powerful standardization behaviors. However, it encounters a challenge of limitation to cover a wider range of diseases. To further enhance standardization performance, we build RetSTA-7B, which integrates a substantial amount of standardized data generated by RetSTA-7B-Zero along with corresponding English data, covering diverse complex clinical scenarios and achieving report-level standardization for the first time. Experimental results demonstrate that RetSTA-7B outperforms other compared LLMs in bilingual standardization task, which validates its superior performance and generalizability. The checkpoints are available at https://github.com/AB-Story/RetSTA-7B.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Clinical Diagnostic Report Standardization on English Clinical Diagnostic Reports (test)](<https://www.sota2.com/research/sota/clinical-diagnostic-report-standardization-on-english-clinical-diagnostic-reports-test.md>): Clinical diagnostic report standardization; English clinical diagnostic reports (test); BLEU-1: 92.69.

- [Standardization on Chinese clinical diagnostic reports](<https://www.sota2.com/research/sota/standardization-on-chinese-clinical-diagnostic-reports.md>): Standardization; Chinese clinical diagnostic reports; BLEU-1: 93.35.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2503.09358>)

[PDF](<https://arxiv.org/pdf/2503.09358.pdf>)

[Implementation](<https://github.com/AB-Story/RetSTA-7B>)
