CoChat

FFA-GPT: an automated pipeline for fundus fluorescein angiography interpretation and question-answer

Open access

Published version of a preprint

The DOI matches its Crossref record; 55 of the 55 references it cites were found in a registry or an index.

Abstract

Fundus fluorescein angiography (FFA) is a crucial diagnostic tool for chorioretinal diseases, but its interpretation requires significant expertise and time. Prior studies have used Artificial Intelligence (AI)-based systems to assist FFA interpretation, but these systems lack user interaction and comprehensive evaluation by ophthalmologists. Here, we used large language models (LLMs) to develop an automated interpretation pipeline for both report generation and medical question-answering (QA) for FFA images. The pipeline comprises two parts: an image-text alignment module (Bootstrapping Language-Image Pre-training) for report generation and an LLM (Llama 2) for interactive QA. The model was developed using 654,343 FFA images with 9392 reports. It was evaluated both automatically, using language-based and classification-based metrics, and manually by three experienced ophthalmologists. The automatic evaluation of the generated reports demonstrated that the system can generate coherent and comprehensible free-text reports, achieving a BERTScore of 0.70 and F1 scores ranging from 0.64 to 0.82 for detecting top-5 retinal conditions. The manual evaluation revealed acceptable accuracy (68.3%, Kappa 0.746) and completeness (62.3%, Kappa 0.739) of the generated reports. The generated free-form answers were evaluated manually, with the majority meeting the ophthalmologists’ criteria (error-free: 70.7%, complete: 84.0%, harmless: 93.7%, satisfied: 65.3%, Kappa: 0.762–0.834). This study introduces an innovative framework that combines multi-modal transformers and LLMs, enhancing ophthalmic image interpretation, and facilitating interactive communications during medical consultation.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41746-024-01101-z

Cites

55 of 55 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig. 1 Schematic diagram of this study. FFA fundus fluorescein angiography, GPT generative pre-trained transformer, BLIP bootstrapping language-image pre-training.
Fig. 1 Schematic diagram of this study. FFA fundus fluorescein angiography, GPT generative pre-trained transformer, BLIP bootstrapping language-image pre-training.CC BY · PubMed Central
Fig. 2 Demonstration of the integrated interface of our model. FFA fundus fluorescein angiography, GPT generative pre-trained transformer, OD right eye.
Fig. 2 Demonstration of the integrated interface of our model. FFA fundus fluorescein angiography, GPT generative pre-trained transformer, OD right eye.CC BY · PubMed Central
Fig. 3 Human evaluation. A Report generation. B Question answering. O Ophthalmologist.
Fig. 3 Human evaluation. A Report generation. B Question answering. O Ophthalmologist.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 55 references

Research works printed but not linked: 3

  1. Loshchilov, I. & Hutter, F. Decoupled Weight Decay Regularization. International Conference on Learning Representations (2018).
  2. Lin, C.-Y. ROUGE: A Package for Automatic Evaluation of Summaries. Text. Summariz. Branches Out. 74, 81 (2004).
  3. Zhang, T., Kishore, V., Wu, F., Weinberger, K. Q. & Artzi, Y. BERTScore: Evaluating Text Generation with BERT. International Conference on Learning Representations (2020).

Cited by

See all 88

Metadata

Authors
Chen, X., Zhang, W., Xu, P., Zhao, Z., Zheng, Y., Shi, D., & He, M.
Affiliations
  • Hong Kong Polytechnic University (HK)
  • Sun Yat-sen University (CN)
Corresponding author
Shi, Danli
Venue
npj Digital Medicine
Published
2024-05-03
Volume
7
Issue
1
Pages
111-111
ISSN
2398-6352 (ISSN-L)
OpenAlex
W4396605652
Cited by
72
References
50
Citations by year
2026: 25 · 2025: 37 · 2024: 10
FWCI
18.34
Type
journal article
Language
en
Open access
Licence
Locations
  • npj Digital Medicine (publishedVersion, cc-by)
  • Research Square (acceptedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • PolyU Institutional Research Archive (Hong Kong Polytechnic University) (submittedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • Minerva Access (University of Melbourne) (submittedVersion, cc-by)
Funders
  • Start-up Fund for RAPs under the Strategic Hiring Scheme
  • National Natural Science Foundation of China (82171034)
  • Global STEM Professorship Scheme from HKSAR
Topics
  • Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Retinal Imaging and Analysis
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
Keywords
fundus fluorescein angiography, automated reporting, medical question answering, large language models, Llama 2, image-text alignment, chorioretinal diseases, multimodal transformer

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: FFA-GPT: an automated pipeline for fundus fluorescein angiography interpretation and question-answer. https://app.cochat.ai/papers/10.1038/s41746-024-01101-z
The paper
Chen, X., Zhang, W., Xu, P., Zhao, Z., Zheng, Y., Shi, D., & He, M. (2024). FFA-GPT: an automated pipeline for fundus fluorescein angiography interpretation and question-answer. npj Digital Medicine. https://doi.org/10.1038/s41746-024-01101-z

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.