Prediction of visual impairment in retinitis pigmentosa using deep learning and multimodal fundus images

The British Journal of Ophthalmology · 6 authors, 6 centres

AI SUMMARY

FIDELITY 100%

This summary was generated by AI from a single paper. It has not been reviewed by a clinician and is not clinical advice. Verify against the source before acting on it.

AGENT 01 · STRUCTURED SUMMARY

TRACE TO SOURCE

“

TL;DR

A retrospective study developed and tested deep learning algorithms to predict visual impairment in retinitis pigmentosa using only scanning laser ophthalmoscopy images. The study found that optical coherence tomography (OCT) images alone could reliably predict if a patient's visual acuity was better or worse than 20/40.

Full summary

594 CHARS

This retrospective cohort study developed deep learning (DL) algorithms to predict visual impairment in retinitis pigmentosa (RP) using confocal scanning laser ophthalmoscopy (cSLO) images. Three DL models were trained on infrared (IR), optical coherence tomography (OCT), or combined images (CI). For the binary task of distinguishing Snellen VA 20/40 or better from worse, the OCT model performed best, with an area under the curve (AUC) of 0.87 in internal testing and 0.87 in external testing. The findings suggest potential applications for clinical trial screening and patient monitoring.

STUDY TYPE

cohort

SPECIALTY

ophthalmology

SUMMARISED BY

AI pipeline

FIDELITY CHECK

100% · A

ORIGINAL PAPER

PMC10579177

Prediction of visual impairment in retinitis pigmentosa using deep learning and multimodal fundus images

The British Journal of Ophthalmology

READ THE FULL PAPER

ABSTRACT

Background The efficiency of clinical trials for retinitis pigmentosa (RP) treatment is limited by the screening burden and lack of reliable surrogate markers for functional end points. Automated methods to determine visual acuity (VA) may help address these challenges. We aimed to determine if VA could be estimated using confocal scanning laser ophthalmoscopy (cSLO) imaging and deep learning (DL). Methods Snellen corrected VA and cSLO imaging were obtained retrospectively. The Johns Hopkins University (JHU) dataset was used for 10-fold cross-validations and internal testing. The Amsterdam University Medical Centers (AUMC) dataset was used for external independent testing. Both datasets had the same exclusion criteria: visually significant media opacities and images not centred on the central macula. The JHU dataset included patients with RP with and without molecular confirmation. The AUMC dataset only included molecularly confirmed patients with RP. Using transfer learning, three versions of the ResNet-152 neural network were trained: infrared (IR), optical coherence tomography (OCT) and combined image (CI). Results In internal testing (JHU dataset, 2569 images, 462 eyes, 231 patients), the area under the curve (AUC) for the binary classification task of distinguishing between Snellen VA 20/40 or better and worse than Snellen VA 20/40 was 0.83, 0.87 and 0.85 for IR, OCT and CI, respectively. In external testing (AUMC dataset, 349 images, 166 eyes, 83 patients), the AUC was 0.78, 0.87 and 0.85 for IR, OCT and CI, respectively. Conclusions Our algorithm showed robust performance in predicting visual impairment in patients with RP, thus providing proof-of-concept for predicting structure-function correlation based solely on cSLO imaging in patients with RP.

CITATION EXPORT

Tin Yan Alvin Liu, Carlthan Ling, Leo Hahn et al.. Prediction of visual impairment in retinitis pigmentosa using deep learning and multimodal fundus images. The British Journal of Ophthalmology. (2023). https://doi.org/10.1136/bjo-2021-320897

AUTHORS

6 · 6 CENTRES

Tin Yan Alvin Liu, Carlthan Ling, Leo Hahn, Craig K Jones, Camiel JF Boon, Mandeep S Singh

1 Wilmer Eye Institute, Johns Hopkins Hospital, Baltimore, Maryland, USA
2 Department of Ophthalmology, University of Maryland Medical System, Baltimore, Maryland, USA
3 Department of Ophthalmology, Amsterdam UMC Locatie AMC, Amsterdam, The Netherlands
4 Malone Center for Engineering in Healthcare, Whiting School of Engineering, Johns Hopkins University, Baltimore, Maryland, USA
5 Department of Ophthalmology, Leiden University Medical Center, Leiden, The Netherlands
6 Department of Genetic Medicine, School of Medicine, Johns Hopkins University, Baltimore, Maryland, USA