advertisement

WGW-2021

Abstract #82092 Published in IGR 20-4

Accurate prediction of glaucoma from colour fundus images with a convolutional neural network that relies on active and transfer learning

Hemelings R; Elen B; Barbosa-Breda J; Lemmens S; Meire M; Pourjavan S; Vandewalle E; Van de Veire S; Blaschko MB; De Boever P; Stalmans I
Acta Ophthalmologica 2020; 98: e94-e100

See also comment(s) by Gustavo de Moraes & Bruna Melchior Silva


PURPOSE: To assess the use of deep learning (DL) for computer-assisted glaucoma identification, and the impact of training using images selected by an active learning strategy, which minimizes labelling cost. Additionally, this study focuses on the explainability of the glaucoma classifier. METHODS: This original investigation pooled 8433 retrospectively collected and anonymized colour optic disc-centred fundus images, in order to develop a deep learning-based classifier for glaucoma diagnosis. The labels of the various deep learning models were compared with the clinical assessment by glaucoma experts. Data were analysed between March and October 2018. Sensitivity, specificity, area under the receiver operating characteristic curve (AUC), and amount of data used for discriminating between glaucomatous and non-glaucomatous fundus images, on both image and patient level. RESULTS: Trained using 2072 colour fundus images, representing 42% of the original training data, the trained DL model achieved an AUC of 0.995, sensitivity and specificity of, respectively, 98.0% (CI 95.5%-99.4%) and 91% (CI 84.0%-96.0%), for glaucoma versus non-glaucoma patient referral. CONCLUSIONS: These results demonstrate the benefits of deep learning for automated glaucoma detection based on optic disc-centred fundus images. The combined use of transfer and active learning in the medical community can optimize performance of DL models, while minimizing the labelling cost of domain-specific mavens. Glaucoma experts are able to make use of heat maps generated by the deep learning classifier to assess its decision, which seems to be related to inferior and superior neuroretinal rim (within ONH), and RNFL in superotemporal and inferotemporal zones (outside ONH).

Full article

Classification:

6.9.5 Other (Part of: 6 Clinical examination methods > 6.9 Computerized image analysis)
6.30 Other (Part of: 6 Clinical examination methods)
2.13 Retina and retinal nerve fibre layer (Part of: 2 Anatomical structures in glaucoma)
6.8.2 Posterior segment (Part of: 6 Clinical examination methods > 6.8 Photography)



Issue 20-4

Select Issue


advertisement

Oculus