AI and Rare Diseases ── Immune and connective tissue ── 2026-10-09

Figure for a study classifying cystoid macular edema from fluorescein angiography images of 117 patients with retinal vasculitis, 207 images in all. Rare disease and expert-dependent reading lead to transfer learning with an ImageNet-pretrained ResNet-18, then patient-level nested cross-validation. The AUROC was 0.708, moderate, and with no external validation and remaining errors it cannot be deployed clinically. — Image abstract — the whole article on one page (click to enlarge)

1 Immune and connective tissue papers. Lead: Classification of cystoid macular edema status from retinal vasculitis fluorescein angiography images using a convolutional neural network

Journals covered and how papers are chosen: see the index

Autoinflammatory, immunodeficiency and rare connective-tissue diseases: treatment, trials and AI

Classification of cystoid macular edema status from retinal vasculitis fluorescein angiography images using a convolutional neural network
Frontiers in Ophthalmology · 2026-10-07 · Evidence: Retrospective observational (model development with internal nested cross-validation; no external validation)
Abstract
Introduction: Cystoid macular edema (CME) is a vision-threatening complication of retinal vasculitis, a rare inflammatory disease for which large imaging datasets are difficult to obtain. Detection of CME on fluorescein angiography (FA) requires expert interpretation, motivating automated image-based approaches to support clinical decision-making. Deep learning methods, particularly convolutional neural networks (CNNs), have shown strong performance in medical image analysis but are constrained by limited labeled data in rare diseases. Transfer learning may mitigate this limitation by adapting pretrained models to small, task-specific datasets.
Methods: We analyzed 207 de-identified late-phase 55° FA images from 117 patients with retinal vasculitis. The primary target was concurrent patient-level CME status, established through specialist review of clinical records and optical coherence tomography obtained at the same clinical visit as FA. A patient was classified as CME-positive when CME was present in at least one eye. An ImageNet-pretrained ResNet-18 was evaluated using five-fold nested, patient-level cross-validation. Within each outer-development cohort, 144 candidate configurations were compared by four-fold inner cross-validation and selected according to mean inner-validation AUROC. Each selected configuration was evaluated only on its corresponding untouched outer-test fold.
Results: Across 117 pooled patient-level outer-test predictions, the model-selection pipeline achieved an AUROC of 0.708 (95% CI, 0.610–0.802), an AUPRC of 0.626 (95% CI, 0.493–0.755), and an accuracy of 0.726 (95% CI, 0.641–0.803). Sensitivity was 0.694 (95% CI, 0.558–0.822), specificity was 0.750 (95% CI, 0.643–0.853), and the F1 score was 0.680 (95% CI, 0.563–0.780). Exploratory Grad-CAM analysis visualized regions associated with model predictions. Discussion The nested model-selection pipeline showed moderate discrimination with a relatively balanced operating profile and slightly higher specificity than sensitivity. Clinically relevant false-positive and false-negative errors, together with the absence of external validation, preclude clinical deployment.
Journal IF-equivalent: 2.1 (OpenAlex 2-year mean citedness, value as of 2026-10-08, retrieved 2026-10-09; not the official Clarivate IF)
Reference: Wang C, Chakrabarty K, Anesi SD, Chang PY. Classification of cystoid macular edema status from retinal vasculitis fluorescein angiography images using a convolutional neural network. Front Ophthalmol. 2026 Oct 7;6:1901237. doi:10.3389/fopht.2026.1901237.
Checked: Abstract only

← Back to this issue