The enigma of sclera-specific autoimmunity in scleritis.

Scleritis is a severe and painful ophthalmic disorder, in which a pathogenic role for collagen-directed autoimmunity was repeatedly suggested. We evaluated the presence of sclera-specific antibodies in a large cohort of patients with non-infectious scleritis. Therefore, we prospectively collected serum samples from 121 patients with non-infectious scleritis in a multicenter cohort study in the Netherlands. In addition, healthy (n = 39) and uveitis controls (n = 48) were included. Serum samples were tested for anti-native human type II collagen antibodies using a validated enzyme-linked immunosorbent assay (ELISA). Further, sclera-specific antibodies were determined using indirect immunofluorescence (IIF) on primate retinal/scleral cryosections. Lastly, human leukocyte antigen (HLA) typing was performed in 111 patients with scleritis. Anti-type II collagen antibodies were found in 13% of scleritis patients, in 10% of healthy controls and in 11% of uveitis controls (p = 0.91). A specific reaction to scleral nerve tissue on IIF was observed in 33% of patients with scleritis, which was higher than in healthy controls (11%; p = 0.01), but similar to uveitis controls (25%; p = 0.36). Reactivity to the scleral nerve tissue was significantly associated with earlier onset of scleritis (48 versus 56 years; p < 0.001), bilateral involvement (65% versus 42%; p = 0.01), and less frequent development of scleral necrosis (5% versus 22%; p = 0.02). HLA-B27 was found to be twice as prevalent in patients with scleritis (15.3%) compared to a healthy population (7.2%). In conclusion, scleral nerve autoantibody reactivity was more common in scleritis and uveitis patients in contrast to healthy controls. Further research is needed to characterize these scleral-nerve directed antibodies and assess their clinical value.

Prediction of molecular subclasses of uveal melanoma by deep learning using routine haematoxylin-eosin-stained tissue slides.

AIMS: Uveal melanoma has a high propensity to metastasize. Prognosis is associated with specific driver mutations and copy number variations, and these can only be obtained after genetic testing. In this study we evaluated the efficacy of patient outcome prediction using deep learning on haematoxylin and eosin (HE)-stained primary uveal melanoma slides in comparison to molecular testing. METHODS: In this retrospective study of patients with uveal melanoma, 113 patients from the Erasmus Medical Centre who underwent enucleation had tumour tissue analysed for molecular classification between 1993 and 2020. Routine HE-stained slides were scanned to obtain whole-slide images (WSI). After annotation of regions of interest, tiles of 1024 × 1024 pixels were extracted at a magnification of 40×. An ablation study to select the best-performing deep-learning model was carried out using three state-of-the-art deep-learning models (EfficientNet, Vision Transformer, and Swin Transformer). RESULTS: Deep-learning models were subjected to a training cohort (n = 40), followed by a validation cohort (n = 20), and finally underwent a test cohort (n = 48). A k-fold cross-validation (k = 3) of validation and test cohorts (n = 113 of three classes: BAP1, SF3B1, EIF1AX) demonstrated Swin Transformer as the best-performing deep-learning model to predict molecular subclasses based on HE stains. The model achieved an accuracy of 0.83 ± 0.09 on the validation cohort and 0.75 ± 0.04 on the test cohort. Within the subclasses, this model correctly predicted 70% BAP1-mutated, 61% SF3B1-mutated and 80% EIF1AX-mutated UM in the test set. CONCLUSIONS: This study showcases the potential of the deep-learning methodology for predicting molecular subclasses in a multiclass manner using HE-stained WSI. This development holds promise for advanced prognostication of UM patients without the need of molecular or immunohistochemical testing. Additionally, this study suggests there are distinct histopathological features per subclass; mainly utilizing epithelioid cellular morphology for BAP1-classification, but an unknown feature distinguishes EIF1AX and SF3B1.