Search

BACKGROUND: Nonophthalmologist physicians do not confidently perform direct ophthalmos-copy. The use of artificial intelligence to detect papilledema and other optic-disk abnormalities from fundus photographs has not been well studied METHODS: We trained, validated, and externally tested a deep-learning system to classify optic disks as being normal or having papilledema or other abnormalities from 15,846 retrospectively collected ocular fundus photographs that had been obtained with pharmacologic pupillary dilation and various digital cameras in persons from multiple ethnic populations. Of these photographs, 14,341 from 19 sites in 11 coun-tries were used for training and validation, and 1505 photographs from 5 other sites were used for external testing. Performance at classifying the optic-disk ap-pearance was evaluated by calculating the area under the receiver-operating-characteristic curve (AUC), sensitivity, and specificity, as compared with a reference standard of clinical diagnoses by neuro-ophthalmologists RESULTS: The training and validation data sets from 6779 patients included 14,341 photo-graphs: 9156 of normal disks, 2148 of disks with papilledema, and 3037 of disks with other abnormalities. The percentage classified as being normal ranged across sites from 9.8 to 100%; the percentage classified as having papilledema ranged across sites from zero to 59.5%. In the validation set, the system discriminated disks with papilledema from normal disks and disks with nonpapilledema abnor-malities with an AUC of 0.99 (95% confidence interval [CI], 0.98 to 0.99) and normal from abnormal disks with an AUC of 0.99 (95% CI, 0.99 to 0.99). In the external-testing data set of 1505 photographs, the system had an AUC for the detection of papilledema of 0.96 (95% CI, 0.95 to 0.97), a sensitivity of 96.4% (95% CI, 93.9 to 98.3), and a specificity of 84.7% (95% CI, 82.3 to 87.1).CONCLUSIONSA deep-learning system using fundus photographs with pharmacologically dilated pupils differentiated among optic disks with papilledema, normal disks, and disks with nonpapilledema abnormalities. (Funded by the Singapore National Medical Research Council and the SingHealth Duke–NUS Ophthalmology and Visual Sci-ences Academic Clinical Program.)

Behavioral alterations emerging after central or peripheral vision loss suggest that cerebral reorganization occurs for both the afferented and deafferented early visual cortex (EVC). We explored the functional reorganization of the central and peripheral EVC following visual field defects specifically affecting central or peripheral vision. Compared to normally sighted, afferented central and peripheral EVC enhance their functional connectivity with areas involved in visual processing, whereas deafferented central and peripheral EVC increase their functional connectivity with more remote regions. The connectivity pattern of afferented EVC suggests adaptive changes that might enhance the visual processing capacity whereas the connectivity pattern of deafferented EVC may reflect the involvement of these regions in high-order mechanisms. Characterizing and understanding the plastic changes induced by these visual defects is essential for any attempt to develop efficient rehabilitation strategies.

International audience; In the congenitally blind, language processing involves visual areas. In the case of normal visual development however, it remains unclear whether later visual loss induces interactions between the language and visual areas. This study compared the resting-state functional connectivity (FC) of retinotopic and language areas in two unique groups of late visually deprived subjects: (1) blind individuals suffering from retinitis pigmentosa (RP), (2) RP subjects without a visual periphery but with preserved central “tunnel vision”, both of whom were contrasted with sighted controls. The results showed increased FC between Broca's area and the visually deprived areas in the peripheral V1 for individuals with tunnel vision, and both the peripheral and central V1 for blind individuals. These findings suggest that FC can develop in the adult brain between the visual and language systems in the completely and partially blind. These changes start in the deprived areas and increase in size (involving both foveal and peripheral V1) and strength (from negative to positive FC) as the disease and sensory deprivation progress. These observations support the claim that functional connectivity between remote systems that perform completely different tasks can change in the adult brain in cases of total and even partial visual deprivation.