We aimed to determine the effect of optic disc tilt on deep learning-based optic disc classification. Image annotation was performed to label pathologic changes of the optic disc (normal, glaucomatous optic disc changes, disc swelling, and disc pallor) and note the appearance of a tilted optic disc (non-tilted versus tilted). Deep learning-based classification modeling was implemented to develop an optic-disc appearance classification. We acquired 2,507 fundus photographs from 2,236 subjects. Of the 2,507 data, 1,010 (40.3%) had tilted optic discs. The AUC of the models trained and tested using the non-tilted disc dataset was 0.988 ± 0.002, 0.991 ± 0.003, and 0.986 ± 0.003 for VGG16, VGG19, and DenseNet121, respectively. The AUC of the models trained and tested using the tilted disc dataset was 0.924 ± 0.046, 0.928 ± 0.017, and 0.935 ± 0.008. The model performance indicated by the AUC was better for non-tilted discs, regardless of the dataset used for training. In each pathologic change, non-tilted disc models showed better sensitivity than the tilted disc model. In the groups of glaucoma, disc pallor, and disc swelling, non-tilted disc models showed better specificity than the tilted disc model. We developed deep learning-based optic disc appearance classification systems using the fundus photographs of patients with and without tilted optic discs. The classification accuracy was lower in patients with the appearance of tilted discs compared to non-tilted discs, suggesting the need for identifying and adjusting for the effect of optic disc tilt on the optic disc classification algorithm in future development.
We evaluated the prognostic value of the preoperative macular ganglion cell inner plexiform layer (mGCIPL) thickness along with peripapillary retinal nerve fiber layer (pRNFL) thickness measured by optical coherence tomography (OCT) and estimated an optimal cut-off value to predict postoperative visual field (VF) recovery in adult patients with chiasmal compression after decompression surgery. Two hundred forty eyes of 240 patients aged 20 years or older for which preoperative high-definition Cirrus OCT parameters and pre- and postoperative visual function data were available. The prognostic power of pRNFL and mGCIPL thicknesses for complete postoperative VF recovery or significant VF improvement (improvement ≥ 2 dB in the mean deviation) were assessed. The cut-off values for OCT parameters for VF recovery were estimated. The study found that the higher the preoperative pRNFL and mGCIPL thicknesses, the higher the probability of complete postoperative VF recovery (p = 0.0378 and p = 0.0051, respectively) or significant VF improvement (p = 0.0436 and p = 0.0177, respectively). The area under the receiver operating characteristic analysis of preoperative OCT parameters demonstrated that the mGCIPL thickness showed an area under the curve (AUC) of more than 0.7 for complete VF recovery after decompression surgery (AUC = 0.725, 95% CI: 0.655, 0.795), and the optimal mGCIPL thickness cut-off value for complete VF recovery was 77.25 µm (sensitivity 69% and specificity 69%). Preoperative mGCIPL thickness was a powerful predictor of visual functional outcome after decompression surgery for chiasmal compression.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.