Purpose
Existing summary statistics based upon optical coherence tomography (OCT) scans and/or visual fields (VF) are suboptimal for distinguishing between healthy and glaucomatous eyes in the clinic. This study evaluates the extent to which a hybrid deep learning method (HDLM), combined with a single wide-field OCT protocol, can distinguish eyes previously classified as either healthy suspects or mild glaucoma.
Patients and Methods
102 eyes from 102 patients, with or suspected open-angle glaucoma, had previously been classified by two glaucoma experts as either glaucomatous (57 eyes) or healthy/suspects (45 eyes). The HDLM had access only to information from a single, wide-field (9×12mm) swept-source OCT scan per patient. Convolutional neural networks were used to extract rich features from maps derived from these scans. Random forest classifier was used to train a model based on these features to predict the existence of glaucomatous damage. The algorithm was compared against traditional OCT and VF metrics.
Results
The accuracy of the HDLM ranged from 63.7% to 93.1% depending upon the input map. The RNFL probability map had the best accuracy (93.1%), with 4 false positives, and 3 false negatives. In comparison, the accuracy of the OCT and 24-2 and 10-2 VF metrics ranged from 66.7% to 87.3%. The OCT quadrants analysis had the best accuracy (87.3%) of the metrics, with 4 FP and 9 FN.
Conclusion
The HDLM protocol outperforms standard OCT and VF clinical metrics in distinguishing healthy suspect eyes from eyes with early glaucoma. It should be possible to further improve this algorithm and with improvement it might be useful for screening