Interpretable Detection of Epiretinal Membrane from Optical Coherence Tomography with Deep Neural Networks

Purpose To automatically detect epiretinal membranes (ERMs) of different sizes in various OCT scans of the central and paracentral macula region and classify them by size using deep neural networks (DNNs). Methods 11,061 OCT-images of 624 volume OCT scans (624 eyes of 461 patients) were included and graded according to the presence of an ERM and its size (small 100-1000µm, large >1000 µm). The data set was divided into training, validation and test sets (comprising of 75%, 10%, 15% of the data, respectively). An ensemble of DNNs was trained and saliency maps were generated using Guided Backprob. OCT-scans were also transformed into a one-dimensional value using t-SNE analysis. Results The DNNs’ receiver-operating-characteristics on the test set showed a high performance for no ERM, small ERM and large ERM cases (AUC: 0.99, 0.92, 0.99, respectively; 3-way accuracy: 89%), with small ERMs being the most difficult ones to detect. t-SNE analysis sorted cases by size and, in particular, revealed increased classification uncertainty at the transitions between groups. Saliency maps reliably highlighted ERMs, regardless of the presence of other OCT features (i.e. retinal thickening, intraretinal pseudocysts, epiretinal proliferation) and entities such as ERM-retinoschisis, macular pseudohole and lamellar macular hole. Conclusion DNNs can reliably detect and grade ERMs according to their size not only in the fovea but also in the paracentral region. This is also achieved in cases of hard-to-detect, small ERMs. In addition, the generated saliency maps can be used effectively to highlight small ERMs that might otherwise be missed. The proposed model could be used for screening programs or decision support systems in the future.