iERM: An Interpretable Deep Learning System to Classify Epiretinal Membrane for Different Optical Coherence Tomography Devices: A Multi-Center Analysis

Abstract

Background: Epiretinal membranes (ERM) have been found to be common among individuals >50 years old. However, the severity grading assessment for ERM based on optical coherence tomography (OCT) images has remained a challenge due to lacking reliable and interpretable analysis methods. Thus, this study aimed to develop a two-stage deep learning (DL) system named iERM to provide accurate automatic grading of ERM for clinical practice. Methods: The iERM was trained based on human segmentation of key features to improve classification performance and simultaneously provide interpretability to the classification results. We developed and tested iERM using a total of 4547 OCT B-Scans of four different commercial OCT devices that were collected from nine international medical centers. Results: As per the results, the integrated network effectively improved the grading performance by 1–5.9% compared with the traditional classification DL model and achieved high accuracy scores of 82.9%, 87.0%, and 79.4% in the internal test dataset and two external test datasets, respectively. This is comparable to retinal specialists whose average accuracy scores are 87.8% and 79.4% in two external test datasets. Conclusion: This study proved to be a benchmark method to improve the performance and enhance the interpretability of the traditional DL model with the implementation of segmentation based on prior human knowledge. It may have the potential to provide precise guidance for ERM diagnosis and treatment.

Two-in-One Sensor Based on PV4D4-Coated TiO2 Films for Food Spoilage Detection and as a Breath Marker for Several Diseases

“…In this regards, an interesting example of such an advance can be seen in a previous study [1] where a system of computer-aided diagnostics improved the results of a plain X-ray using machine learning. Another good example is an interpretable deep learning system in the study of Kai Jin et al [2], where the main goal was to classify the epiretinal membrane for different optical coherence tomography devices, which, however, still needs further research, as its potential demonstrated. As a matter of fact, even previous and further studies, which will be seen in this work, have as their main goal minimal to non-invasive diagnosis, where much of the potential lies with gas detectors and sensors.…”

Multi-threshold image segmentation using an enhanced fruit fly optimization for COVID-19 X-ray images

“…Stability analysis and structural validations are the bases of the studies with some mathematical background [95] . To preserve the fairness and validity of the experiments, all the algorithms involved in the experiments were performed in the same environment [96] , [97] , [98] . The population size was 30, and the maximum number of evaluations was 300,000.…”

An interpretable transformer network for the retinal disease classification using optical coherence tomography

“…Song et al 12 proposed a depth inference mechanism for the diagnosis of glaucoma, which combined OCT and visual field (VF) examination to effectively utilize complementary information from different modalities. jin et al 13 proposed to improve the performance and interpretability of traditional DL models by implementing segmentation based on prior human knowledge. Vidal et al 14 transforms binary masks into photorealistic OCT images using image-to-image generative adversarial networks.…”