convolutional mixture of experts model: a comparative study on automatic macular diagnosis in retinal optical coherence tomography imaging

Background: macular disorders, such as diabetic macular edema (dme) and age-related maculardegeneration (amd) are among the major ocular diseases. having one of these diseases can lead tovision impairments or even permanent blindness in a not-so-long time span. so, the early diagnosisof these diseases are the main goals for researchers in the field. methods: this study is designed inorder to present a comparative analysis on the recent convolutional mixture of experts (cmoe) modelsfor distinguishing normal macular oct from dme and amd. for this purpose, we considered threerecent cmoe models called mixture ensemble of convolutional neural networks (me-cnn), multiscaleconvolutional mixture of experts (mcme), and wavelet-based convolutional mixture of experts(wcme) models. for this research study, the models were evaluated on a database of three differentmacular oct sets. two first oct sets were acquired by heidelberg imaging systems consisting of 148and 45 subjects respectively and set3 was constituted of 384 bioptigen oct acquisitions. to providebetter performance insight into the cmoe ensembles, we extensively analyzed the models based on the5-fold cross-validation method and various classification measures such as precision and average areaunder the roc curve (auc). results: experimental evaluations showed that the mcme and wcmeoutperformed the me-cnn model and presented overall precisions of 98.14% and 96.06% for alignedocts respectively. for non-aligned retinal octs, these values were 93.95% and 95.56%. conclusion:based on the comparative analysis, although the mcme model outperformed the other cmoe modelsin the analysis of aligned retinal octs, the wcme offers a robust model for diagnosis of non-alignedretinal octs. this allows having a fast and robust computer-aided system in macular oct imagingwhich does not rely on the routine computerized processes such as denoising, segmentation of retinallayers, and also retinal layers alignment.