Synthesis of neural network structure for the analysis of complex structured ocular fundus images

This paper proposes an algorithm for synthesizing a neural network (NN) structure to analyze complex structured, low entropy, ocular fundus images, characterized by iterative tuning of the adaptive model’s solver modules. This algorithm will assist in synthesizing models of NNs that meet the predetermined characteristics of the classification quality. The relevance of automating the process of ocular diagnostics of fundus pathologies is due to the need to develop domestic medical decision-making systems. Because of using the developed algorithm, the NN structure is synthesized, which will include two solver modules, and is intended to classify the dual-alternative information. Automated hybrid NN structures for intelligent segmentation of complex structured, low entropy, retinal images should provide increased efficiency of ocular diagnostics of fundus pathologies, reduce the burden on specialists, and decrease the negative impact of the human factor in diagnosis.

A Dedicated Low-Cost Fluorescence Microfluidic Device Reader for Point-of-Care Ocular Diagnostics

Microfluidic fluorescence assay devices show great promise as preclinical and clinical diagnostic instruments. Normally, fluorescence signals from microfluidic chips are quantified by analysis of images obtained with a commercial fluorescence microscope. This method is unnecessarily expensive, time consuming, and requires significant operator training, particularly when considering future clinical translation of the technology. In this work, we developed a dedicated low cost fluorescence microfluidic device reader (FMDR) to read sandwich immunofluorescence assay (sIFA) devices configured to detect vascular endothelial growth factor ligand concentrations in ocular fluid samples. Using a series of sIFA calibration standards and a limited set of human ocular fluid samples, we demonstrated that our FMDR reader has similar sensitivity and accuracy to a fluorescence microscope for this task, with significantly lower total cost and reduced reading time. We anticipate that the reader could be used with minor modifications for virtually any fluorescence microfluidic device.