Patch-Based and Non-Patch-Based inputs Comparison into Deep Neural Models: Application for the Segmentation of Retinal Diseases on Optical Coherence Tomography Volumes

TL;DR

This study compares patch-based and non-patch-based deep learning inputs for retinal disease segmentation in OCT images, demonstrating that patch-based approaches significantly improve accuracy over full-image methods.

Contribution

It provides a fair comparison of patch-based versus non-patch-based inputs in deep models for retinal disease segmentation, highlighting the superior performance of patch-based methods.

Findings

Patch-based models achieved a DSC of 0.88 for SRF segmentation.

Deep models outperformed human performance with a DSC of 0.71.

Overlapping patches improved model accuracy compared to full-image inputs.

Abstract

Worldwide, sight loss is commonly occurred by retinal diseases, with age-related macular degeneration (AMD) being a notable facet that affects elderly patients. Approaching 170 million persons wide-ranging have been spotted with AMD, a figure anticipated to rise to 288 million by 2040. For visualizing retinal layers, optical coherence tomography (OCT) dispenses the most compelling non-invasive method. Frequent patient visits have increased the demand for automated analysis of retinal diseases, and deep learning networks have shown promising results in both image and pixel-level 2D scan classification. However, when relying solely on 2D data, accuracy may be impaired, especially when localizing fluid volume diseases. The goal of automatic techniques is to outperform humans in manually recognizing illnesses in medical data. In order to further understand the benefit of deep learning models, we studied the effects of the input size. The dice similarity coefficient (DSC) metric showed a human performance score of 0.71 for segmenting various retinal diseases. Yet, the deep models surpassed human performance to establish a new era of advancement of segmenting the diseases on medical images. However, to further improve the performance of the models, overlapping patches enhanced the performance of the deep models compared to feeding the full image. The highest score for a patch-based model in the DSC metric was 0.88 in comparison to the score of 0.71 for the same model in non-patch-based for SRF fluid segmentation. The objective of this article is to show a fair comparison between deep learning models in relation to the input (Patch-Based vs. NonPatch-Based).