Analyzing an Imitation Learning Network for Fundus Image Registration Using a Divide-and-Conquer Approach

TL;DR

This paper introduces an interpretable imitation learning network using a divide-and-conquer approach for registering fundus images, significantly improving accuracy and enabling better analysis of the registration process.

Contribution

It presents a novel divide-and-conquer imitation learning framework for fundus image registration that enhances interpretability and reduces registration error.

Findings

Reduces registration error by up to 95%

Improves interpretability of deep learning registration models

Analyzes influence of input and hyperparameters on results

Abstract

Comparison of microvascular circulation on fundoscopic images is a non-invasive clinical indication for the diagnosis and monitoring of diseases, such as diabetes and hypertensions. The differences between intra-patient images can be assessed quantitatively by registering serial acquisitions. Due to the variability of the images (i.e. contrast, luminosity) and the anatomical changes of the retina, the registration of fundus images remains a challenging task. Recently, several deep learning approaches have been proposed to register fundus images in an end-to-end fashion, achieving remarkable results. However, the results are difficult to interpret and analyze. In this work, we propose an imitation learning framework for the registration of 2D color funduscopic images for a wide range of applications such as disease monitoring, image stitching and super-resolution. We follow a divide-and-conquer approach to improve the interpretability of the proposed network, and analyze both the influence of the input image and the hyperparameters on the registration result. The results show that the proposed registration network reduces the initial target registration error up to 95\%.