Towards automatic initialization of registration algorithms using simulated endoscopy images

TL;DR

This paper proposes a neural network-based method to automatically initialize registration algorithms in endoscopic procedures by predicting the endoscope's location relative to preoperative images using simulated scenes, aiming to streamline clinical workflows.

Contribution

The study introduces a novel approach using simulated endoscopy scenes and neural networks for automatic coarse alignment, reducing manual intervention in image registration.

Findings

Achieved 76.53% accuracy in predicting endoscope location.

Demonstrated feasibility of using simulated data for training neural networks in medical image registration.

Identified potential for improving automatic initialization in clinical workflows.

Abstract

Registering images from different modalities is an active area of research in computer aided medical interventions. Several registration algorithms have been developed, many of which achieve high accuracy. However, these results are dependent on many factors, including the quality of the extracted features or segmentations being registered as well as the initial alignment. Although several methods have been developed towards improving segmentation algorithms and automating the segmentation process, few automatic initialization algorithms have been explored. In many cases, the initial alignment from which a registration is initiated is performed manually, which interferes with the clinical workflow. Our aim is to use scene classification in endoscopic procedures to achieve coarse alignment of the endoscope and a preoperative image of the anatomy. In this paper, we show using simulated scenes that a neural network can predict the region of anatomy (with respect to a preoperative image) that the endoscope is located in by observing a single endoscopic video frame. With limited training and without any hyperparameter tuning, our method achieves an accuracy of 76.53 (+/-1.19)%. There are several avenues for improvement, making this a promising direction of research. Code is available at https://github.com/AyushiSinha/AutoInitialization.