Vision-Based Neurosurgical Guidance: Unsupervised Localization and Camera-Pose Prediction

TL;DR

This paper introduces an unsupervised deep learning approach for endoscopic surgical guidance that recognizes anatomy and predicts camera pose, aiding navigation without requiring extensive labeled data.

Contribution

It presents a novel anatomy recognition method that constructs a surgical path from videos and estimates viewing angles, enabling guidance during endoscopic procedures.

Findings

Effective on real surgical videos and synthetic data

Provides accurate localization and camera-pose estimation

Offers an online tool for researchers to use and extend

Abstract

Localizing oneself during endoscopic procedures can be problematic due to the lack of distinguishable textures and landmarks, as well as difficulties due to the endoscopic device such as a limited field of view and challenging lighting conditions. Expert knowledge shaped by years of experience is required for localization within the human body during endoscopic procedures. In this work, we present a deep learning method based on anatomy recognition, that constructs a surgical path in an unsupervised manner from surgical videos, modelling relative location and variations due to different viewing angles. At inference time, the model can map an unseen video's frames on the path and estimate the viewing angle, aiming to provide guidance, for instance, to reach a particular destination. We test the method on a dataset consisting of surgical videos of transsphenoidal adenomectomies, as well as on a synthetic dataset. An online tool that lets researchers upload their surgical videos to obtain anatomy detections and the weights of the trained YOLOv7 model are available at: https://surgicalvision.bmic.ethz.ch.