3D Semantic Mapping from Arthroscopy using Out-of-distribution Pose and Depth and In-distribution Segmentation Training

TL;DR

This paper presents a novel 3D semantic mapping system for knee arthroscopy that integrates out-of-distribution pose and depth estimation with in-distribution segmentation, enabling automatic intraoperative 3D mapping.

Contribution

It introduces the first system combining out-of-distribution pose and depth estimation with in-distribution segmentation for 3D mapping in arthroscopy.

Findings

Successfully trained depth and pose estimators using out-of-distribution data.

Achieved accurate semantic segmentation of knee structures.

Generated 3D semantic maps from arthroscopic images.

Abstract

Minimally invasive surgery (MIS) has many documented advantages, but the surgeon's limited visual contact with the scene can be problematic. Hence, systems that can help surgeons navigate, such as a method that can produce a 3D semantic map, can compensate for the limitation above. In theory, we can borrow 3D semantic mapping techniques developed for robotics, but this requires finding solutions to the following challenges in MIS: 1) semantic segmentation, 2) depth estimation, and 3) pose estimation. In this paper, we propose the first 3D semantic mapping system from knee arthroscopy that solves the three challenges above. Using out-of-distribution non-human datasets, where pose could be labeled, we jointly train depth+pose estimators using selfsupervised and supervised losses. Using an in-distribution human knee dataset, we train a fully-supervised semantic segmentation system to label arthroscopic image pixels into femur, ACL, and meniscus. Taking testing images from human knees, we combine the results from these two systems to automatically create 3D semantic maps of the human knee. The result of this work opens the pathway to the generation of intraoperative 3D semantic mapping, registration with pre-operative data, and robotic-assisted arthroscopy