H-Net: A Multitask Architecture for Simultaneous 3D Force Estimation and Stereo Semantic Segmentation in Intracardiac Catheters

TL;DR

This paper introduces H-Net, a lightweight multitask neural network that simultaneously performs 3D force estimation and stereo semantic segmentation of intracardiac catheters from biplane X-ray images, advancing real-time catheter navigation.

Contribution

It presents the first integrated architecture capable of concurrent catheter segmentation from two views and 3D force estimation, optimized for limited computational resources.

Findings

Achieved state-of-the-art performance in segmentation accuracy.

Demonstrated precise 3D force estimation from stereo images.

Validated effectiveness on intracardiac catheter datasets.

Abstract

The success rate of catheterization procedures is closely linked to the sensory data provided to the surgeon. Vision-based deep learning models can deliver both tactile and visual information in a sensor-free manner, while also being cost-effective to produce. Given the complexity of these models for devices with limited computational resources, research has focused on force estimation and catheter segmentation separately. However, there is a lack of a comprehensive architecture capable of simultaneously segmenting the catheter from two different angles and estimating the applied forces in 3D. To bridge this gap, this work proposes a novel, lightweight, multi-input, multi-output encoder-decoder-based architecture. It is designed to segment the catheter from two points of view and concurrently measure the applied forces in the x, y, and z directions. This network processes two simultaneous X-Ray images, intended to be fed by a biplane fluoroscopy system, showing a catheter's deflection from different angles. It uses two parallel sub-networks with shared parameters to output two segmentation maps corresponding to the inputs. Additionally, it leverages stereo vision to estimate the applied forces at the catheter's tip in 3D. The architecture features two input channels, two classification heads for segmentation, and a regression head for force estimation through a single end-to-end architecture. The output of all heads was assessed and compared with the literature, demonstrating state-of-the-art performance in both segmentation and force estimation. To the best of the authors' knowledge, this is the first time such a model has been proposed