Goal-conditioned reinforcement learning for ultrasound navigation guidance

TL;DR

This paper introduces a goal-conditioned reinforcement learning framework with contrastive learning enhancements to assist novice sonographers in ultrasound navigation, improving accuracy and generalization across patient variations.

Contribution

It presents a novel contrastive patient batching method and data-augmented contrastive loss for ultrasound navigation, enabling a single model to handle multiple views with improved generalization.

Findings

Achieved an average position error of 6.56 mm and angle error of 9.36 degrees.

Demonstrated effective navigation to complex interventional views like LAA.

Outperformed models trained on individual views in accuracy and generalization.

Abstract

Transesophageal echocardiography (TEE) plays a pivotal role in cardiology for diagnostic and interventional procedures. However, using it effectively requires extensive training due to the intricate nature of image acquisition and interpretation. To enhance the efficiency of novice sonographers and reduce variability in scan acquisitions, we propose a novel ultrasound (US) navigation assistance method based on contrastive learning as goal-conditioned reinforcement learning (GCRL). We augment the previous framework using a novel contrastive patient batching method (CPB) and a data-augmented contrastive loss, both of which we demonstrate are essential to ensure generalization to anatomical variations across patients. The proposed framework enables navigation to both standard diagnostic as well as intricate interventional views with a single model. Our method was developed with a large dataset of 789 patients and obtained an average error of 6.56 mm in position and 9.36 degrees in angle on a testing dataset of 140 patients, which is competitive or superior to models trained on individual views. Furthermore, we quantitatively validate our method's ability to navigate to interventional views such as the Left Atrial Appendage (LAA) view used in LAA closure. Our approach holds promise in providing valuable guidance during transesophageal ultrasound examinations, contributing to the advancement of skill acquisition for cardiac ultrasound practitioners.