Abstract
Transesophageal echocardiography (TEE) plays a pivotal role
in cardiology for diagnostic and interventional procedures. However, us-
ing 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 aug-
ment 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 vari-
ations 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 competi-
tive 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 clo-
sure. Our approach holds promise in providing valuable guidance during
transesophageal ultrasound examinations, contributing to the advance-
ment of skill acquisition for cardiac ultrasound practitioners
in cardiology for diagnostic and interventional procedures. However, us-
ing 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 aug-
ment 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 vari-
ations 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 competi-
tive 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 clo-
sure. Our approach holds promise in providing valuable guidance during
transesophageal ultrasound examinations, contributing to the advance-
ment of skill acquisition for cardiac ultrasound practitioners
| Original language | English |
|---|---|
| Title of host publication | Goal-conditioned reinforcement learning for ultrasound navigation guidance |
| Publisher | Medical Image Computing and Computer Assisted Intervention – MICCAI |
| Publication status | Accepted/In press - 2024 |