TY - JOUR
T1 - Automatic Plane Pose Estimation for Cardiac Left Ventricle Coverage Estimation via Deep Adversarial Regression Network
AU - Zhang, Le
AU - Bronik, Kevin
AU - Piechnik, Stefan K.
AU - Lima, Joao A.C.
AU - Neubauer, Stefan
AU - Petersen, Steffen E.
AU - Frangi, Alejandro F.
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2024
Y1 - 2024
N2 - Accurate segmentation of the ventricles plays a crucial role in determining cardiac functional parameters such as ventricular volume, ventricular mass, and ejection fraction. However, poor image quality, such as inadequate coverage of the left ventricle (LV) and right ventricle (RV) in cardiac magnetic resonance (CMR) image sequences, can significantly affect the assessment of cardiac function. This study investigates issues related to missing or corrupted imaging planes, which often lead to incomplete ventricle coverage. To address the challenge of estimating ventricle coverage in CMR images regardless of variations in imaging parameters such as device type, magnetic field strength, and protocol execution, we introduce a novel convolutional neural network (CNN) based on adversarial learning. Additionally, we integrate supplementary information (e.g., cross-view image data) as privileged information to enhance the interpretability of our model's predictions and identify potential biases or inaccuracies. This research represents the first attempt to automatically estimate ventricular coverage by identifying missing slices and plane orientations in CMR images using a dataset-agnostic approach. The effectiveness of the proposed model is demonstrated through the evaluation of datasets from three diverse and sizable image acquisition cohorts, demonstrating superior performance compared to existing methods.
AB - Accurate segmentation of the ventricles plays a crucial role in determining cardiac functional parameters such as ventricular volume, ventricular mass, and ejection fraction. However, poor image quality, such as inadequate coverage of the left ventricle (LV) and right ventricle (RV) in cardiac magnetic resonance (CMR) image sequences, can significantly affect the assessment of cardiac function. This study investigates issues related to missing or corrupted imaging planes, which often lead to incomplete ventricle coverage. To address the challenge of estimating ventricle coverage in CMR images regardless of variations in imaging parameters such as device type, magnetic field strength, and protocol execution, we introduce a novel convolutional neural network (CNN) based on adversarial learning. Additionally, we integrate supplementary information (e.g., cross-view image data) as privileged information to enhance the interpretability of our model's predictions and identify potential biases or inaccuracies. This research represents the first attempt to automatically estimate ventricular coverage by identifying missing slices and plane orientations in CMR images using a dataset-agnostic approach. The effectiveness of the proposed model is demonstrated through the evaluation of datasets from three diverse and sizable image acquisition cohorts, demonstrating superior performance compared to existing methods.
KW - Adversarial learning (AL)
KW - deep learning (DL)
KW - privileged information (PI)
KW - regression network
KW - ventricle pose estimation
UR - http://www.scopus.com/inward/record.url?scp=85192983144&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85192983144&partnerID=8YFLogxK
U2 - 10.1109/TAI.2024.3394798
DO - 10.1109/TAI.2024.3394798
M3 - Article
AN - SCOPUS:85192983144
SN - 2691-4581
VL - 5
SP - 4738
EP - 4752
JO - IEEE Transactions on Artificial Intelligence
JF - IEEE Transactions on Artificial Intelligence
IS - 9
ER -