FERN: A Fetal Echocardiography Registration Network for 2D-to-3D Alignment

Paula Ramirez Gilliland, David F A Lloyd, Jacqueline Matthew, Reza Razavi, Milou PM van Poppel, Andrew P. King, Maria Deprez
Proceedings of The 8th International Conference on Medical Imaging with Deep Learning, PMLR 301:494-514, 2026.

Abstract

2D Freehand echocardiography remains the primary imaging modality for routine fetal cardiac care, essential in the antenatal detection of Congenital Heart Disease (CHD). However, there is a lack of spatial context which requires 3D imaging. Current 3D methods, such as Spatio-Temporal Image Correlation (STIC), face limitations in success rate, image quality, and ease of use, and come at the cost of lower spatial and temporal resolution compared to 2D acquisitions. This work studies the feasibility of aligning real high spatial and temporal resolution 2D fetal echocardiography into a reference 3D space defined by lower resolution 3D STIC. FERN, a $\textbf{F}$etal $\textbf{E}$chocardiography $\textbf{R}$egistration $\textbf{N}$etwork, employs transformers for standard fetal echocardiography view alignment. The network is trained on simulated 2D slices derived from 3D volumes at end-diastole, and validated on real 2D acquisitions from fetuses with Coarctation of the Aorta and Right Aortic Arch diagnoses, achieving a mean Euclidean distance of 2.98 $\pm$ 1.27 mm on cardiac region-of-interest points between predicted and manually selected planes. Compared to manually aligned planes, improved image similarity to an average atlas is achieved, confirmed by blinded best plane selection. This work demonstrates that high spatial and temporal resolution 2D fetal echocardiography can be integrated into a 3D context provided by lower-resolution 3D acquisitions or fetal cardiac atlases, potentially resulting in a new 3D visualization tool for enhanced CHD diagnosis.

Cite this Paper

BibTeX
@InProceedings{pmlr-v301-gilliland26a, title = {FERN: A Fetal Echocardiography Registration Network for 2D-to-3D Alignment}, author = {Gilliland, Paula Ramirez and Lloyd, David F A and Matthew, Jacqueline and Razavi, Reza and van Poppel, Milou PM and King, Andrew P. and Deprez, Maria}, booktitle = {Proceedings of The 8th International Conference on Medical Imaging with Deep Learning}, pages = {494--514}, year = {2026}, editor = {Tasdizen, Tolga and Elhabian, Shireen and Summers, Ronald and Chen, Chen and Koch, Lisa and Zhuang, Yan}, volume = {301}, series = {Proceedings of Machine Learning Research}, month = {09--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v301/main/assets/gilliland26a/gilliland26a.pdf}, url = {https://proceedings.mlr.press/v301/gilliland26a.html}, abstract = {2D Freehand echocardiography remains the primary imaging modality for routine fetal cardiac care, essential in the antenatal detection of Congenital Heart Disease (CHD). However, there is a lack of spatial context which requires 3D imaging. Current 3D methods, such as Spatio-Temporal Image Correlation (STIC), face limitations in success rate, image quality, and ease of use, and come at the cost of lower spatial and temporal resolution compared to 2D acquisitions. This work studies the feasibility of aligning real high spatial and temporal resolution 2D fetal echocardiography into a reference 3D space defined by lower resolution 3D STIC. FERN, a $\textbf{F}$etal $\textbf{E}$chocardiography $\textbf{R}$egistration $\textbf{N}$etwork, employs transformers for standard fetal echocardiography view alignment. The network is trained on simulated 2D slices derived from 3D volumes at end-diastole, and validated on real 2D acquisitions from fetuses with Coarctation of the Aorta and Right Aortic Arch diagnoses, achieving a mean Euclidean distance of 2.98 $\pm$ 1.27 mm on cardiac region-of-interest points between predicted and manually selected planes. Compared to manually aligned planes, improved image similarity to an average atlas is achieved, confirmed by blinded best plane selection. This work demonstrates that high spatial and temporal resolution 2D fetal echocardiography can be integrated into a 3D context provided by lower-resolution 3D acquisitions or fetal cardiac atlases, potentially resulting in a new 3D visualization tool for enhanced CHD diagnosis.} }
Endnote
%0 Conference Paper %T FERN: A Fetal Echocardiography Registration Network for 2D-to-3D Alignment %A Paula Ramirez Gilliland %A David F A Lloyd %A Jacqueline Matthew %A Reza Razavi %A Milou PM van Poppel %A Andrew P. King %A Maria Deprez %B Proceedings of The 8th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2026 %E Tolga Tasdizen %E Shireen Elhabian %E Ronald Summers %E Chen Chen %E Lisa Koch %E Yan Zhuang %F pmlr-v301-gilliland26a %I PMLR %P 494--514 %U https://proceedings.mlr.press/v301/gilliland26a.html %V 301 %X 2D Freehand echocardiography remains the primary imaging modality for routine fetal cardiac care, essential in the antenatal detection of Congenital Heart Disease (CHD). However, there is a lack of spatial context which requires 3D imaging. Current 3D methods, such as Spatio-Temporal Image Correlation (STIC), face limitations in success rate, image quality, and ease of use, and come at the cost of lower spatial and temporal resolution compared to 2D acquisitions. This work studies the feasibility of aligning real high spatial and temporal resolution 2D fetal echocardiography into a reference 3D space defined by lower resolution 3D STIC. FERN, a $\textbf{F}$etal $\textbf{E}$chocardiography $\textbf{R}$egistration $\textbf{N}$etwork, employs transformers for standard fetal echocardiography view alignment. The network is trained on simulated 2D slices derived from 3D volumes at end-diastole, and validated on real 2D acquisitions from fetuses with Coarctation of the Aorta and Right Aortic Arch diagnoses, achieving a mean Euclidean distance of 2.98 $\pm$ 1.27 mm on cardiac region-of-interest points between predicted and manually selected planes. Compared to manually aligned planes, improved image similarity to an average atlas is achieved, confirmed by blinded best plane selection. This work demonstrates that high spatial and temporal resolution 2D fetal echocardiography can be integrated into a 3D context provided by lower-resolution 3D acquisitions or fetal cardiac atlases, potentially resulting in a new 3D visualization tool for enhanced CHD diagnosis.
APA
Gilliland, P.R., Lloyd, D.F.A., Matthew, J., Razavi, R., van Poppel, M.P., King, A.P. & Deprez, M.. (2026). FERN: A Fetal Echocardiography Registration Network for 2D-to-3D Alignment. Proceedings of The 8th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 301:494-514 Available from https://proceedings.mlr.press/v301/gilliland26a.html.

Related Material