Cardiac Computed Tomography Angiography Plane Prediction and Comprehensive LV Segmentation

Davis Marc Vigneault, Ashish Manohar, Abraham Hernandez, Krista Tin Chi Wong, Fanwei Kong, Tea Gegenava, Koen Nieman, Dominik Fleischmann
Proceedings of The 8th International Conference on Medical Imaging with Deep Learning, PMLR 301:1638-1652, 2026.

Abstract

The use of cardiac computed tomography angiography (CCTA) has dramatically increased over the past decade, with an increasingly recognized role for functional assessment; however, reformatting these datasets into standard cardiac planes and performing quantitativeanalysis remains time consuming and disruptive to clinical workflows. Here, we propose a fully automated, volumetric, end-to-end trained network for simultaneous detection of standard cardiac planes and comprehensive left ventricular (LV) segmentation in the predicted short axis coordinate system. The architecture consists of a coarse segmentation module, a transformation module, and a fine segmentation module. The coarse segmentation module provides an initial segmentation of the full field of view (FOV) axial images at low resolution. The transformation module predicts the rotations corresponding to the standard cardiac planes (short axis, SAX; two chamber, 2CH; three chamber, 3CH; and four chamber, 4CH) and reformats the source volume into the predicted SAX coordinate system at high resolution. Finally, the fine segmentation module segments the narrow FOV, high resolution SAX volume. The dataset consisted of 313 CCTA studies partitioned into training, validation, and testing in an 80:10:10 split. Architectural decisions are justified using ablation experiments. On the test set, the proposed architecture achieved accurate plane predictions (mean angle errors of $9.1\pm6.2^\circ$, $9.5\pm5.4^\circ$, $9.0\pm5.9^\circ$, and $8.8\pm5.9^\circ$ for the SAX, 2CH, 3CH, and 4CH planes, respectively) and high quality segmentations (Dice scores of $0.955\pm0.008$, $0.928\pm0.016$, and $0.808\pm0.029$ for the bloodpool, myocardium, and trabeculations, respectively). This fully automated pipeline has the potential to replace current manual workflows, expediting the availability of standard cardiac planes and quantitative analysis for clinical interpretation.

Cite this Paper

BibTeX
@InProceedings{pmlr-v301-vigneault26a, title = {Cardiac Computed Tomography Angiography Plane Prediction and Comprehensive LV Segmentation}, author = {Vigneault, Davis Marc and Manohar, Ashish and Hernandez, Abraham and Wong, Krista Tin Chi and Kong, Fanwei and Gegenava, Tea and Nieman, Koen and Fleischmann, Dominik}, booktitle = {Proceedings of The 8th International Conference on Medical Imaging with Deep Learning}, pages = {1638--1652}, 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/vigneault26a/vigneault26a.pdf}, url = {https://proceedings.mlr.press/v301/vigneault26a.html}, abstract = {The use of cardiac computed tomography angiography (CCTA) has dramatically increased over the past decade, with an increasingly recognized role for functional assessment; however, reformatting these datasets into standard cardiac planes and performing quantitativeanalysis remains time consuming and disruptive to clinical workflows. Here, we propose a fully automated, volumetric, end-to-end trained network for simultaneous detection of standard cardiac planes and comprehensive left ventricular (LV) segmentation in the predicted short axis coordinate system. The architecture consists of a coarse segmentation module, a transformation module, and a fine segmentation module. The coarse segmentation module provides an initial segmentation of the full field of view (FOV) axial images at low resolution. The transformation module predicts the rotations corresponding to the standard cardiac planes (short axis, SAX; two chamber, 2CH; three chamber, 3CH; and four chamber, 4CH) and reformats the source volume into the predicted SAX coordinate system at high resolution. Finally, the fine segmentation module segments the narrow FOV, high resolution SAX volume. The dataset consisted of 313 CCTA studies partitioned into training, validation, and testing in an 80:10:10 split. Architectural decisions are justified using ablation experiments. On the test set, the proposed architecture achieved accurate plane predictions (mean angle errors of $9.1\pm6.2^\circ$, $9.5\pm5.4^\circ$, $9.0\pm5.9^\circ$, and $8.8\pm5.9^\circ$ for the SAX, 2CH, 3CH, and 4CH planes, respectively) and high quality segmentations (Dice scores of $0.955\pm0.008$, $0.928\pm0.016$, and $0.808\pm0.029$ for the bloodpool, myocardium, and trabeculations, respectively). This fully automated pipeline has the potential to replace current manual workflows, expediting the availability of standard cardiac planes and quantitative analysis for clinical interpretation.} }
Endnote
%0 Conference Paper %T Cardiac Computed Tomography Angiography Plane Prediction and Comprehensive LV Segmentation %A Davis Marc Vigneault %A Ashish Manohar %A Abraham Hernandez %A Krista Tin Chi Wong %A Fanwei Kong %A Tea Gegenava %A Koen Nieman %A Dominik Fleischmann %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-vigneault26a %I PMLR %P 1638--1652 %U https://proceedings.mlr.press/v301/vigneault26a.html %V 301 %X The use of cardiac computed tomography angiography (CCTA) has dramatically increased over the past decade, with an increasingly recognized role for functional assessment; however, reformatting these datasets into standard cardiac planes and performing quantitativeanalysis remains time consuming and disruptive to clinical workflows. Here, we propose a fully automated, volumetric, end-to-end trained network for simultaneous detection of standard cardiac planes and comprehensive left ventricular (LV) segmentation in the predicted short axis coordinate system. The architecture consists of a coarse segmentation module, a transformation module, and a fine segmentation module. The coarse segmentation module provides an initial segmentation of the full field of view (FOV) axial images at low resolution. The transformation module predicts the rotations corresponding to the standard cardiac planes (short axis, SAX; two chamber, 2CH; three chamber, 3CH; and four chamber, 4CH) and reformats the source volume into the predicted SAX coordinate system at high resolution. Finally, the fine segmentation module segments the narrow FOV, high resolution SAX volume. The dataset consisted of 313 CCTA studies partitioned into training, validation, and testing in an 80:10:10 split. Architectural decisions are justified using ablation experiments. On the test set, the proposed architecture achieved accurate plane predictions (mean angle errors of $9.1\pm6.2^\circ$, $9.5\pm5.4^\circ$, $9.0\pm5.9^\circ$, and $8.8\pm5.9^\circ$ for the SAX, 2CH, 3CH, and 4CH planes, respectively) and high quality segmentations (Dice scores of $0.955\pm0.008$, $0.928\pm0.016$, and $0.808\pm0.029$ for the bloodpool, myocardium, and trabeculations, respectively). This fully automated pipeline has the potential to replace current manual workflows, expediting the availability of standard cardiac planes and quantitative analysis for clinical interpretation.
APA
Vigneault, D.M., Manohar, A., Hernandez, A., Wong, K.T.C., Kong, F., Gegenava, T., Nieman, K. & Fleischmann, D.. (2026). Cardiac Computed Tomography Angiography Plane Prediction and Comprehensive LV Segmentation. Proceedings of The 8th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 301:1638-1652 Available from https://proceedings.mlr.press/v301/vigneault26a.html.

Related Material