CyclePhase: Robust phase detection in cardiovascular imaging through cyclic motion estimation

Soufiane Ben Haddou, Rudolf L. M. van Herten, Connie R. Bezzina, R. Nils Planken, Joost Daemen, Jolanda J. Wentzel, José P. Henriques, Ivana Išgum
Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, PMLR 315:1821-1839, 2026.

Abstract

Accurate cardiac phase detection is essential for cardiovascular imaging applications requiring temporally aligned measurements. While existing methods treat phase detection as discrete frame classification, we propose a fundamentally different approach that models cardiac phase as a continuous cyclic variable on the unit circle. Our method introduces gradient-based input transformations to isolate motion from static anatomy, thereby making it robust to appearance variations, such as calcifications, in intravascular ultrasound (IVUS). Through multi-objective optimization combining temporal consistency via Earth mover’s distance with continuous phase regression, we achieve superior performance across both IVUS and cardiac MRI. Experiments demonstrate that explicitly modelling cardiac periodicity yields more accurate and temporally coherent phase detection compared to classification-based approaches, with particular improvements in artefact-heavy clinical scenarios. Our unified framework eliminates the need for modality-specific preprocessing or segmentation masks, providing an end-to-end solution for cardiac motion characterization.

Cite this Paper

BibTeX
@InProceedings{pmlr-v315-ben-haddou26a, title = {CyclePhase: Robust phase detection in cardiovascular imaging through cyclic motion estimation}, author = {Ben Haddou, Soufiane and van Herten, Rudolf L. M. and Bezzina, Connie R. and Planken, R. Nils and Daemen, Joost and Wentzel, Jolanda J. and Henriques, Jos{\'e} P. and I{\v{s}}gum, Ivana}, booktitle = {Proceedings of The 9th International Conference on Medical Imaging with Deep Learning}, pages = {1821--1839}, year = {2026}, editor = {Huo, Yuankai and Gao, Mingchen and Kuo, Chang-Fu and Jin, Yueming and Deng, Ruining}, volume = {315}, series = {Proceedings of Machine Learning Research}, month = {08--10 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v315/main/assets/ben-haddou26a/ben-haddou26a.pdf}, url = {https://proceedings.mlr.press/v315/ben-haddou26a.html}, abstract = {Accurate cardiac phase detection is essential for cardiovascular imaging applications requiring temporally aligned measurements. While existing methods treat phase detection as discrete frame classification, we propose a fundamentally different approach that models cardiac phase as a continuous cyclic variable on the unit circle. Our method introduces gradient-based input transformations to isolate motion from static anatomy, thereby making it robust to appearance variations, such as calcifications, in intravascular ultrasound (IVUS). Through multi-objective optimization combining temporal consistency via Earth mover’s distance with continuous phase regression, we achieve superior performance across both IVUS and cardiac MRI. Experiments demonstrate that explicitly modelling cardiac periodicity yields more accurate and temporally coherent phase detection compared to classification-based approaches, with particular improvements in artefact-heavy clinical scenarios. Our unified framework eliminates the need for modality-specific preprocessing or segmentation masks, providing an end-to-end solution for cardiac motion characterization.} }
Endnote
%0 Conference Paper %T CyclePhase: Robust phase detection in cardiovascular imaging through cyclic motion estimation %A Soufiane Ben Haddou %A Rudolf L. M. van Herten %A Connie R. Bezzina %A R. Nils Planken %A Joost Daemen %A Jolanda J. Wentzel %A José P. Henriques %A Ivana Išgum %B Proceedings of The 9th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2026 %E Yuankai Huo %E Mingchen Gao %E Chang-Fu Kuo %E Yueming Jin %E Ruining Deng %F pmlr-v315-ben-haddou26a %I PMLR %P 1821--1839 %U https://proceedings.mlr.press/v315/ben-haddou26a.html %V 315 %X Accurate cardiac phase detection is essential for cardiovascular imaging applications requiring temporally aligned measurements. While existing methods treat phase detection as discrete frame classification, we propose a fundamentally different approach that models cardiac phase as a continuous cyclic variable on the unit circle. Our method introduces gradient-based input transformations to isolate motion from static anatomy, thereby making it robust to appearance variations, such as calcifications, in intravascular ultrasound (IVUS). Through multi-objective optimization combining temporal consistency via Earth mover’s distance with continuous phase regression, we achieve superior performance across both IVUS and cardiac MRI. Experiments demonstrate that explicitly modelling cardiac periodicity yields more accurate and temporally coherent phase detection compared to classification-based approaches, with particular improvements in artefact-heavy clinical scenarios. Our unified framework eliminates the need for modality-specific preprocessing or segmentation masks, providing an end-to-end solution for cardiac motion characterization.
APA
Ben Haddou, S., van Herten, R.L.M., Bezzina, C.R., Planken, R.N., Daemen, J., Wentzel, J.J., Henriques, J.P. & Išgum, I.. (2026). CyclePhase: Robust phase detection in cardiovascular imaging through cyclic motion estimation. Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 315:1821-1839 Available from https://proceedings.mlr.press/v315/ben-haddou26a.html.

Related Material