Evaluation of 3D Ultrasound Reconstruction and 2D/3D Segmentation for Neonatal Hip Dysplasia Screening

Wiebke Heyer, Katharina Ott, Christian Weihsbach, Reza Sorbi, Lisa Lange, Jürgen Lichtenstein, Anna Hell, Sebastian Lippross, Lasse Hansen, Mattias P. Heinrich
Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, PMLR 315:4448-4478, 2026.

Abstract

Early detection of developmental dysplasia of the hip relies heavily on the correct acquisition and interpretation of ultrasound images. Yet, conventional single-plane imaging provides only a limited view of the neonatal hip, is operator-dependent and sensitive to probe orientation. In this study, we present a clinically oriented validation of a dual-sweep 3D ultrasound approach aimed at improving anatomical coverage and simplifying the diagnostic process. Our dataset comprises 50 optically tracked acquisitions and 150 untracked freehand sweeps from newborns, enabling the reconstruction of volumetric representations of the hip from standard handheld 2D ultrasound. We evaluate 2D and 3D nnU-Net–based segmentation models to quantify how volumetric context influences the delineation of key joint structures. Results demonstrate that the combination of 2D slice-based and 3D volumetric segmentation yields the most robust performance, particularly in cases with anatomical variability or suboptimal sweep direction. The study also highlights remaining challenges, including motion artefacts and inconsistent sweep trajectories, that affect reconstruction quality.

Cite this Paper

BibTeX
@InProceedings{pmlr-v315-heyer26a, title = {Evaluation of 3D Ultrasound Reconstruction and 2D/3D Segmentation for Neonatal Hip Dysplasia Screening}, author = {Heyer, Wiebke and Ott, Katharina and Weihsbach, Christian and Sorbi, Reza and Lange, Lisa and Lichtenstein, J\"urgen and Hell, Anna and Lippross, Sebastian and Hansen, Lasse and Heinrich, Mattias P.}, booktitle = {Proceedings of The 9th International Conference on Medical Imaging with Deep Learning}, pages = {4448--4478}, 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/heyer26a/heyer26a.pdf}, url = {https://proceedings.mlr.press/v315/heyer26a.html}, abstract = {Early detection of developmental dysplasia of the hip relies heavily on the correct acquisition and interpretation of ultrasound images. Yet, conventional single-plane imaging provides only a limited view of the neonatal hip, is operator-dependent and sensitive to probe orientation. In this study, we present a clinically oriented validation of a dual-sweep 3D ultrasound approach aimed at improving anatomical coverage and simplifying the diagnostic process. Our dataset comprises 50 optically tracked acquisitions and 150 untracked freehand sweeps from newborns, enabling the reconstruction of volumetric representations of the hip from standard handheld 2D ultrasound. We evaluate 2D and 3D nnU-Net–based segmentation models to quantify how volumetric context influences the delineation of key joint structures. Results demonstrate that the combination of 2D slice-based and 3D volumetric segmentation yields the most robust performance, particularly in cases with anatomical variability or suboptimal sweep direction. The study also highlights remaining challenges, including motion artefacts and inconsistent sweep trajectories, that affect reconstruction quality.} }
Endnote
%0 Conference Paper %T Evaluation of 3D Ultrasound Reconstruction and 2D/3D Segmentation for Neonatal Hip Dysplasia Screening %A Wiebke Heyer %A Katharina Ott %A Christian Weihsbach %A Reza Sorbi %A Lisa Lange %A Jürgen Lichtenstein %A Anna Hell %A Sebastian Lippross %A Lasse Hansen %A Mattias P. Heinrich %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-heyer26a %I PMLR %P 4448--4478 %U https://proceedings.mlr.press/v315/heyer26a.html %V 315 %X Early detection of developmental dysplasia of the hip relies heavily on the correct acquisition and interpretation of ultrasound images. Yet, conventional single-plane imaging provides only a limited view of the neonatal hip, is operator-dependent and sensitive to probe orientation. In this study, we present a clinically oriented validation of a dual-sweep 3D ultrasound approach aimed at improving anatomical coverage and simplifying the diagnostic process. Our dataset comprises 50 optically tracked acquisitions and 150 untracked freehand sweeps from newborns, enabling the reconstruction of volumetric representations of the hip from standard handheld 2D ultrasound. We evaluate 2D and 3D nnU-Net–based segmentation models to quantify how volumetric context influences the delineation of key joint structures. Results demonstrate that the combination of 2D slice-based and 3D volumetric segmentation yields the most robust performance, particularly in cases with anatomical variability or suboptimal sweep direction. The study also highlights remaining challenges, including motion artefacts and inconsistent sweep trajectories, that affect reconstruction quality.
APA
Heyer, W., Ott, K., Weihsbach, C., Sorbi, R., Lange, L., Lichtenstein, J., Hell, A., Lippross, S., Hansen, L. & Heinrich, M.P.. (2026). Evaluation of 3D Ultrasound Reconstruction and 2D/3D Segmentation for Neonatal Hip Dysplasia Screening. Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 315:4448-4478 Available from https://proceedings.mlr.press/v315/heyer26a.html.

Related Material