From Surface to Viscera: 3D Estimation of Internal Anatomy from Body Surface Point Clouds

Salih Furkan Atici, Eytan Kats, Daniel Mensing, Mattias P Heinrich
Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, PMLR 315:2666-2681, 2026.

Abstract

Accurate pre-scan positioning in diagnostic imaging is essential for guiding acquisition and reducing manual calibration time, yet current automated approaches typically rely on dense volumetric representations that are not leveraging the geometric properties or sparsity of surface representations. In this work, we introduce a sparse, point-cloud–based framework for estimating patient-specific 3D locations and shapes of multiple internal organs directly from the body surface. Our method leverages a new dual-encoder PointTransformer architecture: one encoder processes a mean-shape point cloud comprising 20 anatomical structures, while a second encoder extracts features from the patient’s body-surface point cloud. A shared decoder then predicts a deformed shape estimating the hidden individual anatomy patient. This enables accurate organ localization without volumetric rasterization or autoencoder-style bottlenecks. Trained on the German National Cohort (NAKO) dataset, our model substantially outperforms volumetric convolutional autoencoder (CAE) baselines, achieving a mean Chamfer Distance less than 5 mm and markedly lower surface-distance errors. These results demonstrate that sparse geometric learning with deformable point-cloud priors offers an efficient and highly effective alternative improving over dense convolutional deep learning methods for automated imaging workflow optimization.

Cite this Paper

BibTeX
@InProceedings{pmlr-v315-atici26a, title = {From Surface to Viscera: 3D Estimation of Internal Anatomy from Body Surface Point Clouds}, author = {Atici, Salih Furkan and Kats, Eytan and Mensing, Daniel and Heinrich, Mattias P}, booktitle = {Proceedings of The 9th International Conference on Medical Imaging with Deep Learning}, pages = {2666--2681}, 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/atici26a/atici26a.pdf}, url = {https://proceedings.mlr.press/v315/atici26a.html}, abstract = {Accurate pre-scan positioning in diagnostic imaging is essential for guiding acquisition and reducing manual calibration time, yet current automated approaches typically rely on dense volumetric representations that are not leveraging the geometric properties or sparsity of surface representations. In this work, we introduce a sparse, point-cloud–based framework for estimating patient-specific 3D locations and shapes of multiple internal organs directly from the body surface. Our method leverages a new dual-encoder PointTransformer architecture: one encoder processes a mean-shape point cloud comprising 20 anatomical structures, while a second encoder extracts features from the patient’s body-surface point cloud. A shared decoder then predicts a deformed shape estimating the hidden individual anatomy patient. This enables accurate organ localization without volumetric rasterization or autoencoder-style bottlenecks. Trained on the German National Cohort (NAKO) dataset, our model substantially outperforms volumetric convolutional autoencoder (CAE) baselines, achieving a mean Chamfer Distance less than 5 mm and markedly lower surface-distance errors. These results demonstrate that sparse geometric learning with deformable point-cloud priors offers an efficient and highly effective alternative improving over dense convolutional deep learning methods for automated imaging workflow optimization.} }
Endnote
%0 Conference Paper %T From Surface to Viscera: 3D Estimation of Internal Anatomy from Body Surface Point Clouds %A Salih Furkan Atici %A Eytan Kats %A Daniel Mensing %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-atici26a %I PMLR %P 2666--2681 %U https://proceedings.mlr.press/v315/atici26a.html %V 315 %X Accurate pre-scan positioning in diagnostic imaging is essential for guiding acquisition and reducing manual calibration time, yet current automated approaches typically rely on dense volumetric representations that are not leveraging the geometric properties or sparsity of surface representations. In this work, we introduce a sparse, point-cloud–based framework for estimating patient-specific 3D locations and shapes of multiple internal organs directly from the body surface. Our method leverages a new dual-encoder PointTransformer architecture: one encoder processes a mean-shape point cloud comprising 20 anatomical structures, while a second encoder extracts features from the patient’s body-surface point cloud. A shared decoder then predicts a deformed shape estimating the hidden individual anatomy patient. This enables accurate organ localization without volumetric rasterization or autoencoder-style bottlenecks. Trained on the German National Cohort (NAKO) dataset, our model substantially outperforms volumetric convolutional autoencoder (CAE) baselines, achieving a mean Chamfer Distance less than 5 mm and markedly lower surface-distance errors. These results demonstrate that sparse geometric learning with deformable point-cloud priors offers an efficient and highly effective alternative improving over dense convolutional deep learning methods for automated imaging workflow optimization.
APA
Atici, S.F., Kats, E., Mensing, D. & Heinrich, M.P.. (2026). From Surface to Viscera: 3D Estimation of Internal Anatomy from Body Surface Point Clouds. Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 315:2666-2681 Available from https://proceedings.mlr.press/v315/atici26a.html.

Related Material