TY - GEN
T1 - 3D Lung Reconstruction from X-Rays
T2 - 23rd IEEE International Symposium on Biomedical Imaging, ISBI 2026
AU - Houmeau, Alice Le Nilias
AU - Cresson, Thierry
AU - De Guise, Jacques
AU - Chartrand-Lefebvre, Carl
AU - Vázquez, Carlos
N1 - Publisher Copyright:
© 2026 IEEE.
PY - 2026
Y1 - 2026
N2 - Deep learning has enabled 3D anatomical reconstruction from 2D radiographs through two main paradigms: image-to-segmentation and image-to-mesh methods. Yet, their relative performance remains poorly understood for the same anatomy. This study compares KVNet, a biplanar segmentation-based network, with the occupancybased model X2V, the state-of-the-art single-view implicit image-to-mesh model for lung reconstruction, on the same dataset of 646 cases. KV-Net achieves higher volumetric and surface accuracy, while X2V produces plausible global shapes with lower computational costs. Beyond whole-organ metrics, a regional analysis highlights distinct challenges across lung zones: occupancy-based models struggle to capture thin lower regions, whereas segmentation networks achieve a twofold reduction in average surface error across all regions. These results provide the first region-aware comparison between image-to-segmentation and image-to-mesh approaches for 3D lung reconstruction from X-rays.
AB - Deep learning has enabled 3D anatomical reconstruction from 2D radiographs through two main paradigms: image-to-segmentation and image-to-mesh methods. Yet, their relative performance remains poorly understood for the same anatomy. This study compares KVNet, a biplanar segmentation-based network, with the occupancybased model X2V, the state-of-the-art single-view implicit image-to-mesh model for lung reconstruction, on the same dataset of 646 cases. KV-Net achieves higher volumetric and surface accuracy, while X2V produces plausible global shapes with lower computational costs. Beyond whole-organ metrics, a regional analysis highlights distinct challenges across lung zones: occupancy-based models struggle to capture thin lower regions, whereas segmentation networks achieve a twofold reduction in average surface error across all regions. These results provide the first region-aware comparison between image-to-segmentation and image-to-mesh approaches for 3D lung reconstruction from X-rays.
KW - 3D reconstruction
KW - explicit segmentation methods
KW - neural implicit methods
KW - organ meshes
KW - voxel
KW - X-ray
UR - https://www.scopus.com/pages/publications/105041632928
U2 - 10.1109/ISBI61048.2026.11516055
DO - 10.1109/ISBI61048.2026.11516055
M3 - Contribution to conference proceedings
AN - SCOPUS:105041632928
T3 - Proceedings - International Symposium on Biomedical Imaging
BT - ISBI 2026 - 23rd IEEE International Symposium on Biomedical Imaging
PB - IEEE Computer Society
Y2 - 8 April 2026 through 11 April 2026
ER -