Filters








3 Hits in 2.2 sec

PialNN: A Fast Deep Learning Framework for Cortical Pial Surface Reconstruction [article]

Qiang Ma, Emma C. Robinson, Bernhard Kainz, Daniel Rueckert, Amir Alansary
2021 arXiv   pre-print
In this work, we introduce Pial Neural Network (PialNN), a 3D deep learning framework for pial surface reconstruction.  ...  This is fast and memory-efficient, which allows reconstructing a pial surface mesh with 150k vertices in one second.  ...  Conclusion PialNN is a fast and memory-efficient deep learning framework for cortical pial surface reconstruction.  ... 
arXiv:2109.03693v1 fatcat:q4sbwk724ngrlortqmmhkmvjbi

CorticalFlow^++: Boosting Cortical Surface Reconstruction Accuracy, Regularity, and Interoperability [article]

Rodrigo Santa Cruz, Léo Lebrat, Darren Fu, Pierrick Bourgeat, Jurgen Fripp, Clinton Fookes, Olivier Salvado
2022 arXiv   pre-print
Recently, supervised deep learning approaches have been introduced to speed up this task cutting down the reconstruction time from hours to seconds.  ...  Last, we recast pial surface prediction as the deformation of the predicted white surface leading to a one-to-one mapping between white and pial surface vertices.  ...  Similarly, PialNN [17] also learns a deformable model but focuses only on pial surface reconstruction, receiving as input the white matter surface generated with traditional methods.  ... 
arXiv:2206.06598v1 fatcat:2lkklx27uza2rcmien5yhlfp4y

CortexODE: Learning Cortical Surface Reconstruction by Neural ODEs [article]

Qiang Ma, Liu Li, Emma C. Robinson, Bernhard Kainz, Daniel Rueckert, Amir Alansary
2022 arXiv   pre-print
We present CortexODE, a deep learning framework for cortical surface reconstruction.  ...  CortexODE can be integrated to an automatic learning-based pipeline, which reconstructs cortical surfaces efficiently in less than 5 seconds.  ...  CONCLUSION In this work, we introduce CortexODE, a novel geometric deep learning framework for cortical surface deformation.  ... 
arXiv:2202.08329v2 fatcat:lgmvezhb4ncopobpvmvykdjpz4