Bone-GAN: Generation of virtual bone microstructure of high resolution peripheral quantitative computed tomography.

Autor: Thomsen FSL; National Scientific and Technical Research Council (CONICET), Buenos Aires, Argentina.; Department of Radiology, Neuroradiology and Nuclear Medicine, Johannes Wesling University Hospital, Ruhr University Bochum, Bochum, Germany.; Department of Electrical and Computer Engineering, Institute for Computer Science and Engineering, National University of the South (DIEC-ICIC-UNS), Bahía Blanca, Argentina., Iarussi E; National Scientific and Technical Research Council (CONICET), Buenos Aires, Argentina.; Laboratory of Artificial Intelligence, University Torcuato Di Tella, Buenos Aires, Argentina., Borggrefe J; Department of Radiology, Neuroradiology and Nuclear Medicine, Johannes Wesling University Hospital, Ruhr University Bochum, Bochum, Germany., Boyd SK; McCaig Institute for Bone and Joint Health, University of Calgary, Canada., Wang Y; Spine lab, Department of Orthopedic Surgery, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China., Battié MC; Common Spinal Disorders Research Group, Faculty of Rehabilitation Medicine, University of Alberta, Edmonton, Canada.
Jazyk: angličtina
Zdroj: Medical physics [Med Phys] 2023 Nov; Vol. 50 (11), pp. 6943-6954. Date of Electronic Publication: 2023 Jun 01.
DOI: 10.1002/mp.16482
Abstrakt: Background: Data-driven development of medical biomarkers of bone requires a large amount of image data but physical measurements are generally too restricted in size and quality to perform a robust training.
Purpose: This study aims to provide a reliable in silico method for the generation of realistic bone microstructure with defined microarchitectural properties. Synthetic bone samples may improve training of neural networks and serve for the development of new diagnostic parameters of bone architecture and mineralization.
Methods: One hundred-fifty cadaveric lumbar vertebrae from 48 different male human spines were scanned with a high resolution peripheral quantitative CT. After prepocessing the scans, we extracted 10,795 purely spongeous bone patches, each with a side length of 32 voxels (5 mm) and isotropic voxel size of 164 μm. We trained a volumetric generative adversarial network (GAN) in a progressive manner to create synthetic microstructural bone samples. We then added a style transfer technique to allow the generation of synthetic samples with defined microstructure and gestalt by simultaneously optimizing two entangled loss functions. Reliability testing was performed by comparing real and synthetic bone samples on 10 well-understood microstructural parameters.
Results: The method was able to create synthetic bone samples with visual and quantitative properties that effectively matched with the real samples. The GAN contained a well-formed latent space allowing to smoothly morph bone samples by their microstructural parameters, visual appearance or both. Optimum performance has been obtained for bone samples with voxel size 32 × 32 × 32, but also samples of size 64 × 64 × 64 could be synthesized.
Conclusions: Our two-step-approach combines a parameter-agnostic GAN with a parameter-specific style transfer technique. It allows to generate an unlimited anonymous database of microstructural bone samples with sufficient realism to be used for the development of new data-driven methods of bone-biomarkers. Particularly, the style transfer technique can generate datasets of bone samples with specific conditions to simulate certain bone pathologies.
(© 2023 The Authors. Medical Physics published by Wiley Periodicals LLC on behalf of American Association of Physicists in Medicine.)
Databáze: MEDLINE
Externí odkaz: