Deep learning based high-resolution reconstruction of trabecular bone microstructures from low-resolution CT scans using GAN-CIRCLE

Abstract

Osteoporosis is a common age-related disease characterized by reduced bone density and increased fracture-risk. Microstructural quality of trabecular bone (Tb), commonly found at axial skeletal sites and at the end of long bones, is an important determinant of bone-strength and fracture-risk. High-resolution emerging CT scanners enable in vivo measurement of Tb microstructures at peripheral sites. However, resolution-dependence of microstructural measures and wide resolution-discrepancies among various CT scanners together with rapid upgrades in technology warrant data harmonization in CT-based cross-sectional and longitudinal bone studies. This paper presents a deep learning-based method for high-resolution reconstruction of Tb microstructures from low-resolution CT scans using GAN-CIRCLE. A network was developed and evaluated using post-registered ankle CT scans of nineteen volunteers on both low-and highresolution CT scanners. 9,000 matching pairs of low-and high-resolution patches of size 64×64 were randomly harvested from ten volunteers for training and validation. Another 5,000 matching pairs of patches from nine other volunteers were used for evaluation. Quantitative comparison shows that predicted high-resolution scans have significantly improved structural similarity index (p < 0.01) with true high-resolution scans as compared to the same metric for low-resolution data. Different Tb microstructural measures such as thickness, spacing, and network area density are also computed from low-and predicted high-resolution images, and compared with the values derived from true high-resolution scans. Thickness and network area measures from predicted

A Review of Experimentally Informed Micromechanical Modeling of Nanoporous Metals: From Structural Descriptors to Predictive Structure–Property Relationships

“…One drawback of this thickness computation method lies in the increased computation time needed. Although it is discussed and used in the medicine community [68][69][70], this algorithm is yet to be used by research groups in the community of nanoporous metals.…”

Making Radiomics More Reproducible across Scanner and Imaging Protocol Variations: A Review of Harmonization Methods

“…ML-based techniques have emerged to provide effective solutions to translate images across various domains by harmonizing images as opposed to radiomic features alone. Examples include ML-based adaptive dictionary learning [ 61 ] and DL methods like using GANs [ 62 , 63 , 64 , 65 , 66 , 67 , 68 , 69 , 70 ]. Methods using coefficients of spherical harmonics to harmonize diffusion MRI have been explored [ 61 , 71 , 72 , 73 ].…”

“…Guha et al [ 63 ] conducted a study that transforms low-resolution (LR) CT scans of trabecular (Tb) bone microstructures into high-resolution (HR) CT scans, obtained from two scanners (LR from Siemens FLASH and HR from Siemens FORCE; paired images), using GAN-CIRCLE, of which the architecture is shown in Figure 3 . This DL-based method was inspired by You et al [ 80 ] and is monitored by three losses: the identical, residual, and cycle consistency loss.…”

Edge-guided second-order total generalized variation for Gaussian noise removal from depth map

“…As a major noise type in depth map, Gaussian noise has been widely concerned by researchers. Consequently effective denoising methods have appeared, such as, filtering-based methods [1][2][3] , partial differential equation (PDE)-based methods [4][5][6] , sparse representation-based dictionary learning methods [7][8][9][10][11] , deep learning-based methods [12][13][14][15][16][17][18][19][20] , and recent variation minimization-based methods [21][22][23][24] .…”