Continuum finite element analysis generalizes in vivo trabecular bone microstructural strength measures between two CT scanners with different image resolution

Guha, Indranil; Zhang, Xiaoliu; Nadeem, Syed Ahmed; Levy, Steven M.; Saha, Punam K.

doi:10.1088/2057-1976/acbb0a

Cited by 1 publication

(2 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To determine the performance of our methods in data from an elderly population, we evaluated their performance over a VOI resembling the bone microstructural quality similar to elderly people. The elderly VOI selection methods were previously validated 46 . Values of Tb.vBMD, Tb.NA, and Tb.PW measures from true LRCT and HRCT images over elderly VOIs were significantly lower ( p < 0.001) than their values from respective images over normal VOIs at the 4%−6% tibial location.…”

Section: Resultsmentioning

confidence: 99%

“…The elderly VOI selection methods were previously validated. 46 Values of Tb.vBMD, Tb.NA, and Tb.PW measures from true LRCT and HRCT images over elderly VOIs were significantly lower (p < 0.001) than their values from respective images over normal VOIs at the 4%−6% tibial location. On the other hand, values of Tb.Sp and Tb.Th measures from true LRCT and HRCT images over elderly VOIs were signif-F I G U R E 6 Standardized Bland-Altman plots for different Tb measures computed from LRCT, true HRCT, and predicted HRCT images using supervised and unsupervised 3DGAN-CIRCLE methods and the methods by Chaudhari et al 40 and Zhang et al 39 The trend lines through the standardized residual values for LRCT and four predicted HRCT are shown for better visual comparison of residual trends.…”

Section: Dgan-circlementioning

confidence: 99%

See 1 more Smart Citation

Deep learning‐based harmonization of trabecular bone microstructures between high‐ and low‐resolution CT imaging

Guha,

Nadeem,

Zhang

et al. 2024

Medical Physics

Self Cite

View full text Add to dashboard Cite

BackgroundOsteoporosis is a bone disease related to increased bone loss and fracture‐risk. The variability in bone strength is partially explained by bone mineral density (BMD), and the remainder is contributed by bone microstructure. Recently, clinical CT has emerged as a viable option for in vivo bone microstructural imaging. Wide variations in spatial‐resolution and other imaging features among different CT scanners add inconsistency to derived bone microstructural metrics, urging the need for harmonization of image data from different scanners.PurposeThis paper presents a new deep learning (DL) method for the harmonization of bone microstructural images derived from low‐ and high‐resolution CT scanners and evaluates the method's performance at the levels of image data as well as derived microstructural metrics.MethodsWe generalized a three‐dimensional (3D) version of GAN‐CIRCLE that applies two generative adversarial networks (GANs) constrained by the identical, residual, and cycle learning ensemble (CIRCLE). Two GAN modules simultaneously learn to map low‐resolution CT (LRCT) to high‐resolution CT (HRCT) and vice versa. Twenty volunteers were recruited. LRCT and HRCT scans of the distal tibia of their left legs were acquired. Five‐hundred pairs of LRCT and HRCT image blocks of voxels were sampled for each of the twelve volunteers and used for training in supervised as well as unsupervised setups. LRCT and HRCT images of the remaining eight volunteers were used for evaluation. LRCT blocks were sampled at 32 voxel intervals in each coordinate direction and predicted HRCT blocks were stitched to generate a predicted HRCT image.ResultsMean ± standard deviation of structural similarity (SSIM) values between predicted and true HRCT using both 3DGAN‐CIRCLE‐based supervised (0.84 ± 0.03) and unsupervised (0.83 ± 0.04) methods were significantly (p < 0.001) higher than the mean SSIM value between LRCT and true HRCT (0.75 ± 0.03). All Tb measures derived from predicted HRCT by the supervised 3DGAN‐CIRCLE showed higher agreement (CCC [0.956 0.991]) with the reference values from true HRCT as compared to LRCT‐derived values (CCC [0.732 0.989]). For all Tb measures, except Tb plate‐width (CCC = 0.866), the unsupervised 3DGAN‐CIRCLE showed high agreement (CCC [0.920 0.964]) with the true HRCT‐derived reference measures. Moreover, Bland‐Altman plots showed that supervised 3DGAN‐CIRCLE predicted HRCT reduces bias and variability in residual values of different Tb measures as compared to LRCT and unsupervised 3DGAN‐CIRCLE predicted HRCT. The supervised 3DGAN‐CIRCLE method produced significantly improved performance (p < 0.001) for all Tb measures as compared to the two DL‐based supervised methods available in the literature.Conclusions3DGAN‐CIRCLE, trained in either unsupervised or supervised fashion, generates HRCT images with high structural similarity to the reference true HRCT images. The supervised 3DGAN‐CIRCLE improves agreements of computed Tb microstructural measures with their reference values and outperforms the unsupervised 3DGAN‐CIRCLE. 3DGAN‐CIRCLE offers a viable DL solution to retrospectively improve image resolution, which may aid in data harmonization in multi‐site longitudinal studies where scanner mismatch is unavoidable.

show abstract

Section: Resultsmentioning

confidence: 99%