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

Indranil Guha; Syed Ahmed Nadeem; Xiaoliu Zhang; Paul A DiCamillo; Steven M Levy; Ge Wang; Punam K Saha

doi:10.1002/mp.17003

Back

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

Journal article

Open access

Peer reviewed

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

Indranil Guha, Syed Ahmed Nadeem, Xiaoliu Zhang, Paul A DiCamillo, Steven M Levy, Ge Wang and Punam K Saha

Medical physics (Lancaster), Vol.51(6), pp.4258-4270

06/2024

DOI: 10.1002/mp.17003

PMCID: PMC11147700

PMID: 38415781

Appears in UI Libraries Support Open Access

Files and links (1)

url

https://doi.org/10.1002/mp.17003View

Published (Version of record) Open Access

Abstract

Osteoporosis 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. This 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. We 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. Mean ± 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. 3DGAN-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.

Osteoporosis

CT imaging

deep learning

microstructure

trabecular bone

harmonization

3DGAN-CIRCLE

high-resolution reconstruction

UIOWA OA Agreement

Details

Title: Subtitle: Deep learning-based harmonization of trabecular bone microstructures between high- and low-resolution CT imaging
Creators: Indranil Guha - University of Iowa
Syed Ahmed Nadeem - University of Iowa
Xiaoliu Zhang - University of Iowa
Paul A DiCamillo - University of Iowa
Steven M Levy - University of Iowa
Ge Wang - Rensselaer Polytechnic Institute
Punam K Saha - University of Iowa
Resource Type: Journal article
Publication Details: Medical physics (Lancaster), Vol.51(6), pp.4258-4270
Publisher: Wiley
DOI: 10.1002/mp.17003
PMID: 38415781
PMCID: PMC11147700
eISSN: 2473-4209
Grant note: UL1-RR024979 / NIH HHS R01 HL142042 / NIH HHS R01 DE12101 / NIH HHS
Language: English
Electronic publication date: 02/28/2024
Date published: 06/2024
Academic Unit: Preventive and Community Dentistry; Radiology; Electrical and Computer Engineering; Epidemiology
Record Identifier: 9984563459802771

Metrics

5 Record Views