A novel deep learning method for large-scale analysis of bone marrow adiposity using UK Biobank Dixon MRI data

David M Morris; Chengjia Wang; Giorgos Papanastasiou; Calum D Gray; Wei Xu; Samuel Sjöström; Sammy Badr; Julien Paccou; Scott Ik Semple; Tom MacGillivray; William P Cawthorn

doi:10.1016/j.csbj.2023.12.029

A novel deep learning method for large-scale analysis of bone marrow adiposity using UK Biobank Dixon MRI data

Comput Struct Biotechnol J. 2023 Dec 27:24:89-104. doi: 10.1016/j.csbj.2023.12.029. eCollection 2024 Dec.

Authors

David M Morris^{1

2}, Chengjia Wang^{1

3}, Giorgos Papanastasiou^{2

4}, Calum D Gray², Wei Xu⁵, Samuel Sjöström¹, Sammy Badr^{6

7}, Julien Paccou^{6

8}, Scott Ik Semple^{1

2}, Tom MacGillivray⁹, William P Cawthorn¹

Affiliations

¹ University/BHF Centre for Cardiovascular Science, University of Edinburgh, The Queen's Medical Research Institute, Edinburgh BioQuarter, 47 Little France Crescent, Edinburgh EH16 4TJ, UK.
² Edinburgh Imaging, University of Edinburgh, The Queen's Medical Research Institute, Edinburgh BioQuarter, 47 Little France Crescent, Edinburgh EH16 4TJ, UK.
³ School of Mathematics and Computer Sciences, Heriot-Watt University, Edinburgh EH14 1AS, UK.
⁴ School of Computer Science and Electronic Engineering, Wivenhoe Park, The University of Essex, Colchester CO4 3SQ, UK.
⁵ Centre for Global Health, Usher Institute, University of Edinburgh, Edinburgh EH8 9AG, UK.
⁶ University of Lille, Marrow Adiposity and Bone Laboratory (MABlab) ULR 4490, F-59000 Lille, France.
⁷ CHU Lille, Department of Radiology and Musculoskeletal Imaging, F-59000 Lille, France.
⁸ CHU Lille, Department of Rheumatology, F-59000 Lille, France.
⁹ Centre for Clinical Brain Sciences, University of Edinburgh, The Queen's Medical Research Institute, Edinburgh BioQuarter, 47 Little France Crescent, Edinburgh EH16 4TJ, UK.

Abstract

Background: Bone marrow adipose tissue (BMAT) represents > 10% fat mass in healthy humans and can be measured by magnetic resonance imaging (MRI) as the bone marrow fat fraction (BMFF). Human MRI studies have identified several diseases associated with BMFF but have been relatively small scale. Population-scale studies therefore have huge potential to reveal BMAT's true clinical relevance. The UK Biobank (UKBB) is undertaking MRI of 100,000 participants, providing the ideal opportunity for such advances.

Objective: To establish deep learning for high-throughput multi-site BMFF analysis from UKBB MRI data.

Materials and methods: We studied males and females aged 60-69. Bone marrow (BM) segmentation was automated using a new lightweight attention-based 3D U-Net convolutional neural network that improved segmentation of small structures from large volumetric data. Using manual segmentations from 61-64 subjects, the models were trained to segment four BM regions of interest: the spine (thoracic and lumbar vertebrae), femoral head, total hip and femoral diaphysis. Models were tested using a further 10-12 datasets per region and validated using datasets from 729 UKBB participants. BMFF was then quantified and pathophysiological characteristics assessed, including site- and sex-dependent differences and the relationships with age, BMI, bone mineral density, peripheral adiposity, and osteoporosis.

Results: Model accuracy matched or exceeded that for conventional U-Nets, yielding Dice scores of 91.2% (spine), 94.5% (femoral head), 91.2% (total hip) and 86.6% (femoral diaphysis). One case of severe scoliosis prevented segmentation of the spine, while one case of Non-Hodgkin Lymphoma prevented segmentation of the spine, femoral head and total hip because of T2 signal depletion; however, successful segmentation was not disrupted by any other pathophysiological variables. The resulting BMFF measurements confirmed expected relationships between BMFF and age, sex and bone density, and identified new site- and sex-specific characteristics.

Conclusions: We have established a new deep learning method for accurate segmentation of small structures from large volumetric data, allowing high-throughput multi-site BMFF measurement in the UKBB. Our findings reveal new pathophysiological insights, highlighting the potential of BMFF as a novel clinical biomarker. Applying our method across the full UKBB cohort will help to reveal the impact of BMAT on human health and disease.

Keywords: Ageing; Biomarkers; Bone; Bone marrow adipose tissue; Bone marrow adiposity; Bone marrow fat fraction; Deep learning; Magnetic resonance imaging; Osteoporosis; Predictive analytics; Sex differences; UK Biobank.

Abstract

Grants and funding