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

• Published in: Computational and structural biotechnology journal Vol. 24; pp. 89 - 104
• Main Authors: Morris, David M., Wang, Chengjia, Papanastasiou, Giorgos, Gray, Calum D., Xu, Wei, Sjöström, Samuel, Badr, Sammy, Paccou, Julien, Semple, Scott IK, MacGillivray, Tom, Cawthorn, William P.
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.12.2024; Elsevier; Research Network of Computational and Structural Biotechnology
• Subjects: Ageing; Biomarkers; Bone; Bone marrow adipose tissue; Bone marrow adiposity; Bone marrow fat fraction; Deep learning; Life Sciences; Magnetic resonance imaging; Osteoporosis; Predictive analytics; Sex differences; UK Biobank; Deep learning; Osteoporosis; Magnetic resonance imaging; Bone marrow adiposity; Ageing; Biomarkers; Bone marrow adipose tissue; Sex differences; Bone; Bone marrow fat fraction; Predictive analytics; UK Biobank
• ISSN: 2001-0370; 2001-0370
• DOI: 10.1016/j.csbj.2023.12.029

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. To establish deep learning for high-throughput multi-site BMFF analysis from UKBB MRI data. 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. 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. 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. [Display omitted] •We establish a new deep learning method for image segmentation.•Our method improves segmentation of small structures from large volumetric data.•Using our method, we assess bone marrow fat fraction (BMFF) in UK Biobank MRI data.•This is the first use of deep learning for large-scale, multi-site BMFF analysis.•Our results highlight the potential of BMFF as a new clinical biomarker.