A novel deep learning method for large-scale analysis of bone marrow adiposity using UK Biobank Dixon MRI data.
A novel deep learning method for large-scale analysis of bone marrow adiposity using UK Biobank Dixon MRI data.
复制标题
一种新型的深度学习方法，用于使用UK Biobank Dixon MRI数据对骨髓肥胖进行大规模分析。
DOI：
10.1016/j.csbj.2023.12.029
复制
发表时间：
2024-12
影响因子：
6
通讯作者：
中科院分区：
文献类型：
--
作者：
骨髓脂肪组织 (BMAT) 代表健康人> 10% 的脂肪量，可以通过磁共振成像 (MRI) 测量为骨髓脂肪分数 (BMFF)。人类 MRI 研究已经发现了几种与 BMFF 相关的疾病，但规模相对较小。因此，人群规模的研究具有揭示 BMAT 真正临床相关性的巨大潜力。英国生物银行 (UKBB) 正在对 100,000 名参与者进行 MRI，为此类进展提供了理想的机会。建立深度学习，以便根据 UKBB MRI 数据进行高通量多部位 BMFF 分析。我们研究了 60-69 岁的男性和女性。使用新型轻量级基于注意力的 3D U-Net 卷积神经网络实现骨髓 (BM) 分割的自动化，该网络改进了大体积数据中小结构的分割。使用 61-64 名受试者的手动分割，训练模型来分割四个感兴趣的 BM 区域：脊柱（胸椎和腰椎）、股骨头、全髋和股骨骨干。每个区域还使用 10-12 个数据集对模型进行了测试，并使用 729 位 UKBB 参与者的数据集进行了验证。然后对 BMFF 进行量化并评估病理生理学特征，包括部位和性别依赖性差异以及与年龄、BMI、骨矿物质密度、外周肥胖和骨质疏松症的关系。模型精度与传统 U-Net 相当或超过，Dice 得分为 91.2%（脊柱）、94.5%（股骨头）、91.2%（全髋）和 86.6%（股骨骨干）。 1 例严重脊柱侧凸导致脊柱无法分割，1 例非霍奇金淋巴瘤由于 T2 信号缺失而导致脊柱、股骨头和全髋部无法分割；然而，成功的分割并未受到任何其他病理生理学变量的干扰。由此产生的 BMFF 测量结果证实了 BMFF 与年龄、性别和骨密度之间的预期关系，并确定了新的部位和性别特异性特征。我们建立了一种新的深度学习方法，用于从大体积数据中精确分割小结构，从而允许在 UKBB 中进行高通量多站点 BMFF 测量。我们的研究结果揭示了新的病理生理学见解，凸显了 BMFF 作为新型临床生物标志物的潜力。将我们的方法应用于整个 UKBB 队列将有助于揭示 BMAT 对人类健康和疾病的影响。我们建立了一种新的图像分割深度学习方法。我们的方法改进了大体积数据中小结构的分割。使用我们的方法，我们评估了英国生物银行 MRI 数据中的骨髓脂肪分数 (BMFF)。这是深度学习首次用于大规模、多站点 BMFF 分析。我们的结果凸显了 BMFF 作为新的临床生物标志物的潜力。
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. 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.
登录
查看更多内容
影响因子：
2.5
作者：
Shen, Wei;Velasquez, Gilbert;Chen, Jun;Jin, Ye;Heymsfield, Steven B.;Gallagher, Dympna;Pi-Sunyer, F. Xavier
通讯作者：
Pi-Sunyer, F. Xavier
DOI：
10.1038/oby.2010.106
发表时间：
2011-01
期刊：
Obesity (Silver Spring, Md.)
影响因子：
--
作者：
Bredella MA;Torriani M;Ghomi RH;Thomas BJ;Brick DJ;Gerweck AV;Rosen CJ;Klibanski A;Miller KK
通讯作者：
Miller KK
影响因子：
--
作者：
Zhu, Maochang;Bin, Sheng;Sun, Gengxin
通讯作者：
Sun, Gengxin
影响因子：
5.2
作者：
Cordes C;Baum T;Dieckmeyer M;Ruschke S;Diefenbach MN;Hauner H;Kirschke JS;Karampinos DC
通讯作者：
Karampinos DC
影响因子：
6.7
作者：
Kart, Turkay;Fischer, Marc;Gatidis, Sergios
通讯作者：
Gatidis, Sergios