论文标题
在流行病学队列研究的三维全身MRI中，通过深度学习对脂肪组织室的完全自动化和标准化分割
Fully Automated and Standardized Segmentation of Adipose Tissue Compartments by Deep Learning in Three-dimensional Whole-body MRI of Epidemiological Cohort Studies
论文作者
论文摘要
目的：能够快速，可靠的评估来自全身MRI的皮下和内脏脂肪组织室。方法：从全身MR图像中对不同脂肪组织室的定量和定位是检查代谢条件的高度兴趣。为了正确鉴定和表型，需要增加代谢疾病风险的个体，需要将脂肪组织自动分割为皮下和内脏脂肪组织。在这项工作中，我们提出了一个3D卷积神经网络（DCNET），以提供强大而客观的分割。在这项回顾性研究中，我们从Tuebingen家庭研究和德国糖尿病研究中心（TUEF/DZD）（TUEF/DZD）中收集了1000例（66美元$ \ PM $ 13岁； 523名女性），以及300例（53美元$ \ \ \ $ \ $ \ $ 11 $ $ \ PM 11岁； 152名妇女）从德国国家组合（NAKO）进行培训，并进行了验证验证，并进行了验证，并进行了验证，并进行了验证，并进行了验证，并进行了A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A S A相提所转化。这些数据集具有可变的成像序列，成像对比度，接收器线圈布置，扫描仪和成像场强度。将所提出的DCNET与可比的3D UNET分割进行了比较，从敏感性，特异性，精度，准确性和骰子重叠。结果：可以通过高骰子重叠（0.94），敏感性（96.6％），特异性（95.1％），精度（92.1％），精度（98.4％）和3D全部MR DataSet（3D MR MR数据范围coppereage 450x450x2000mmm field），特异性（95.1％），精度（92.1％）和精度（98.4％）来获得快速（5-7秒）和可靠的脂肪组织分割。分割面罩和脂肪组织曲线自动报告给参考医师。结论：在3D全身MR数据集中，自动脂肪组织分割是可行的，并且可以通过拟议的DCNET推广到不同的流行病学队列研究。
Purpose: To enable fast and reliable assessment of subcutaneous and visceral adipose tissue compartments derived from whole-body MRI. Methods: Quantification and localization of different adipose tissue compartments from whole-body MR images is of high interest to examine metabolic conditions. For correct identification and phenotyping of individuals at increased risk for metabolic diseases, a reliable automatic segmentation of adipose tissue into subcutaneous and visceral adipose tissue is required. In this work we propose a 3D convolutional neural network (DCNet) to provide a robust and objective segmentation. In this retrospective study, we collected 1000 cases (66$\pm$ 13 years; 523 women) from the Tuebingen Family Study and from the German Center for Diabetes research (TUEF/DZD), as well as 300 cases (53$\pm$ 11 years; 152 women) from the German National Cohort (NAKO) database for model training, validation, and testing with a transfer learning between the cohorts. These datasets had variable imaging sequences, imaging contrasts, receiver coil arrangements, scanners and imaging field strengths. The proposed DCNet was compared against a comparable 3D UNet segmentation in terms of sensitivity, specificity, precision, accuracy, and Dice overlap. Results: Fast (5-7seconds) and reliable adipose tissue segmentation can be obtained with high Dice overlap (0.94), sensitivity (96.6%), specificity (95.1%), precision (92.1%) and accuracy (98.4%) from 3D whole-body MR datasets (field of view coverage 450x450x2000mm${}^3$). Segmentation masks and adipose tissue profiles are automatically reported back to the referring physician. Conclusion: Automatic adipose tissue segmentation is feasible in 3D whole-body MR data sets and is generalizable to different epidemiological cohort studies with the proposed DCNet.
