Automatic segmentation of human supraclavicular adipose tissue using high-resolution T2-weighted magnetic resonance imaging
Automatic segmentation of human supraclavicular adipose tissue using high-resolution T2-weighted magnetic resonance imaging
复制标题
使用高分辨率 T2 加权磁共振成像自动分割人体锁骨上脂肪组织
DOI：
10.1007/s10334-022-01056-w
复制
发表时间：
2022-12-20
影响因子：
2.3
通讯作者：
Zou，Chao
中科院分区：
文献类型：
--
作者：
Wu，Bingxia;Cheng，Chuanli;Zou，Chao
目的使用高分辨率 T2 加权磁共振图像实现人体锁骨上脂肪组织 (sclavAT) 的有效分割。方法使用 3.0 T MRI 扫描仪从 29 名志愿者的横向或冠状平面获取覆盖人体锁骨上区域的高分辨率 1.0 mm 各向同性 3D T2 加权图像。每个受试者的横向/冠状动脉扫描通常有 144/288 个切片，这相当于 29 名志愿者总共有 6816 个图像。训练 U-NET 网络来分割锁骨上脂肪组织 (sclavAT)。通过使用骰子相似系数（DSC）、精确率（PR）和召回率（RR）等定量指标将输出结果与手动标签进行比较来评估自动分割方法的性能。自动分割的图像用于计算 sclavAT 体积并配准到 MR 脂肪分数 (FF) 图像以量化 sclavAT 区域的脂肪成分。评估所有受试者的体重指数（BMI）、sclavAT区域的体积和FF之间的关系。结果自动sclavAT分割方法在测试数据集上的DSC、PR和RR分别为0.920±0.048、0.915±0.070和0.930±0.058。 sclavAT 的体积和平均 FF 均与 BMI 强相关，相关系数分别为 0.703 和 0.625（p< 0.05）。自动分割方法的平均计算时间约为每个切片 0.06 秒，而手动标记则超过 5 分钟。结论本研究表明，所提出的使用 U-Net 网络的自动分割方法能够高效、准确地识别人类 sclavAT。
ObjectiveTo achieve efficient segmentation of human supraclavicular adipose tissue (sclavAT) using high-resolution T2-weighted magnetic resonance images.MethodsHigh-resolution 1.0 mm isotropic 3D T2-weighted images covering human supraclavicular area were acquired in transverse or coronary plane from 29 volunteers using a 3.0 T MRI scanner. There were typically 144/288 slices for the transverse/coronary scans for each subject, which amounts to a total of 6816 images in 29 volunteers. A U-NET network was trained to segment the supraclavicular adipose tissue (sclavAT). The performance of the automatic segmentation method was evaluated by comparing the output results with the manual labels using the quantitative indices of dice similarity coefficient (DSC), precision rate (PR), and recall rate (RR). The auto-segmented images were used to calculate the sclavAT volumes and registered to the MR fat fraction (FF) images to quantify the fat component of the sclavAT area. The relationship between body mass index (BMI), the volume and FF of sclavAT area was evaluated for all subjects.ResultsThe DSC, PR and RR of the automatic sclavAT segmentation method on the testing datasets were 0.920 ± 0.048, 0.915 ± 0.070 and 0.930 ± 0.058. The volume and the mean FF of sclavAT were both found to be strongly correlated to BMI, with the correlation coefficient of 0.703 and 0.625 (p< 0.05), respectively. The averaged computation time of the automatic segmentation method was approximately 0.06 s per slice, compared to more than 5 min for manual labeling.ConclusionThe present study demonstrates that the proposed automatic segmentation method using U-Net network is able to identify human sclavAT efficiently and accurately.