3D Neural Networks for Visceral and Subcutaneous Adipose Tissue Segmentation using Volumetric Multi-Contrast MRI.
3D Neural Networks for Visceral and Subcutaneous Adipose Tissue Segmentation using Volumetric Multi-Contrast MRI.
复制标题
DOI：
10.1109/embc46164.2021.9630110
复制
发表时间：
2021-11
期刊：
影响因子：
--
通讯作者：
Wu HH
中科院分区：
文献类型：
--
作者：
Kafali SG;Shih SF;Li X;Chowdhury S;Loong S;Barnes S;Li Z;Wu HH
肥胖者体内内脏(VAT)和皮下脂肪(SAT)的数量较多，增加了患心脏代谢性疾病的风险。量化SAT和VAT的参考标准使用磁共振图像(MRI)的手动注释，这需要专业知识且耗时。尽管已经有研究对基于深度学习的自动SAT和增值税分割方法进行了研究，但增值税的性能仍然不佳(Dice分数在0.43到0.89之间)。以前的工作有关键的局限性，没有充分考虑来自MRI的多对比信息和3D解剖环境，这对于解决VAT复杂的空间变化结构至关重要。另一个挑战是代表SAT/VAT的像素数量和分布之间的不平衡。本工作提出了一种基于3D U-Net的网络，该网络利用来自双回波Dixon MRI的全视野体积T1加权、水和脂肪图像作为多通道输入，自动分割超重/肥胖成年人的SAT和VAT。此外，本文还将3D U-Net扩展到一种新的基于注意力的竞争性密集3D U-Net(ACD 3D U-Net)，该模型训练了一类频率平衡骰子损失(FBDL)。在初始测试数据集中，与人工标注相比，所提出的3D U-Net和带有FBDL的ACD 3D U-Net分别获得了SAT的3D Dice分数0.99±0.01和0.99±0.01，VAT的0.95±0.04和0.96±0.04。所提出的3D网络具有快速的推理时间(<；60ms/Slice)，并且可以实现SAT和VAT的自动分割。
Individuals with obesity have larger amounts of visceral (VAT) and subcutaneous adipose tissue (SAT) in their body, increasing the risk for cardiometabolic diseases. The reference standard to quantify SAT and VAT uses manual annotations of magnetic resonance images (MRI), which requires expert knowledge and is time-consuming. Although there have been studies investigating deep learning-based methods for automated SAT and VAT segmentation, the performance for VAT remains suboptimal (Dice scores of 0.43 to 0.89). Previous work had key limitations of not fully considering the multi-contrast information from MRI and the 3D anatomical context, which are critical for addressing the complex spatially varying structure of VAT. An additional challenge is the imbalance between the number and distribution of pixels representing SAT/VAT. This work proposes a network based on 3D U-Net that utilizes the full field-of-view volumetric T1-weighted, water, and fat images from dual-echo Dixon MRI as the multi-channel input to automatically segment SAT and VAT in adults with overweight/obesity. In addition, this work extends the 3D U-Net to a new Attention-based Competitive Dense 3D U-Net (ACD 3D U-Net) trained with a class frequency-balancing Dice loss (FBDL). In an initial testing dataset, the proposed 3D U-Net and ACD 3D U-Net with FBDL achieved 3D Dice scores of (mean±standard deviation) 0.99±0.01 and 0.99±0.01 for SAT, and 0.95±0.04 and 0.96±0.04 for VAT, respectively, compared to manual annotations. The proposed 3D networks had rapid inference time (<60 ms/slice) and can enable automated segmentation of SAT and VAT.