Adipose Tissue Segmentation in Unlabeled Abdomen MRI using Cross Modality Domain Adaptation.
Adipose Tissue Segmentation in Unlabeled Abdomen MRI using Cross Modality Domain Adaptation.
复制标题
使用交叉模态域的适应性适应未标记的腹部MRI中的脂肪组织分割。
DOI：
10.1109/embc44109.2020.9176009
复制
发表时间：
2020-07
期刊：
影响因子：
--
通讯作者：
Bagci U
中科院分区：
文献类型：
--
作者：
Masoudi S;Anwar SM;Harmon SA;Choyke PL;Turkbey B;Bagci U
腹部脂肪定量是关键，因为多个重要器官位于该区域内。虽然计算机断层扫描（CT）是一种高度敏感的方式分割身体脂肪，它涉及电离辐射，这使得磁共振成像（MRI）是一个优选的替代方案，用于此目的。此外，MRI中的上级软组织对比度可导致更准确的结果。然而，在MRI扫描中分割脂肪是高度劳动密集型的。在这项研究中，我们提出了一种基于深度学习技术的算法，通过跨模态自适应自动量化MR图像中的脂肪组织。我们的方法不需要对MR扫描进行监督标记，相反，我们利用循环生成对抗网络（C-GAN）来构建一个管道，将现有的MR扫描转换为等效的合成CT（s-CT）图像，其中由于CT图像中HU（hounsfield单位）的描述性，脂肪分割相对更容易。MRI扫描的脂肪分割结果由放射科专家进行评价。我们的分割结果的定性评价显示，MR图像中内脏和皮下脂肪分割的平均成功分数为3.80/5和4.54/5。
Abdominal fat quantification is critical since multiple vital organs are located within this region. Although computed tomography (CT) is a highly sensitive modality to segment body fat, it involves ionizing radiations which makes magnetic resonance imaging (MRI) a preferable alternative for this purpose. Additionally, the superior soft tissue contrast in MRI could lead to more accurate results. Yet, it is highly labor intensive to segment fat in MRI scans. In this study, we propose an algorithm based on deep learning technique(s) to automatically quantify fat tissue from MR images through a cross modality adaptation. Our method does not require supervised labeling of MR scans, instead, we utilize a cycle generative adversarial network (C-GAN) to construct a pipeline that transforms the existing MR scans into their equivalent synthetic CT (s-CT) images where fat segmentation is relatively easier due to the descriptive nature of HU (hounsfield unit) in CT images. The fat segmentation results for MRI scans were evaluated by expert radiologist. Qualitative evaluation of our segmentation results shows average success score of 3.80/5 and 4.54/5 for visceral and subcutaneous fat segmentation in MR images*.