论文标题
自动分割CT图像用于腹侧人体成分分析
Automatic segmentation of CT images for ventral body composition analysis
论文作者
论文摘要
目的：已知身体成分与包括糖尿病，癌症和心血管疾病在内的许多疾病有关。在本文中，我们开发了一种全自动的身体组织分解程序，以分段与身体成分分析有关的三个主要隔室 - 皮下脂肪组织（SAT），内脏脂肪组织（VAT）和肌肉。另外三个隔室 - 在分割过程中还分割了腹腔，肺和骨骼，以帮助分割主要隔室。 方法：开发具有密度连接层的卷积神经网络（CNN）模型以执行腹腔分割。开发了图像处理工作流程，以使用CNN模型将任何患者CT的腹腔分割，然后使用磁滞阈值进一步将身体组织分为多个隔室，然后进行形态操作。首先要分割腹腔，以便将室内和外部腹腔内外相似的隔室分离。 结果：对腹腔分割CNN模型进行了训练和测试，并在60 CTS中用手动标记的腹腔标记。腹腔分割的骰子得分（平均+/-标准偏差）为0.966 +/- 0.012。在具有静脉内（IV）和口服对比的CT数据集上测试，骰子得分为0.96 +/- 0.02，0.94 +/- 0.06，0.96 +/- 0.04，0.95 +/- 0.04，0.95 +/- 0.04和0.99 +/- 0.99 +/- 0.01，骨骼，sat，suscle，suscle，suscle and said，muscle和ung and bone and sat，sat，muscle and said，sat，muscle和ung。对于非conterst ct数据集，相应的骰子得分为0.97 +/- 0.02、0.94 +/- 0.07、0.93 +/- 0.06、0.91 +/- 0.04和0.99 +/- 0.01。 结论：制定了人体组织分解程序，以自动分段腹体的多个隔室。提出的方法可以从CT图像中对3D腹侧身体组成指标进行全自动定量。
Purpose: Body composition is known to be associated with many diseases including diabetes, cancers and cardiovascular diseases. In this paper, we developed a fully automatic body tissue decomposition procedure to segment three major compartments that are related to body composition analysis - subcutaneous adipose tissue (SAT), visceral adipose tissue (VAT) and muscle. Three additional compartments - the ventral cavity, lung and bones were also segmented during the segmentation process to assist segmentation of the major compartments. Methods: A convolutional neural network (CNN) model with densely connected layers was developed to perform ventral cavity segmentation. An image processing workflow was developed to segment the ventral cavity in any patient's CT using the CNN model, then further segment the body tissue into multiple compartments using hysteresis thresholding followed by morphological operations. It is important to segment ventral cavity firstly to allow accurate separation of compartments with similar Hounsfield unit (HU) inside and outside the ventral cavity. Results: The ventral cavity segmentation CNN model was trained and tested with manually labelled ventral cavities in 60 CTs. Dice scores (mean +/- standard deviation) for ventral cavity segmentation were 0.966+/-0.012. Tested on CT datasets with intravenous (IV) and oral contrast, the Dice scores were 0.96+/-0.02, 0.94+/-0.06, 0.96+/-0.04, 0.95+/-0.04 and 0.99+/-0.01 for bone, VAT, SAT, muscle and lung, respectively. The respective Dice scores were 0.97+/-0.02, 0.94+/-0.07, 0.93+/-0.06, 0.91+/-0.04 and 0.99+/-0.01 for non-contrast CT datasets. Conclusion: A body tissue decomposition procedure was developed to automatically segment multiple compartments of the ventral body. The proposed method enables fully automated quantification of 3D ventral body composition metrics from CT images.
