深度学习在盆腔CT身体成分评估中自动分割肌肉、脂肪和骨骼的应用
研究开发并验证了一种基于U-Net的深度卷积神经网络,用于在盆腔轴位CT图像上自动分割身体成分。在200例受试者的手动分割参考标准下,模型对背景、盆腔内容物、皮下脂肪、肌肉、肌间脂肪和骨骼的Dice分数分别为1.00、0.98、0.97、0.95、0.91和0.92。结论认为该模型可实现盆腔CT多组织的准确自动分割,对身体成分研究有前景。
要点
- U-Net模型在盆腔轴位CT上自动分割肌肉、脂肪和骨骼的Dice分数为0.91-0.97。
- 自动分割单张CT图像耗时GPU 0.07秒、CPU 2.51秒。
- 模型对肌间脂肪和骨骼的分割精度相对较低(Dice 0.91和0.92)。
核心结论
- 基于CNN的模型能够准确自动分割盆腔CT图像上的多种组织,对身体成分研究具有前景。
研究设计与样本
- 研究为深度学习模型开发与验证,手动分割200例受试者共200张髋臼上缘轴位CT图像作为参考标准,随机分为训练集(180/200)和测试集(20/200)。
诊断标准与关键数值
- 以手动分割为参考标准,Dice分数:背景1.00、盆腔内容物0.98、皮下脂肪0.97、肌肉0.95、肌间脂肪0.91、骨骼0.92。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
OBJECTIVE: To develop a deep convolutional neural network (CNN) to automatically segment an axial CT image of the pelvis for body composition measures. We hypothesized that a deep CNN approach would achieve high accuracy when compared to manual segmentations as the reference standard.
MATERIALS AND METHODS: We manually segmented 200 axial CT images at the supra-acetabular level in 200 subjects, labeling background, subcutaneous adipose tissue (SAT), muscle, inter-muscular adipose tissue (IMAT), bone, and miscellaneous intra-pelvic content. The dataset was randomly divided into training (180/200) and test (20/200) datasets. Data augmentation was utilized to enlarge the training dataset and all images underwent preprocessing with histogram equalization. Our model was trained for 50 epochs using the U-Net architecture with batch size of 8, learning rate of 0.0001, Adadelta optimizer and a dropout of 0.20. The Dice (F1) score was used to assess similarity between the manual segmentations and the CNN predicted segmentations.
RESULTS: The CNN model with data augmentation of N = 3000 achieved accurate segmentation of body composition for all classes. The Dice scores were as follows: background (1.00), miscellaneous intra-pelvic content (0.98), SAT (0.97), muscle (0.95), IMAT (0.91), and bone (0.92). Mean time to automatically segment one CT image was 0.07 s (GPU) and 2.51 s (CPU).
CONCLUSIONS: Our CNN-based model enables accurate automated segmentation of multiple tissues on pelvic CT images, with promising implications for body composition studies.
引用
- Hemke R, Buckless CG, Tsao A, et al. Deep learning for automated segmentation of pelvic muscles, fat, and bone from CT studies for body composition assessment. Skeletal Radiol. 2019. PMID: 31396667. doi:10.1007/s00256-019-03289-8
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。