文献速递腹部技术与安全CT

基于深度学习的CT腹部自动分割用于身体成分分析

Automated Abdominal Segmentation of CT Scans for Body Composition Analysis Using Deep Learning.
PubMed 文献 · Radiology · 2018-12-11

本研究为回顾性研究,训练基于U-Net架构的卷积神经网络对2430例二维CT进行腹部自动分割,并在270例测试集及2369例肝细胞癌患者数据集中验证。模型在皮下、肌肉、内脏脂肪分区的Dice评分与专家手动分割相当或更优,提示可能实现三维CT身体成分指标的完全自动定量。

要点

  • 基于U-Net的卷积神经网络可自动分割腹部皮下、肌肉、内脏脂肪组织。
  • 测试集Dice评分分别为皮下0.98±0.03、肌肉0.96±0.02、内脏0.97±0.01。
  • 肝细胞癌数据集Dice评分分别为皮下0.94±0.05、肌肉0.92±0.04、内脏0.98±0.02。

核心结论

  • 模型在测试数据集和肝细胞癌数据集上的表现达到或超过专家手动分割CT图像的准确度。
  • 模型可较好地泛化至腹部多个层面,可能实现三维CT身体成分指标的完全自动定量。

研究设计与样本

  • 回顾性研究,训练集为2430例二维CT检查,测试集为270例CT检查。
  • 另在2369例肝细胞癌患者的独立数据集中进一步测试。
  • CT检查实施于1997年至2015年,患者平均年龄67岁,男性平均67岁(范围29-94岁),女性平均66岁(范围31-97岁)。
  • 采用基于U-Net架构的卷积神经网络进行腹部自动分割,以参考分割为对照。
  • 分割性能差异采用双向方差分析及Bonferroni校正评估。

诊断标准与关键数值

  • 测试集中,模型与参考分割相比,皮下脂肪组织Dice评分为0.98±0.03,肌肉组织为0.96±0.02,内脏脂肪组织为0.97±0.01。
  • 肝细胞癌数据集中,皮下脂肪组织Dice评分为0.94±0.05,肌肉组织为0.92±0.04,内脏脂肪组织为0.98±0.02。

临床应用与阅片要点

  • 模型性能达到或超过专家手动分割的准确度,可能用于三维CT身体成分指标的完全自动定量。

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

Purpose To develop and evaluate a fully automated algorithm for segmenting the abdomen from CT to quantify body composition. Materials and Methods For this retrospective study, a convolutional neural network based on the U-Net architecture was trained to perform abdominal segmentation on a data set of 2430 two-dimensional CT examinations and was tested on 270 CT examinations. It was further tested on a separate data set of 2369 patients with hepatocellular carcinoma (HCC). CT examinations were performed between 1997 and 2015. The mean age of patients was 67 years; for male patients, it was 67 years (range, 29-94 years), and for female patients, it was 66 years (range, 31-97 years). Differences in segmentation performance were assessed by using two-way analysis of variance with Bonferroni correction. Results Compared with reference segmentation, the model for this study achieved Dice scores (mean ± standard deviation) of 0.98 ± 0.03, 0.96 ± 0.02, and 0.97 ± 0.01 in the test set, and 0.94 ± 0.05, 0.92 ± 0.04, and 0.98 ± 0.02 in the HCC data set, for the subcutaneous, muscle, and visceral adipose tissue compartments, respectively. Performance met or exceeded that of expert manual segmentation. Conclusion Model performance met or exceeded the accuracy of expert manual segmentation of CT examinations for both the test data set and the hepatocellular carcinoma data set. The model generalized well to multiple levels of the abdomen and may be capable of fully automated quantification of body composition metrics in three-dimensional CT examinations. © RSNA, 2018 Online supplemental material is available for this article. See also the editorial by Chang in this issue.

来源:Radiology,查看原文。版权归原作者所有。

引用

  1. Weston AD, Korfiatis P, Kline TL, et al. Automated Abdominal Segmentation of CT Scans for Body Composition Analysis Using Deep Learning. Radiology. 2018. PMID: 30526356. doi:10.1148/radiol.2018181432

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。