文献速递腹部技术与安全CT

基于门静脉期计算机断层扫描图像的肝脏和脾脏自动分割与体积测量的深度学习算法

Deep Learning Algorithm for Automated Segmentation and Volume Measurement of the Liver and Spleen Using Portal Venous Phase Computed Tomography Images.
PubMed 文献 · Korean J Radiol · 2020-01-01

本研究利用813例门静脉期CT图像训练深度学习算法(DLA),在包含150例不同肝脏条件(健康肝、脂肪肝、慢性肝病、肝硬化、肝切除术后)的测试集1中,肝脏和脾脏分割的平均DSS分别为0.973和0.974,不同肝脏条件间DSS无显著差异;体积测量的Bland-Altman 95% LOA肝脏为-0.17±3.07%、脾脏为-0.56±3.78%。在测试集2中,外院与本机构CT图像的分割性能相当(肝脏DSS 0.982 vs. 0.983,p=0.28;脾脏DSS 0.969 vs. 0.968,p=0.41)。

要点

  • DLA在门静脉期CT上实现全自动肝脾分割,测试集1肝脏和脾脏平均DSS分别为0.973和0.974。
  • 不同肝脏条件(健康肝、脂肪肝、慢性肝病、肝硬化、肝切除术后)间分割DSS无显著差异(肝脏p=0.60,脾脏p=0.26)。
  • 体积测量与手动分割的Bland-Altman 95% LOA肝脏为-0.17±3.07%,脾脏为-0.56±3.78%。

诊断标准与关键数值

  • 测试集1中DLA肝脏和脾脏分割的平均DSS分别为0.973和0.974。
  • 测试集1中不同肝脏条件间DSS无显著差异,肝脏p=0.60,脾脏p=0.26。
  • 测试集1中体积测量Bland-Altman 95% LOA:肝脏体积-0.17±3.07%,脾脏体积-0.56±3.78%。
  • 测试集2中本机构与外院CT图像分割DSS:肝脏0.983 vs. 0.982(p=0.28),脾脏0.968 vs. 0.969(p=0.41)。

临床应用与阅片要点

  • DLA可基于门静脉期CT图像自动分割肝脏和脾脏,在健康肝、脂肪肝、慢性肝病、肝硬化及肝切除术后患者中均获得高DSS。
  • 体积测量与手动分割的一致性以Bland-Altman 95% LOA评估,肝脏和脾脏体积的LOA分别约为-0.17±3.07%和-0.56±3.78%。
  • DLA在本机构与外院CT图像上的分割性能相当,提示其可能适用于不同来源的门静脉期CT图像。

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: Measurement of the liver and spleen volumes has clinical implications. Although computed tomography (CT) volumetry is considered to be the most reliable noninvasive method for liver and spleen volume measurement, it has limited application in clinical practice due to its time-consuming segmentation process. We aimed to develop and validate a deep learning algorithm (DLA) for fully automated liver and spleen segmentation using portal venous phase CT images in various liver conditions.

MATERIALS AND METHODS: A DLA for liver and spleen segmentation was trained using a development dataset of portal venous CT images from 813 patients. Performance of the DLA was evaluated in two separate test datasets: dataset-1 which included 150 CT examinations in patients with various liver conditions (i.e., healthy liver, fatty liver, chronic liver disease, cirrhosis, and post-hepatectomy) and dataset-2 which included 50 pairs of CT examinations performed at ours and other institutions. The performance of the DLA was evaluated using the dice similarity score (DSS) for segmentation and Bland-Altman 95% limits of agreement (LOA) for measurement of the volumetric indices, which was compared with that of ground truth manual segmentation.

RESULTS: In test dataset-1, the DLA achieved a mean DSS of 0.973 and 0.974 for liver and spleen segmentation, respectively, with no significant difference in DSS across different liver conditions (p = 0.60 and 0.26 for the liver and spleen, respectively). For the measurement of volumetric indices, the Bland-Altman 95% LOA was -0.17 ± 3.07% for liver volume and -0.56 ± 3.78% for spleen volume. In test dataset-2, DLA performance using CT images obtained at outside institutions and our institution was comparable for liver (DSS, 0.982 vs. 0.983; p = 0.28) and spleen (DSS, 0.969 vs. 0.968; p = 0.41) segmentation.

CONCLUSION: The DLA enabled highly accurate segmentation and volume measurement of the liver and spleen using portal venous phase CT images of patients with various liver conditions.

来源:Korean J Radiol,查看原文。版权归原作者所有。

引用

  1. Ahn Y, Yoon JS, Lee SS, et al. Deep Learning Algorithm for Automated Segmentation and Volume Measurement of the Liver and Spleen Using Portal Venous Phase Computed Tomography Images. Korean J Radiol. 2020. PMID: 32677383. doi:10.3348/kjr.2020.0237

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。