基于深度神经网络在伴广泛肺实质异常的胸部CT图像上自动分割肺实质
研究纳入203例2017年1月至5月的薄层平扫胸部CT,其中150例肺实质病变范围超过40%,由5名放射科医师逐层手动勾画肺边界,用2D和3D U-Net模型分割全肺及左右肺,内部验证Dice系数99.4%–99.6%,外部验证98.4%±1.0%,在ILD范围大于75%的31例中Dice系数为97.9%–98.0%。
要点
- 2D U-Net全肺模型内部验证Dice系数99.6%±0.3%,对广泛肺实质病变分割性能优秀。
- 外部验证(日内瓦大学医院ILD数据集)Dice系数98.4%±1.0%,提示模型可泛化。
- ILD范围大于75%的31例中Dice系数仍达97.9%–98.0%。
诊断标准与关键数值
- 内部验证Dice相似系数:2D U-Net全肺模型99.6%±0.3%,2D U-Net左右肺分开模型99.5%±0.3%,3D U-Net全肺模型99.4%±0.5%,3D U-Net左右肺分开模型99.4%±0.5%。
- 外部验证数据集Dice相似系数:2D U-Net全肺模型98.4%±1.0%,2D U-Net左右肺分开模型98.4%±1.0%。
- 31例ILD范围大于75%肺实质面积的病例中,Dice相似系数:2D U-Net全肺模型97.9%±1.3%,2D U-Net左右肺分开模型98.0%±1.2%。
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: We aimed to develop a deep neural network for segmenting lung parenchyma with extensive pathological conditions on non-contrast chest computed tomography (CT) images.
MATERIALS AND METHODS: Thin-section non-contrast chest CT images from 203 patients (115 males, 88 females; age range, 31-89 years) between January 2017 and May 2017 were included in the study, of which 150 cases had extensive lung parenchymal disease involving more than 40% of the parenchymal area. Parenchymal diseases included interstitial lung disease (ILD), emphysema, nontuberculous mycobacterial lung disease, tuberculous destroyed lung, pneumonia, lung cancer, and other diseases. Five experienced radiologists manually drew the margin of the lungs, slice by slice, on CT images. The dataset used to develop the network consisted of 157 cases for training, 20 cases for development, and 26 cases for internal validation. Two-dimensional (2D) U-Net and three-dimensional (3D) U-Net models were used for the task. The network was trained to segment the lung parenchyma as a whole and segment the right and left lung separately. The University Hospitals of Geneva ILD dataset, which contained high-resolution CT images of ILD, was used for external validation.
RESULTS: The Dice similarity coefficients for internal validation were 99.6 ± 0.3% (2D U-Net whole lung model), 99.5 ± 0.3% (2D U-Net separate lung model), 99.4 ± 0.5% (3D U-Net whole lung model), and 99.4 ± 0.5% (3D U-Net separate lung model). The Dice similarity coefficients for the external validation dataset were 98.4 ± 1.0% (2D U-Net whole lung model) and 98.4 ± 1.0% (2D U-Net separate lung model). In 31 cases, where the extent of ILD was larger than 75% of the lung parenchymal area, the Dice similarity coefficients were 97.9 ± 1.3% (2D U-Net whole lung model) and 98.0 ± 1.2% (2D U-Net separate lung model).
CONCLUSION: The deep neural network achieved excellent performance in automatically delineating the boundaries of lung parenchyma with extensive pathological conditions on non-contrast chest CT images.
引用
- Yoo SJ, Yoon SH, Lee JH, et al. Automated Lung Segmentation on Chest Computed Tomography Images with Extensive Lung Parenchymal Abnormalities Using a Deep Neural Network. Korean J Radiol. 2020. PMID: 33169549. doi:10.3348/kjr.2020.0318
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。