用于CT肺叶分割的多任务学习V-Net开发及其在病变肺中的应用
开发多任务学习V-Net用于CT肺叶分割,利用气管支气管树信息增强分割精度,并同步分割肺叶与辅助组织。在包含严重肺癌、COVID-19肺炎、肺塌陷和COPD的外部数据集上验证,各肺叶Dice分数为正常肺0.97、COPD 0.94、肺癌0.94、COVID-19肺炎0.94、肺塌陷0.92,均p<0.05。
要点
- 多任务学习V-Net结合气管支气管树信息可提高肺叶分割精度。
- 在正常肺及四种病变肺上肺叶分割Dice分数均较高(0.92–0.97)。
- 模型有望作为放射科医生和研究人员定义肺叶分布及辅助治疗规划的工具。
核心结论
- 尽管存在严重异常,模型在肺叶分割上表现良好,显示组织学习的益处,所提模型有望在临床环境中采用,作为放射科医生和研究人员定义肺部疾病肺叶分布并辅助疾病治疗规划的稳健工具。
研究设计与样本
- 开发多任务学习V-Net,利用气管支气管树信息增强分割精度,通过多任务学习结合V-Net-attention并行分割肺叶和辅助组织;使用外部数据集验证,该数据集包含四种不同肺部疾病患者:严重肺癌、COVID-19肺炎、肺塌陷和慢性阻塞性肺疾病(COPD),训练数据未包含这些病例。
诊断标准与关键数值
- 正常肺Dice分数0.97,p<0.05。
- COPD Dice分数0.94,p<0.05。
- 肺癌Dice分数0.94,p<0.05。
- COVID-19肺炎Dice分数0.94,p<0.05。
- 肺塌陷Dice分数0.92,p<0.05。
临床应用与阅片要点
- 作者认为所提模型有望在临床环境中采用,作为放射科医生和研究人员定义肺部疾病肺叶分布并辅助疾病治疗规划的稳健工具。
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
AIM: To develop a multi-task learning (MTL) V-Net for pulmonary lobar segmentation on computed tomography (CT) and application to diseased lungs.
MATERIALS AND METHODS: The described methodology utilises tracheobronchial tree information to enhance segmentation accuracy through the algorithm's spatial familiarity to define lobar extent more accurately. The method undertakes parallel segmentation of lobes and auxiliary tissues simultaneously by employing MTL in conjunction with V-Net-attention, a popular convolutional neural network in the imaging realm. Its performance was validated by an external dataset of patients with four distinct lung conditions: severe lung cancer, COVID-19 pneumonitis, collapsed lungs, and chronic obstructive pulmonary disease (COPD), even though the training data included none of these cases.
RESULTS: The following Dice scores were achieved on a per-segment basis: normal lungs 0.97, COPD 0.94, lung cancer 0.94, COVID-19 pneumonitis 0.94, and collapsed lung 0.92, all at p<0.05.
CONCLUSION: Despite severe abnormalities, the model provided good performance at segmenting lobes, demonstrating the benefit of tissue learning. The proposed model is poised for adoption in the clinical setting as a robust tool for radiologists and researchers to define the lobar distribution of lung diseases and aid in disease treatment planning.
引用
- Boubnovski, Chen, Linton-Reid, et al. Development of a multi-task learning V-Net for pulmonary lobar segmentation on CT and application to diseased lungs. Clin Radiol. 2022. PMID: 35636974. doi:10.1016/j.crad.2022.04.012
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。