基于PET与CT双模态深度学习神经网络的全自动肺癌分割
本研究构建了基于诊断性PET与模拟CT双模态输入的3D卷积神经网络,用于放疗计划的肺癌自动分割,在290对图像上按3:1:1划分训练/验证/测试,并以医师手动勾画为金标准。按大体肿瘤体积(GTV)大小分层训练策略在对应测试集上取得最佳Dice相似系数0.83±0.07,多观察者评审中88.75%的自动轮廓被接受或修改后接受。
要点
- 双模态3D网络在未分层模型下平均Dice系数为0.79±0.10,分层模型最佳Dice为0.83±0.07。
- 按GTV大小分层训练时,大GTV(>25 mL)模型用全尺寸GTV训练、小GTV(<25 mL)模型仅用小GTV训练效果最佳。
- 多观察者评审中91.25%手动轮廓 vs 88.75%自动轮廓被接受或修改后接受。
核心结论
- 利用大型临床PET与CT图像数据库及双模态架构,所提出的3D网络结合基于GTV的分层策略可生成临床有用的肺癌轮廓,在医师评审中具有高接受度。
研究设计与样本
- 构建3D卷积神经网络,含2条平行卷积路径独立提取多分辨率特征和1条反卷积路径,跳跃连接融合特征后输出肿瘤分割。
- 在290对来自本诊所肺癌患者的PET与CT图像上按3:1:1划分训练/验证/测试,以医师手动勾画为金标准。
- 研究基于GTV大小的分层训练策略以改善性能,尤其针对小肿瘤,并由多名放射肿瘤科医师评估网络生成分割的临床可接受性。
主要发现
- 未分层3D双模态模型手动与自动轮廓比较的平均Dice相似系数为0.79±0.10,Hausdorff距离为5.8±3.2 mm,双向局部距离为2.8±1.5 mm。
- 分层模型最佳组合在对应测试集上的Dice相似系数为0.83±0.07,Hausdorff距离为5.9±2.5 mm,双向局部距离为2.8±1.4 mm。
- 分层训练的最佳结果为:大GTV(>25 mL)模型用全尺寸GTV训练,小GTV(<25 mL)模型仅用小GTV训练。
- 多观察者评审中,91.25%手动轮廓 vs 88.75%自动轮廓被接受或修改后接受。
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)。
原文
PURPOSE: To develop an automated lung tumor segmentation method for radiation therapy planning based on deep learning and dual-modality positron emission tomography (PET) and computed tomography (CT) images. METHODS AND MATERIALS: A 3-dimensional (3D) convolutional neural network using inputs from diagnostic PETs and simulation CTs was constructed with 2 parallel convolution paths for independent feature extraction at multiple resolution levels and a single deconvolution path. At each resolution level, the extracted features from the convolution arms were concatenated and fed through the skip connections into the deconvolution path that produced the tumor segmentation. Our network was trained/validated/tested by a 3:1:1 split on 290 pairs of PET and CT images from patients with lung cancer treated at our clinic, with manual physician contours as the ground truth. A stratified training strategy based on the magnitude of the gross tumor volume (GTV) was investigated to improve performance, especially for small tumors. Multiple radiation oncologists assessed the clinical acceptability of the network-produced segmentations. RESULTS: The mean Dice similarity coefficient, Hausdorff distance, and bidirectional local distance comparing manual versus automated contours were 0.79 ± 0.10, 5.8 ± 3.2 mm, and 2.8 ± 1.5 mm for the unstratified 3D dual-modality model. Stratification delivered the best results when the model for the large GTVs (>25 mL) was trained with all-size GTVs and the model for the small GTVs (<25 mL) was trained with small GTVs only. The best combined Dice similarity coefficient, Hausdorff distance, and bidirectional local distance from the 2 stratified models on their corresponding test data sets were 0.83 ± 0.07, 5.9 ± 2.5 mm, and 2.8 ± 1.4 mm, respectively. In the multiobserver review, 91.25% manual versus 88.75% automatic contours were accepted or accepted with modifications. CONCLUSIONS: By using an expansive clinical PET and CT image database and a dual-modality architecture, the proposed 3D network with a novel GTVbased stratification strategy generated clinically useful lung cancer contours that were highly acceptable on physician review.
引用
- Wang S, Mahon R, Weiss E, et al. Automated Lung Cancer Segmentation Using a PET and CT Dual-Modality Deep Learning Neural Network. Int J Radiat Oncol Biol Phys. 2022. PMID: 35934160. doi:10.1016/j.ijrobp.2022.07.2312
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。