基于患者特异性自适应卷积神经网络在纵向影像研究中分割肺部肿瘤
这项纵向影像研究纳入9例肺癌患者,每周采集6-7次T2加权MRI,用于开发患者特异性自适应卷积神经网络(A-net),以模拟自适应放疗工作流程并分割肿瘤。A-net的精确度、DICE系数和均方根表面距离分别为0.81±0.10、0.82±0.10和2.4±1.4 mm,优于基于人群的算法的0.63±0.21、0.64±0.19和4.1±3.0 mm。作者认为A-net可融入纵向影像研究的临床工作流程,并可能成为辅助自适应放疗决策的工具。
要点
- A-net利用既往每周MRI及肿瘤轮廓分割当前MRI,训练每周更新。
- A-net精确度0.81±0.10、DICE 0.82±0.10、均方根表面距离2.4±1.4 mm。
- 基于人群的算法对应值为0.63±0.21、0.64±0.19、4.1±3.0 mm,A-net表现更优。
核心结论
- A-net可融入纵向影像研究的临床工作流程,并可能成为辅助自适应放疗决策的工具。
研究设计与样本
- 纵向影像研究,纳入9例肺癌患者,放疗期间每周采集6-7次T2加权MRI。
- 所有扫描上的肿瘤由人工勾画作为参考标准。
- 开发患者特异性自适应卷积神经网络(A-net),模拟自适应放疗工作流程,利用既往每周MRI和肿瘤轮廓分割当前每周MRI。
- 训练数据增强:将感兴趣体积内每个体素扩展为3×3 cm图像块作为输入,输出为对应图像块的分类(背景或肿瘤)。
- 每周更新训练以纳入最新MRI扫描;基于人群的神经网络采用留一法训练和验证。
主要发现
- A-net在计算机集群上训练在2小时内收敛良好。
- A-net分割每周MRI的精确度0.81±0.10、DICE系数0.82±0.10、均方根表面距离2.4±1.4 mm。
- 基于人群的算法精确度0.63±0.21、DICE系数0.64±0.19、均方根表面距离4.1±3.0 mm,A-net表现优于基于人群的算法。
关键数值与推荐
- A-net精确度0.81±0.10、DICE系数0.82±0.10、均方根表面距离2.4±1.4 mm。
- 基于人群的算法精确度0.63±0.21、DICE系数0.64±0.19、均方根表面距离4.1±3.0 mm。
临床怎么用
- 原文未据此给出推荐。
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 design a deep learning algorithm that automatically delineates lung tumors seen on weekly magnetic resonance imaging (MRI) scans acquired during radiotherapy and facilitates the analysis of geometric tumor changes. METHODS: This longitudinal imaging study comprised 9 lung cancer patients who had 6-7 weekly T2-weighted MRI scans during radiotherapy. Tumors on all scans were manually contoured as the ground truth. Meanwhile, a patient-specific adaptive convolutional neural network (A-net) was developed to simulate the workflow of adaptive radiotherapy and to utilize past weekly MRI and tumor contours to segment tumors on the current weekly MRI. To augment the training data, each voxel inside the volume of interest was expanded to a 3 × 3 cm patch as the input, whereas the classification of the corresponding patch, background or tumor, was the output. Training was updated weekly to incorporate the latest MRI scan. For comparison, a population-based neural network was implemented, trained, and validated on the leave-one-out scheme. Both algorithms were evaluated by their precision, DICE coefficient, and root mean square surface distance between the manual and computerized segmentations. RESULTS: Training of A-net converged well within 2 h of computations on a computer cluster. A-net segmented the weekly MR with a precision, DICE, and root mean square surface distance of 0.81 ± 0.10, 0.82 ± 0.10, and 2.4 ± 1.4 mm, and outperformed the population-based algorithm with 0.63 ± 0.21, 0.64 ± 0.19, and 4.1 ± 3.0 mm, respectively. CONCLUSION: A-net can be feasibly integrated into the clinical workflow of a longitudinal imaging study and become a valuable tool to facilitate decision- making in adaptive radiotherapy.
引用
- Wang C, Tyagi N, Rimner A, et al. Segmenting lung tumors on longitudinal imaging studies via a patient-specific adaptive convolutional neural network. Radiother Oncol. 2018. PMID: 30773175. doi:10.1016/j.radonc.2018.10.037
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。