文献速递头颈部肿瘤放疗放疗物理与技术

卷积神经网络用于7通道多参数MRI头颈肿瘤分割的留一分析

Convolutional neural networks for head and neck tumor segmentation on 7-channel multiparametric MRI: a leave-one-out analysis.
PubMed 文献 · Radiat Oncol · 2020-07-29

本研究基于头颈癌患者的多参数MRI(含T2w、增强前后T1w、T2*、灌注和扩散序列共7个输入通道),训练卷积神经网络(CNN)分割原发肿瘤和淋巴结转移。通过留一通道分析比较各通道对分割性能的贡献,发现去除T2*通道对Dice相似系数(DSC)影响最大,去除ADC通道影响最小,提示可优先保留信息量大的序列以缩短扫描时间。

要点

  • CNN分割DSC最高达0.65。
  • 去除T2*通道对原发瘤和淋巴结转移的DSC影响最大(ΔDSC分别5.7%和5.8%)。
  • 去除ADC通道对分割性能影响最小(ΔDSC分别2.4%和2.2%)。

核心结论

  • 通过留一通道分析可识别对头颈肿瘤自动分割贡献最大的MRI序列,从而优化扫描协议、缩短扫描时间,并可能辅助放疗计划中GTV的定义。

研究设计与样本

  • 头颈癌患者接受多参数MRI(T2w、增强前后T1w、T2*、灌注ktrans和ve、扩散ADC),在放化疗前及期间共3个时间点采集。
  • 以7个MRI对比通道和手动定义的GTV(原发肿瘤和淋巴结转移)训练CNN进行病灶分割。
  • 将含全部通道的参考CNN与逐一剔除一个通道训练的CNN比较,以识别各通道对分割任务的贡献,并采用统计分析处理分割性能的随机波动。

主要发现

  • CNN分割性能最高DSC为0.65。
  • 不含T2*数据的网络结果通常最差,与原发肿瘤和淋巴结转移相比含全部通道网络ΔDSC分别为5.7%和5.8%。
  • ADC输入通道对分割性能影响最小,原发肿瘤和淋巴结转移ΔDSC分别为2.4%和2.2%。

临床怎么用

  • 可优先保留对自动分割贡献大的MRI序列(如T2*),减少信息冗余序列以缩短扫描时间、提高患者配合度。
  • 优化后的CNN可辅助放疗计划中GTV的定义。

局限性

  • 研究为留一通道分析,样本量和统计效能未在摘要中报告。
  • CNN最高DSC为0.65,分割性能仍有提升空间。
  • 试验为回顾性注册(DRKS00003830),未报告外部验证结果。

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

BACKGROUND: Automatic tumor segmentation based on Convolutional Neural Networks (CNNs) has shown to be a valuable tool in treatment planning and clinical decision making. We investigate the influence of 7 MRI input channels of a CNN with respect to the segmentation performance of head&neck cancer. METHODS: Head&neck cancer patients underwent multi-parametric MRI including T2w, pre- and post-contrast T1w, T2*, perfusion (ktrans, ve) and diffusion (ADC) measurements at 3 time points before and during radiochemotherapy. The 7 different MRI contrasts (input channels) and manually defined gross tumor volumes (primary tumor and lymph node metastases) were used to train CNNs for lesion segmentation. A reference CNN with all input channels was compared to individually trained CNNs where one of the input channels was left out to identify which MRI contrast contributes the most to the tumor segmentation task. A statistical analysis was employed to account for random fluctuations in the segmentation performance. RESULTS: The CNN segmentation performance scored up to a Dice similarity coefficient (DSC) of 0.65. The network trained without T2* data generally yielded the worst results, with ΔDSCGTV-T = 5.7% for primary tumor and ΔDSCGTV-Ln = 5.8% for lymph node metastases compared to the network containing all input channels. Overall, the ADC input channel showed the least impact on segmentation performance, with ΔDSCGTV-T = 2.4% for primary tumor and ΔDSCGTV-Ln = 2.2% respectively. CONCLUSIONS: We developed a method to reduce overall scan times in MRI protocols by prioritizing those sequences that add most unique information for the task of automatic tumor segmentation. The optimized CNNs could be used to aid in the definition of the GTVs in radiotherapy planning, and the faster imaging protocols will reduce patient scan times which can increase patient compliance. TRIAL REGISTRATION: The trial was registered retrospectively at the German Register for Clinical Studies (DRKS) under register number DRKS00003830 on August 20th, 2015.

来源:Radiat Oncol,查看原文。版权归原作者所有。

引用

  1. Bielak L, Wiedenmann N, Berlin A, et al. Convolutional neural networks for head and neck tumor segmentation on 7-channel multiparametric MRI: a leave-one-out analysis. Radiat Oncol. 2020. PMID: 32727525. doi:10.1186/s13014-020-01618-z

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。