文献速递头颈部肿瘤放疗放疗物理与技术

使用卷积深度学习神经网络自动检测和分割HPV相关口咽癌受累淋巴结

Auto-detection and segmentation of involved lymph nodes in HPV-associated oropharyngeal cancer using a convolutional deep learning neural network.
PubMed 文献 · Clin Transl Radiat Oncol · 2022-06-18

本研究针对90例接受II-IV区颈清扫的淋巴结阳性HPV相关口咽癌患者,利用术前头颈部CT训练基于残差U-net架构的深度学习卷积神经网络(DL-CNN)分割受累淋巴结,并开发淋巴结自动检测模型。测试阶段共识分割掩膜中位Dice为0.92,检测模型AUC为0.98,结论认为该单机构研究展示了自动分割的可行性,但需外部数据集验证以明确其在放疗计划工作流中的作用。

要点

  • DL-CNN测试阶段共识分割掩膜中位Dice为0.92(IQR 0.89-0.95),中位体积相似性为0.97(IQR 0.94-0.99)。
  • 淋巴结自动检测模型区分淋巴结阳性与阴性CT的AUC为0.98。
  • 作者指出未来需包括外部数据集验证的研究以明确该模型在放疗计划工作流中的作用。

核心结论

  • 该单机构研究结果表明,使用DL-CNN可成功实现对HPV相关口咽癌患者的淋巴结自动分割。
  • 作者指出未来需包括外部数据集验证的研究以明确其在更广泛放疗计划工作流中的作用。

研究设计与样本

  • 对90例因淋巴结阳性HPV相关口咽癌接受II-IV区颈清扫的患者,在术前头颈部CT上进行受累淋巴结的真实分割,其中训练/验证集70例、测试集20例。
  • 采用5折交叉验证训练5个基于残差U-net架构的DL-CNN子模型。
  • 通过阈值化分割模型输出开发淋巴结自动检测模型,以区分「淋巴结阳性」与「淋巴结阴性」头颈部CT,并用受试者工作特征曲线下面积(AUC)评估。

主要发现

  • DL-CNN验证阶段,所有子模型分割掩膜的中位Dice≥0.90,中位体积相似性评分≥0.95。
  • 测试阶段,DL-CNN产生的共识分割掩膜中位Dice为0.92(IQR,0.89-0.95),中位体积相似性为0.97(IQR,0.94-0.99),中位Hausdorff距离为4.52 mm(IQR,1.22-8.38)。
  • 检测模型AUC为0.98。

局限性

  • 该研究为单机构研究。
  • 作者指出未来需包括外部数据集验证的研究以明确其在更大放疗肿瘤治疗计划工作流中的作用。

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: Segmentation of involved lymph nodes on head and neck computed tomography (HN-CT) scans is necessary for the radiotherapy planning of early-stage human papilloma virus (HPV) associated oropharynx cancers (OPC). We aimed to train a deep learning convolutional neural network (DL-CNN) to segment involved lymph nodes on HN-CT scans. METHODS: Ground-truth segmentation of involved nodes was performed on pre-surgical HN-CT scans for 90 patients who underwent levels II-IV neck dissection for node-positive HPV-OPC (training/validation [n = 70] and testing [n = 20]). A 5-fold cross validation approach was used to train 5 DL-CNN sub-models based on a residual U-net architecture. Validation and testing segmentation masks were compared to ground-truth masks using predetermined metrics. A lymph auto-detection model to discriminate between "node-positive" and "node-negative" HN-CT scans was developed by thresholding segmentation model outputs and evaluated using the area under the receiver operating characteristic curve (AUC). RESULTS: In the DL-CNN validation phase, all sub-models yielded segmentation masks with median Dice ≥ 0.90 and median volume similarity score of ≥ 0.95. In the testing phase, the DL-CNN produced consensus segmentation masks with median Dice of 0.92 (IQR, 0.89-0.95), median volume similarity of 0.97 (IQR, 0.94-0.99), and median Hausdorff distance of 4.52 mm (IQR, 1.22-8.38). The detection model achieved an AUC of 0.98. CONCLUSION: The results from this single-institution study demonstrate the successful automation of lymph node segmentation for patients with HPV-OPC using a DL-CNN. Future studies, including validation with an external dataset, are necessary to clarify its role in the larger radiation oncology treatment planning workflow.

来源:Clin Transl Radiat Oncol,查看原文。版权归原作者所有。

引用

  1. Taku N, Wahid KA, van Dijk LV, et al. Auto-detection and segmentation of involved lymph nodes in HPV-associated oropharyngeal cancer using a convolutional deep learning neural network. Clin Transl Radiat Oncol. 2022. PMID: 35782963. doi:10.1016/j.ctro.2022.06.007

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。