用于预测 RTOG 0522 临床试验中头颈部鳞状细胞癌放射治疗所致口干症的深度学习模型。
A Deep Learning Model for Predicting Xerostomia Due to Radiation Therapy for Head and Neck Squamous Cell Carcinoma in the RTOG 0522 Clinical Trial.
机构信息
University of Pennsylvania, Philadelphia, Pennsylvania; National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.
University of Pennsylvania, Philadelphia, Pennsylvania.
出版信息
Int J Radiat Oncol Biol Phys. 2019 Oct 1;105(2):440-447. doi: 10.1016/j.ijrobp.2019.06.009. Epub 2019 Jun 13.
PURPOSE
Xerostomia commonly occurs in patients who undergo head and neck radiation therapy and can seriously affect patients' quality of life. In this study, we developed a xerostomia prediction model with radiation treatment data using a 3-dimensional (3D) residual convolutional neural network (rCNN). The model can be used to guide radiation therapy to reduce toxicity.
METHODS AND MATERIALS
A total of 784 patients with head and neck squamous cell carcinoma enrolled in the Radiation Therapy Oncology Group 0522 clinical trial were included in this study. Late xerostomia is defined as xerostomia of grade ≥2 occurring in the 12th month of radiation therapy. The computed tomography (CT) planning images, 3D dose distributions, and contours of the parotid and submandibular glands were included as 3D rCNN inputs. Comparative experiments were performed for the 3D rCNN model without 1 of the 3 inputs and for the logistic regression model. Accuracy, sensitivity, specificity, F-score, and area under the receiver operator characteristic curve were evaluated.
RESULTS
The proposed model achieved promising prediction results. The performance metrics for 3D rCNN model with contour, CT images, and radiation therapy dose; 3D rCNN without contour; 3D rCNN without CT images; 3D rCNN without the dose; logistic regression with the dose and clinical parameters; and logistic regression without clinical parameters were as follows: accuracy: 0.76, 0.74, 0.73, 0.65, 0.64, and 0.56; sensitivity: 0.76, 0.72, 0.77, 0.59, 0.72, and 0.75; specificity: 0.76, 0.76, 0.71, 0.69, 0.59, and 0.43; F-score: 0.70, 0.68, 0.69, 0.56, 0.60, and 0.57; and area under the receiver operator characteristic curve: 0.84, 0.82, 0.78, 0.70, 0.74, and 0.68, respectively.
CONCLUSIONS
The proposed model uses 3D rCNN filters to extract low- and high-level spatial features and to achieve promising performance. This is a potentially effective model for predicting objective toxicity for supporting clinical decision making.
目的
口干症常发生于接受头颈部放射治疗的患者，严重影响患者的生活质量。本研究采用三维（3D）残差卷积神经网络（rCNN），利用放射治疗数据建立口干症预测模型，以指导放射治疗降低毒性。
方法和材料
本研究共纳入接受放射治疗肿瘤组 0522 临床试验的 784 例头颈部鳞状细胞癌患者。迟发性口干症定义为放射治疗第 12 个月出现≥2 级口干症。将 CT 规划图像、3D 剂量分布和腮腺及颌下腺轮廓作为 3D rCNN 的输入。比较了没有 3 个输入中的 1 个输入的 3D rCNN 模型和逻辑回归模型的性能。评估准确性、敏感性、特异性、F 分数和接收器操作特性曲线下面积。
结果
提出的模型取得了有希望的预测结果。具有轮廓、CT 图像和放射治疗剂量的 3D rCNN 模型、无轮廓的 3D rCNN、无 CT 图像的 3D rCNN、无剂量的 3D rCNN、具有剂量和临床参数的逻辑回归以及无临床参数的逻辑回归的性能指标分别为：准确性：0.76、0.74、0.73、0.65、0.64 和 0.56；敏感性：0.76、0.72、0.77、0.59、0.72 和 0.75；特异性：0.76、0.76、0.71、0.69、0.69 和 0.43；F 分数：0.70、0.68、0.69、0.56、0.60 和 0.57；以及接收器操作特性曲线下面积：0.84、0.82、0.78、0.70、0.74 和 0.68。
结论
该模型使用 3D rCNN 滤波器提取低水平和高水平的空间特征，取得了令人满意的性能。这是一种预测客观毒性的潜在有效模型，可为支持临床决策提供帮助。
Zotero 插件