摘要
目的利用深度学习预测鼻咽癌患者疗程中的解剖图像,用于及时发现鼻咽癌患者放疗疗程中可能发生的解剖结构变化。方法收集2020年1月1日至2022年12月31日于中国医学科学院肿瘤医院就诊的230例T 3-T 4期鼻咽癌患者的图像资料,包括计划CT(pCT)和各分次的锥形线束CT(CBCT)图像。使用3D Unet神经网络预测放疗第k+1周的解剖图像,输入包括pCT、第1-3天的CBCT和第2-k周的各1次CBCT。训练了4个模型分别用于预测第3-6周的解剖图像。在预测图像和真实图像上勾画出鼻咽原发肿瘤(GTV_(nx))和左右腮腺,通过评估预测图像和真实图像上勾画结构的一致性来评估模型性能。结果本研究提出的方法能较准确预测整个放疗疗程中的解剖图像。预测与真实图像上感兴趣轮廓的一致性较高,GTV_(nx)、左腮腺、右腮腺的戴斯相似性系数平均值分别为0.96、0.90、0.92,平均豪斯多夫距离分别为3.28、4.18、3.86 mm,平均最小距离分别为0.37、0.70、0.60 mm。结论利用深度学习方法预测鼻咽癌患者疗程中解剖图像的方法准确可行,有助于提前预测和准备治疗策略,实现个性化治疗。
Objective To develop a deep learning method to predict the anatomical images of nasopharyngeal carcinoma patients during the treatment course,which could detect the anatomical variation for specific patients in advance.Methods Imaging data including planning CT(pCT)and cone-beam CT(CBCT)for each fraction of 230 patients with T_(3)-T_(4) staging nasopharyngeal carcinoma who treated in Cancer Hospital Chinese Academy of Medical Sciences from January 1,2020 to December 31,2022 were collected.The anatomical images of week k+1 were predicted using a 3D Unet model with inputs of pCT,CBCT on days 1-3,and CBCT of weeks 2-k.In this experiment,we trained four models to predict anatomical images of weeks 3-6,respectively.The nasopharynx gross tumor volume(GTV_(nx))and bilateral parotid glands were delineated on the predicted and real images(ground truth).The performance of models was evaluated by the consistence of the delineation between the predicted and ground truth images.Results The proposed method could predict the anatomical images over the radiotherapy course.The contours of interest in the predicted image were consistent with those in the real image,with Dice similarity coefficient of 0.96,0.90,0.92,mean Hausdorff distance of 3.28,4.18 and 3.86 mm,and mean distance to agreement of 0.37,0.70,and 0.60 mm,for GTV_(nx),left parotid,and right parotid,respectively.Conclusion This deep learning method is an accurate and feasible tool for predicting the patient's anatomical images,which contributes to predicting and preparing treatment strategy in advance and achieving individualized treatment.
作者
杨碧凝
刘宇翔
张国梁
门阔
戴建荣
Yang Bining;Liu Yuxiang;Zhang Guoliang;Men Kuo;Dai Jianrong(Department of Radiation Oncology,National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital,Chinese Academy of Medical Sciences and Peking Union Medical College,Beijing 100021,China)
出处
《中华放射肿瘤学杂志》
CSCD
北大核心
2024年第4期333-338,共6页
Chinese Journal of Radiation Oncology
基金
中国癌症基金会北京希望马拉松专项基金(LC2022B16)
国家自然科学基金(12205375)。
关键词
鼻咽肿瘤
解剖结构变化
人工智能
深度学习
放射疗法
自适应
Nasopharyngeal neoplasms
Anatomical changes
Artificial intelligence
Deep learning
Radiotherapy,adaptive
