利用基于图像配准的深度学习方法提高磁共振引导前列腺癌放疗自动勾画精度
Improving auto-segmentation accuracy for online magnetic resonance imaging-guided prostate radiotherapy by registration-based deep learning method
王云祥 1杨碧凝 1刘宇翔 1朱冀 1卢宁宁 1戴建荣 1门阔1
作者信息
- 1. 国家癌症中心/国家肿瘤临床医学研究中心/中国医学科学院北京协和医学院肿瘤医院放射治疗科,北京 100021
- 折叠
摘要
目的:改进在线磁共振图像中前列腺靶区和危及器官的自动勾画性能,提高磁共振引导前列腺癌在线自适应放射治疗的效率.方法:对40例接受磁共振引导在线自适应放射治疗的前列腺癌患者进行回顾性研究,其中训练集25例、验证集5例、测试集10例.将模拟定位图像与相应勾画信息和在线磁共振图像进行配准后输入深度学习网络,实现对磁共振图像的自动勾画,并与形变配准方法和单MR输入的深度学习方法进行比较.结果:本文方法的自动勾画准确性整体优于形变配准方法和单MR输入的深度学习方法,临床靶区、膀胱、直肠和左、右侧股骨头的平均Dice相似性指数分别达0.896、0.941、0.840、0.943和0.940.结论:本文方法能有效提高磁共振引导前列腺癌在线自适应放射治疗中自动勾画的准确性和效率.
Abstract
Objective To improve the performance of auto-segmentation of prostate target area and organs-at-risk in online magnetic resonance image and enhance the efficiency of magnetic resonance imaging-guided adaptive radiotherapy(MRIgART)for prostate cancer.Methods A retrospective study was conducted on 40 patients who underwent MRIgART for prostate cancer,including 25 in the training set,5 in the validation set,and 10 in the test set.The planning CT images and corresponding contours,along with online MR images,were registered and input into a deep learning network for online MR image auto-segmentation.The proposed method was compared with deformable image registration(DIR)method and single-MR-input deep learning(SIDL)method.Results The overall accuracy of the proposed method for auto-segmentation was superior to those of DIR and SIDL methods,with average Dice similarity coefficients of 0.896 for clinical target volume,0.941 for bladder,0.840 for rectum,0.943 for left femoral head and 0.940 for right femoral head,respectively.Conclusion The proposed method can effectively improve the accuracy and efficiency of auto-segmentation in MRIgART for prostate cancer.
关键词
前列腺癌/磁共振引导在线自适应放射治疗/图像配准/深度学习/自动勾画Key words
prostate cancer/online magnetic resonance imaging-guided adaptive radiotherapy/image registration/deep learning/auto-segmentation引用本文复制引用
基金项目
国家自然科学基金(11975313)
中国医科院中央级公益性科研院所基本科研业务费专项健康长寿专项(2021-JKCS-003)
出版年
2024
NETL
NSTL
万方数据