用于肿瘤调强放射治疗影像分析与转换的深度学习方法

Deep Learning Methods for Image Analysis and Synthesis for Intensity Modulated Radiotherapy: a Review

癌症已成为严重威胁人类健康的主要公共卫生问题。60%~70%的癌症患者需要进行放射治疗。调强放疗是当前主要的临床放疗技术。对近几年基于深度学习的影像分析与转换方法在肿瘤调强放疗计划中的应用进展及关键技术进行综述,包括计算机断层扫描(CT)、锥形束CT(CBCT)、磁共振成像(MRI)、正电子发射断层扫描(PET)引导的肿瘤调强放疗技术应用现状与发展趋势,肿瘤CT/CBCT/MRI/PET影像放疗靶区分割、影像配准以及转换深度卷积神经网络、生成对抗网络的有监督或无监督学习方法,并对未来的研究方向进行展望。

Cancer is a common problem that seriously threatens human health. 60% to 70% of cancer patients need radiotherapy. Currently intensity modulated radiotherapy(IMRT) is one main radiotherapy technique that is widely applied in clinics. This paper reviewed deep learning methods, key technologies and future directions for IMRT, including clinical CT/CBCT/MRI/PET-guided IMRT technologies, and supervised or unsupervised deep convolutional neural networks or generative adversarial networks for the segmentation, registration and image-to-image translation of CT/CBCT/MRI/PET images of tumors.