基于每日千伏级CT图像的患者特异性自动分割用于自适应放射治疗
本研究基于首批接受RefleXion系统治疗的患者数据,探索利用迁移学习在每日RefleXion千伏级CT(kVCT)图像上实现深度学习患者特异性自动分割以促进自适应放疗。针对头颈和盆腔癌症,患者特异性网络在头颈3个危及器官和盆腔8个靶区及危及器官的平均DSC分别为0.88和0.90,优于群体网络(0.70和0.63)和配准方法(0.72和0.72)。患者特异性自动分割获得的剂量分布更接近手动轮廓的结果。
要点
- 患者特异性迁移学习网络在头颈和盆腔kVCT图像上分割精度高于群体网络和临床配准方法。
- 患者特异性网络DSC随纵向训练病例数增加而逐渐升高,超过6例训练后趋于饱和。
- 基于患者特异性自动分割的靶区和危及器官平均剂量及剂量体积直方图更接近手动轮廓结果。
核心结论
- 基于患者特异性迁移学习的RefleXion kVCT图像自动分割可实现更高精度,优于常见群体网络和临床基于配准的方法。
- 该方法在提高RefleXion自适应放疗的剂量评估精度方面显示出前景。
研究设计与样本
- 研究基于首批接受RefleXion系统治疗的患者数据,探索深度学习患者特异性自动分割。
- 头颈和盆腔癌症群体数据集分别包含67例和56例患者,用于初始训练深度卷积分割网络。
- 通过迁移学习微调网络权重,将预训练的群体网络适配至特定RefleXion患者。
- 收集6例RefleXion头颈病例和4例盆腔病例,每例使用初始计划CT和5至26套每日kVCT图像分别进行患者特异性学习和评估。
主要发现
- 患者特异性网络在头颈3个感兴趣危及器官的平均DSC为0.88,在盆腔8个靶区及危及器官为0.90。
- 群体网络在头颈和盆腔的平均DSC分别为0.70和0.63,配准方法均为0.72。
- 患者特异性网络的DSC随纵向训练病例数增加而逐渐升高,超过6例训练后趋于饱和。
- 与使用配准轮廓相比,患者特异性自动分割获得的靶区和危及器官平均剂量及剂量体积直方图更接近手动轮廓的结果。
局限性
- 原文未报告局限性。
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: This study explored deep-learning-based patient-specific auto-segmentation using transfer learning on daily RefleXion kilovoltage computed tomography (kVCT) images to facilitate adaptive radiation therapy, based on data from the first group of patients treated with the innovative RefleXion system. METHODS AND MATERIALS: For head and neck (HaN) and pelvic cancers, a deep convolutional segmentation network was initially trained on a population data set that contained 67 and 56 patient cases, respectively. Then the pretrained population network was adapted to the specific RefleXion patient by fine-tuning the network weights with a transfer learning method. For each of the 6 collected RefleXion HaN cases and 4 pelvic cases, initial planning computed tomography (CT) scans and 5 to 26 sets of daily kVCT images were used for the patient-specific learning and evaluation separately. The performance of the patient-specific network was compared with the population network and the clinical rigid registration method and evaluated by the Dice similarity coefficient (DSC) with manual contours being the reference. The corresponding dosimetric effects resulting from different auto-segmentation and registration methods were also investigated. RESULTS: The proposed patient-specific network achieved mean DSC results of 0.88 for 3 HaN organs at risk (OARs) of interest and 0.90 for 8 pelvic target and OARs, outperforming the population network (0.70 and 0.63) and the registration method (0.72 and 0.72). The DSC of the patient-specific network gradually increased with the increment of longitudinal training cases and approached saturation with more than 6 training cases. Compared with using the registration contour, the target and OAR mean doses and dose-volume histograms obtained using the patient-specific auto-segmentation were closer to the results using the manual contour. CONCLUSIONS: Auto-segmentation of RefleXion kVCT images based on the patient-specific transfer learning could achieve higher accuracy, outperforming a common population network and clinical registration-based method. This approach shows promise in improving dose evaluation accuracy in RefleXion adaptive radiation therapy.
引用
- Chen Y, Gensheimer MF, Bagshaw HP, et al. Patient-Specific Auto-segmentation on Daily kVCT Images for Adaptive Radiation Therapy. Int J Radiat Oncol Biol Phys. 2023. PMID: 37141982. doi:10.1016/j.ijrobp.2023.04.026
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。