Wang Yiling, Lombardo Elia, Wang Jie, Fan Yu, Zhao Yue, Corradini Stefanie, Belka Claus, Riboldi Marco, Kurz Christopher, Landry Guillaume
Department of Radiation Oncology, Radiation Oncology Key Laboratory of Sichuan Province, Sichuan Clinical Research Center for Cancer, Sichuan Cancer Hospital & Institute, Sichuan Cancer Center, University of Electronic Science and Technology of China, Chengdu, China.
Department of Radiation Oncology, LMU University Hospital, LMU Munich, Munich, Germany.
Phys Imaging Radiat Oncol. 2025 May 28;34:100789. doi: 10.1016/j.phro.2025.100789. eCollection 2025 Apr.
Deep learning-based tumor tracking is promising for real-time magnetic-resonance-imaging (MRI)-guided radiotherapy. We investigate the applicability of a tumor tracking model developed for 0.35 T MRI-linac sagittal cine-MRI for 1.5 T interleaved orthogonal cine-MRI and implement transfer learning to further improve its performance.
We collected 3600 cine-MRI frames in sagittal, coronal and axial planes from 24 patients (validation 10, testing 14) treated on a 1.5 T MRI-linac, where two expert clinicians manually segmented target labels. A transformer-based deformation model trained on 0.35T MRI-linac images (baseline model, BL) was evaluated and used as a starting point to train patient-specific (PS) models. The Dice similarity coefficient (DSC) and the surface distance (50th and 95th percentiles, SD50%, SD95%) were used to compare the obtained target segmentations with the ground truth labels. The percentage of negative Jacobian determinant values (NegJ), accounting for the folding pixel ratio, was determined.
Outperformed by all the PS models, the BL model averaged in a DSC of 0.85, SD50% of 1.9 mm, SD95% of 5.9 mm and NegJ of 0.45 % in testing. The best PS model averaged in a DSC of 0.90, SD50% of 1.3 mm, SD95% of 3.9 mm and NegJ of 0.02 % in testing.
We have found the 0.35 T model trained on sagittal cine-MRIs cannot be directly applied to a 1.5 T interleaved orthogonal cine-MRI system. However, PS transfer learning could improve the target tracking performance and reach an accuracy comparable to the inter-observer variability.
基于深度学习的肿瘤追踪技术在实时磁共振成像（MRI）引导放疗中具有广阔前景。我们研究了为0.35T MRI直线加速器矢状位电影MRI开发的肿瘤追踪模型在1.5T交错正交电影MRI中的适用性，并实施迁移学习以进一步提高其性能。
我们从24例在1.5T MRI直线加速器上接受治疗的患者（10例用于验证，14例用于测试）中收集了矢状面、冠状面和轴位的3600帧电影MRI图像，由两名专业临床医生手动分割目标标签。对在0.35T MRI直线加速器图像上训练的基于Transformer的变形模型（基线模型，BL）进行评估，并以此为起点训练患者特异性（PS）模型。使用骰子相似系数（DSC）和表面距离（第50和第95百分位数，SD50%，SD95%）将获得的目标分割结果与真实标签进行比较。确定负雅可比行列式值（NegJ）的百分比，以计算折叠像素比例。
在测试中，BL模型的表现不如所有PS模型，其DSC平均为0.85，SD50%为1.9mm，SD95%为5.9mm，NegJ为0.45%。最佳PS模型在测试中的DSC平均为0.90，SD50%为1.3mm，SD95%为3.9mm，NegJ为0.02%。
我们发现，在矢状位电影MRI上训练的0.35T模型不能直接应用于1.5T交错正交电影MRI系统。然而，PS迁移学习可以提高目标追踪性能，达到与观察者间变异性相当的准确性。
