METHODS: A pre-trained model was developed using 120 scans with ring and tandem applicator on a 3T magnetic resonance (MR) scanner (RT3). Four OARs were segmented and evaluated. Segmentation performance was evaluated by Volumetric Dice Similarity Coefficient (vDSC), 95 % Hausdorff Distance (HD95), surface DSC, and Added Path Length (APL). The model was fine-tuned on three out-of-distribution target groups. Pre- and post-TL outcomes, and influence of number of fine-tuning scans, were compared. A model trained with one group (Single) and a model trained with all four groups (Mixed) were evaluated on both seen and unseen data distributions.
RESULTS: TL enhanced segmentation accuracy across target groups, matching the pre-trained model\'s performance. The first five fine-tuning scans led to the most noticeable improvements, with performance plateauing with more data. TL outperformed training-from-scratch given the same training data. The Mixed model performed similarly to the Single model on RT3 scans but demonstrated superior performance on unseen data.
CONCLUSIONS: TL can improve a model\'s generalizability for OAR segmentation in MR-guided cervical brachytherapy, requiring less fine-tuning data and reduced training time. These results provide a foundation for developing adaptable models to accommodate clinical settings.
方法:在3T磁共振(MR)扫描仪(RT3)上使用环形和串联涂药器进行120次扫描,开发了预训练模型。对四个OAR进行了分段和评估。分割性能通过体积骰子相似系数(vDSC)进行评估,95%Hausdorff距离(HD95),表面DSC,并添加路径长度(APL)。该模型在三个分布外的目标群体上进行了微调。前和后TL结果,以及微调扫描次数的影响,进行了比较。在观察到的和未观察到的数据分布上评估用一组训练的模型(单个)和用所有四组训练的模型(混合)。
结果:TL提高了目标群体的分割精度,匹配预训练模型的性能。前五次微调扫描导致了最明显的改进,随着更多数据的增加,性能趋于稳定。在给定相同的训练数据的情况下,TL的性能优于从头开始训练。混合模型在RT3扫描上的表现类似于单一模型,但在看不见的数据上表现出卓越的性能。
结论:TL可以提高MR引导的颈椎近距离放射治疗中OAR分割模型的普适性,需要较少的微调数据和减少的训练时间。这些结果为开发适应临床环境的适应性模型提供了基础。