Astaraki Mehdi, Toma-Dasu Iuliana
Department of Medical Radiation Physics, Stockholm University, Stockholm, Sweden.
Department of Oncology-Pathology, Karolinska Institutet, Solna, Sweden.
Head Neck Tumor Segm MR Guid Appl (2024). 2025;15273:112-122. doi: 10.1007/978-3-031-83274-1_8. Epub 2025 Mar 3.
The adoption of online adaptive MR-guided radiotherapy (MRgRT) for Head and Neck Cancer (HNC) treatment faces challenges due to the complexity of manual HNC tumor delineation. This study focused on the problem of HNC tumor segmentation and investigated the effects of different preprocessing techniques, robust segmentation models, and ensembling steps on segmentation accuracy to propose an optimal solution. We contributed to the MICCAI Head and Neck Tumor Segmentation for MR-Guided Applications (HNTS-MRG) challenge which contains segmentation of HNC tumors in Task1) pre-RT and Task2) mid-RT MR images. In the internal validation phase, the most accurate results were achieved by ensembling two models trained on maximally cropped and contrast-enhanced images which yielded average volumetric Dice scores of (0.680, 0.785) and (0.493, 0.810) for (GTVp, GTVn) on pre-RT and mid-RT volumes. For the final testing phase, the models were submitted under the team's name of "Stockholm_Trio" and the overall segmentation performance achieved aggregated Dice scores of (0.795, 0.849) and (0.553, 0.865) for pre- and mid-RT tasks, respectively. The developed models are available at https://github.com/Astarakee/miccai24.
由于头颈部癌（HNC）手动肿瘤轮廓勾画的复杂性，采用在线自适应磁共振引导放疗（MRgRT）治疗HNC面临挑战。本研究聚焦于HNC肿瘤分割问题，研究了不同预处理技术、稳健分割模型和集成步骤对分割准确性的影响，以提出最佳解决方案。我们参与了医学图像计算与计算机辅助干预国际会议（MICCAI）的头颈部肿瘤磁共振引导应用分割（HNTS-MRG）挑战赛，该挑战赛包括在任务1）放疗前和任务2）放疗中期磁共振图像中对HNC肿瘤进行分割。在内部验证阶段，通过集成在最大裁剪和对比度增强图像上训练的两个模型获得了最准确的结果，在放疗前和放疗中期体积上，（GTVp，GTVn）的平均体积骰子系数得分分别为（0.680，0.785）和（0.493，0.810）。在最终测试阶段，模型以“Stockholm_Trio”团队的名义提交，放疗前和放疗中期任务的总体分割性能分别获得了聚合骰子系数得分（0.795，0.849）和（0.553，0.865）。所开发的模型可在https://github.com/Astarakee/miccai24获取。
