Tumor volume segmentation on MRI is a challenging and time-consuming process that is performed manually in typical clinical settings. This work presents an approach to automated delineation of head and neck tumors on MRI scans, developed in the context of the MICCAI Head and Neck Tumor Segmentation for MR-Guided Applications (HNTS-MRG) 2024 Challenge. Rather than designing a new, task-specific convolutional neural network, the focus of this research was to propose improvements to the configuration commonly used in medical segmentation tasks, relying solely on the traditional U-Net architecture. The empirical results presented in this article suggest the superiority of patch-wise normalization used for both training and sliding window inference. They also indicate that the performance of segmentation models can be enhanced by applying a scheduled data augmentation policy during training. Finally, it is shown that a small improvement in quality can be achieved by using Gaussian weighting to combine predictions for individual patches during sliding window inference. The model with the best configuration obtained an aggregated Dice Similarity Coefficient (DSCagg) of 0.749 in Task 1 and 0.710 in Task 2 on five cross-validation folds. The ensemble of five models (one best model per validation fold) showed consistent results on a private test set of 50 patients with an DSCagg of 0.752 in Task 1 and 0.718 in Task 2 (team name: andrei.iantsen). The source code and model weights are freely available at www.github.com/iantsen/hntsmrg.

翻译：MRI肿瘤体积分割是一项具有挑战性且耗时的过程，在典型临床环境中通常依赖人工操作。本研究提出了一种基于MRI扫描的头颈部肿瘤自动勾画方法，该方法是在MICCAI头颈部肿瘤分割MR引导应用挑战赛（HNTS-MRG）2024的背景下开发的。与设计新的任务专用卷积神经网络不同，本研究的重点在于改进医学分割任务中常用配置，仅基于传统U-Net架构进行优化。本文实证结果表明：在训练和滑动窗口推理中采用分块归一化方法具有显著优势；通过在训练过程中应用计划性数据增强策略可提升分割模型性能；最后研究证实，在滑动窗口推理阶段采用高斯加权融合各图像块预测结果可小幅提升分割质量。最优配置模型在五折交叉验证中，任务1的聚合Dice相似系数（DSCagg）达到0.749，任务2达到0.710。由五个模型（每折验证集最优模型）组成的集成模型在包含50例患者的私有测试集上表现稳定，任务1的DSCagg为0.752，任务2为0.718（团队名称：andrei.iantsen）。源代码与模型权重已公开于www.github.com/iantsen/hntsmrg。