标题： 改进U-Net配置以在MRI上自动勾画头颈癌 显示英文标题

标题： Improving the U-Net Configuration for Automated Delineation of Head and Neck Cancer on MRI

摘要： 肿瘤体积分割在MRI上是一个具有挑战性和耗时的过程，在典型的临床环境中通常由人工完成。 这项工作提出了一种在MICCAI头颈肿瘤分割用于MRI引导应用（HNTS-MRG）2024挑战背景下自动划分头颈肿瘤的方法。 而不是设计一个新的特定任务的卷积神经网络，本研究的重点是提出对医学分割任务中常用配置的改进，仅依赖传统的U-Net架构。 本文呈现的实验结果表明，在训练和滑动窗口推理中使用的逐块归一化方法具有优越性。 它们还表明，在训练过程中应用计划的数据增强策略可以提高分割模型的性能。 最后，通过在滑动窗口推理期间使用高斯加权来结合单个补丁的预测，可以实现质量的小幅提升。 最佳配置的模型在五折交叉验证中的任务1获得了0.749的综合Dice相似性系数（DSCagg），任务2获得了0.710。 五个模型的集成（每个验证折叠一个最佳模型）在50名患者的私有测试集上表现出一致的结果，任务1的DSCagg为0.752，任务2的DSCagg为0.718（团队名称：andrei.iantsen）。 源代码和模型权重可在www.github.com/iantsen/hntsmrg免费获得。 显示英文摘要

摘要： 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.