Convolutional neural networks (CNNs) have recently emerged as a powerful approach for automatic segmentation of brain tumor subregions on 3D multi-parametric MRI scans. Learning rate is a crucial hyperparameter in the training of CNNs, impacting the performance of the learned model. Different learning rate policies trace unique trajectories in the optimization landscape that converge to local minima with varying generalization properties. In this work, we empirically evaluated nine learning rate policy-optimizer pairs with two state-of-the-art architectures, namely 2D slice-based U-Net and 3D DeepMedicRes, on an augmented brain tumor dataset of 534 subjects. Segmentation performance was quantified in terms of Dice similarity coefficient and Hausdorff distance metrics. The policies were ranked based on the final ranking score (FRS) employed by the BraTS challenge, with the statistical significance of the rankings evaluated by random permutation test. For 2D slice-based U-Net architecture, an overall ranking of learning rate policies showed that the polynomial decay policy with Adam optimizer significantly outperformed other policies for the task of individual and hierarchical segmentation of tumor subregions (p < 10⁻⁴). For 3D segment-based DeepMedicRes architecture, polynomial decay policy with Adam optimizer performed significantly better than all other policies, with the exception of polynomial decay with SGD optimizer for the same task (p < 10⁻⁴). Based on the FRS, polynomial decay policy with Adam and SGD optimizer occupied the top two positions respectively, but the difference was not statistically significant (p > 0.3). These findings were also validated on the BraTS 2019 Validation dataset which comprised of an additional 125 subjects.

卷积神经网络 (CNN) 最近已成为在 3D 多参数 MRI 扫描中自动分割脑肿瘤子区域的强大方法。学习率是 CNN 训练中的一个关键超参数，会影响学习模型的性能。不同的学习率策略跟踪优化环境中的独特轨迹，这些轨迹收敛到具有不同泛化特性的局部最小值。在这项工作中，我们在 534 名受试者的增强脑肿瘤数据集上凭经验评估了具有两种最先进架构的九个学习率策略优化器对，即基于 2D 切片的 U-Net 和 3D DeepMedicRes。分割性能根据 Dice 相似系数和 Hausdorff 距离度量进行量化。根据 BraTS 挑战采用的最终排名分数 (FRS) 对策略进行排名，并通过随机排列测试评估排名的统计显着性。对于基于 2D 切片的 U-Net 架构，学习率策略的总体排名表明，使用 Adam 优化器的多项式衰减策略显着优于其他策略，用于肿瘤子区域的单个和分层分割任务。p < 10 ^-4 )。对于基于 3D 段的 DeepMedicRes 架构，使用 Adam 优化器的多项式衰减策略的性能明显优于所有其他策略，除了使用 SGD 优化器进行相同任务的多项式衰减 ( p < 10 ^-4 )。基于FRS，Adam和SGD优化器的多项式衰减策略分别占据前两位，但差异无统计学意义（p >0.3）。这些发现也在 BraTS 2019 验证数据集上得到了验证，该数据集包含另外 125 名受试者。