The performance of deep neural networks typically increases with the number of training images. However, not all images have the same importance towards improved performance and robustness. In fetal brain MRI, abnormalities exacerbate the variability of the developing brain anatomy compared to non-pathological cases. A small number of abnormal cases, as is typically available in clinical datasets used for training, are unlikely to fairly represent the rich variability of abnormal developing brains. This leads machine learning systems trained by maximizing the average performance to be biased toward non-pathological cases. This problem was recently referred to as hidden stratification. To be suited for clinical use, automatic segmentation methods need to reliably achieve high-quality segmentation outcomes also for pathological cases. In this paper, we show that the state-of-the-art deep learning pipeline nnU-Net has difficulties to generalize to unseen abnormal cases. To mitigate this problem, we propose to train a deep neural network to minimize a percentile of the distribution of per-volume loss over the dataset. We show that this can be achieved by using Distributionally Robust Optimization (DRO). DRO automatically reweights the training samples with lower performance, encouraging nnU-Net to perform more consistently on all cases. We validated our approach using a dataset of 368 fetal brain T2w MRIs, including 124 MRIs of open spina bifida cases and 51 MRIs of cases with other severe abnormalities of brain development.
翻译:深心神经网络的性能通常会随着培训图像的增加而增加。然而,并非所有图像对于提高性能和稳健性都具有同等的重要性。在胎儿大脑MRI中,异常性会加剧发育中的大脑解剖结果与非病理病例相比的变异性。在用于培训的临床数据集中通常可以找到的少量异常病例,不可能公正地代表异常发育大脑的丰富变异性。这导致通过最大限度地提高平均性能以偏向非病理案例的方式来培训的机器学习系统。这个问题最近被称为隐性分解。要适合临床使用,自动分解方法需要可靠地实现病理病例的高质量分解结果。在本文中,我们表明目前最先进的深层次学习管道NNNU-Net的异常案例很难被归纳为看不见的异常案例。为了缓解这一问题,我们建议训练一个深心神经网络,以最大限度地减少对非病理案例的分量损失分布的百分百分率。我们指出,这可以通过使用Drotaly Robust Opart optalitalization, 包括DRIMIs 持续地用我们DRIN 3 样的自动重新测试。