Modern deep neural networks achieved remarkable progress in medical image segmentation tasks. However, it has recently been observed that they tend to produce overconfident estimates, even in situations of high uncertainty, leading to poorly calibrated and unreliable models. In this work we introduce Maximum Entropy on Erroneous Predictions (MEEP), a training strategy for segmentation networks which selectively penalizes overconfident predictions, focusing only on misclassified pixels. Our method is agnostic to the neural architecture, does not increase model complexity and can be coupled with multiple segmentation loss functions. We benchmark the proposed strategy in two challenging segmentation tasks: white matter hyperintensity lesions in magnetic resonance images (MRI) of the brain, and atrial segmentation in cardiac MRI. The experimental results demonstrate that coupling MEEP with standard segmentation losses leads to improvements not only in terms of model calibration, but also in segmentation quality.

翻译：现代深度神经网络在医学图像分割任务中取得了显著进展。然而，近期研究发现，这类模型即使在高度不确定的情况下，也倾向于产生过度自信的估计，导致模型标定不良、可靠性不足。本文提出错误预测上的最大熵（MEEP），这是一种针对分割网络的训练策略，通过选择性惩罚过度自信的预测，仅关注被错误分类的像素。该方法不依赖特定网络架构，不增加模型复杂度，并可兼容多种分割损失函数。我们在两项具有挑战性的分割任务中评估该策略：脑部磁共振图像（MRI）中的白质高信号病灶分割，以及心脏MRI中的心房分割。实验结果表明，将MEEP与标准分割损失结合使用，不仅能改善模型标定质量，还能提升分割性能。