论文标题
培训后深网的不确定性校准用于医疗图像分割
Post Training Uncertainty Calibration of Deep Networks For Medical Image Segmentation
论文作者
论文摘要
通常对用于自动图像分割的神经网络进行训练以达到最大的准确性，而对置信度评分的校准的关注较少。但是，精心校准的置信分数为用户提供了宝贵的信息。我们研究了几种直接实施的事后校准方法，其中一些是新颖的。将它们与蒙特卡洛（MC）辍学进行了比较。它们被应用于在Brats 2018和Isles 2018上训练经过交叉凝集（CE）和软骰子（SD）损失的神经网络。令人惊讶的是，经过SD损失训练的模型不一定比受过训练的CE损失的模型要少。在所有情况下，至少一种事后方法都改善了校准。结果的一致性有限，因此我们无法得出一种卓越的方法。在所有情况下，事后校准都与MC辍学竞争。尽管与基本模型相比，平均校准有所改善，但校准的主题级方差仍然相似。
Neural networks for automated image segmentation are typically trained to achieve maximum accuracy, while less attention has been given to the calibration of their confidence scores. However, well-calibrated confidence scores provide valuable information towards the user. We investigate several post hoc calibration methods that are straightforward to implement, some of which are novel. They are compared to Monte Carlo (MC) dropout. They are applied to neural networks trained with cross-entropy (CE) and soft Dice (SD) losses on BraTS 2018 and ISLES 2018. Surprisingly, models trained on SD loss are not necessarily less calibrated than those trained on CE loss. In all cases, at least one post hoc method improves the calibration. There is limited consistency across the results, so we can't conclude on one method being superior. In all cases, post hoc calibration is competitive with MC dropout. Although average calibration improves compared to the base model, subject-level variance of the calibration remains similar.
