Abstract
Out of distribution (OOD) medical images are frequently encountered, e.g. because of site- or scanner differences, or image corruption. OOD images come with a risk of incorrect image segmentation, potentially negatively affecting downstream diagnoses or treatment. To ensure robustness to such incorrect segmentations, we propose Laplacian Segmentation Networks (LSN) that jointly model epistemic (model) and aleatoric (data) uncertainty in image segmentation. We capture data uncertainty with a spatially correlated logit distribution. For model uncertainty, we propose the first Laplace approximation of the weight posterior that scales to large neural networks with skip connections that have high-dimensional outputs. Empirically, we demonstrate that modelling spatial pixel correlation allows the Laplacian Segmentation Network to successfully assign high epistemic uncertainty to out-of-distribution objects appearing within images.
Abstract (translated)
分布外的医疗图像经常遇到,例如由于站点或扫描仪差异,或者图像损坏等原因。分布外图像有可能导致图像分割不正确,可能对该后续诊断或治疗产生负面影响。为了确保对不正确分割的鲁棒性,我们提出了拉普拉斯分割网络(LSN),该网络同时建模图像分割中的知识(模型)和 aleatoric(数据)不确定性。我们使用空间相关logit分布来捕捉数据不确定性。对于模型不确定性,我们提出了拉普拉斯后估计权重的第一项近似,该近似可以扩展到具有高维输出的 skip 连接的大型神经网络。经验上,我们证明建模空间像素相关性可以让拉普拉斯分割网络成功地将分布外物体在图像中出现的知识不确定性分配给它们。
URL
https://arxiv.org/abs/2303.13123