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.
翻译:在医学图像分析中,经常会出现不同来源的图像,例如不同设备产生的图像或图像损坏。这种情况会导致错误的图像分割,从而可能对后续的诊断或治疗产生负面影响。为了确保对这些错误分割具有鲁棒性,我们提出了Laplacian分割网络(LSN),该网络同时建模了图像分割的基于模型的不确定性(推测性不确定性)和基于数据的不确定性(数据不确定性)。我们将数据不确定性表示为空间相关的逻辑分布。对于模型不确定性,我们提出了基于拉普拉斯近似的权重后验概率模型,适用于具有高维输出和跳跃连接的大型神经网络。实验结果表明,采用空间像素相关性建模可以使Laplacian分割网络成功地将高的推测不确定性分配给在图像内部出现的“域外”(即不在训练数据中的)物体。