Robust and accurate segmentation for elongated physiological structures is challenging, especially in the ambiguous region, such as the corneal endothelium microscope image with uneven illumination or the fundus image with disease interference. In this paper, we present a spatial and scale uncertainty-aware network (SSU-Net) that fully uses both spatial and scale uncertainty to highlight ambiguous regions and integrate hierarchical structure contexts. First, we estimate epistemic and aleatoric spatial uncertainty maps using Monte Carlo dropout to approximate Bayesian networks. Based on these spatial uncertainty maps, we propose the gated soft uncertainty-aware (GSUA) module to guide the model to focus on ambiguous regions. Second, we extract the uncertainty under different scales and propose the multi-scale uncertainty-aware (MSUA) fusion module to integrate structure contexts from hierarchical predictions, strengthening the final prediction. Finally, we visualize the uncertainty map of final prediction, providing interpretability for segmentation results. Experiment results show that the SSU-Net performs best on cornea endothelial cell and retinal vessel segmentation tasks. Moreover, compared with counterpart uncertainty-based methods, SSU-Net is more accurate and robust.

翻译：细长生理结构的鲁棒精确分割极具挑战性，尤其在光照不均的角膜内皮显微镜图像或存在病变干扰的眼底图像等模糊区域。本文提出一种空间与尺度不确定感知网络（SSU-Net），该网络充分利用空间与尺度不确定性来突出模糊区域并整合分层结构上下文。首先，通过蒙特卡洛dropout近似贝叶斯网络，我们估计认知性和偶然性空间不确定性图。基于这些空间不确定性图，提出门控软性不确定感知（GSUA）模块，引导模型聚焦于模糊区域。其次，提取不同尺度下的不确定性，并提出多尺度不确定感知（MSUA）融合模块，整合分层预测的结构上下文以强化最终预测结果。最后，将最终预测的不确定性图可视化，为分割结果提供可解释性。实验表明，SSU-Net在角膜内皮细胞和视网膜血管分割任务中表现最佳。此外，与同类基于不确定性的方法相比，SSU-Net具有更高的准确性和鲁棒性。