When applying a Deep Learning model to medical images, it is crucial to estimate the model uncertainty. Voxel-wise uncertainty is a useful visual marker for human experts and could be used to improve the model's voxel-wise output, such as segmentation. Moreover, uncertainty provides a solid foundation for out-of-distribution (OOD) detection, improving the model performance on the image-wise level. However, one of the frequent tasks in medical imaging is the segmentation of distinct, local structures such as tumors or lesions. Here, the structure-wise uncertainty allows more precise operations than image-wise and more semantic-aware than voxel-wise. The way to produce uncertainty for individual structures remains poorly explored. We propose a framework to measure the structure-wise uncertainty and evaluate the impact of OOD data on the model performance. Thus, we identify the best UE method to improve the segmentation quality. The proposed framework is tested on three datasets with the tumor segmentation task: LIDC-IDRI, LiTS, and a private one with multiple brain metastases cases.
翻译:在对医学图像应用深学习模型时,必须估计模型的不确定性。对于人类专家来说,从Voxel到Voxel的不确定性是一种有用的视觉标记,可用于改进模型的Voxel-wise输出,例如分解。此外,不确定性为在图像水平上进行分解、改进模型性能提供了坚实的基础。然而,医学成像的经常任务之一是将不同的地方结构,如肿瘤或腐蚀进行分解。在这里,结构-逻辑的不确定性使得比图像更精确的操作比图像更准确,比对 voxel-with的识别更准确。为单个结构产生不确定性的方法仍然没有得到很好的探讨。我们提出了一个框架,用以衡量结构性不确定性和评估OOOD数据对模型性能的影响。因此,我们确定了改善分解质量的最佳方法。拟议框架在三个数据集上测试,这三个数据集是肿瘤分解任务:LIDDC-IDRI、LITS和多个脑转移案例的私人数据集。