论文标题
探索3D医疗图像细分的结构不确定性
Exploring Structure-Wise Uncertainty for 3D Medical Image Segmentation
论文作者
论文摘要
在将深度学习模型应用于医学图像时，对于估计模型不确定性至关重要。 Voxel的不确定性是人类专家的有用视觉标记，可用于改善模型的体素输出，例如分割。此外，不确定性为分布（OOD）检测提供了坚实的基础，从而提高了图像级别的模型性能。但是，医学成像中经常执行的任务之一是分割不同的局部结构，例如肿瘤或病变。在这里，与图像的不确定性相比，与图像相比，与体素的不确定性相比，与图像相比，与体素的不确定性更为精确。产生各个结构的不确定性的方法仍然很探索。我们提出了一个框架来衡量结构的不确定性，并评估OOD数据对模型性能的影响。因此，我们确定了提高细分质量的最佳UE方法。提出的框架在三个数据集上进行了测试，该数据集具有肿瘤分割任务：LIDC-IDRI，LITS和一个具有多个脑转移病例的私人框架。
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.
