arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2301.04517cs.CV
收藏

用于衡量分布偏移下血管分割方法性能的新数据集

A new dataset for measuring the performance of blood vessel segmentation methods under distribution shifts

Federal University of São Carlos(圣卡洛斯联邦大学);São Carlos Institute of Physics, University of São Paulo(圣保罗大学圣卡洛斯物理研究所);University of Ottawa(渥太华大学);Ottawa Hospital Research Institute(渥太华医院研究所)

Matheus Viana da Silva, Natália de Carvalho Santos, Julie Ouellette, Baptiste Lacoste, Cesar Henrique Comin

AI总结:

本文提出异构血管分割数据集 VessMAP,通过从大规模未标注数据中筛选典型、非典型及离群图像,评估分割算法在分布偏移和多样样本下的性能。

摘要:

为训练监督式机器学习算法创建数据集可能是一项艰巨任务。医学图像分割尤其如此,因为图像标注通常需要一名或多名专家,而仅为单张图像创建真值标签就可能耗费数小时。此外,被标注样本必须充分代表可能影响成像组织的不同状况,以及图像采集过程中可能出现的变化,这一点至关重要。要实现这一点,只能同时考虑数据集中的典型样本、非典型样本,甚至离群样本。我们介绍了 VessMAP,这是一个异构血管分割数据集,通过从更大的未标注数据集中精心采样相关图像获得。研究还开发了一种方法,用于从基础数据集中选择原型样本和非典型样本,从而定义一组多样化图像,可用于衡量分割算法在彼此高度不同的样本上的性能。为展示该新数据集的潜力,我们证明了神经网络的验证性能会根据用于训练网络的数据划分而发生显著变化。

英文摘要:

Creating a dataset for training supervised machine learning algorithms can be a demanding task. This is especially true for medical image segmentation since one or more specialists are usually required for image annotation, and creating ground truth labels for just a single image can take up to several hours. In addition, it is paramount that the annotated samples represent well the different conditions that might affect the imaged tissues as well as possible changes in the image acquisition process. This can only be achieved by considering samples that are typical in the dataset as well as atypical, or even outlier, samples. We introduce VessMAP, a heterogeneous blood vessel segmentation dataset acquired by carefully sampling relevant images from a larger non-annotated dataset. A methodology was developed to select both prototypical and atypical samples from the base dataset, thus defining an assorted set of images that can be used for measuring the performance of segmentation algorithms on samples that are highly distinct from each other. To demonstrate the potential of the new dataset, we show that the validation performance of a neural network changes significantly depending on the splits used for training the network.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑