Active learning with noise modeling for medical image annotation
Active learning with noise modeling for medical image annotation
复制标题
DOI：
10.1109/isbi.2018.8363578
复制
发表时间：
2018-04
期刊：
影响因子：
--
通讯作者：
Jian Wu;S. Ruan;C. Lian;S. Mutic;M. Anastasio;Hua Li
中科院分区：
文献类型：
--
作者：
Jian Wu;S. Ruan;C. Lian;S. Mutic;M. Anastasio;Hua Li
主动学习是一种有效的解决方案，用于选择信息丰富的训练数据集（示例），预定义的分类器从中学习以优化其性能。它已被广泛应用于信息提取、分类和过滤。大多数现有的主动学习方法没有单独考虑图像噪声来指导信息样本的选择，这可能导致次优标注。由于图像中固有的噪声存在，大量的图像，以及不同的成像模式，使用主动学习的医学图像标注是一个更具挑战性的任务。在这项研究中，我们开发了一种新的低秩建模为基础的多标签主动学习（LRMMAL）方法有效的医学图像标注。与传统的主动学习方法不同，LRMAL方法创新性地度量了图像噪声，并将其与样本标签不确定性和标签相关性的度量相结合，形成一种新的采样过程，以确定最具信息量的样本进行标注。在胸部CT图像上的实验结果以及与其他四种多标记主动学习方法的比较表明了LRMMAL方法的上级性能。
Active learning is an effective solution to select informative training datasets (examples) from which a pre-defined classifier learns for optimizing its performance. It has been widely applied for information extraction, classification, and filtering. Most existing active learning methods do not consider image noise separately to guide the selection of informative examples, which might lead to sub-optimal annotation. Due to the intrinsic presence of noise in images, large amount of images, and varied imaging modalities, using active learning for medical image annotation is an even more challenging task. In this study, we develop a novel low-rank modeling-based multi-label active learning (LRMMAL) method for effective medical image annotation. Different to those traditional active learning methods, the LRMMAL method innovatively measures image noise and combines it with the measures of example label uncertainty and label correlation into a new sampling process to determine most informative examples for annotation. Experimental results on thoracic CT images and comparisons with other four multi-label active learning methods illustrate the superior performance of the LRMMAL method.