Department of Computer Science and Information Technology, La Trobe University, Melbourne, Australia.
Department of Computer Science and Information Technology, La Trobe University, Melbourne, Australia.
Comput Methods Programs Biomed. 2022 Apr;216:106628. doi: 10.1016/j.cmpb.2022.106628. Epub 2022 Jan 14.
Medical image classification is often challenging for two reasons: a lack of labelled examples due to expensive and time-consuming annotation protocols, and imbalanced class labels due to the relative scarcity of disease-positive individuals in the wider population. Semi-supervised learning methods exist for dealing with a lack of labels, but they generally do not address the problem of class imbalance. Hence, the purpose of this study is to explore a new approach to perturbation-based semi-supervised learning which tackles the problem of applying semi-supervised learning to medical image classification with imbalanced training data.
In this study we propose Adaptive Blended Consistency Loss (ABCL), a simple yet effective drop-in replacement for consistency loss in perturbation-based semi-supervised learning methods. ABCL counteracts data skew by adaptively mixing the target class distribution of the consistency loss in accordance with class frequency. Our proposed method is evaluated and compared with existing methods on two different imbalanced medical image classification datasets. An ablation study is also provided to analyse the properties and effectiveness of our proposed method.
Our experiments with ABCL reveal improvements to unweighted average recall (UAR) when compared with existing consistency losses that are not designed to counteract class imbalance and other existing methods. Our proposed ABCL method is able to improve the performance of the baseline consistency loss approach from 0.59 to 0.67 UAR and outperforms methods that address the class imbalance problem for labelled data (between 0.51 and 0.59 UAR) and for unlabelled data (0.61 UAR) on the imbalanced skin cancer dataset. On the imbalanced retinal fundus glaucoma dataset, ABCL (combined with Weighted Cross Entropy loss) achieves 0.67 UAR, which is an improvement over the best existing approach (0.57 UAR).
Overall the results show the effectiveness of ABCL to alleviate the class imbalance problem for semi-supervised classification for medical images.
医学图像分类通常具有挑战性，原因有二：一是由于昂贵且耗时的注释协议，导致标签示例不足；二是由于疾病阳性个体在更广泛的人群中相对较少，导致类别标签不平衡。存在用于处理标签不足的半监督学习方法，但它们通常无法解决类别不平衡的问题。因此，本研究旨在探索一种基于扰动的半监督学习的新方法，该方法解决了将半监督学习应用于具有不平衡训练数据的医学图像分类的问题。
在本研究中，我们提出了自适应混合一致性损失（ABCL），这是一种简单而有效的替代基于扰动的半监督学习方法中一致性损失的方法。ABCL 通过根据类别频率自适应混合一致性损失的目标类别分布来对抗数据倾斜。我们提出的方法在两个不同的不平衡医学图像分类数据集上进行了评估和比较，并进行了消融研究以分析我们提出的方法的特性和有效性。
我们的 ABCL 实验表明，与未设计用于对抗类别不平衡的现有一致性损失以及其他现有方法相比，UAR 得到了提高。我们提出的 ABCL 方法能够将基线一致性损失方法的性能从 0.59 提高到 0.67 UAR，并且优于针对有标签数据（0.51 至 0.59 UAR）和无标签数据（0.61 UAR）解决类别不平衡问题的方法在不平衡的皮肤癌数据集上。在不平衡的视网膜青光眼数据集上，ABCL（与加权交叉熵损失相结合）可实现 0.67 UAR，优于最佳现有方法（0.57 UAR）。
总体而言，结果表明 ABCL 能够有效缓解医学图像半监督分类中的类别不平衡问题。
