论文标题
在基于深度学习的OCT图像中,由于数据泄漏而导致的测试准确性的通胀膨胀
Inflation of test accuracy due to data leakage in deep learning-based classification of OCT images
论文作者
论文摘要
在对光学相干断层扫描(OCT)数据的深入学习应用时,通常使用源自体积数据的2D图像来训练分类网络。鉴于OCT系统的千分尺分辨率,在可见的结构和噪声中,连续图像通常非常相似。因此,不适当的数据拆分可能会导致训练和测试集之间的重叠,其中很大一部分文献忽略了这一方面。在这项研究中,使用三个OCT开放式访问数据集(Kermany's and Srinivasan's Ophthalmology数据集以及AIIMS乳房组织数据集)证明了三个分类任务的数据集分解对模型评估的影响。结果表明,分类性能在MATTHEWS相关系数(准确性:5%至30%)方面膨胀了0.07,对于在数据集中测试的模型不当,突出了数据集处理对模型评估的相当大影响。这项研究旨在提高人们对数据集分裂重要性的认识,因为在对OCT数据上实施深度学习方面的研究兴趣增加。
In the application of deep learning on optical coherence tomography (OCT) data, it is common to train classification networks using 2D images originating from volumetric data. Given the micrometer resolution of OCT systems, consecutive images are often very similar in both visible structures and noise. Thus, an inappropriate data split can result in overlap between the training and testing sets, with a large portion of the literature overlooking this aspect. In this study, the effect of improper dataset splitting on model evaluation is demonstrated for three classification tasks using three OCT open-access datasets extensively used, Kermany's and Srinivasan's ophthalmology datasets, and AIIMS breast tissue dataset. Results show that the classification performance is inflated by 0.07 up to 0.43 in terms of Matthews Correlation Coefficient (accuracy: 5% to 30%) for models tested on datasets with improper splitting, highlighting the considerable effect of dataset handling on model evaluation. This study intends to raise awareness on the importance of dataset splitting given the increased research interest in implementing deep learning on OCT data.