Top-rank convolutional neural network and its application to medical image-based diagnosis. (December 2021)

• Record Type: Journal Article
• Authors: Zheng, Yan; Zheng, Yuchen; Suehiro, Daiki; Uchida, Seiichi
• Is Part Of: Pattern recognition. Volume 120(2021)
• Publication Date: 2021-12
• Subjects: Top-rank learning -- Representation learning -- Medical diagnosis; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2021.108138
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: To the authors' best knowledge, this is the first proposal of combining top-rank learning with representation learning for medical image analysis by end-to-end way. The p-norm relaxation of the loss function enables an end-to-end training framework of top-rank learning and representation learning. Results on medical image diagnosis proved that our TopRank CNN achieves more "absolute top samples" (i.e., absolutely positive samples) than other methods. Graphical abstract: Abstract: Top-rank learning identifies a real-valued ranking function that will provide more absolute top samples. These are highly reliable positive samples that are ranked higher than the highest-ranked negative samples. Therefore, top-rank learning is useful for tasks that require reliable decisions. Additionally, it inherits the merits of the ranking functions, such as robustness to the unbalanced condition. However, conventional top-rank learning tasks are formulated as linear or kernel-based problems and are thus limited in coping with complicated tasks. In this study, we propose a Top-rank convolutional neural network (TopRank CNN) to realize top-rank learning with representation learning for complicated tasks. Given that the original objective function of top-rank learning suffers from overfitting, we employ the p -norm relaxation of the original loss function in the proposed method. We prove the usefulness of TopRank CNN experimentally with medical diagnosis tasks that require reliable decisions and robustness to the unbalanced condition.