Top-rank convolutional neural network and its application to medical image-based diagnosis

作者：

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.

摘要

•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.

论文关键词：Top-rank learning,Representation learning,Medical diagnosis

论文评审过程：Received 25 September 2020, Revised 29 January 2021, Accepted 28 June 2021, Available online 29 June 2021, Version of Record 10 July 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108138