Densely Connected Neural Network With Unbalanced Discriminant and Category Sensitive Constraints for Polyp Recognition

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

4 Scopus Citations
View graph of relations

Author(s)

  • Wenjian Qin
  • Bulat Ibragimov
  • Guanglei Zhang
  • Bin Han
  • Max Q.-H. Meng
  • Lei Xing

Related Research Unit(s)

Detail(s)

Original languageEnglish
Article number8842597
Pages (from-to)574-583
Journal / PublicationIEEE Transactions on Automation Science and Engineering
Volume17
Issue number2
Online published17 Sep 2019
Publication statusPublished - Apr 2020

Abstract

Automatic polyp recognition in endoscopic images is challenging because of the low contrast between polyps and the surrounding area, the fuzzy and irregular polyp borders, and varying imaging light conditions. In this article, we propose a novel densely connected convolutional network with 'unbalanced discriminant (UD)' loss and 'category sensitive (CS)' loss (DenseNet-UDCS) for the task. We first utilize densely connected convolutional network (DenseNet) as the basic framework to conduct end-to-end polyp recognition task. Then, the proposed dual constraints, UD loss and CS loss, are simultaneously incorporated into the DenseNet model to calculate discriminative and suitable image features. The UD loss in our network effectively captures classification errors from both majority and minority categories to deal with the strong data imbalance of polyp images and normal ones. The CS loss imposes the ratio of intraclass and interclass variations in the deep feature learning process to enable features with large interclass variation and small intraclass compactness. With the joint supervision of UD loss and CS loss, a robust DenseNet-UDCS model is trained to recognize polyps from endoscopic images. The experimental results achieved polyp recognition accuracy of 93.19%, showing that the proposed DenseNet-UDCS can accurately characterize the endoscopic images and recognize polyps from the images. In addition, our DenseNet-UDCS model is superior in detection accuracy in comparison with state-of-the-art polyp recognition methods.

Research Area(s)

  • Category sensitive (CS) loss, densely connected convolutional network (DenseNet), polyp image classification, unbalanced discriminant (UD) loss

Citation Format(s)

Densely Connected Neural Network With Unbalanced Discriminant and Category Sensitive Constraints for Polyp Recognition. / Yuan, Yixuan; Qin, Wenjian; Ibragimov, Bulat; Zhang, Guanglei; Han, Bin; Meng, Max Q.-H.; Xing, Lei.

In: IEEE Transactions on Automation Science and Engineering, Vol. 17, No. 2, 8842597, 04.2020, p. 574-583.

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review