Biomedical image classification based on a feature concatenation and ensemble of deep CNNs

• Main Authors: Nguyen, Long D., Gao, Ruihan, Lin, Dongyun, Lin, Zhiping
• Other Authors: School of Electrical and Electronic Engineering
• Format: Article
• Language: English
• Published: 2021
• Subjects: Engineering::Electrical and electronic engineering; Deep Convolutional Neural Network; Transfer Learning
• Online Access: https://hdl.handle.net/10356/146840
• Institution: Nanyang Technological University

Deep learning and more specifically Convolutional Neural Network (CNN) is a cutting edge technique which has been applied to many fields including biomedical image classification. To further improve the classification performance for biomedical images, in this paper, a feature concatenation method and a feature concatenation and ensemble method are proposed to combine several CNNs with different depths and structures. Three datasets, namely 2D Hela dataset, PAP smear dataset, and Hep-2 cell image dataset, are used as benchmarks for testing the proposed methods. It is shown from experiments that the feature concatenation and ensemble method outperforms each individual CNN, and the feature concatenation method, as well as several state-of-the-art methods in terms of classification accuracy.