Title: Cost-sensitive ensemble classification algorithm for medical image

Authors: Minghui Zhang; Haiwei Pan; Niu Zhang; Xiaoqin Xie; Zhiqiang Zhang; Xiaoning Feng

Addresses: Harbin Finance University, Harbin, 150001, China ' Harbin Engineering University, Harbin, 150001, China ' Harbin Engineering University, Harbin, 150001, China ' Harbin Engineering University, Harbin, 150001, China ' Harbin Engineering University, Harbin, 150001, China ' Harbin Engineering University, Harbin, 150001, China

Abstract: Medical image classification is an important part in domain-specific application image mining. In this paper, we quantify the domain knowledge about medical image for feature extraction. We propose a cost-sensitive ensemble classification (CEC) algorithm which uses a new training method and adopts a new method to acquire parameters. In the weak classifier training process, we mark the samples that are wrongly classified in the former iteration, use the method of re-sampling in the samples that are correctly classified, and put all the wrongly classified samples in the next training. The classification can pay more attention to those samples that are hardly classified. The weight parameters of weak classifiers are determined not only by the error rates, but also by their abilities to recognise the positive samples. Experimental results show that our algorithm is more efficient for medical image classification.

Keywords: medical image; domain knowledge; cost-sensitive learning; ensemble classification.

DOI: 10.1504/IJCSE.2018.091763

International Journal of Computational Science and Engineering, 2018 Vol.16 No.3, pp.282 - 288

Received: 18 Jul 2015
Accepted: 23 Feb 2016

Published online: 03 May 2018 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article