A New Classifier Fusion Method based on Historical and On-line Classification Reliability for Recognizing Common CT Imaging Signs of Lung Diseases

CT technology developed quickly from the conventional single-slice acquisitions to volume acquisition with multi-slice, hence, it contains more and more image information and can highlight the density difference between the normal and diseased lungs [1]. However, it is time-consuming for radiologists to identify a large number of abnormal lesions from the CT images. Therefore, the problem of recognizing lesions in lung CT images automatically for aiding radiologists in the diagnosis of lung diseases has received extensive attention in recent years.

Source: Computerized Medical Imaging and Graphics - October 13, 2014 Category: Radiology Authors: Ling Ma, Xiabi Liu, Li Song, Chunwu Zhou, Xinming Zhao, Yanfeng Zhao Source Type: research