Automatic classification for solitary pulmonary nodule in CT image by fractal analysis based on fractional Brownian motion model
作者：
Highlights：
• We propose a fractal-based feature set for solitary pulmonary nodule classification.
• The proposed fractal-based feature set is derived from the fractional Brownian motion model.
• The classification results are evaluated by accuracy, sensitivity, specificity, PPV, NPV, and the area under ROC.
• Very high classification performance can be achieved by our proposed method.
• Distinction between malignant and benign nodule can be done in one single post-contrast CT scan.
摘要
•We propose a fractal-based feature set for solitary pulmonary nodule classification.•The proposed fractal-based feature set is derived from the fractional Brownian motion model.•The classification results are evaluated by accuracy, sensitivity, specificity, PPV, NPV, and the area under ROC.•Very high classification performance can be achieved by our proposed method.•Distinction between malignant and benign nodule can be done in one single post-contrast CT scan.
论文关键词：Classification,CT image,Solitary pulmonary nodule,Fractal dimension,Fractional Brownian motion
论文评审过程：Received 21 October 2012, Revised 21 April 2013, Accepted 14 June 2013, Available online 24 June 2013.
论文官网地址：https://doi.org/10.1016/j.patcog.2013.06.017
