期刊
IMAGING SCIENCE JOURNAL
卷 64, 期 5, 页码 285-297出版社
TAYLOR & FRANCIS LTD
DOI: 10.1080/13682199.2016.1178412
关键词
Image segmentation; Brain tumour; Genetic methods; Feature extraction; Neural network
Segmentation is an important aspect of medical image processing. For improving the accuracy in the detection of tumour and improving the speed of execution in segmentation, a new geneticbased genetic algorithm with fuzzy initialisation and seeded modified region growing (GFSMRG) method with back propagation neural network (BPNN) is proposed and presented in this paper. The proposed system consists of four steps: pre-processing, segmentation, feature extraction and classification. The GFSMRG method and its components, feature extraction and classification are explained in detail. The performance analysis of the GFSMRG method with respect to accuracy and time complexity are also discussed. The performance of this method has been validated both quantitatively and qualitatively by using the performance metrics such as Similarity Index, Jaccard Index, Sensitivity, Specificity and Accuracy.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据