Ultrasound image segmentation using a novel multi-scale Gaussian kernel fuzzy clustering and multi-scale vector field convolution

作者：

Highlights：

• A novel MsGKFCM clustering technique is proposed.

• For boundary detection MsVFC technique is used.

• The methods are evaluated using JI, DS, HD, AD, Accuracy and F-measure.

• Performed one-way ANOVA test to statistically assess the superiority of the method.

• The Proposed method outperforms among state of art methods in breast US datasets.

摘要

•A novel MsGKFCM clustering technique is proposed.•For boundary detection MsVFC technique is used.•The methods are evaluated using JI, DS, HD, AD, Accuracy and F-measure.•Performed one-way ANOVA test to statistically assess the superiority of the method.•The Proposed method outperforms among state of art methods in breast US datasets.

论文关键词：Ultrasound image segmentation,Speckle reduction,Multi-scale Gaussian kernel induced fuzzy C-means,Multi-scale vector field convolution

论文评审过程：Received 6 September 2017, Revised 4 August 2018, Accepted 10 August 2018, Available online 11 August 2018, Version of Record 25 August 2018.

论文官网地址：https://doi.org/10.1016/j.eswa.2018.08.013