Automatic tumor segmentation in single-spectral MRI using a texture-based and contour-based algorithm

作者：

Highlights：

• We propose a new fully automatic method to detect and segment brain lesions.

• The method is based on a texture-based and a contour-based algorithm.

• The algorithm is independent of multi-spectral MRI, and local or global registration.

摘要

•We propose a new fully automatic method to detect and segment brain lesions.•The method is based on a texture-based and a contour-based algorithm.•The algorithm is independent of multi-spectral MRI, and local or global registration.

论文关键词：MR Imaging,Tumor lesion segmentation,Texture features,Regularized winnow,Skippy greedy snake

论文评审过程：Received 17 April 2016, Revised 9 December 2016, Accepted 25 January 2017, Available online 2 February 2017, Version of Record 7 February 2017.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.01.036