MR医学影像文献Zhan-2017-Multimodal spatial-based segmentatio.pdfVIP

Biomedical Signal Processing and Control 31 (2017) 52–62 Contents lists available at ScienceDirect Biomedical Signal Processing and Control j o u r n a l h o m ep a g e: w w w. elsev /locate/bspc Multimodal spatial-based segmentation framework for white matter lesions in multi-sequence magnetic resonance images Tianming Zhan a,∗ , Renping Yu b , Yu Zheng c , Yongzhao Zhan a , Liang Xiao b , Zhihui Wei b a School of Computer Science Communications Engineering, Jiangsu University, 301, Xuefu Road, Jingkou District, Zhenjiang, Jiangsu 212013, PR China b School of Computer Science Technology, Nanjing University of Science and Technology, 200, Xiaolingwei, Xuanwu District, Nanjing, Jiangsu 210094, PR China c Jiangsu Jingjiang People’s Hospital The Affiliated Hospital with Medical School of Yangzhou University, 28, Zhongzhou Road, Jingjiang, Jiangsu 214500, PR China a r t i c l e i n f o a b s t r a c t Article history: Objective: Multi-sequence magnetic resonance (MR) imaging is a frequently used method for character- Received 24 September 2015 ising and quantifying white matter (WM) lesions in the human brain. The number and size of lesions are Received in revised form 23 June 2016 commonly determined to assess the diseases in clinical settings. Accurate WM lesion segmentation is Accepted 23 June 2016 very important for disease diagnosis and progression surveillance. The goal of this paper is to present an Available online 21 July 2016 approach for improving WM lesion segmentation accuracy.