Rapid identification of neuronal structures in electronic microscope image using novel combined multi-scale image features

详细信息    查看全文

• 作者：Jingwen Zhao ^{jingwenzhao13@fudan.edu.cn}Author Vitae ; Hui Li ^{Hui_li@fudan.edu.cn}Author Vitae ; Meng Duan ^{mduan11@fudan.edu.cn}Author Vitae ; Shuo Hong Wang ^{sh_wang@fudan.edu.cn}Author Vitae ; Yan Qiu Chen ; ^{chenyq@fudan.edu.cn}Author Vitae
• 关键词：Electronic microscopy ; Membrane ; Neuron segmentation
• 刊名：Neurocomputing
• 出版年：2017
• 出版时间：22 March 2017
• 年：2017
• 卷：230
• 期：Complete
• 页码：152-159
• 全文大小：1064 K
• 卷排序：230

文摘

This paper proposes an incremental scheme to identify the neurons in electronic microscope image. It first computes the probability of each pixel being cell membrane and then determines the image areas of the neurons. Our contributions also include novel combined multi-scale image features that are computationally efficient and provide strong discrimination ability for differentiating membrane pixels from other pixels. Experiment results show that the proposed system offers much higher speed than the compared state-of-the-art methods while produces comparably high accuracy.