M3Net: A multi-model, multi-size, and multi-view deep neural network for brain magnetic resonance image segmentation
作者：
Highlights：
• A multi-model, multi-size and multi-view deep model for Brain MR Image Segmentation.
• Using both ‘deep’ (U-Net) and ‘shallow’ (BPNN) models to segment Brain MR Images.
• Using multi-size patches extracted on three view planes as the input of our model.
• Using CAE for image restoration and using an atlas to include brain anatomy into U-Nets.
• Outperforms widely used segmentation methods on simulated and clinical MR images.
摘要
•A multi-model, multi-size and multi-view deep model for Brain MR Image Segmentation.•Using both ‘deep’ (U-Net) and ‘shallow’ (BPNN) models to segment Brain MR Images.•Using multi-size patches extracted on three view planes as the input of our model.•Using CAE for image restoration and using an atlas to include brain anatomy into U-Nets.•Outperforms widely used segmentation methods on simulated and clinical MR images.
论文关键词：Brain image segmentation,Deep learning,U-Net,Convolutional auto-encoder,Back propagation neural network,Magnetic resonance imaging image
论文评审过程：Received 10 June 2018, Revised 28 February 2019, Accepted 2 March 2019, Available online 2 March 2019, Version of Record 16 March 2019.
论文官网地址：https://doi.org/10.1016/j.patcog.2019.03.004
