White Matter, Gray Matter and Cerebrospinal Fluid Segmentation from Brain Magnetic Resonance Imaging Using Adaptive U-Net and Local Convolutional Neural Network. (14th September 2021)

• Record Type: Journal Article
• Authors: Bao, Pham The; Tuan, Tran Anh; Tuan, Tran Anh; Thuy, Le Nhi Lam; Kim, Jin Young; Tavares, João Manuel R S
• Is Part Of: Computer journal. Volume 65:Number 12(2022)
• Page Start: 3081
• Page End: 3090
• Publication Date: 2021-09-14
• Subjects: medical imaging -- image segmentation -- deep learning -- brain magnetic resonance imaging segmentation -- convolutional neural network -- adaptive U-net -- sure and unsure regions -- local convolutional neural network; Computers -- Periodicals; 005.1
• DOI: 10.1093/comjnl/bxab127
• Languages: English
• ISSNs: 0010-4620

Abstract

Abstract: According to the World Alzheimer Report 2015, 46 million people are living with dementia in the world. The diagnosis of diseases helps doctors treating patients better. One of the signs of diseases is related to white matter, grey matter and cerebrospinal fluid. Therefore, the automatic segmentation of three tissues in brain imaging especially from magnetic resonance imaging (MRI) plays an important role in medical analysis. In this research, we proposed an effective approach to segment automatically these tissues in three-dimensional (3D) brain MRI. First, a deep learning model is used to segment the sure and unsure regions. In the unsure region, another deep learning model is used to classify each pixel. In the experiments, an adaptive U-net model is used to segment the sure and unsure regions, and the Local Convolutional Neural Network (CNN) model with multiple inputs is used to classify each pixel only in the unsure region. Our method was evaluated with a real image database, Internet Brain Segmentation Repository database, with 18 persons (IBSR 18) (https://www.nitrc.org/projects/ibsr ) and compared with state of art methods being the results very promising.