Multi-channel multi-scale fully convolutional network for 3D perivascular spaces segmentation in 7T MR images

• Published in: Medical image analysis Vol. 46; pp. 106 - 117
• Main Authors: Lian, Chunfeng, Zhang, Jun, Liu, Mingxia, Zong, Xiaopeng, Hung, Sheng-Che, Lin, Weili, Shen, Dinggang
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.05.2018; Elsevier BV
• Subjects: 7T MR images; Algorithms; Artificial neural networks; Brain; Brain - diagnostic imaging; Brain mapping; Deep learning; Fourier transforms; Fully convolutional networks; Humans; Image enhancement; Image Enhancement - methods; Image filters; Image processing; Image segmentation; Imaging, Three-Dimensional - methods; Localization; Lymphatic System - diagnostic imaging; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Medical imaging; Morphology; Multiscale analysis; Neural networks; Neural Networks, Computer; NMR; Nuclear magnetic resonance; Pattern Recognition, Automated - methods; Perivascular spaces; Radiology; Reproducibility of Results; Segmentation; Sensitivity and Specificity; Deep learning; Fully convolutional networks; 7T MR images; Segmentation; Perivascular spaces

•A novel fully convolutional network to segment perivascular spaces in 7T MR images.•Multi-channel inputs to afford tubular structural information and fine image details.•Multi-scale features to characterize associations between PVSs and adjacent tissues.•Auto-context strategy to provide auxiliary g...