Computer-aided diagnosis of human brain tumor through MRI: A survey and a new algorithm
作者：
Highlights：
• We review the recent published segmentation and classification techniques for the brain magnetic resonance images (MRI).
• We proposed a hybrid intelligent technique for automatic detection of brain tumor through MR Images.
• The technique has three stages: segmentation, features extraction/reduction and classification of MR images into normal or abnormal.
• The experiments were carried out on 101 images (14 normal and 87 abnormal) from a real human brain MRI dataset.
• The classification accuracy on both training and test images is 99%.
摘要
•We review the recent published segmentation and classification techniques for the brain magnetic resonance images (MRI).•We proposed a hybrid intelligent technique for automatic detection of brain tumor through MR Images.•The technique has three stages: segmentation, features extraction/reduction and classification of MR images into normal or abnormal.•The experiments were carried out on 101 images (14 normal and 87 abnormal) from a real human brain MRI dataset.•The classification accuracy on both training and test images is 99%.
论文关键词：Human brain tumors,Medical imaging,Medical informatics,Magnetic resonance images,Segmentation,Feature extractions,Classification,Intelligent computer-aided diagnosis systems
论文评审过程：Available online 20 February 2014.
论文官网地址：https://doi.org/10.1016/j.eswa.2014.01.021
