Tumor Detection in MRI Brain Images Based on Saliency Computational Modeling. Issue 5 (2020)

• Record Type: Journal Article
• Authors: Jian, Muwei; Zhang, Xianxin; Ma, Lifu; Yu, Hui
• Is Part Of: IFAC-PapersOnLine. Volume 53:Issue 5(2020)
• Page Start: 43
• Page End: 46
• Publication Date: 2020
• Subjects: Brain image -- leision region -- saliency detection -- morphology -- saliency modeling; Automatic control -- Periodicals; 629.805
• DOI: 10.1016/j.ifacol.2021.04.123
• Languages: English
• ISSNs: 2405-8963

Abstract

Abstract: In recent years, the issue of tumor detection for Magnetic Resonance Imaging (MRI) brain images has become a research hotspot in the field of medical imaging, multimedia and pattern recognition. In this paper, we propose a tumor detection method based on saliency modeling for MRI brain images. Firstly, in order to overcome the influence of the skull, we utilize the morphological method to strip the skull of the MRI brain images. Then, we introduce a principal local contrast based saliency-detection method to enhance the foreground regions which facilitates to get the leision region. Finally, the results are further improved by denoising, segmentation and morphological operations. Experiments performed on MRI brain images show that the proposed method is useful and effective.