Mri Brain Image Segmentation Based on Cascaded Fractional-Order Darwinian Particle Swarm Optimization and Mean Shift

Abstract

Abstract:Image segmentation is an initiative with massive interest in many imaging applications, such as medical images and computer vision. It is considered as a challenging problem, so we need to develop an efficient, fast technique for medical image segmentation. In this paper, the proposed framework is based on two segmentation methods: Fractional-order Darwinian Particle Swarm Optimization (FODPSO) and Mean Shift segmentation (MS). FODPSO is a favorable method for specifying a predefined number of clusters and it can find the optimal set of thresholds with a higher between-class variance in less computational time. In the pre-processing phase,the MRI image is filtered and the skull is removed. In the segmentation phase, the result of FODPSO is used as the input to MS. Finally, we make a validation to thesegmented image.We compared our proposed system with some state of the art segmentation techniques using brain benchmark data set. The experimental results show that the proposed system enhances the accuracy of the MRI brain image segmentation.

Comparative Study and Analysis of Recent Computer Aided Diagnosis Systems for Masses Detection in Mammograms

“…As shown in Table 5, all are analysed to deduce the advantages and the disadvantages of each. As confirmed by Table 5 and the results in Table 3 and Table 4, it is proved that recently the CNNs are deployed to develop CAD systems since it obtains better results than the conventional mass detection models because they can extract features representing the lesions exist in mammograms without feature engineering [7,8]. Based on the datasets comparison, we can conclude that the INbreast and the CBIS-DDSM are the most suitable datasets that can be used to localize lesions.…”

“…Large number of CAD systems are proposed using different machine learning models and now designed using various deep learning models to detect accurately any existing cancers in the screened mammogram for early diagnosis and treatment [4][5][6]. So, this paper mainly introduces a complete survey for the most recent state of art for the developed CADs used in the breast cancer localization and classification as well [7,8]. This paper aims as well to be a starting point for proposing better cancer detection accuracy based on the presented work that is introduced in form of many different views [9][10][11][12][13].…”

Experimental Comparative Study on Autoencoder Performance for Aided Melanoma Skin Disease Recognition

“…In the last years, simultaneously with improvements in the computational power of GPUs, methodologies based on deep learning are mainly characterized as one of the most powerful approaches in image processing, such as [6][7][8][9][10]. Image segmentation has been a hot topic since its emergence and since then many researchers have worked on the detection and segmentation of melanoma.…”

Image segmentation-based optimization algorithms: A Review

“…MRI brain image has many regions like Gray matter, White matter, CSF, skull etc. An efficient segmentation of brain regions must be done which make clinicians, to provide the appropriate treatment [52,53,54]. The MRI brain images are chosen from brain web database.…”