Multiple sclerosis exploration based on automatic MRI modalities segmentation approach with advanced volumetric evaluations for essential feature extraction

Ghribi, Olfa; Sellami, Lamia; Slima, Mohamed Ben; Mhiri, Chokri; Dammak, Mariem; Hamida, Ahmed Ben

doi:10.1016/j.bspc.2017.07.008

Cited by 27 publications

(18 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this experiment, we compared the proposed MS identification method, FRFE + MLP + ST-Jaya, with state-of-the-art approaches, including GLCM-GLRL [ 8 ], MAMSM [ 9 ], RF [ 10 ], and HWT + LR [ 11 ]. Strict statistical analysis, i.e., the 10 × 10-fold cross validation was implemented.…”

Section: Experiments Results and Discussionmentioning

confidence: 99%

“…The reason is the amplitude-modulation and frequency-modulation are originally designed for communication [ 34 ]. The algorithm with average performance was GLCM-GLRL [ 8 ], which combined gray-level cooccurrence matrix and gray-level run-length matrix. The second-best algorithm was the RF [ 10 ].…”

Section: Experiments Results and Discussionmentioning

confidence: 99%

“…For instances, Ghribi et al [ 8 ] proposed a segmentation method based on gray-level co-occurrence matrix (GLCM) and gray-level run length (GLRL) methods. Murray et al [ 9 ] presented a multiscale amplitude-modulation frequency-modulation (MAMSM) method.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multiple Sclerosis Identification Based on Fractional Fourier Entropy and a Modified Jaya Algorithm

Wang

Cheng

Phillips

et al. 2018

Entropy

View full text Add to dashboard Cite

Aim: Currently, identifying multiple sclerosis (MS) by human experts may come across the problem of "normal-appearing white matter", which causes a low sensitivity. Methods: In this study, we presented a computer vision based approached to identify MS in an automatic way. This proposed method first extracted the fractional Fourier entropy map from a specified brain image. Afterwards, it sent the features to a multilayer perceptron trained by a proposed improved parameter-free Jaya algorithm. We used cost-sensitivity learning to handle the imbalanced data problem. Results: The 10 × 10-fold cross validation showed our method yielded a sensitivity of 97.40 ± 0.60%, a specificity of 97.39 ± 0.65%, and an accuracy of 97.39 ± 0.59%. Conclusions: We validated by experiments that the proposed improved Jaya performs better than plain Jaya algorithm and other latest bioinspired algorithms in terms of classification performance and training speed. In addition, our method is superior to four state-of-the-art MS identification approaches.

show abstract

Section: Experiments Results and Discussionmentioning

confidence: 99%

Section: Experiments Results and Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Multiple Sclerosis Identification Based on Fractional Fourier Entropy and a Modified Jaya Algorithm

Wang

Cheng

Phillips

et al. 2018

Entropy

View full text Add to dashboard Cite

show abstract

“…Even though it has high accuracy but it has some of the limitations such as lack of context, hard to find borders of images. Abdulraqeb et al [17] presented the automatic brain tumor segmentation. He used the MRI images for segmentation of tumor in brain.…”

Section: Related Workmentioning

confidence: 99%

Active Contour Model for Brain MR Tumor Segmentation and Volume Estimation

Kumar*,

Sridevi

2019

IJEAT

View full text Add to dashboard Cite

Brain MR tumor segmentation and estimation of volume is a critical task in medical applications. Brain tumors are analyzed by the common test method known as magnetic resonance imaging (MRI) which provides a detail image of brain. The proposed work involves detection of tumor in brain using deep learning based active contour model. Segmentation is the main objective of the proposed work for achieving detailed information about the tumor and accurate volume estimation to detect the size of the tumor. The Euclidean similarity factor (ESF) is used for considering the spatial distances and intensity differences of the region there by preserving all the fine details of the image. 3D convolutional neural network (3DCNN) is used for extracting the features and segmentation to identify the tumor location in the brain. Finally, shoelace method is used to estimate the volume of the tumor, and it provides treatment planning, surgical methods, estimation of dose, etc. The simulation results in this suggested approach could attain effective performance as compared with the existing approaches.

show abstract

“…Recently, a few studies have focused on MS classification based on convolutional neural networks (CNNs) without lesion segmentation (Wang et al, 2018;Zhang et al, 2018;Marzullo et al, 2019). Zhang et al (2018) have proposed a 10-layer CNN-PreLU-Dropout approach for identifying MS patients based on 2D T 2 -weighted axial MRI data that outperforms other modern MS identification approaches (Murray et al, 2010;Wang et al, 2016;Wu and Lopez, 2017;Ghirbi et al, 2018). Wang et al (2018) have proposed an improved structure of the CNN-PreLU-Dropout approach (Zhang et al, 2018) by incorporating batch normalization, and stochastic pooling applied to the same data and achieved superior performance compared to the original method (Zhang et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

Investigation of Deep-Learning-Driven Identification of Multiple Sclerosis Patients Based on Susceptibility-Weighted Images Using Relevance Analysis

et al. 2020

View full text Add to dashboard Cite

The diagnosis of multiple sclerosis (MS) is usually based on clinical symptoms and signs of damage to the central nervous system, which is assessed using magnetic resonance imaging. The correct interpretation of these data requires excellent clinical expertise and experience. Deep neural networks aim to assist clinicians in identifying MS using imaging data. However, before such networks can be integrated into clinical workflow, it is crucial to understand their classification strategy. In this study, we propose to use a convolutional neural network to identify MS patients in combination with attribution algorithms to investigate the classification decisions. The network was trained using images acquired with susceptibility-weighted imaging (SWI), which is known to be sensitive to the presence of paramagnetic iron components and is routinely applied in imaging protocols for MS patients. Different attribution algorithms were used to the trained network resulting in heatmaps visualizing the contribution of each input voxel to the classification decision. Based on the quantitative image perturbation method, we selected DeepLIFT heatmaps for further investigation. Single-subject analysis revealed veins and adjacent voxels as signs for MS, while the population-based study revealed relevant brain areas common to most subjects in a class. This pattern was found to be stable across different echo times and also for a multi-echo trained network. Intensity analysis of the relevant voxels revealed a group difference, which was found to be primarily based on the T1w magnitude images, which are part of the SWI calculation. This difference was not observed in the phase mask data.

show abstract

Multiple sclerosis exploration based on automatic MRI modalities segmentation approach with advanced volumetric evaluations for essential feature extraction

Cited by 27 publications

References 26 publications

Multiple Sclerosis Identification Based on Fractional Fourier Entropy and a Modified Jaya Algorithm

Multiple Sclerosis Identification Based on Fractional Fourier Entropy and a Modified Jaya Algorithm

Active Contour Model for Brain MR Tumor Segmentation and Volume Estimation

Investigation of Deep-Learning-Driven Identification of Multiple Sclerosis Patients Based on Susceptibility-Weighted Images Using Relevance Analysis

Contact Info

Product

Resources

About