Multiple Sclerosis Detection Based on Biorthogonal Wavelet Transform, RBF Kernel Principal Component Analysis, and Logistic Regression

Wang, Shuihua; Zhan, Tianming; Chen, Yi; Zhang, Yin; Yang, Ming; Lu, Huimin; Wang, Hainan; Liu, Bin; Phillips, P. Jonathon

doi:10.1109/access.2016.2620996

Cited by 107 publications

(41 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this experiment, we compared our CNN-DO-BN-SP method with traditional AI methods: Multiscale AM-FM (Murray et al, 2010 ), ARF (Nayak et al, 2016 ), BWT-LR (Wang et al, 2016 ), 4-level HWT (Wu and Lopez, 2017 ), and MBD (Zhang et al, 2017 ). The results were presented in Table 10 .…”

Section: Experiments Results and Discussionmentioning

confidence: 99%

“…For instances, Murray et al ( 2010 ) proposed to use multiscale amplitude modulation and frequency modulation (AM-FM) to identify MS. Nayak et al ( 2016 ) presented a novel method, combining AdaBoost with random forest (ARF). Wang et al ( 2016 ) combined biorthogonal wavelet transform (BWT) and logistic regression (LR). Wu and Lopez ( 2017 ) used four-level Haar wavelet transform (HWT).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multiple Sclerosis Identification by 14-Layer Convolutional Neural Network With Batch Normalization, Dropout, and Stochastic Pooling

et al. 2018

Self Cite

View full text Add to dashboard Cite

Aim: Multiple sclerosis is a severe brain and/or spinal cord disease. It may lead to a wide range of symptoms. Hence, the early diagnosis and treatment is quite important.Method: This study proposed a 14-layer convolutional neural network, combined with three advanced techniques: batch normalization, dropout, and stochastic pooling. The output of the stochastic pooling was obtained via sampling from a multinomial distribution formed from the activations of each pooling region. In addition, we used data augmentation method to enhance the training set. In total 10 runs were implemented with the hold-out randomly set for each run.Results: The results showed that our 14-layer CNN secured a sensitivity of 98.77 ± 0.35%, a specificity of 98.76 ± 0.58%, and an accuracy of 98.77 ± 0.39%.Conclusion: Our results were compared with CNN using maximum pooling and average pooling. The comparison shows stochastic pooling gives better performance than other two pooling methods. Furthermore, we compared our proposed method with six state-of-the-art approaches, including five traditional artificial intelligence methods and one deep learning method. The comparison shows our method is superior to all other six state-of-the-art approaches.

show abstract

Section: Experiments Results and Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Multiple Sclerosis Identification by 14-Layer Convolutional Neural Network With Batch Normalization, Dropout, and Stochastic Pooling

et al. 2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…Artificial Neural Networks (ANN) are currently one of the main techniques applied by the scientific community (FAN et al, 2013). Several techniques can be used, such as Multilayer Perceptron (MLP) (BOUGHRARA et al, 2016), Radial Basis Function (RBF) (WANG et al, 2016), Extreme Learning Machine (ELM) (SA JUNIOR; BACKES, 2016), Fuzzy Logic (KIM; KIM; KIM, 2015), Genetic Algorithms (GA) (MOREIRA et al, 2018). Another efficient method is genetic programming (GP), that generate knowledge base vectors.…”

Section: Classificationmentioning

confidence: 99%

Computer vision systems in unmanned aerial vehicle: a review

Mendes

Borille

2019

jme

View full text Add to dashboard Cite

Inspections in areas of difficult access or hostile to the human, pattern recognition, surveillance and monitoring, are some of the many applications in with Unmanned Aerial Vehicles (UAV), can be a solution, opening up new perspectives for the use of this technology. The navigation and the position of the UAVs can be made by autonomous method through the computational vision, which is a technology of construction of artificial systems capable of read information from images or any multidimensional data and making decisions. This work presents a review of the use of computer vision systems by UAVs, with a focus on its many applications. The main objective is to analyze the latest technologies used for the development of computer vision in UAVs, through the tools of data search, information storage and, mainly, processing and analysis of data. The researches encompasses a publication of recent works, 2011 onwards, from the Science Direct portal. For each work were analyzed the objectives, methodology and results. Based in this analysis, was made a comparison between the techniques and their challenges. From this, future outlook scenarios of UAVs using computational vision are mentioned.

show abstract

“…The biorthogonal wavelet transform is found to be efficient for transforming the input MRI image. The transformed image can be further efficiently analyzed with the principal component analysis [27]. From the analyzed image, the lesion of the MS [28,29] can be efficiently detected with the regression model.…”

Section: Related Workmentioning

confidence: 99%

An Approach for Analyzing Noisy Multiple Sclerosis Images Using Truncated Beta Gaussian Mixture Model

Anuradha¹,

Satyanarayana²,

Srinivas³

2018

IJIGSP

View full text Add to dashboard Cite

Abstract-Sclerosis is a disease that triggers mainly due to damage of nerve cells in the brain and spinal cord. Various impairments are observed with this disease. Analyzing this type of images is needed for the medical research field for early stage identification. So, the present paper uses Bivariate Gaussian Mixture distribution for analyzing the noisy sclerosis images. For this, the present paper uses neural network for classification. The proposed method is evaluated with various images of brain web repository and the results show the efficiency of the proposed method.

show abstract

Multiple Sclerosis Detection Based on Biorthogonal Wavelet Transform, RBF Kernel Principal Component Analysis, and Logistic Regression

Cited by 107 publications

References 65 publications

Multiple Sclerosis Identification by 14-Layer Convolutional Neural Network With Batch Normalization, Dropout, and Stochastic Pooling

Multiple Sclerosis Identification by 14-Layer Convolutional Neural Network With Batch Normalization, Dropout, and Stochastic Pooling

Computer vision systems in unmanned aerial vehicle: a review

An Approach for Analyzing Noisy Multiple Sclerosis Images Using Truncated Beta Gaussian Mixture Model

Contact Info

Product

Resources

About