Texture Analysis of Brain MRI and Classification with BPN for the Diagnosis of Dementia

Sivapriya, T. R.; Saravanan, V.; Thangaiah, P. Ranjit Jeba

doi:10.1007/978-3-642-24043-0_56

Cited by 12 publications

(10 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An assessment on identification of dementia is done using texture analysis of brain MRI followed by classification with the back propagation network and wavelets is presented in [2]. The steps for classification are: The region of interest can be obtained from the mri image by GLCM, wavelets and Haralick features.…”

Section: Literature Surveymentioning

confidence: 99%

A Comparative Study on Brain Tumor Diagnosis Techniques Using MRI Image Processing

Pradeepini¹,

Babu²,

Tejaswini³

et al. 2018

IJET

View full text Add to dashboard Cite

Image processing is a technique to carry out certain operations on an image so as to obtain some helpful information from it i.e., an enhanced image would be more advantageous. It is a similar to that of signal processing where input would be the image and the output obtained through this processing would be attributes/characteristics corresponding to that image. Currently, Image processing is one among the trending technologies. It is definitely one significant study area in the fields of engineering and computer science. Medical images have a vital role in the diagnosis of disorders & for checking the accurate functioning of organs. Hence, this is an active research area where several methods are being used and developed in order to make diagnosis facile. This medicinal imaging technology gave the doctors an insight for diagnosis of internal parts of the body. Also it helped doctors in performing Minimally Invasive Surgery, more commonly called as the keyhole surgeries which is done by inserting long and thin instruments into the body through small incisions to reach the internal organs instead of traditional operation techniques. The brain is the utmost important internal organ in our body and tumors effecting it could be very critical and hazardous situation. The brain tumor is a soft intracranial mass made up by irregular growth of cells of the tissue in the brain or around the brain. MRI Imaging play a vital role in brain tumors for evaluation, diagnosis and treatment arrangement.

show abstract

Section: Literature Surveymentioning

confidence: 99%

A Comparative Study on Brain Tumor Diagnosis Techniques Using MRI Image Processing

Pradeepini¹,

Babu²,

Tejaswini³

et al. 2018

IJET

View full text Add to dashboard Cite

show abstract

“…The use of wavelet transform as a multiscale analysis for texture description was first suggested by Mallat [29]. Recent developments in the wavelet transform [30,31] provide good multiresolution analytical tool for texture analysis and can achieve a high accuracy rate.…”

Section: 1texture Analysismentioning

confidence: 99%

An Efficient Wavelet Based Feature Reduction and Classification Technique for the Diagnosis of Dementia

Sivapriya¹

2011

IJCSEIT

View full text Add to dashboard Cite

show abstract

“…Depending on ROI selection, feature extraction procedure and selection, they achieved between 64.3% and 96.4% classification accuracy, and that most texture features correlated with the mini-mental state examination (MMSE) score. Sivapriya et al showed in [104] that texture analysis in brain MRI using wavelets, and classification with back propagation network (BPN) gave high classification accuracy in AD. Li et al [105], extracted 3D texture features from gray level co-occurrence matrix and run length matrix in the hippocampus area of MR images and found that entropy, grey level non-uniformity, and run length non-uniformity showed significant differences between AD patients, patients with mild cognitive impairment (MCI), and normal controls, and that the texture features were correlated with mini-mental state examination (MMSE) score.…”

Section: Texture Analysis In Brain Mri In Dementiamentioning

confidence: 99%

“…Not many have applied texture analysis in a machine learning (ML) environment to successfully discern different dementias from each other and from healthy controls [101,183,106,105,102,104,103]. A contribution of this thesis has been to apply 2D-and 3D texture analysis in white matter (WM), WML regions as well as normal appearing white matter (NAWM) on FLAIR and T1-weighted MR images as a computer based application for dementia diagnosis.…”

Section: Texture Analysis In Ad and Lbdmentioning

confidence: 99%

Classifying Alzheimer's disease, Lewy body dementia, and normal controls using 3D texture analysis in magnetic resonance images

Oppedal

Engan

Eftestøl

et al. 2017

Biomedical Signal Processing and Control

View full text Add to dashboard Cite

IntroductionExpected age is increasing globally and dementia is a common outcome for an increasing number of people. Dementia is a demanding syndrome for the patient and the environment as well as it is costly for society. Damaging changes to the cerebral blood flow also called white matter lesions (WML) are common in the elderly and is expected to increase as age advances. It has been reported that these types of lesions affect cognition in healthy elderly. They are also associated to Alzheimer's disease but have not been much studied in DLB. Quantitative analysis and machine learning have a potential to contribute in understanding the disease process as well as aid in diagnosis. MethodsQuantitative analysis of WML volumes were calculated using an automatic segmentation routine on magnetic resonance images (MRI) of subjects with Alzheimer's disease (AD), Lewy body dementia (LBD), and normal controls (NC). Statistical tests were performed to compare groups as well as to investigate relations to cognition. Additionally, WML volumes were used as features in a machine learning (ML) environment to check whether WML volume were able to classify subjects with AD and LBD from NC. Texture analysis (TA) may be able to document changes at a microstructural level and was performed in WML an non-WML regions of the different types of MRI's (FLAIR and T1). 2D-and 3D TA features were calculated and used in classification with the aim to serve as a tool for computer aided diagnosis (CAD) in dementia. The dataset used was imbalanced meaning that the number of subjects in each group were very different. Two methods for handling the imbalanced data were tested, namely upsampling and cost-sensitive classification.v Results and conclusionsSeverity of WML did neither differ significantly between subjects with dementia and NC nor between mildly demented patients with AD and LBD. WML severity were associated with cognitive decline in AD, but not LBD suggesting that WML contributes to cognitive decline in AD, but not LBD. More studies of the potential clinical impact of WML in patients with LBD are needed.The best classification results obtained using WML volumes as features in an ML framework discerning subjects with dementia from healthy controls were an area under curve (AUC) of 0.73 and 95% confidence interval of 0.57 to 0.83.We experienced better classification results when using TA features compared to WML volumes in classification and better results when performing classification on TA features calculated from T1 MRI compared to FLAIR MRI. A total accuracy, reported as mean with standard deviation in brackets over cross validation folds, of 0.97(0.07) or higher was reported for the dementia vs. NC, AD vs. NC, and LBD vs. NC classification problems for both the 2D-and 3D texture analysis approaches. In the AD vs. LBD case a total accuracy of 0.73(0.16) was reported using the 2D TA approach slightly exceeded by the 3D TA approach were 0.79(0.15) was reported.It seems like the results do not differ much when performing anal...

show abstract

Texture Analysis of Brain MRI and Classification with BPN for the Diagnosis of Dementia

Cited by 12 publications

References 22 publications

A Comparative Study on Brain Tumor Diagnosis Techniques Using MRI Image Processing

A Comparative Study on Brain Tumor Diagnosis Techniques Using MRI Image Processing

An Efficient Wavelet Based Feature Reduction and Classification Technique for the Diagnosis of Dementia

Classifying Alzheimer's disease, Lewy body dementia, and normal controls using 3D texture analysis in magnetic resonance images

Contact Info

Product

Resources

About