Texture classification of MR images of the brain in ALS using M-CoHOG: A multi-center study

2020 ◽  
Vol 79 ◽  
pp. 101659 ◽  
Author(s):  
G.M. Mashrur E Elahi ◽  
Sanjay Kalra ◽  
Lorne Zinman ◽  
Angela Genge ◽  
Lawrence Korngut ◽  
...  
Keyword(s):  
Texture Classification ◽  
Mr Images ◽  
Multi Center Study ◽  
The Brain ◽  
Center Study

Classification of Brain MR Images Using Corpus Callosum Shape Measurements

2017 ◽  
pp. 1427-1436
Author(s):  
Gaurav Vivek Bhalerao ◽  
Niranjana Sampathila
Keyword(s):  
Neural Network ◽  
Corpus Callosum ◽  
Clustering Algorithm ◽  
Neurological Diseases ◽  
Back Propagation ◽  
Mr Images ◽  
Dementia Patients ◽  
Male Patients ◽  
The Brain

The corpus callosum is the largest white matter structure in the brain, which connects the two cerebral hemispheres and facilitates the inter-hemispheric communication. Abnormal anatomy of corpus callosum has been revealed for various brain related diseases. Being an important biomarker, Magnetic Resonance Imaging of the brain followed by corpus callosum segmentation and feature extraction has found to be important for the diagnosis of many neurological diseases. This paper focuses on classification of T1-weighted mid-sagittal MR images of brain for dementia patients. The corpus callosum is segmented using K-means clustering algorithm and corresponding shape based measurements are used as features. Based on these shape based measurements, a back-propagation neural network is trained separately for male and female dataset. The input data consists of 54 female and 31 male patients. This paper reports classification accuracy up to 92% for female patients and 94% for male patients using neural network classifier.

scholarly journals A Review on Some Classification Methods of Brain Tumor MRI Datasets

2020 ◽  
pp. 421-424
Author(s):  
Nirmal Mungale ◽  
Snehal Kene ◽  
Amol Chaudhary
Keyword(s):  
Brain Tumor ◽  
Brain Mri ◽  
Mr Images ◽  
Classification Techniques ◽  
Abnormal Growth ◽  
Life Threatening ◽  
Magnetic Resonance Imaging Mri ◽  
Recent Classification ◽  
The Brain

Brain tumor is a life-threatening disease. Brain tumor is formed by the abnormal growth of cells inside and around the brain. Identification of the size and type of tumor is necessary for deciding the course of treatment of the patient. Magnetic Resonance Imaging (MRI) is one of the methods for detection of tumor in the brain. The classification of MR Images is a difficult task due to variety and complexity of brain tumors. Various classification techniques have been identified for brain MRI tumor images. This paper reviews some of these recent classification techniques.

Phantoms for texture analysis of MR images. Long-term and multi-center study

2004 ◽  
Vol 31 (3) ◽  
pp. 616-622 ◽  
Author(s):  
Daniel Jirák ◽  
Monika Dezortová ◽  
Milan Hájek
Keyword(s):  
Texture Analysis ◽  
Mr Images ◽  
Multi Center Study ◽  
Center Study

scholarly journals Stability of R2* and quantitative susceptibility mapping of the brain tissue in a large scale multi-center study

2017 ◽  
Vol 7 (1) ◽  
Author(s):  
Rongpin Wang ◽  
Guangyou Xie ◽  
Maoxiong Zhai ◽  
Zhongping Zhang ◽  
Bing Wu ◽  
...  
Keyword(s):  
Brain Tissue ◽  
Large Scale ◽  
Susceptibility Mapping ◽  
Quantitative Susceptibility Mapping ◽  
Multi Center Study ◽  
The Brain ◽  
Center Study

scholarly journals Classification of brain lesions on magnetic resonance imaging using superpixel, PSO and convolutional neural network

2019 ◽  
Author(s):  
Carolina L. S. Cipriano ◽  
Giovanni L. F. Da Silva ◽  
Jonnison L. Ferreira ◽  
Aristófanes C. Silva ◽  
Anselmo Cardoso De Paiva
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Active Regions ◽  
Pso Algorithm ◽  
Resonance Imaging ◽  
Mr Images ◽  
Clinical Routine ◽  
The Brain ◽  
Manual Classification

One of the most severe and common brain tumors is gliomas. Manual classification of injuries of this type is a laborious task in the clinical routine. Therefore, this work proposes an automatic method to classify lesions in the brain in 3D MR images based on superpixels, PSO algorithm and convolutional neural network. The proposed method obtained results for the complete, central and active regions, an accuracy of 87.88%, 70.51%, 80.08% and precision of 76%, 84%, 75% for the respective regions. The results demonstrate the difficulty of the network in the classification of the regions found in the lesions.

scholarly journals Improved Classification of Brain Tumor in MR Images using RNN Classification Framework

2020 ◽  
Vol 9 (3) ◽  
pp. 1098-1101
Keyword(s):  
Brain Tumor ◽  
Pituitary Tumors ◽  
Classification Problem ◽  
Mr Images ◽  
Mri Brain ◽  
Important Constraint ◽  
Classification Framework ◽  
The Brain ◽  
Aided Diagnosis

Classification of brain tumor for medical applications is considered as an important constraint in computer-aided diagnosis (CAD). In this paper, we study the classification of brain tumor by considering the constraint as a classification problem in order to segregate the tumors among pituitary tumors, gliomatumorand meningioma tumor. This method adopts deep learning principle to extract the brain features from the MRI images. In this study, Recurrent Neural Network is used to classify the extracted features from brain. The experiments are carried out in terms of three fold crossvalidation process over MRI brain image dataset. The results show that the proposed RNN classifier classifies the brain tumors effectively with 98% of mean classification accuracy than other existing methods.

scholarly journals Texture Classification of 3D MR Images using 2.5D Rank Filters

2019 ◽  
Vol 8 (12) ◽  
pp. 3078-3081
Keyword(s):  
Augmented Reality ◽  
Computer Games ◽  
External Surface ◽  
Texture Classification ◽  
Mr Images ◽  
Video Memory ◽  
3D Volume

The 3-D items utilized in 3D computer games and augmented reality are empty polygon networks with surfaces concerned them. Then again, volume information portrayal stores the external surface highlights, yet in addition the highlights inside the volume. For instance, representation of 3-D MRI/CT information is tied in with appearing inside parts as well. Envisioning volumetric information requires more video memory. A large portion of the genuine 3D volume information created particularly by MRI scanners is dim dimension pictures. This paper tends to a novel system of texturizing the MRI information slides and its handling for extraction of shallow and volumetric highlights.

Sign in / Sign up

Export Citation Format

Share Document