scholarly journals A simple model for glioma grading based on texture analysis applied to conventional brain MRI

2020 ◽  
Author(s):  
José Gerardo Suárez-García ◽  
Javier Miguel Hernández-López ◽  
Eduardo Moreno-Barbosa ◽  
Benito de Celis-Alonso
Keyword(s):  
Texture Analysis ◽  
Low Cost ◽  
Brain Mri ◽  
Texture Features ◽  
Classification Model ◽  
Low Grade ◽  
Mri Contrast ◽  
Glioma Grading ◽  
Sensitivity Specificity

AbstractAccuracy of glioma grading is fundamental for the diagnosis, treatment planning and prognosis of patients. The purpose of this work was to develop a low cost and easy to implement classification model which distinguishes low grade gliomas (LGGs) from high grade gliomas (HGGs), through texture analysis applied to conventional brain MRI. Different combinations between MRI contrasts (T1Gd and T2) and one segmented glioma region (necrotic and non-enhancing tumor core (NCR/NET)) were studied. Texture features obtained from the Gray Level Size Zone Matrix (GLSZM) were calculated. An under-samplig method was proposed to divide the data into different training subsets and subsequently extract complementary information for the creation of distinct classification models. The sensitivity, specificity and accuracy of the models were calculated. The best model was explicitly reported. The best model included only three texture features and reached a sensitivity, specificity and accuracy of 94.12%, 88.24% and 91.18% respectively. According to the features of the model, when the NCR/NET region was studied, HGGs had a more heterogeneous texture than LGGs in the T1Gd images and LGGs had a more heterogeneous texture than HGGs in the T2 images. These novel results partially contrast with results from literature. The best model proved to be useful for the classification of gliomas. Complementary results showed that heterogeneity of gliomas depended on the studied MRI contrast. The model presented stands out as a simple, low cost, easy to implement, reproducible and highly accurate glioma classifier. What is more important, it should be accessible to populations with reduced economic and scientific resources.

CLASSIFICATION OF BRAIN MRI IMAGES BY USING THE AUTOMATIC SEGMENTATION AND TEXTURE ANALYSIS

2020 ◽  
Vol 3 (4) ◽  
pp. 263-275
Author(s):  
Anastasia Viktorivna Karliuk ◽  
Ievgen Arnoldovich Nastenko ◽  
Olena Kostiantinivna Nosovets ◽  
Vitalii Olegovich Babenko
Keyword(s):  
Brain Tumor ◽  
Texture Analysis ◽  
Pituitary Tumor ◽  
Automatic Segmentation ◽  
Brain Mri ◽  
Magnetic Resonance Tomography ◽  
Texture Features ◽  
Classification Model ◽  
Tumor Type ◽  
Type Definition

Brain tumor is a relatively severe human disease type. Its timely diagnosis and tumor type definition are an actual task in modern medicine. Lately, the segmentation methods on 3D brain images (like computer and magnetic resonance tomography) are used for definition of a certain tumor type. Nevertheless, the segmentation is usually conducted manually, which requires a lot of time and depends on the experience of a doctor. This paper looks at the possibility of creating a method for the automatic segmentation of images. As a training sample, the medical database of MRI brain tomography with three tumor types (meningioma, glioma, and pituitary tumor) was taken. Taking into account the different slices, the base had: 708 examples of meningioma, 1426 examples of glioma, and 930 examples of pituitary tumor. The database authors marked the regions of interest on each image, which were used as a tutor (supervised learning) for automatic segmentation model. Before model creation, currently existing popular automatic segmentation models were analyzed. U-Net deep convolution neural network architecture was used as the most suitable one. As the result of its use, the model was obtained, which can segment the image correctly in seventy four percent of six hundred images (testing sample). After obtaining the automatic segmentation model, the Random Forest models for three “One versus All” tasks and one multiclass task were created for brain tumor classification. The total sample was divided into training (70 %), testing (20 %), and examining (10 %) ones before creating the models. The accuracy of the models in the examining sample varies from 84 to 94 percent. For model classification creation, the texture features were used, obtained by texture analysis method, and created by the co-authors of the Department of Biomedical Cybernetics in the task of liver ultrasound image classification. They were compared with well-known Haralick texture features. The comparison showed that the best way to achieve an accurate classification model is to combine all the features into one stack

scholarly journals A simple model for glioma grading based on texture analysis applied to conventional brain MRI

PLoS ONE ◽  
2020 ◽  
Vol 15 (5) ◽  
pp. e0228972
Author(s):  
José Gerardo Suárez-García ◽  
Javier Miguel Hernández-López ◽  
Eduardo Moreno-Barbosa ◽  
Benito de Celis-Alonso
Keyword(s):  
Simple Model ◽  
Texture Analysis ◽  
Brain Mri ◽  
Glioma Grading

scholarly journals MRI Radiomics to Differentiate Between Low Grade Glioma and Glioblastoma Peritumoral Region

2021 ◽  
Author(s):  
Nauman Malik ◽  
Benjamin Geraghty ◽  
Archya Dasgupta ◽  
Pejman Jabehdar Maralani ◽  
Michael Sandhu ◽  
...  
Keyword(s):  
Feature Selection ◽  
Image Data ◽  
Texture Features ◽  
Low Grade Glioma ◽  
Feature Reduction ◽  
Recursive Feature Elimination ◽  
Low Grade ◽  
Reduction Techniques ◽  
Leave One Out ◽  
Sensitivity Specificity

Abstract Background The peritumoral region (PTR) of glioblastoma (GBM) appears as a T2W-hyperintensity and is characterized by microscopic tumor and edema. Infiltrative low grade glioma (LGG) comprises tumor cells that seem similar to GBM PTR on MRI. The work here explored if a radiomics-based approach can distinguish between LGG and GBM PTR, which can have future implications on existing treatment paradigms. Methods Patients with GBM and LGG imaged using a 1.5 T MRI were included in the study. Image data from cases of GBM PTR, and LGG were manually segmented guided by T2W hyperintensity. A set of 91 first-order and texture features were determined from each of T1W-contrast, and T2W-FLAIR, diffusion-weighted imaging sequences. Applying filtration techniques, a total of 3822 features were obtained. Different feature reduction techniques were employed, and a subsequent model was constructed using four machine learning classifiers. Leave-one-out cross-validation was used to assess classifier performance. Results The analysis included 42 GBM and 36 LGG. The best performance was obtained using AdaBoost classifier using all the features with a sensitivity, specificity, accuracy, and area of curve (AUC) of 91%, 86%, 89%, and 0.96, respectively. Amongst the feature selection techniques, the recursive feature elimination technique had the best results, with an AUC ranging from 0.87 to 0.92. Evaluation with the F-test resulted in the most consistent feature selection with 3 T1W-contrast texture features chosen in over 90% of instances. Conclusions Quantitative analysis of conventional MRI sequences can effectively demarcate GBM PTR from LGG, which is otherwise indistinguishable on visual estimation.

scholarly journals Classificação de imagens multiespectrais LANDSAT TM e feições de textura: mapeamento da cobertura da terra

FLORESTA ◽  
1997 ◽  
Vol 27 (12) ◽  
Author(s):  
RUTH EMÍLIA NOGUEIRA LOCK ◽  
FLÁVIO FELIPE KIRCHNER
Keyword(s):  
Land Cover ◽  
Texture Analysis ◽  
Maximum Likelihood Method ◽  
Texture Features ◽  
Landsat Tm ◽  
Likelihood Method ◽  
Landsat Tm Image ◽  
Tm Image ◽  
Initial Results

Este trabalho mostra os resultados iniciais de uma pesquisa sobre classificação de imagens multiespectrais considerando feições de textura, aplicada ao mapeamento da cobertura da terra, com ênfase na separação das classes de cobertura vegetal. Para tanto foi efetuado um levantamento bibliográfico e estudo sobre o assunto, que está resumido na parte inicial. Na seqüência relata-se a parte prática, onde foi feita a classificação multiespectral da imagem LANDSAT-5 TM da Ilha de São Francisco do Sul-SC, utilizando o algoritmo de classificação Máxima verossimilhança. Para testar as potencialidades das feições de textura foram efetuadas quatro classificações distintas para obter as mesmas informações agrupadas em dez classes. Na primeira etapa foi efetuada somente a classificação multiespectral, nas outras foram consideradas feições de textura e classificação espectral. Classification of LANDSAT TM’s multiespectral images and texture features: land cover mapping Abstract This paper shows the initial results of a research regarding multiespectral image classification using texture analysis for land cover maping. A bibliographic review was conducted wich is disposed in the first part of this work. Following this, a classification of the LANDSAT TM image of São Francisco island, SC, was performed using the Maximum Likelihood Method. To test the texture analysis potentialities, four distinct classifications were performed to obtain the same informations grouped into ten classes. In the first one only a multiespectral classification was performed, and in the other three the texture analysis was considered.

scholarly journals A Review on Brain Tumor Classification Methodologies

2019 ◽  
pp. 346-359 ◽  
Author(s):  
Bichitra Panda ◽  
Chandra Sekhar Panda
Keyword(s):  
Feature Extraction ◽  
Brain Tumor ◽  
Brain Tumors ◽  
Brain Mri ◽  
Tumor Classification ◽  
Low Grade ◽  
High Grade ◽  
Mr Images ◽  
The Brain

Brain tumor is one of the leading disease in the world. So automated identification and classification of tumors are important for diagnosis. Magnetic resonance imaging (MRI)is widely used modality for imaging brain. Brain tumor classification refers to classify the brain MR images as normal or abnormal, benign or malignant, low grade or high grade or types. This paper reviews various techniques used for the classification of brain tumors from MR images. Brain tumor classification can be divided into three phases as preprocessing, feature extraction and classification. As segmentation is not mandatory for classification, hence resides in the first phase. The feature extraction phase also contains feature reduction. DWT is efficient for both preprocessing and feature extraction. Texture analysis based on GLCM gives better features for classification where PCA reduces the feature vector maintaining the accuracy of classification of brain MRI. Shape features are important where segmentation has already been performed. The use of SVM along with appropriate kernel techniques can help in classifying the brain tumors from MRI. High accuracy has been achieved to classify brain MRI as normal or abnormal, benign or malignant and low grade or high grade. But classifying the tumors into more particular types is more challenging.

scholarly journals Texture Analysis to Detect Cerebral Degeneration in Amyotrophic Lateral Sclerosis

2018 ◽  
Vol 45 (5) ◽  
pp. 533-539 ◽  
Author(s):  
Abdullah Ishaque ◽  
Rouzbeh Maani ◽  
Jerome Satkunam ◽  
Peter Seres ◽  
Dennell Mah ◽  
...  
Keyword(s):  
Amyotrophic Lateral Sclerosis ◽  
Texture Analysis ◽  
Brain Mri ◽  
Texture Features ◽  
Visual Assessment ◽  
Image Resolution ◽  
Healthy Controls ◽  
Als Patients ◽  
Lateral Sclerosis ◽  
Cerebral Degeneration

AbstractBackgroundEvidence of cerebral degeneration is not apparent on routine brain MRI in amyotrophic lateral sclerosis (ALS). Texture analysis can detect change in images based on the statistical properties of voxel intensities. Our objective was to test the utility of texture analysis in detecting cerebral degeneration in ALS. A secondary objective was to determine whether the performance of texture analysis is dependent on image resolution.MethodsHigh-resolution (0.5×0.5 mm2 in-plane) coronal T2-weighted MRI of the brain were acquired from 12 patients with ALS and 19 healthy controls on a 4.7 Tesla MRI system. Image data sets at lower resolutions were created by down-sampling to 1×1, 2×2, 3×3, and 4×4 mm2. Texture features were extracted from a slice encompassing the corticospinal tract at the different resolutions and tested for their discriminatory power and correlations with clinical measures. Subjects were also classified by visual assessment by expert reviewers.ResultsTexture features were different between ALS patients and healthy controls at 1×1, 2×2, and 3×3 mm2 resolutions. Texture features correlated with measures of upper motor neuron function and disability. Optimal classification performance was achieved when best-performing texture features were combined with visual assessment at 2×2 mm2 resolution (0.851 area under the curve, 83% sensitivity, 79% specificity).ConclusionsTexture analysis can detect subtle abnormalities in MRI of ALS patients. The clinical yield of the method is dependent on image resolution. Texture analysis holds promise as a potential source of neuroimaging biomarkers in ALS.

scholarly journals Texture Analysis of 18F-FDG PET/CT for Differential Diagnosis Spinal Metastases

2021 ◽  
Vol 7 ◽  
Author(s):  
Xin Fan ◽  
Han Zhang ◽  
Yuzhen Yin ◽  
Jiajia Zhang ◽  
Mengdie Yang ◽  
...  
Keyword(s):  
Texture Analysis ◽  
Diagnostic Performance ◽  
Spinal Metastases ◽  
Texture Features ◽  
Classification Model ◽  
Support Vector ◽  
Kaplan Meier ◽  
Texture Parameters ◽  
Pet Ct ◽  
Fdg Pet Ct

Purpose: To evaluate the value of texture analysis for the differential diagnosis of spinal metastases and to improve the diagnostic performance of 2-deoxy-2-[fluorine-18]fluoro-D-glucose positron emission tomography/computed tomography (18F-FDG PET/CT) for spinal metastases.Methods: This retrospective analysis of patients who underwent PET/CT between December 2015 and January 2020 at Shanghai Tenth People's Hospital due to high FDG uptake lesions in the spine included 45 cases of spinal metastases and 44 cases of benign high FDG uptake lesions in the spine. The patients were randomly divided into a training group of 65 and a test group of 24. Seventy-two PET texture features were extracted from each lesion, and the Mann-Whitney U-test was used to screen the training set for texture parameters that differed between the two groups in the presence or absence of spinal metastases. Then, the diagnostic performance of the texture parameters was screened out by receiver operating characteristic (ROC) curve analysis. Texture parameters with higher area under the curve (AUC) values than maximum standardized uptake values (SUVmax) were selected to construct classification models using logistic regression, support vector machines, and decision trees. The probability output of the model with high classification accuracy in the training set was used to compare the diagnostic performance of the classification model and SUVmax using the ROC curve. For all patients with spinal metastases, survival analysis was performed using the Kaplan-Meier method and Cox regression.Results: There were 51 texture parameters that differed meaningfully between benign and malignant lesions, of which four had higher AUC than SUVmax. The texture parameters were input to build a classification model using logistic regression, support vector machine, and decision tree. The accuracy of classification was 87.5, 83.34, and 75%, respectively. The accuracy of the manual diagnosis was 84.27%. Single-factor survival analysis using the Kaplan-Meier method showed that intensity was correlated with patient survival.Conclusion: Partial texture features showed higher diagnostic value for spinal metastases than SUVmax. The machine learning part of the model combined with the texture parameters was more accurate than manual diagnosis. Therefore, texture analysis may be useful to assist in the diagnosis of spinal metastases.

The role of MRI texture analysis based on susceptibility-weighted imaging in predicting Fuhrman grade of clear cell renal cell carcinoma

2020 ◽  
pp. 028418512095196
Author(s):  
Jun Sun ◽  
Liang Pan ◽  
Tingting Zha ◽  
Wei Xing ◽  
Jie Chen ◽  
...  
Keyword(s):  
Texture Analysis ◽  
Texture Features ◽  
Multivariable Logistic Regression Analysis ◽  
Low Grade ◽  
High Grade ◽  
Grade Group ◽  
Cell Renal Cell Carcinoma ◽  
Fuhrman Grade ◽  
Texture Model

Background The Fuhrman nuclear grade system is one of the most important independent indicators in patients with clear cell renal cell carcinoma (ccRCC) for aggressiveness and prognosis. Preoperative assessment of tumor aggressiveness is important for surgical decision-making. Purpose To explore the role of magnetic resonance imaging (MRI) texture analysis based on susceptibility-weighted imaging (SWI) in predicting Fuhrman grade of ccRCC. Material and Methods A total of 45 patients with SWI and surgically proven ccRCC were divided into two groups: the low-grade group (Fuhrman I/II, n = 29) and the high-grade group (Fuhrman III/IV, n = 16). Texture features were extracted from SWI images. Feature selection was performed, and multivariable logistic regression analysis was performed to develop the SWI-based texture model for grading ccRCCs. Receiver operating characteristic (ROC) curve analysis and leave-group-out cross-validation (LGOCV) were performed to test the reliability of the model. Results A total of 396 SWI-based texture features were extracted from each SWI image. The SWI-based texture model developed by multivariable logistic regression analysis was: SWIscore = –0.59 + 1.60 * ZonePercentage. The area under the ROC curve of the SWI-based texture model for differentiating high-grade ccRCC from low-grade ccRCC was 0.81 (95% confidence interval 0.67–0.94), with 80% accuracy, 56.25% sensitivity, and 93.10% specificity. After 100 LGOCVs, the mean accuracy, sensitivity, and specificity were 90.91%, 91.83%, and 89.89% for the training sets, and 77.29%, 80.52%, and 71.44% for the test sets, respectively. Conclusion SWI-based texture analysis might be a reliable quantitative approach for differentiating high-grade ccRCC from low-grade ccRCC.

scholarly journals Diagnostic Value of Machine Learning-Based Quantitative Texture Analysis in Differentiating Benign and Malignant Thyroid Nodules

2019 ◽  
Vol 2019 ◽  
pp. 1-7
Author(s):  
Bulent Colakoglu ◽  
Deniz Alis ◽  
Mert Yergin
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Texture Analysis ◽  
Thyroid Nodules ◽  
Intraclass Correlation ◽  
Texture Features ◽  
Diagnostic Value ◽  
External Data ◽  
Wrapper Method ◽  
Sensitivity Specificity

Aim. The aim of this study is to evaluate the diagnostic value of machine learning- (ML-) based quantitative texture analysis in the differentiation of benign and malignant thyroid nodules. Materials and methods. A sum of 306 quantitative textural features of 235 thyroid nodules (102 malignant, 43.4%; 133 benign, 56.4%) of a total of 198 patients were investigated using the random forest ML classifier. Feature selection and dimension reduction were conducted using reproducibility testing and a wrapper method. The diagnostic accuracy, sensitivity, specificity, and area under curve (AUC) of the proposed method were compared with the histopathological or cytopathological findings as reference methods. Results. Of the 306 initial texture features, 284 (92.2%) showed good reproducibility (intraclass correlation ≥0.80). The random forest classifier accurately identified 87 out of 102 malignant thyroid nodules and 117 out of 133 benign thyroid nodules, which is a diagnostic sensitivity of 85.2%, specificity of 87.9%, and accuracy of 86.8%. The AUC of the model was 0.92. Conclusions. Quantitative textural analysis of thyroid nodules using ML classification can accurately discriminate benign and malignant thyroid nodules. Our findings should be validated by multicenter prospective studies using completely independent external data.

Sign in / Sign up

Export Citation Format

Share Document