Optimizing Medical Image Classification Using Diverse Feature Extraction Methods for Brain Tumor

PURPOSEMost factors identified in prior studies on meningioma enlargement are qualitative, with limited quantitative evaluation. Predicting future tumor growth from initial imaging of incidentally discovered meningiomas could inform treatment decisions. This study quantitatively evaluates imaging data at diagnosis to identify characteristics associated with tumor enlargement. METHODSWe compared MRI T2 features from the initial imaging of 10 patients in a clearly enlarged group with 10 in a non-enlarged group. Using 3D Slicer and Slicer Radiomics plug-ins, we created a program to set regions of interest (ROIs) in the tumor and calculate various features. Additional ROIs were placed in the outer tumor edge, brain, and white matter contralateral to the tumor. Inter-ROI ratios of features were calculated and compared using PyRadiomics software. We analyzed 107 features across seven classifications: one-dimensional statistics, shape features, Gray Level Co-occurrence Matrix, Gray Level Run Length Matrix, Gray Level Size Zone Matrix, Gray Level Dependence Matrix, and Neighbouring Gray Tone Difference Matrix. A t-test was conducted to identify significant predictors. RESULTSTwenty-four features showed significant differences (p<0.05), including 10 one-dimensional statistics, 1 shape feature, 5 Gray Level Co-occurrence Matrix, 6 Gray Level Run Length Matrix, 1 Gray Level Size Zone Matrix, and 1 Gray Level Dependence Matrix. CONCLUSIONSWe identified potential quantitative predictors of incidentally discovered meningioma growth. Future analysis with a larger sample size will refine these predictors and support the development of a predictive formula and corresponding program.

The major hurdle for segmenting lung lobes in computed tomographic (CT) images is to identify fissure regions, which encase lobar fissures. Accurate identification of these regions is difficult due to the variable shape and appearance of the fissures, along with the low contrast and high noise associated with CT images. This paper studies the effectiveness of two texture analysis methods - the gray level co-occurrence matrix (GLCM) and the gray level run length matrix (GLRLM) - in identifying fissure regions from isotropic CT image stacks. To classify GLCM and GLRLM texture features, we applied a feed-forward back-propagation neural network and achieved the best classification accuracy utilizing 16 quantized levels for computing the GLCM and GLRLM texture features and 64 neurons in the input/hidden layers of the neural network. Tested on isotropic CT image stacks of 24 patients with the pathologic lungs, we obtained accuracies of 86% and 87% for identifying fissure regions using the GLCM and GLRLM methods, respectively. These accuracies compare favorably with surgeons/radiologists' accuracy of 80% for identifying fissure regions in clinical settings. This shows promising potential for segmenting lung lobes using the GLCM and GLRLM methods.

Relationship of CT Radiomics and Dose Texture to Radiation-Induced Swallow Dysfunction in Head and Neck Cancer

Texture is one of the most important features in the analysis of images. It has been increasingly used in computer vision applications. In this study, the ability of three statistical texture analysis measures to perform lamb grading were compared with respect to the classification accuracy. The texture measures examined were the grey level difference method (GLDM), the spatial grey level co-occurrence matrix (GLCM) and the grey level run length matrix (GLRM). In addition, some image geometric features were also measured. The dimensionality of the input feature space was reduced using principal component analysis (PCA). The classification was performed using individual reduced feature sets and their combinations. Both discriminant function analysis (DFA) and artificial neural network (ANN) analysis were used for classification of lamb chop images into different grades. The results indicated that GLCM is the best texture measure, of the three texture measures considered, for lamb grading. The geometric features also performed equally well. Both GLCM and geometric features performed better than GLRM and GLDM. The higher classification performance was achieved by combining feature sets. The ANN produced higher classifications than DFA

Magnetic Resonance Imaging plays a vital part in diagnosis of mutant cells in the endometrial layer of women reproductive system. This Endometrial carcinoma (EC) is one among the type of uterine cancer acts as a major challenge for the medical practitioners for early diagnosis and classification. This study explores advanced imaging techniques and artificial intelligence (AI) for improved EC identification. The Methodology incudes, an approach of extracting texture features using Local Binary Patterns (LBP), Histogram of Oriented Gradients (HOG), Gray Level Co-occurrence Matrix (GLCM), and Gray Level Run Length Matrix (GLRLM) from the image data. These features are fused using a hybrid approach to capture complementary information. Machine learning classifiers including Random Forest (RF), Radial Basis Function (RBF), Artificial Neural Network (ANN), Support Vector Machine (SVM), Extreme Learning Machine (ELM), and Adaptive Neuro-Fuzzy Inference System (ANFIS) are trained and evaluated. Results demonstrate significant improvements in classification accuracy, with the hybrid feature extraction method achieving significant accuracy. Explainable AI (XAI) techniques are employed to interpret and visualize classifier decisions, providing details into the discriminative features contributing to EC classification.. The findings support the potential of integrating advanced imaging and machine learning, facilitated by XAI, for precise EC diagnosis and therapeutic planning.

Lung cancer is one among the major causes of cancer related deaths. Fortunately, an early stage diagnosis can increase the survival rates of the patients. Sputum cytology is one of the easiest and cost-effective method for lung cancer diagnosis. Chances of misdiagnosis and sampling error related to sputum cytology led to the concept of malignancy associated changes. Malignancy associated changes (MAC) are the subtle changes that happens to the normal appearing cells near or distant from the malignant cells. Literature suggests that these changes can be used as an indicator for lung cancer rather than using malignant cells which are very less in number compared to the normal appearing cells in sputum cytology images. The proposed work is intended to detect cells with MAC from sputum smear images. Analysis of nuclei texture features of sputum cell nuclei using Gray Level Co-occurrence Matrix and Gray Level Run Length Matrix from both normal and cancer patients revealed that both type of cells could be differentiated. Among 110 texture features calculated for each nuclei, a set of 35 features which clearly distinguishes normal cells and normal appearing cells were chosen. Support Vector Machine (SVM) classifier is used to classify the cells into two classes i.e cells with MAC and cells without MAC. This study demonstrates that the presence of MAC cells in conventional microscopic sputum cytology images can be identified using image processing techniques and it can have some significance in the early detection of lung cancer.

In recent times, the detection of brain tumour is a common fatality in the field of the health community. Generally, the brain tumor is an abnormal mass of tissue where the cells grow up and increase uncontrollably, apparently unregulated by mechanisms that control cells. A number of techniques have been developed so far; however, the time consumption in detecting brain tumor is still a challenge in the field of image processing. This paper intends to propose a new detection model even accurately. The model includes certain processes like Preprocessing, Segmentation, Feature Extraction and Classification. Particularly, two extreme processes like contrast enhancement and skull stripping are processed under initial phase, in the segmentation process, this paper uses Fuzzy Means Clustering (FCM) algorithm. Both Gray Level Co-occurrence Matrix (GLCM) as well as Gray-Level Run-Length Matrix (GRLM) features are extracted in feature extraction phase. Moreover, this paper uses Deep Belief Network (DBN) for classification. The DBN is integrated with the optimization approach, and hence this paper introduces the optimized DBN, for which Grey Wolf Optimization (GWO) is used here. The proposed model is termed as GW-DBN model. The proposed model compares its performance over other conventional methods in terms of Accuracy, Specificity, Sensitivity, Precision, Negative Predictive Value (NPV), F 1 Score and Matthews Correlation Coefficient (MCC), False negative rate (FNR), False positive rate (FPR) and False Discovery Rate (FDR), and proven the superiority of proposed work.

Traditionally, the quality traits of meat products have been determined by means of physico-chemical methods. As an alternative, computer vision algorithms applied on MRI have been proposed, mainly, because of the non-destructive, non-ionizing and innocuous nature of MRI. Usually, the computer vision algorithms developed to analyze meat quality are based in classical textures. In this paper, a new texture algorithm (called RTA, Radial Texture Algorithm) based on the radial distribution of the images and second order statistics is proposed. The results obtained by RTA were compared to the obtained by means of three well known classical texture algorithms: GLCM (Gray Level Co-occurrence Matrix), GLRLM (Gray Level Run Length Matrix) and NGLDM (Neighbouring Gray Level Dependence Matrix) and correlated to the results obtained by means of physico-chemical methods. GLRLM and NGLDM achieved correlation coefficients between 0.50 and 0.75 whereas RTA and GLCM reached very good to excellent relationship (R > 0.75) for the quality parameters of loins. RTA achieved the best results (0.988 for moisture, 0.883 for lipid content and 0.992 for salt content). These high correlation coefficients confirm the new algorithm as a firm alternative to the classical computational approaches in order to compute the quality traits of meat products in a non-destructive and efficient way.

Accurate glioma grading plays an important role in patient treatment. To investigate the influence of varied texture retrieving models on the efficacy of grading glioma with support vector machine (SVM). Retrospective. In all, 117 glioma patients including 25, 29, and 63 grade II, III, and IV gliomas, respectively, based on WHO 2007. 3.0T MRI/ T1 WI, T2 fluid-attenuated inversion recovery, contrast enhanced T1 , arterial spinal labeling, diffusion-weighted imaging (0, 30, 50, 100, 200, 300, 500, 800, 1000, 1500, 2000, 3000, and 3500 sec/mm2 ), and dynamic contrast-enhanced. Texture attributes from 30 parametric maps were retrieved using four models, including Global, gray-level co-occurrence matrix (GLCM), gray-level run-length matrix (GLRLM), and gray-level size-zone matrix (GLSZM). Attributes derived from varied models were input into radial basis function SVM (RBF-SVM) combined with attribute selection using SVM-recursive feature elimination (SVM-RFE). The SVM model was trained and established with 80% randomly selected data of each category using 10-fold crossvalidation. The model performance was further tested using the remaining 20% data. Ten-fold crossvalidation was used to validate the model performance. Based on 30 parametric maps, 90, 240, 390, or 390 texture attributes were retrieved using the Global, GLCM, GLRLM, or GLSZM model, respectively. SVM-RFE was able to reduce attribute redundancy as well as improve RBF-SVM performance. Training data were oversampled by applying the Synthetic Minority Oversampling Technique (SMOTE) method to overcome the data imbalance problem; test results were able to further demonstrate the classifying performance of the final models. GLSZM using gray-level 64 was the optimal model to retrieve powerful image texture attributes to produce enough classifying power with an accuracy / area under the curve of 0.760/0.867 for the training and 0.875/0.971 for the independent test. Fifteen attributes were selected with SVM-RFE to provide comparable classifying efficacy. When using image textures-based SVM classification of gliomas, the GLSZM model in combination with gray-level 64 and attribute selection may be an optimized solution. 2 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;49:1263-1274.

An MRI radiomics approach to predict the efficacy of chemotherapy for osteosarcoma.

Breast cancer is one of the main causes of death in women and ranks first in cancer cases in Indonesia. Therefore, an early detection and prevention of breast cancer is necessary, one of which is through mammography procedures. A machine learning classifier such as Support Vector Machines (SVM) could be used as an aid to the doctors and radiologist in diagnosing breast cancer from the mammogram images. The aim of this paper is to compare two feature extraction methods used in SVM, namely the Gray Level Co-Occurrence Matrix (GLCM) and first order with two kernels for each method, namely Gaussian and Polynomial. Classification using SVM method is carried out by testing several parameters such as the value of C, gamma, degree and varying the pixel spacing values ​​in GLCM, which usually in previous studies only used the default pixel spacing. The dataset consists of 500 mammogram images containing 250 benign and malignant images, respectively. This study is expected to find out the best method with the highest accuracy between these two texture feature extractions and and able to distinguish between benign and malignant classes correctly. The result achieved that Gray Level Co-Occurrence Matrix (GLCM) feature extraction method with both Gaussian and Polynomial kernel yields the best performance with an accuracy of 89%.

Background The impact of variable b-value combinations on apparent diffusion coefficient (ADC)-based radiomics features has not been fully addressed in literature. Purpose To investigate the correlation between radiomics features extracted from ADC maps and various b-value combinations in cervical cancer. Material and Methods Diffusion-weighted images (b-values: 0, 600, 800, and 1000 s/mm2) of 20 patients with cervical cancer were included. Tumors were identified with the largest transversal cross-section and manually segmented by radiologist. For each b-value combination, 92 radiomics features were extracted and coefficient of variance (CV) was used to evaluate the robustness of radiomics features with different b-value combinations. Features with CV &gt; 5% were normalized by the mean feature variation across the group. Results Out of a total of 92 radiomics features, 18 were classified as robust features with CV ≤5%. Among the rest (CV &gt; 5%), 11, 23, and 40 features demonstrated 5%&lt; CV ≤10%, 10%&lt; CV ≤20%, and CV &gt; 20%, respectively. A subset of features in each category (CV &gt; 5%) showed strong correlation with the b-value combination variation, including 44% (7/16) features in gray level co-occurrence matrix, 62% (8/13) features in gray level dependence matrix, 64% (9/14) features in first order, 50% (8/16) features in gray level run length matrix, 57% (8/14) features in gray level size matrix, and 20% (1/5) features in neighborhood gray-tone difference matrix. Conclusions Variations in b-value combinations demonstrated impact on radiomics features extracted from ADC maps for cervical cancer. The radiomics features with CV &lt;5% can be considered as robust features and are recommended to be used in multicenter radiomics studies.

Chili is a type of vegetable that has a very high economic value. The problem that often occurs in chili plants is that many agricultural losses are caused by disease. Plant diseases are always considered a very serious problem in all countries because economic growth is largely dependent on the agricultural sector in developing countries. In some plant, diseases sometimes caused by bacteria, viruses and fungi. To anticipate this problem, a method designed into a classification system for diagnosing chili leaf disease by applying the Gray Level Cooccurrence Matrix (GLCM) feature extraction method. Then classified using the Support Vector Machine (SVM) method. The output classification of disease diagnoses in chili obtained an overall accuracy level of 88%. The results obtained prove that the method of extracting the features of Gray Level Co-occurrence Matrix (GLCM) and Support Vector Machine (SVM) can be applied to diagnosing chili plants disease.

MRI is the most important technique, in detecting the brain tumor. In this paper data mining methods are used for classification of MRI images. A new hybrid technique based on the support vector machine (SVM) and fuzzy c-means for brain tumor classification is proposed. The purposed algorithm is a combination of support vector machine (SVM) and fuzzy c-means, a hybrid technique for prediction of brain tumor. In this algorithm the image is enhanced using enhancement techniques such as contrast improvement, and mid-range stretch. Double thresholding and morphological operations are used for skull striping. Fuzzy c-means (FCM) clustering is used for the segmentation of the image to detect the suspicious region in brain MRI image. Grey level run length matrix (GLRLM) is used for extraction of feature from the brain image, after which SVM technique is applied to classify the brain MRI images, which provide accurate and more effective result for classification of brain MRI images.

Medical image denoising using multi-resolution transforms