Medical image denoising using multi-resolution transforms

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.

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

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

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.

Distribution of scattered image patterns hinges on morphological and optical characteristics of cells. This paper applied a numerical method to simulate scattered images of real cell morphologies, which were reconstructed from confocal image stacks dyed by fluorescent stains. Two approaches, contourlet transform (CT) and gray level co-occurrence matrix (GLCM), were then used to analyze the simulated scattered images. The results showed that features extracted using GLCM contained more information than those extracted using CT. Higher classification accuracy could be achieved with a single GLCM parameter than CT and GLCM could achieve higher accuracy with fewer parameters than CT when using multiple parameters. Meanwhile, GLCM requires less computational cost. Thus, GLCM is more suitable and efficient than CT for the analysis of cell-scattered images.

Chapter 17 - Automated detection of diabetic retinopathy from gray-scale fundus images using GLCM and GLRLM-based textural features—a comparative study

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.

To recognize patients at high risk of refractory disease, the identification of novel prognostic parameters improving stratification of newly diagnosed Hodgkin Lymphoma (HL) is still needed. This study investigates the potential value of metabolic and texture features, extracted from baseline 18F-FDG Positron Emission Tomography/Computed Tomography (PET) and Contrast-Enhanced Computed Tomography scan (CECT), together with clinical data, in predicting first-line therapy refractoriness (R) of classical HL (cHL) with mediastinal bulk involvement. We reviewed 69 cHL patients who underwent staging PET and CECT. Lesion segmentation and texture parameter extraction were performed using the freeware software LIFEx 6.3. The prognostic significance of clinical and imaging features was evaluated in relation to the development of refractory disease. Receiver operating characteristic curve, Cox proportional hazard regression and Kaplan-Meier analyses were performed to examine the potential independent predictors and to evaluate their prognostic value. Among clinical characteristics, only stage according to the German Hodgkin Group (GHSG) classification system significantly differed between R and not-R. Among CECT variables, only parameters derived from second order matrices (gray-level co-occurrence matrix (GLCM) and gray-level run length matrix (GLRLM) demonstrated significant prognostic power. Among PET variables, SUVmean, several variables derived from first (histograms, shape), and second order analyses (GLCM, GLRLM, NGLDM) exhibited significant predictive power. Such variables obtained accuracies greater than 70% at receiver operating characteristic analysis and their PFS curves resulted statistically significant in predicting refractoriness. At multivariate analysis, only HISTO_EntropyPET extracted from PET (HISTO_EntropyPET ) and GHSG stage resulted as significant independent predictors. Their combination identified 4 patient groups with significantly different PFS curves, with worst prognosis in patients with higher HISTO_EntropyPET values, regardless of the stage. Imaging radiomics may provide a reference for prognostic evaluation of patients with mediastinal bulky cHL. The best prognostic value in the prediction of R versus not-R disease was reached by combining HISTO_EntropyPET with GHSG stage.

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.

Detecting brain tumor early and accurately is crucial for effective treatment and better patient outcomes. Three feature extraction methods are used in this study: Gray Level Run Length Matrix (GLRLM), Gray Level Co-occurrence Matrix (GLCM), and Gray Level Histogram Features (GLHF)—to classify MRI images of the brain. GLCM measures the relationship between pixel intensities to capture texture information, while GLRLM finds patterns of pixels with similar gray levels, showing areas of texture. The histogram method summarizes the overall intensity in the image, highlighting differences between normal and abnormal areas. A Support Vector Machine (SVM), a classifier designed to differentiate between brain tissue affected by tumors and normal tissue, processes these retrieved features. Using a typical MRI dataset, the research assesses how well each feature extraction method supports accurate classification by the SVM. By comparing their performance, the study identifies which technique is best for distinguishing between healthy and tumor regions in the brain. This analysis offers valuable insights into improving brain tumor detection, potentially benefiting clinical diagnosis and treatment planning.

Noisy multimodal brain image registration using markov random field model

Colposcopy plays a vital role in detecting cervical cancer. Artificial intelligence-based methods have been implemented in the literature for the classification of colposcopy images. However, there is a need for a more effective method that can accurately classify cervigrams. In this paper, ColpoClassifier, a hybrid framework for the classification of cervigrams, is proposed, which consists of feature extraction followed by classification. This paper uses a Gray-level co-occurrence matrix (GLCM), a Gray-level run length matrix (GLRLM), and a histogram of gradients (HOG) for feature extraction. These features are combined to form a feature fusion vector of the form GLCM + GLRLM + HOG. The different machine learning classifiers are used for classification by using individual feature vectors as well as feature fusion vectors. The dataset used in this paper is compiled by downloading images from the WHO website. Two variants of this dataset are created, Dataset-I contains images of the aceto-whitening effect, green filter, iodine application, and raw cervigram while Dataset-II only contains images of the aceto-whitening effect. This paper presents the classification performance on all kinds of images with the individual as well as hybrid feature fusion vector and concludes that hybrid feature fusion vectors on aceto-whitening images have given the best results.

In this paper we have proposed statistical methods for detecting fungal disease and classifying based on disease severity levels. Most fruits diseases are caused by bacteria, fungi, virus, etc of which fungi are responsible for a large number of diseases in fruits. In this study images of fruits, affected by different fungal symptoms are collected and categorized based on disease severity. Statistical features like block wise, gray level co-occurrence matrix (GLCM), gray level runlength matrix (GLRLM) are extracted from these images. The nearest neighbor classifier using Euclidean distance was used to classify images as partially affected, moderately affected, severely affected and normal. The average classification accuracies are 91.37% and 86.715% using GLCM and GLRLM features. The average classification accuracy has increased to 94.085% using block wise features.

This paper presents a method of classifying ultrasound medical images towards dealing with two important aspects: (i) optimal feature subset selection for representing ultrasound medical images and (ii) improvement of classification accuracy by avoiding outliers. An objective function combining the concept of between-class distance and within-class divergence among the training dataset has been proposed as the evaluation criteria of feature selection. Searching for the optimal subset of features has been performed using Multi-Objective Genetic Algorithm (MOGA). Applying the proposed criteria, a subset of Grey Level Co-occurrence Matrix (GLCM) and Grey Level Run Length Matrix (GLRLM) based statistical texture descriptors have been identified that maximizes separability among the classes of the training dataset. To avoid the impact of noisy data during classification, Fuzzy Support Vector Machine (FSVM) has been adopted that reduces the effects of outliers by taking into account the level of significance of each training sample. The proposed approach of ultrasound medical image classification has been tested using a database of 679 ultrasound ovarian images and 89.60% average classification accuracy has been achieved.

Magnetic Resonance Imaging (MRI) is a medical imaging technique that has proven to be particularly valuable for examination of the soft tissues in the body. In this paper, a new denoising technique is proposed to remove the Rician noise from Magnetic Resonance Images using block DCT transform. It is well known that the noise in magnetic resonance imaging has a Rician distribution. Unlike additive Gaussian noise, Rician noise is signal dependent, and separating signal from noise is a difficult task. The proposed method adopt a weighted averaging schedule which uses direct component of small block DCTs to evaluate the weights. The proposed approaches were compared with other transform method such as wavelete thresholding methods, and produced much better results.