Feature Extraction Analysis for Diabetic Retinopathy Detection Using Machine Learning Techniques

Diabetic Retinopathy (DR) is a microangiopathic complication of diabetes mellitus that can cause visual impairment to permanent blindness. Early detection of DR is essential to prevent disease progression, but conventional methods require time, cost, and expertise that are not always available. This study aims to compare the performance of the Random Forest (RF) and Support Vector Machine (SVM) algorithms in DR classification based on texture features extracted from retinal fundus images. The dataset used consists of 3,000 retinal fundus images obtained from the Kaggle platform, divided into 2,400 training data and 600 test data. Image preprocessing includes conversion to grayscale, resizing to a resolution of 128×128 pixels, and normalization. Feature extraction is performed using a combination of Local Binary Pattern (LBP) and Gray Level Co-occurrence Matrix (GLCM) to produce a 14-dimensional feature vector. Performance evaluation uses accuracy, precision, recall, F1-score, ROC curve, and 5-fold cross-validation metrics. The results showed that Random Forest significantly outperformed SVM with an accuracy of 96% compared to 64%, an AUC value of 0.99 compared to 0.72, and an average cross-validation accuracy of 94.5% compared to 63.42%. Random Forest also showed balanced performance in both classes with precision, recall, and F1-score of 0.96, while SVM experienced classification imbalance especially in the disease class. This study proves that Random Forest is a more optimal algorithm for an automatic DR detection system based on fundus image texture features and can support increasing the accessibility of DR screening in areas with limited specialist medical personnel.

Palm tree detection using remote sensing images has received increasing attention in recent years, concerning the issues of sustainability, productivity and profitability. There has been significant progress in the research of using machine learning techniques, especially convolutional neural networks (CNNs) for automatic palm tree detection. However, whether CNNs can actually outperform traditional human-engineered approaches in terms of classification accuracy and detection speed is yet unknown. In the present study, we have compared human-engineered features namely histogram of oriented gradients (HOG), local binary pattern (LBP) and scale-invariant feature transform (SIFT) with features extracted using pre-trained AlexNet model for detecting palm trees in high resolution images obtained via unmanned aerial vehicle (UAV). Support vector machines (SVM) with linear and non-linear kernels were used to classify feature vectors obtained by different feature extractors. Haar-like features used in Viola-Jones framework was also tested in the study. Results showed that features extracted from the fifth convolutional layer of AlexNet achieved the highest accuracy of 96.1% using SVM with RBF kernel as classifier, which surpassed the accuracy obtained by fully-connected CNN, namely 95.6%. The results also suggest that SVM classifier with radial basis function (RBF) kernel using LBP as features is the optimal combination as it achieved comparable accuracy but higher detection speed than CNN approaches.

One of the most common causes of death worldwide is skin cancer and its incidence is increasing. To achieve optimal treatment and improve clinical outcomes for patients, precision skin cancer detection and classification approaches are required, which can be achieved through the application of feature extraction and machine learning algorithms. The development of such algorithms to identify important patterns from skin cancer image datasets enables early detection and more accurate classification and more effective treatment. Although previous studies have tried to detect skin cancer using feature extraction techniques such as HFF, HOG, and GLCM, some weaknesses still need to be improved. This research aims to combine various feature extraction methods such as Gray Level Co-occurrence Matrix, Histogram Oriented Gradients, and Local Binary Patterns and machine learning algorithms such as Support Vector Machine, Random Forest, and Gaussian Naïve Bayes in the classification process between Melanoma and Nevus skin cancers. In this research, the number of datasets used is 17,397 derived from the ISIC Dataset. The results showed that the Histogram Oriented Gradients method with Support Vector Machine algorithm achieved the highest accuracy of 92%. The combination of Gray Level Co-occurrence Matrix and Local Binary Patterns with Random Forest algorithm also achieved an accuracy of 92%, the combination of Gray Level Co-occurrence Matrix, Histogram Oriented Gradients, and Local Binary Patterns with Random Forest algorithm also resulted in an accuracy of 92%. These findings suggest that the combination of various feature extraction methods and machine learning algorithms can improve accuracy in skin cancer classification, which in turn can contribute to early detection and more effective treatment.

Diabetic retinopathy (DR) is a complication of prolonged diabetic mellitus causing damage to the micro-vascular system in retina. Computer-aided detection of DR can significantly reduce time, effort, and cost in early diagnosis and thereby restrict further complications. In this paper, we present a deep learning based framework for automated DR stage classification from fundus retinal images.We design and develop a custom build Convolutional Neural Network (CNN) model named Model-IVS to extract meaningful and discriminative features from the retinal fundus images. The proposed hybrid-CNN combines the multi-scale pyramidal feature processing concept of inception model with the convolutional pipeline based feature extraction concept of VGG-Nets and adopts multi-scale feature concatenation based short-cut connections of DenseNet with learnable convolutions. For the binary classification tasks, we employ Model-IVS as a feature extractor and use Support Vector Machine (SVM) classifier on the reduced features obtained through principal component analysis. The proposed hybrid model is end-to-end trained incrementally on a class-balanced dataset curated from the train set of EyePACS dataset. The cross-dataset generalization of the proposed hybrid CNN based DR classification framework is evaluated on APTOS, MESSIDOR-1 and MESSIDOR-2 datasets. Experimental results demonstrate that our model has outperformed all the existing state-of-the-art methods for DR severity grading task on APTOS dataset. The proposed Model-IVS has achieved best accuracy, AUC-ROC, and kappa score of 84.33%, 0.978 and 0.899, respectively in DR severity grading task. In binary classification tasks like DR screening and referable DR predictions, our Model-IVS feature extraction network with SVM classifier on PCA features has also achieved comparable performance results w.r.t. the state-of-the-art methods. In DR screening task, we recorded an accuracy of 97.84%, 87.42%, and 89.67% on APTOS, MESSIDOR-1, and MESSIDOR-2 datasets, respectively. In referable DR prediction, we achieved AUC-ROC score of 0.987, 0.928, and 0.873 on APTOS, MESSIDOR-1, and MESSIDOR-2 datasets, respectively.

This paper examines the performance of different machine and deep learning algorithms in classifying colon histological images using different feature extraction methods. The relationship between the feature extraction methods and the selected machine learning methods to improve the classification accuracy is analyzed. Widely used methods like local binary patterns, histograms of oriented gradients, Gabor filter and Dobeshi wavelets are investigated for feature extraction from colon histological images. The features extracted by histogram of oriented gradients and Gabor filter methods were used as a single joint feature vector. And popular machine learning methods such as Support vector machine, Decision trees, Random forest, k-nearest neighbors and Naive Bayesian method were used to classify the selected images. The paper also investigates ensemble methods using gradient bousting and voting classifier as examples. The authors also focus on the study of convolutional neural networks as they are one of the main deep learning methods at the moment. The classification methods selected for analysis are compared in terms of classification accuracy and time taken for training and recognition. All pre-defined and adjustable parameters of both feature extraction methods and classification methods were personally selected by the authors as a result of experimental studies, which were conducted using a software tool created in the Python programming language on a set of LC25000 histological images. The software created is easily customizable and can be used in the future to investigate classification methods on other datasets.

Interpreting medical images is certainly a complex task which requires extensive knowledge [1]. According to Computer Aided Diagnosis (CAD) serves as a second opinion that will help radiologists in diagnosis and on the other hand Content-based Image Retrieval uses visual content to help users browse, search and retrieve similar medical images from a database based on the user’s interest [2-4]. The competency of the CBMIR system depends on feature extraction methods [5]. The textural features are very important to determine the content of a medical image. Textural features provide scenic depth, the spatial distribution of tonal variation, and surface orientation [6]. Therefore, this study seeks to compare and evaluate some of the hand-crafted texture feature extraction techniques in CBMIR. This is to help those concerned in enhancing CBIR systems to make informed decisions concerning the selection of the best textural feature extraction techniques. Since there is no clear indication of which of the various texture feature extraction techniques is best suited for a given performance metric when considering which of the techniques to choose for a particular study in CBMIR systems. The objective of this work, therefore, is to comparatively evaluate the performance of the following texture feature extraction techniques; Local Binary Pattern (LBP), Gabor Filter, Gray-Level Co-occurrence Matrix (GLCM), Haralick Descriptor, Features from Accelerated Segment Test (FAST) and Features from Accelerated Segment Test and Binary Robust Independent Elementary Features (FAST &BRIEF) using the metrics; precision, recall, f1-score, mean squared error (MSE), accuracy and time. These techniques are coupled with specific similarity measure to obtain results. The results showed that LBP, Haralick Descriptor, FAST, and GLCM had the best results in terms of (Precision and Accuracy), Time, F1-Score, and Recall respectively. LBP had 82.05% and 88.23% scores for precision and accuracy respectively. The following scores represent the performance of the Haralick descriptor, FAST, and GLCM models respectively; 0.88s, 38.7%, and 44.82%. These test scores are obtained from datasets ranging from 1k-10.5k. Aside from LBP outperforming the other 5 models mentioned, it still outperformed the following proposed models ' [7]’, ‘Tamura texture feature and wavelet transform combined with Hausdorff distance - [8]’, ‘ [9]’ in terms of (precision, accuracy, and recall) and (precision and recall) respectively and probably f1-score (since f1-score is the weighted average of precision and recall). It is believed that an ensemble of LBP, Haralick descriptors, and Support Vector Machine (SVM) can represent a robust system for both medical image retrieval and classification.

The long term diabetes leads to the retinal vascular disease called diabetic retinopathy (DR). As DR is a progressive disease, it should be diagnosed and treated as soon as possible to prevent the patient from blindness. The lesions like microaneurysms, exudates, hemorrhages and abnormal growth of blood vessels etc. will appear in DR. In this paper, the segmentation and classification of exudates is proposed. Exudates are segmented using modified morphological operation which deals with the intervention of optic disc before the detection of exudates. The feature extraction is done using local binary pattern (LBP) and classified using support vector machine (SVM). The proposed method is tested on DIARETDB0 and DIARETDB1, which are freely available datasets. The method is also evaluated on the hospital images. The average sensitivity, specificity and accuracy of 0.92, 0.82, and 0.95 respectively are obtained.

Multimodal biometrics-based systems aim to improve the recognition accuracy of human beings using more than one physical and/or behavioral characteristics of a person. In this paper, different fusion schemes at matching score level and feature level are employed to obtain a robust recognition system using several standard feature extractors. The proposed method involves the consideration of a face–iris multimodal biometric system using score level and feature level fusion. Principal Component Analysis (PCA), subspace Linear Discriminant Analysis (LDA), subpattern-based PCA, modular PCA and Local Binary Patterns (LBP) are global and local feature extraction methods applied on face and iris images. In fact, different feature sets obtained from five local and global feature extraction methods for unimodal iris biometric system are concatenated at feature level fusion called iris feature vector fusion (iris-FVF), while for unimodal face biometric system, LBP is used to achieve efficient texture descriptors. Feature selection is performed using Particle Swarm Optimization (PSO) at feature level fusion step to reduce the dimension of feature vectors for improving the recognition performance. Our proposed method is validated by forming three datasets using ORL, BANCA, FERET face databases and CASIA, UBIRIS iris databases. The results based on recognition performance and ROC analysis demonstrate that the proposed matching score level fusion scheme using Weighted Sum rule, tanh normalization, iris-FVF and facial features extracted by LBP achieves a significant improvement over unimodal and multimodal methods. Support Vector Machine (SVM) and t-norm normalization are also used to improve the recognition performance of the proposed method.

This work has the objective of developing a methodology for the classification of regions of interest (ROI) extracted from mammograms into masses and non-masses. To this end, we conducted a comparative study by combining several techniques in the various stages of the problem. We compared several texture-based techniques for the classification of ROIs. This study combines image processing, phylogenetic trees (PT), local binary patterns (LBP), support vector machines (SVM) and the micro-genetic algorithm (GA). The analysis of texture is performed, either through the combination PT/LBP or with grey levels, to compute the taxonomic diversity () and taxonomic distinction (*) indexes extracted from sub-regions (circular, circular crown, internal mask, external mask and the combination of internal and external mask) of an ROI. A GA is used to estimate the best phylogenetic weights. Then, its results are compared with the results achieved with the use of PT only. We also analyse the behaviour of the methodology when using the ROIs with and without enhancement. This enhancement consists of the application of a mean filter and the contrast-limited adaptive histogram equalisation (CLAHE). PTs and SVM were used to perform the selection of features. To evaluate the performance of the methodologies under analysis, we used the following metrics: sensitivity, specificity, accuracy and area under the receiver operating characteristic (ROC) curve (). Sensitivity and specificity measure the efficiency of the classifier at the correct detection of positive (masses) and negative (non-masses) cases, respectively. Accuracy measures the performance of the classification in both cases. The ROC curve is the graphical representation of the pairs (1-specificity, sensitivity). is the area formed by the ROC curve, which equals to 1 in an ideal test. The comparison of the possible combinations for each stage of the study revealed the following results. In the analyses without feature selection, the best results were (1) 100% accuracy and of 0.99 for the combination of PT, LBP and internal masks and (2) 99.5% accuracy and of 0.99 for the combination of GA, LBP and internal masks for the extraction of features. In the analyses with feature selection, the best results were (1) 100% accuracy and of 1.0 for the combination of GA and LBP (feature extraction) with the union of internal and external masks and (2) 98.5% accuracy and of 0.99 for the combination of PT, LBP and the union of internal and external masks.

The surface electromyography (sEMG) technique is proposed for muscle activation detection and intuitive control of prostheses or robot arms. Motion recognition is widely used to map sEMG signals to the target motions. One of the main factors preventing the implementation of this kind of method for real-time applications is the unsatisfactory motion recognition rate and time consumption. The purpose of this paper is to compare eight combinations of four feature extraction methods (Root Mean Square (RMS), Detrended Fluctuation Analysis (DFA), Weight Peaks (WP), and Muscular Model (MM)) and two classifiers (Neural Networks (NN) and Support Vector Machine (SVM)), for the task of mapping sEMG signals to eight upper-limb motions, to find out the relation between these methods and propose a proper combination to solve this issue. Seven subjects participated in the experiment and six muscles of the upper-limb were selected to record sEMG signals. The experimental results showed that NN classifier obtained the highest recognition accuracy rate (88.7%) during the training process while SVM performed better in real-time experiments (85.9%). For time consumption, SVM took less time than NN during the training process but needed more time for real-time computation. Among the four feature extraction methods, WP had the highest recognition rate for the training process (97.7%) while MM performed the best during real-time tests (94.3%). The combination of MM and NN is recommended for strict real-time applications while a combination of MM and SVM will be more suitable when time consumption is not a key requirement.

The hybrid feature extraction method for classification of adolescence idiopathic scoliosis using Evolving Spiking Neural Network

Diabetes is one of the major health issues. In diabetes patient one serious problem experience is the Diabetic Retinopathy (DR) and visual deficiency and is vascular disease of retina. Hence prediction of DR from patient eye retina becomes very crucial at early stage to cure. We focuses on presenting an empirical method in this research to collect required data and then developing several models to predict the chance of diabetic retinopathy.Here we use diabetic eye retina image dataset as input for prediction and evaluation. There are many techniques and algorithms that help to diagnose DR in retinal fundus images. We utilized some data mining techniques such as Support vector machine (SVM), naïve bayes and Local binary pattern (LBP) to extract image features and analyze image dataset.

In this paper, two levels of classification have been carried out, the first being upper extremity recognition followed by bone abnormality detection. Support vector machines (SVMs), VGG16 and Xception V3 convolutional neural networks (CNNs) were implemented for this purpose, and their performances have been compared. The conventional method (SVM) uses the grey level co-occurrence matrix (GLCM) and local binary pattern (LBP) methods for feature extraction. In the first level, X-ray images from the MURA dataset were classified into seven categories. Next, the images were classified into two classes based on the presence of an abnormality. The VGG16-based model performed the best in the first level of classification with an average accuracy of 94.4% over three trials. In the second level, the SVM model performed the best with an accuracy of 66.33%.

Diabetic retinopathy is a microvascular complication of diabetes mellitus that attacks blood vessels in the retina. The main characteristics of diabetic retinopathy are microaneurysm, retinal haemorrhages, exudates, and neovascularization. One of the methods used to diagnose diabetic retinopathy is by examining the retinal fundus image. The examination is still done manually by an ophthalmologist. Manual examination requires a high level or concentration and misidentification may occur because some diabetic retinopathy characteristics are difficult to see directly, so it is needed a method that can facilitate the ophthalmologist in making decisions to identify diabetic retinopathy. The method proposed in this research is Probabilistic Neural Network to identify diabetes retinopathy. Before the identification stage is carried out, the retinal image will go through the pre-processing stage in the form of resize, green channel, contrast stretching and feature extraction using the Gray Level Co-Occurrence Matrix. After testing in this research, it was concluded that the proposed method was able to identify diabetes retinopathy with an accuracy of 86.8%.

In the field of computer vision and image processing CBIR (Content based image retrieval) system become an active research area. The CBIR technique involves feature extraction based on image features (like color, shape and texture) and defining rules for comparing image. A classifier is also used by authors for image classification. For this purpose an image database taken from James Z. Wang research group website is used by many authors. Due to enormous increase in the size of database traditional methods of image retrieval by using keywords does not provide accurate result. Thus the concept of CBIR system is emerged. In last couple of years many method of feature extraction is developed but since now researcher are not able to develop a system which has gained high accuracy of human visual perception in distinguishing pictures. Therefore earlier researchers have concentrated to increase the retrieval accuracy of CBIR system by using different combination of features. The objective of this paper is to present review on a CBIR technique which combined four kinds of features set including every kind of feature for developing feature vector. Color based features (histogram), statistical features (mean, median and standard deviation), spatial features (Gabor feature and wavelet features) and texture features (GLCM) is used for forming feature vector. A SVM classifier is used with CBIR system to increase retrieval accuracy. SVM (support vector machine) is a machine learning classifier which provides good classification accuracy. Keywords: CBIR, SVM, NN, GLCM, HSV Color space, Euclidean distance matrix.