Glaucoma is the second leading cause of blindness worldwide. It is a disease in which fluid pressure in the eye increases continuously, damaging the optic nerve and causing vision loss. Computational decision support systems for the early detection of glaucoma can help prevent this complication. The retinal optic nerve fiber layer can be assessed using optical coherence tomography, scanning laser polarimetry, and Heidelberg retina tomography scanning methods. In this paper, we present a novel method for glaucoma detection using a combination of texture and higher order spectra (HOS) features from digital fundus images. Support vector machine, sequential minimal optimization, naive Bayesian, and random-forest classifiers are used to perform supervised classification. Our results demonstrate that the texture and HOS features after z-score normalization and feature selection, and when combined with a random-forest classifier, performs better than the other classifiers and correctly identifies the glaucoma images with an accuracy of more than 91%. The impact of feature ranking and normalization is also studied to improve results. Our proposed novel features are clinically significant and can be used to detect glaucoma accurately.
Texture features within images are actively pursued for accurate and efficient glaucoma classification. Energy distribution over wavelet subbands is applied to find these important texture features. In this paper, we investigate the discriminatory potential of wavelet features obtained from the daubechies (db3), symlets (sym3), and biorthogonal (bio3.3, bio3.5, and bio3.7) wavelet filters. We propose a novel technique to extract energy signatures obtained using 2-D discrete wavelet transform, and subject these signatures to different feature ranking and feature selection strategies. We have gauged the effectiveness of the resultant ranked and selected subsets of features using a support vector machine, sequential minimal optimization, random forest, and naïve Bayes classification strategies. We observed an accuracy of around 93% using tenfold cross validations to demonstrate the effectiveness of these methods.
Electrocardiogram (ECG) signals are difficult to interpret, and clinicians must undertake a long training process to learn to diagnose diabetes from subtle abnormalities in these signals. To facilitate these diagnoses, we have developed a technique based on the heart rate variability signal obtained from ECG signals. This technique uses digital signal processing methods and, therefore, automates the detection of diabetes from ECG signals. In this paper, we describe the signal processing techniques that extract features from heart rate (HR) signals and present an analysis procedure that uses these features to diagnose diabetes. Through statistical analysis, we have identified the correlation dimension, Poincaré geometry properties (SD2), and recurrence plot properties (REC, DET, L(mean)) as useful features. These features differentiate the HR data of diabetic patients from those of patients who do not have the illness, and have been validated by using the AdaBoost classifier with the perceptron weak learner (yielding a classification accuracy of 86%). We then developed a novel diabetic integrated index (DII) that is a combination of these nonlinear features. The DII indicates whether a particular HR signal was taken from a person with diabetes. This index aids the automatic detection of diabetes, thereby allowing a more objective assessment and freeing medical professionals for other tasks.
Ablation of neoplastic lesions by using radiofrequency energy is gaining popularity in clinical practice because of the minimally invasive nature of radiofrequency ablation (RFA). Primary and secondary tumors of the liver and lung are treated with RFA when surgery is precluded because of comorbidity. Benign bone tumors are also treated with RFA to relieve pain and prevent further tumor growth. Differentiation between postablation tissue changes and residual disease is difficult with morphologic imaging modalities such as ultrasonography, computed tomography (CT), and magnetic resonance (MR) imaging, thus limiting the use of these modalities to detection of residual disease early after RFA. Fluorine 18 fluorodeoxyglucose (FDG) positron emission tomography (PET) is a functional imaging modality that can be used to study the effects and efficacy of RFA. Lesions that show increased FDG uptake at PET become completely photopenic immediately after RFA, a finding that is suggestive of the completeness of ablation. Focal areas of increased FDG uptake within the ablated zone are suggestive of residual disease. Reactive tissue changes such as inflammation are depicted in the periphery of the ablated lesion and show a uniform low-grade FDG uptake, which can be differentiated from the focal, nodular intense uptake in areas of residual disease. Use of combined FDG PET/CT to detect residual disease early after RFA allows ablation to be repeated, if necessary, to obtain the maximum therapeutic benefit. Note that FDG uptake in the complications sometimes associated with RFA can be a cause of potential false-positive PET results.
In this paper, we present a novel method for the classification of mammograms using a unique weighted association rule based classifier. Images are preprocessed to reveal regions of interest. Texture components are extracted from segmented parts of the image and discretized for rule discovery. Association rules are derived between various texture components extracted from segments of images, and employed for classification based on their intra-and inter-class dependencies. These rules are then employed for the classification of a commonly used mammography dataset, and rigorous experimentation is performed to evaluate the rules' efficacy under different classification scenarios. The experimental results show that this method works well for such datasets, incurring accuracies as high as 89%, which surpasses the accuracy rates of other rule based classification techniques.
Coronary artery disease (CAD) is a leading cause of death worldwide. Heart rate variability (HRV) has been proven to be a non-invasive marker of the autonomic modulation of the heart. Nonlinear analyses of HRV signals have shown that the HRV is reduced significantly in patients with CAD. Therefore, in this work, we extracted nonlinear features from the HRV signals using the following techniques: recurrence plots (RP), Poincare plots, and detrended fluctuation analysis (DFA). We also extracted three types of entropy, namely, Shannon entropy (ShanEn), approximation entropy (ApEn), and sample entropy (SampEn). These features were subjected to principal component analysis (PCA). The significant principal components were evaluated using eight classification techniques, and the performances of these techniques were evaluated to determine which presented the highest accuracy in classifying normal and CAD classes. We observed that the multilayer perceptron (MLP) method resulted in the highest classification accuracy (89.5%) using our proposed technique.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.