No abstract

The experimental results suggest that the proposed approach is accurate and robust in pathological brain detection.

No abstract

In order to detect multiple sclerosis (MS) subjects from healthy controls (HCs) in magnetic resonance imaging, we developed a new system based on machine learning. The MS imaging data was downloaded from the eHealth laboratory at the University of Cyprus, and the HC imaging data was scanned in our local hospital with volunteers enrolled from community advertisement. Inter-scan normalization was employed to remove the gray-level difference. We adjust the misclassification costs to alleviate the effect of unbalanced class distribution to the classification performance. We utilized two-level stationary wavelet entropy (SWE) to extract features from brain images. Then, we compared three machine learning based classifiers: the decision tree, k-nearest neighbors (kNN), and support vector machine. The experimental results showed the kNN performed the best among all three classifiers. In addition, the proposed SWE+kNN approach is superior to four state-of-the-art approaches. Our proposed MS detection approach is effective.

Highlights We proposed a general ResGNet Framework that is suitable for image classification tasks. We propose three novel models for COVID-19 detection. It is the first attempt at applying graph convolutional neural network for COVID-19 detection. Compared to SOTA, our model achieved the best performance in terms of accuracy.

(Aim) Classification of brain images as pathological or healthy case is a key pre-clinical step for potential patients. Manual classification is irreproducible and unreliable. In this study, we aim to develop an automatic classification system of brain images in magnetic resonance imaging (MRI). (Method) Three datasets were downloaded from the Internet. Those images are of T2-weighted along axial plane with size of 256ˆ256. We utilized an s-level decomposition on the basis of dual-tree complex wavelet transform (DTCWT), in order to obtain 12s "variance and entropy (VE)" features from each subband. Afterwards, we used support vector machine (SVM) and its two variants: the generalized eigenvalue proximal SVM (GEPSVM) and the twin SVM (TSVM), as the classifiers. In all, we proposed three novel approaches: DTCWT + VE + SVM, DTCWT + VE + GEPSVM, and DTCWT + VE + TSVM. (Results) The results showed that our "DTCWT + VE + TSVM" obtained an average accuracy of 99.57%, which was not only better than the two other proposed methods, but also superior to 12 state-of-the-art approaches. In addition, parameter estimation showed the classification accuracy achieved the largest when the decomposition level s was assigned with a value of 1. Further, we used 100 slices from real subjects, and we found our proposed method was superior to human reports from neuroradiologists. (Conclusions) This proposed system is effective and feasible.

Extreme learning machine (ELM) is a training algorithm for single hidden layer feedforward neural network (SLFN), which converges much faster than traditional methods and yields promising performance. In this paper, we hope to present a comprehensive review on ELM. Firstly, we will focus on the theoretical analysis including universal approximation theory and generalization. Then, the various improvements are listed, which help ELM works better in terms of stability, efficiency, and accuracy. Because of its outstanding performance, ELM has been successfully applied in many real-time learning tasks for classification, clustering, and regression. Besides, we report the applications of ELM in medical imaging: MRI, CT, and mammogram. The controversies of ELM were also discussed in this paper. We aim to report these advances and find some future perspectives.

No abstract