CoroDet: A deep learning based classification for COVID-19 detection using chest X-ray images.

BACKGROUND AND OBJECTIVE: The Coronavirus 2019, or shortly COVID-19, is a viral disease that causes serious pneumonia and impacts our different body parts from mild to severe depending on patient's immune system. This infection was first reported in Wuhan city of China in December 2019, and afterward, it became a global pandemic spreading rapidly around the world. As the virus spreads through human to human contact, it has affected our lives in a devastating way, including the vigorous pressure on the public health system, the world economy, education sector, workplaces, and shopping malls. Preventing viral spreading requires early detection of positive cases and to treat infected patients as quickly as possible. The need for COVID-19 testing kits has increased, and many of the developing countries in the world are facing a shortage of testing kits as new cases are increasing day by day. In this situation, the recent research using radiology imaging (such as X-ray and CT scan) techniques can be proven helpful to detect COVID-19 as X-ray and CT scan images provide important information about the disease caused by COVID-19 virus. The latest data mining and machine learning techniques such as Convolutional Neural Network (CNN) can be applied along with X-ray and CT scan images of the lungs for the accurate and rapid detection of the disease, assisting in mitigating the problem of scarcity of testing kits. METHODS: Hence a novel CNN model called CoroDet for automatic detection of COVID-19 by using raw chest X-ray and CT scan images have been proposed in this study. CoroDet is developed to serve as an accurate diagnostics for 2 class classification (COVID and Normal), 3 class classification (COVID, Normal, and non-COVID pneumonia), and 4 class classification (COVID, Normal, non-COVID viral pneumonia, and non-COVID bacterial pneumonia). RESULTS: The performance of our proposed model was compared with ten existing techniques for COVID detection in terms of accuracy. A classification accuracy of 99.1% for 2 class classification, 94.2% for 3 class classification, and 91.2% for 4 class classification was produced by our proposed model, which is obviously better than the state-of-the-art-methods used for COVID-19 detection to the best of our knowledge. Moreover, the dataset with x-ray images that we prepared for the evaluation of our method is the largest datasets for COVID detection as far as our knowledge goes. CONCLUSION: The experimental results of our proposed method CoroDet indicate the superiority of CoroDet over the existing state-of-the-art-methods. CoroDet may assist clinicians in making appropriate decisions for COVID-19 detection and may also mitigate the problem of scarcity of testing kits.

Effectiveness of Federated Learning and CNN Ensemble Architectures for Identifying Brain Tumors Using MRI Images.

Medical institutions often revoke data access due to the privacy concern of patients. Federated Learning (FL) is a collaborative learning paradigm that can generate an unbiased global model based on collecting updates from local models trained by client's data while keeping the local data private. This study aims to address the centralized data collection issue through the application of FL on brain tumor identification from MRI images. At first, several CNN models were trained using the MRI data and the best three performing CNN models were selected to form different variants of ensemble classifiers. Afterward, the FL model was constructed using the ensemble architecture. It was trained using model weights from the local model without sharing the client's data (MRI images) using the FL approach. Experimental results show only a slight decline in the performance of the FL approach as it achieved 91.05% accuracy compared to the 96.68% accuracy of the base ensemble model. Additionally, same approach was taken for another slightly larger dataset to prove the scalability of the method. This study shows that the FL approach can achieve privacy-protected tumor classification from MRI images without compromising much accuracy compared to the traditional deep learning approach.

Seizure Prediction Using Undulated Global and Local Features.

In this study, a seizure prediction method is proposed based on a patient-specific approach by extracting undulated global and local features of preictal/ictal and interictal periods of EEG signals. The proposed method consists of feature extraction, classification, and regularization. The undulated global feature is extracted using phase correlation between two consecutive epochs of EEG signals and an undulated local feature is extracted using the fluctuation and deviation of EEG signals within the epoch. These features are further used for classification of preictal/ictal and interictal EEG signals. A regularization technique is applied on the classified outputs for the reduction of false alarms and improvement of the overall prediction accuracy (PA). The experimental results confirm that the proposed method provides high PA (i.e., 95.4%) with low false positive per hour using intracranial EEG signals in different brain locations of 21 patients from a benchmark dataset. Combining global and local features enables the transition point to be determined between different types of signals with greater accuracy, resulting successful versus unsuccessful prediction of seizure. The theoretical contribution of this study may provide an opportunity for the development of a clinical device to predict forthcoming seizure in real time.

Epileptic Seizure Prediction by Exploiting Spatiotemporal Relationship of EEG Signals Using Phase Correlation.

Automated seizure prediction has a potential in epilepsy monitoring, diagnosis, and rehabilitation. Electroencephalogram (EEG) is widely used for seizure detection and prediction. This paper proposes a new seizure prediction approach based on spatiotemporal relationship of EEG signals using phase correlation. This measures the relative change between current and reference vectors of EEG signals which can be used to identify preictal/ictal (before the actual seizure onset/ actual seizure period) and interictal (period between adjacent seizures) EEG signals to predict the seizure. The experiments show that the proposed method is less sensitive to artifacts and provides higher prediction accuracy (i.e., 91.95%) and lower number of false alarms compared to the state-of-the-art methods using intracranial EEG signals in different brain locations of 21 patients from a benchmark data set.

Seizure prediction by analyzing EEG signal based on phase correlation.

Epilepsy is a common neurological disorders characterized by sudden recurrent seizures. Electroencephalogram (EEG) is widely used to diagnose possible epileptic seizure. Many research works have been devoted to predict epileptic seizure by analyzing EEG signal. Seizure prediction by analyzing EEG signals are challenging task due to variations of brain signals of different patients. In this paper, we propose a new approach for feature extraction based on phase correlation in EEG signals. In phase correlation, we calculate relative change between two consecutive segments of an EEG signal and then combine the changes with neighboring signals to extract features. These features are then used to classify preictal/ictal and interictal EEG signals for seizure prediction. Experiment results show that the proposed method carries good prediction rate with greater consistence for the benchmark data set in different brain locations compared to the existing state-of-the-art methods.