ABSTRACT
COVID-19 infection recognition is a very important step in the fight against the COVID-19 pandemic. In fact, many methods have been used to recognize COVID-19 infection including Reverse Transcription Polymerase Chain Reaction (RT-PCR), X-ray scan, and Computed Tomography scan (CT- scan). In addition to the recognition of the COVID-19 infection, CT scans can provide more important information about the evolution of this disease and its severity. With the extensive number of COVID-19 infections, estimating the COVID-19 percentage can help the intensive care to free up the resuscitation beds for the critical cases and follow other protocol for less severity cases. In this paper, we introduce COVID-19 percentage estimation dataset from CT-scans, where the labeling process was accomplished by two expert radiologists. Moreover, we evaluate the performance of three Convolutional Neural Network (CNN) architectures: ResneXt-50, Densenet-161, and Inception-v3. For the three CNN architectures, we use two loss functions: MSE and Dynamic Huber. In addition, two pretrained scenarios are investigated (ImageNet pretrained models and pretrained models using X-ray data). The evaluated approaches achieved promising results on the estimation of COVID-19 infection. Inception-v3 using Dynamic Huber loss function and pretrained models using X-ray data achieved the best performance for slice-level results: 0.9365, 5.10, and 9.25 for Pearson Correlation coefficient (PC), Mean Absolute Error (MAE), and Root Mean Square Error (RMSE), respectively. On the other hand, the same approach achieved 0.9603, 4.01, and 6.79 for PCsubj, MAEsubj, and RMSEsubj, respectively, for subject-level results. These results prove that using CNN architectures can provide accurate and fast solution to estimate the COVID-19 infection percentage for monitoring the evolution of the patient state.
ABSTRACT
The recorded phonocardiogram (PCG) signal is often contaminated by different types of noises that can be seen in the frequency band of the PCG signal, which may change the characteristics of this signal. Discrete wavelet transform (DWT) has become one of the most important and powerful tools of signal representation, but its effectiveness is influenced by the issue of the selected mother wavelet and decomposition level (DL). The selection of the DL and the mother wavelet are the main challenges. This work proposes a new approach for finding an optimal DL and optimal mother wavelet for PCG signal denoising. Our approach consists of two algorithms designed to tackle the problems of noise and variability caused by PCG acquisition in a real clinical environment for different categories of patients. The results obtained are evaluated by examining the coherence analysie (Coh) correlation coefficient (Corr) and the mean square error (MSE) and signal-to-noise ratio (SNR) in simulated noisy PCG signals. The experimental results show that the proposed method can effectively reduce noise.
