Chest Computed Tomography Scan Images for Classification of Coronavirus by Enhanced Convolutional Neural Network and Gabor Filter

Abstract

Coronavirus pandemic disease is caused by severe acute respiratory syndrome coronavirus 2. Generally RT-PCR or other Nucleic testing is used in order to detect covid19. In computed Tomography Scans, it can be clearly viewed that to how much extent the virus has damaged the Lungs. Computed Tomography gives the result in 15 minutes, whereas RT PCR takes 24 hours. PCR only checks whether virus is in nose or throat but the proposed model checks in lungs which is most accurate. The utilization of computed Tomography Scans will give us better and accurate results. The proposed novel model helps to recognize the corona virus in Lungs Computed Tomography Scans and achieved an accuracy of 0.93 with Gabor filter and 0.85 without Gabor filter. The existing models VGG16, VGG19, ResNet50 and M obile Net achieves an accuracy of 0.89,0.91,0.91,0.91 respectively using Gabor filter and 0.78,0.71,0.81 and 0.89 without using Gabor Filter. Gabor filter will help to remove the noise from the data, it is linear filter and orientation sensitive. Our model achieves an accuracy 0.93 which is better than VGG16, VGG19, ResNet50, M obile Net models using Gabor Filter.

COVID-19 Diagnosis: ULGFBP-ResNet51 approach on the CT and the Chest X-ray Images Classification

“…Another method that makes better the categorization of COVID-19 is GF. According to the results of research in [31], recognizing COVID-19 is 93% using GF and CNN. Against, it is 85% without GF in lung computed tomography scans.…”

“…The advantages and disadvantages of some available hand-engineered and deep-learning methods for COVID-19 identification are presented in Table 1. The mixture method makes use of both handengineered and deep-learning methods [3,8,[29][30][31]. In fact, it combines them in the favor of reaching more benefits.…”