A new approach to COVID-19 detection from x-ray images using angle transformation with GoogleNet and LSTM

Abstract

Declared a pandemic disease, COVID-19 has affected the lives of millions of people and had significant effects on public health. Despite the development of effective vaccines against the COVID-19 virus, COVID-19 case rates continue to increase worldwide. According to studies in the literature, artificial intelligence methods are used effectively for the detection of the COVID-19. Especially deep learning-based approaches have achieved very successful results in clinical diagnostic studies and other fields. In this study, a new approach using X-ray images is proposed to detect COVID-19 disease. In the proposed method, the Angle transform (AT) method is first applied to the X-ray images. The AT method proposed in this study is an important novelty in the literature, and there is no such approach in previous studies. This transformation uses the angle information created by each pixel on the image with the surrounding pixels. Using the angle transform approach, eight different images are obtained for each image in the dataset. These images are trained with a hybrid deep learning model, which combines GoogleNet and LSTM models, and COVID-19 disease detection is carried out. A dataset from the Mendeley database is used to test the proposed approach. High classification accuracy of 98.97% is achieved with the AT+GoogleNet+LSTM approach. The results obtained were also compared with other studies in the literature. The presented results reveal that the proposed method is successful for COVID-19 detection using chest X-ray images. Direct transfer methods were also applied to the data set used in the study. However, low success results were observed according to the proposed approach. The proposed approach has the flexibility to be applied effectively to different medical images

Prognostic Nutritional Index, Controlling Nutritional Status (CONUT) Score, and Inflammatory Biomarkers as Predictors of Deep Vein Thrombosis, Acute Pulmonary Embolism, and Mortality in COVID-19 Patients

“…Numerous recent studies have also shown the superior role of superficial and deep learning-based intelligence in the diagnosis of COVID-19 patients using X-rays and CT scans with higher accuracy than the standard diagnostic approach [ 65 , 66 , 67 , 68 , 69 , 70 ].…”

A Survey on Deep Learning in COVID-19 Diagnosis

“…Haritha et al [ 190 ] used GoogleNet to classify X-ray images and predict COVID-19. Kaya et al [ 191 ] first applied the angle transformation (AT) on X-ray images. Then these images are trained using GoogleNet combined with LSTM.…”

Comparative study on deep-learning-based leather surface defect identification

“…Deep learning, which can learn features directly from an original data, has achieved remarkable results in defect detection for industrial products [25,26], equipment fault diagnosis [27], and x-ray images-based COVID-19 detection [28]. Aslam et al [1] suggested that deep learning architectures can serve as a source of guidelines for designing and developing new solutions for leather defect inspection.…”