Efficiency of Artificial Intelligence in Detecting COVID-19 Pneumonia and Other Pneumonia Causes by Quantum Fourier Transform Method

Abstract

The new coronavirus (COVID-19) appeared in Wuhan in December 2019 and has been announced as a pandemic by the World Health Organization (WHO). Currently, this deadly pandemic has caused more than 1 million deaths worldwide. Therefore, it is essential to detect positive cases as early as possible to prevent the further spread of this outbreak. Currently, the most widely used COVID-19 detection technique is a real-time reverse transcription-polymerase chain reaction (RT-PCR). However, RT-PCR is time-consuming to confirm infection in the patient. Because RT-PCR is less sensitive, it provides high false-negative results. Computed tomography (CT) is recommended as a solution to this problem by healthcare professionals because of its higher sensitivity for early and rapid diagnosis. In addition, radiation used in CT poses a serious threat to patients. In this study, we propose a CNN-based method to distinguish COVID-19 pneumonia from other types of viral and bacterial pneumonia using low-dose CT images to reduce the radiation dose used in CT. In our study, we used a data set consisting of 7717 CT images of 350 patients that we collected from Çanakkale Onsekiz Mart University Research Hospital. We used a CNN-based network that suppresses noise to remove interference from low-dose CT images. In the image preprocessing phase, we provided lung segmentation from CT images and applied quantum Fourier transform. By evaluating all possible variations of local knowledge at the same time with quantum Fourier transformation, the most informative spatial information was extracted. In CNN-based architecture, we used pre-trained ResNet50v2 as a feature extractor and fine-tune by training with our dataset. We visualized the efficiency of the ResNet50v2 network using the t-SNE method. We performed the classification process with a fully connected layer. We created a heat map using the GradCam technique to see where the model focuses on the images while classifying. In this experimental study, the results of 99.5%, 99.2%, 99.0%, 99.7%, and 99.1%, were obtained in the context of performance criteria such as accuracy, precision, sensitivity, specificity, and f1 score, respectively. This study revealed the artificial intelligence-based computer-aided diagnosis (CAD)system as an effective and fast method to accurately diagnose COVID-19 pneumonia.

Predicting COVID-19 Cases on a Large Chest X-Ray Dataset Using Modified Pre-trained CNN Architectures

“…Also, several frequency-based studies detect COVID-19 through X-ray and CT images. Acar et al [56] distinguished COVID-19 pneumonia from viral and bacterial pneumonia types with 99.5 % accuracy through CT images using ResNet50v2 CNN and quantum Fourier transform. Chaudhary et al [57] classified three classes with 100 % accuracy using the Fourier-Bessel series expansion-based decomposition (FBSED) method and pre-trained ResNet-50 and AlexNet CNN models.…”

Covid-19 Detection from Chest X-Ray Images Using Advanced Deep Learning Techniques

“…In a similar context, Bhattacharya et al [9] presented a detailed survey, summarized the state-of-the-art research works related to deep learning applications for COVID-19 medical image processing and provided an overview of deep learning and its applications to healthcare found in the last decade. Oztoprak et al [10] collected 717 CT images of 350 patients from a medical research facility and used a CNN-based network that suppresses noise to remove interference from low-dose CT images. They provided lung segmentation from CT images and applied quantum Fourier transform while preprocessing stage, and achieved 99.5%, 99.2%, 99.0%, 99.7%, and 99.1% in the context of performance criteria viz., accuracy, precision, sensitivity, specificity, and f1 score, respectively.…”