To search, Click below search items. |
| All Published Papers Search Service |
|
|
|
Title |
Utilisation of Artificial Intelligence in Medical Image Analysis for COVID-19 Patients Detection |
|
Author |
Mohammed Baz, Hatem Zaini, Hala Abu Zaid, and Matokah Abu Al-Naja |
| Citation |
Vol. 26 No. 1 pp. 85-96 |
|
Abstract |
Coronavirus (COVID-19) disease constitutes one of the devastating pandemics plaguing humanity throughout the centuries; within about a year since its appearing, the cumulative confirmed cases hit 93 million, whereas the death toll exceeds 2 million. Although several vaccines became available for public worldwide, the speed with which Coronavirus is spread and its different mutant strains hinder stopping its outbreak. This, in turn, prompting the desperate need for devising fast, cheap and accurate tools via which the disease can be diagnosed in its early stage. Reverse Transcription Polymerase Chain Reaction (RTPCR) test is the mainstay tool used to detect the COVID19 symptoms. However, due to the high false-negative rate of this test, physicians employ chest radiographs as an adjunct or alternative tool. Despite the wide-availability, low-cost, and timely radiographs screening results, relying on radiologists to interpret them manually stands against using radiographs as a diagnostic tool. Motivated by the need to speed up the radiographic diagnosis of COVID19 and improves its reliability, this paper proposes a novel deep-learning-based framework dubbed Parallel Deep Neural Networks for Covid-19 Diagnosis (PDNCD). PDNCD integrates the competency of convolution neural networks (CNNs) in treating medical images and the prowess of Recurrent Neural Networks (RNNs) in recognising clinicopathological characteristics to process radiographs and contextual resources simultaneously. By this integration, PDNCD can make perfect classifications even for those cases in which the infection signs in radiographs are unclear due to being the disease in early-stage, confounded by other markers or overlapped by other diseases. Extensive assessments of PDNCD carried out using several datasets demonstrate average diagnostic accuracy of 99.9 accuracies, 0.99 F1-score and near-unity area under the receiver operating characteristic curve. |
|
Keywords |
Covid-19, Artificial intelligence, CNN, RNN |
|
URL |
