Medical imaging is a widely used tool in clinical practice for diagnosing or monitoring the progression of several diseases. Usually, descriptions of the findings in medical images are qualitative. However, in recent years, several advances in the acquisition, standardization, and image analysis allow a quantitative description of the image findings, boosting Computer-aided diagnosis tools (CAD). These tools combine elements of computer vision and artificial intelligence (AI) with either radiological or pathology image processing to assist clinicians in interpreting these findings through computational support.
In 2020 the pandemic situation caused by the COVID-19 virus surprised worldwide. This situation represents a big challenge for humanity, highlighting the urgent need to accelerate, in record time, the analysis of large volumes of clinical data. Chest radiography (RX) is the first, among medical diagnostic imaging, recommended when the virus is suspected. One of the main characteristic of this virus is being highly contagious, rapidly increasing the number of infected patients who need radiological images of the thorax to support the diagnosis and monitoring of the disease. This situation has caused fatigue in clinicians and especially radiologists causing a considerable reduction in the precision of the diagnosis.
Artificial intelligence as part of CAD tools has aided in fighting against the coronavirus pandemic. While x-ray in medical examinations is widely available, the interpretation of these images by radiologists is limited due to the human capacity to detect the subtle visual or sub-visual features present in radiological images. Hence, AI can discover patterns in chest X-rays that normally would not be recognized by radiologists. Research and development of several tools based in AI has improved the COVID-19 screening, diagnostics, monitoring, prediction and results in better way improving time response. Besides, most reliable and efficient outcomes has been reported in the literature. Despite AI has been adopted gradually in health applications the adoption is slower than expected. Although, when the battle against the coronavirus pandemic is over, AI will continue to gain importance for the different health systems around the world.
Sources:
Pham, T. D. (2021). Classification of COVID-19 chest X-rays with deep learning: new models or fine tuning?. Health Information Science and Systems, 9(1), 1-11.
Khan, M., Mehran, M. T., Haq, Z. U., Ullah, Z., Naqvi, S. R., Ihsan, M., & Abbass, H. (2021). Applications of artificial intelligence in COVID-19 pandemic: A comprehensive review. Expert systems with applications, 185, 115695.
Artificial Intelligence as aid tool for detection, screening and prediction of COVID-19 on medical images 0
