ABSTRACT
The world today is suffering from a huge pandemic COVID-19 that has infected 106M people around the globe causing 2.33M deaths, as of February 9, 2021. To control the disease from spreading more and to provide accurate healthcare to existing patients, detection of COVID-19 at an early stage is important. As per the World Health Organization, diagnosing pneumonia is a common way of detecting COVID-19. In many situations, a chest X-ray is used to determine the type of pneumonia. However, writing a report for every chest X-ray becomes a tedious and time-taking task for physicians. We propose a novel method of creating reports from chest X-rays images automatically via a deep learning model using image captioning with an attention mechanism employed through CNN–LSTM architecture. On comparing the model that does not use an attention mechanism with our approach, we found that accuracy was increased from 80% to 87.5%. In conclusion, we found that results generated with attention mechanism are better, and the report thus produced can be utilized by doctors and researchers worldwide to analyze new X-rays in lesser time. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.