Machine Learning Algorithm Trained on Images of Everyday Items Detects COVID-19 in Chest X-Rays with 99% Accuracy

New research using machine learning on images of everyday items is improving the accuracy and speed of detecting respiratory diseases, reducing the need for specialist medical expertise.

In a study by researchers at Edith Cowan University (Perth, Australia), the results of this technique, known as transfer learning, achieved a 99.24% success rate when detecting COVID-19 in chest X-rays. The study tackles one of the biggest challenges in image recognition machine learning: algorithms needing huge quantities of data, in this case images, to be able to recognize certain attributes accurately.


According to the researchers, this was incredibly useful for identifying and diagnosing emerging or uncommon medical conditions. The key to significantly decreasing the time needed to adapt the approach to other medical issues was pre-training the algorithm with the large ImageNet database. The researchers hope that the technique can be further refined in future research to increase accuracy and further reduce training time.

"Our technique has the capacity to not only detect COVID-19 in chest x-rays, but also other chest diseases such as pneumonia. We have tested it on 10 different chest diseases, achieving highly accurate results," said ECU School of Science researcher Dr. Shams Islam. "Normally, it is difficult for AI-based methods to perform detection of chest diseases accurately because the AI models need a very large amount of training data to understand the characteristic signatures of the diseases. The data needs to be carefully annotated by medical experts, this is not only a cumbersome process, it also entails a significant cost. Our method bypasses this requirement and learns accurate models with a very limited amount of annotated data. While this technique is unlikely to replace the rapid COVID-19 tests we use now, there are important implications for the use of image recognition in other medical diagnoses."

Related Links:
Edith Cowan University