Artificial intelligence (AI) will become more common in breast cancer screening within the next ten years.
AI models are being developed and used to predict breast cancer in mammography scans with more accuracy than radiologists, Qatar Foundation (QF) researcher told The Peninsula newspaper.
“When using the naked eye to define abnormalities in image data or while analysing tissue, one could go wrong in the analysis. However, with artificial intelligence, classification of abnormal or normal tissue is more accurate,” said Dr. Halima Bensmail, the Principal Scientist and Associate Professor at Qatar Computing Research Institute, part of QF’s Hamad Bin Khalifa University.
The researcher told The Peninsula that AI can reduce false positives and false negatives, making them more reliable than traditional methods. According to Dr. Bensmail, machine learning has evolved over the years to detect abnormalities by analysing complex big data.
“People will always ask, what is the accuracy of your prediction, or what is more important when designing a machine learning model: model performance or model accuracy. This answer depends on the application and the field. But so far, we don’t have any machine learning algorithm or artificial intelligence model that gives us 100 percent accuracy of the prediction,” said Dr. Bensmail.
Read also: Qatar pioneers new study on gene-environment
The use of technologies, including AI, is becoming increasingly popular in diagnostic approaches, with mammography being used as the standard method for early breast cancer detection.
Specific training of machines’ systems by scientists enables the devices to detect massive amounts of data and distinguish the difference between good and bad tissues. The algorithms will then learn to detect the tissues with great accuracy.
Algorithms offer more accurate results, providing an accuracy rate of 90% to 97%.
Due to their promising results, Dr. Bensmail predicts the integration of AI in clinical practice within the next 10 years.