Hyderabad AI model detects breast cancer with 95% accuracy

Researchers in Hyderabad have developed an artificial intelligence system to detect breast cancer from mammogram images, achieving nearly 95% accuracy while using less computing power and memory than comparable models. The study, led by Kumari Jelli and Pavan Kumar Pagadala of the Koneru Lakshmaiah Education Foundation, was published in Scientific Reports.

The model, called Fuzzy RS-Net, recorded 94.9% accuracy, 95.8% sensitivity and 93.8% specificity when tested on a public mammogram database. It reduces image noise, identifies suspicious areas, and analyses patterns to classify images. The researchers reported that it required less processing time and memory than several other AI models used for comparison.

The authors cautioned that the system has only been tested on public databases, not in hospitals. They recommended further validation with larger, more diverse patient data and testing in clinical settings before use. They also called for adding explainable AI tools to help doctors understand the model's findings.