Early breast cancer detection with AI-powered tool

This computer program utilizes thermal infrared images of the breast to analyze heat patterns within the tissue, enabling the identification of potential malignant tumors within just five minutes. The researchers trained PINN using infrared breast scans from thousands of patients, achieving an impressive 91 percent accuracy in identifying harmful tumors during testing.

While mammography remains one of the most effective methods for early breast cancer detection, accessibility is limited due to cost and availability. NTU's PINN offers a non-invasive, painless, and quicker alternative. Unlike traditional mammograms, PINN does not rely on bulky equipment and utilizes an infrared camera for capturing breast images from various angles. This approach ensures a safer option, particularly for women at higher risk or with a family history of breast cancer, as mammograms involve exposure to ionizing radiation.

Associate Prof. Eddie Ng Yin Kwee, the corresponding author, emphasizes: “Our study’s findings, and the development of PINN, centers around AI’s ability to swiftly and accurately analyze vast datasets, specifically thousands of infrared breast scans. We also benefited from machine learning when calibrating PINN as it made the program easily trainable, aiding it to recognize patterns and generalize well to new, unseen data, making it adaptable and reliable. PINN could assist in the early identification of potential abnormalities in breast tissues, not only contributing to better treatment outcomes but also streamlines the screening process, allowing healthcare professionals to prioritize complex cases.”

Developed in consultation with healthcare professionals in Singapore, PINN is set to evolve further. The researchers aim to make it a stand-alone application, running on a portable device equipped with a graphics processing unit and infrared camera. This advancement holds promise for making routine breast examinations more accessible and simpler, potentially revolutionizing breast imaging globally.

As the researchers continue refining PINN, their focus includes predicting tissue properties and tumor sizes and locations. Dr. Anna Midlenko, a Clinical Instructor in the Department of Surgery at Nazarbayev University and a surgical oncologist who consulted on the development of the program, explains: “Tumors, including breast cancer tumors, often have distinct metabolic activity and blood supply compared to normal tissue. As a result, they may generate more heat or have different thermal properties. PINN, which could flag the presence of possible problematic areas in a subject’s breast, could serve as a more accessible test for early detection of breast cancer, especially when the tumors are not yet palpable during self-breast examinations.”

MEDICA-tradefair.com; Source: NTU Singapore