A Transformative Approach for Breast Cancer Detection Using Physics-Informed Neural Network and Surface Temperature Data

Abstract

Early detection is the most effective defense against breast cancer. Mammography is a well-established X-ray based technique that is used for annual or biennial screening of women above age of 40. Since the dense breast tissue sometimes obscures the cancer in an x-ray image, about 10% of screened women are recalled and undergo additional adjunctive modalities, such as ultrasound, digital breast tomosynthesis or magnetic resonance imaging (MRI). These modalities have drawbacks such as additional radiation dosage, overdiagnosis and high cost. A new concurrent multi-spectral imaging approach is recently presented to eliminate the high recall rates by utilizing the breast surface temperature data with an inverse physics-informed neural network algorithm. The multi-spectral imaging does not use any harmful radiations, such as x-rays, is contact-less and does not require breast compression. It has been validated in 23 patients and offers a cost-effective solution to provide improved detection capability of cancerous cells. It is estimated to reduce the recall rates significantly from the current 10%, with a corresponding reduction in the biopsies. This adjunctive approach builds on the strength of mammography and offers a safe adjunct by relying on the higher metabolic rates of cancer cells.