Press "Enter" to skip to content

New York University and NYU Abu Dhabi Develop New Tool for Breast Cancer Detection

New York University (NYU) and Abu Dhabi researchers have developed a new artificial intelligence (AI) system that can detect breast cancer in ultrasound images. The technology, which gives “radiologist-level accuracy,” was built as a decision support tool for physicians by Farah Shamout of Abu Dhabi and Yiqiu Shen and Jamie Oliver of New York University. The findings, published in Nature, showed that the method could assist radiologists in reducing “false positive” and requested biopsy rates while preserving sensitivity.

The AI technology was able to identify malignant lesions by “assigning a likelihood for malignancy and highlighting sections of ultrasound images that are linked with its predictions” after analyzing over 280,000 breast ultrasound exams from over 140,000 patients. In addition, the hybrid model outperformed ultrasound alone in a study involving ten board-certified breast radiologists. According to the researchers, the system’s goal is to reduce unneeded biopsies and the expenses associated with false-positive ultrasound results.

“Ultrasound continues to be a critical tool, often in conjunction with mammography, for the screening, detection and characterisation of breast cancer,” New York University Abu Dhabi explained in a statement. “However, ultrasound can have high false-positive rates, which then lead to unnecessary biopsies, increased costs, and discomfort to patients.”

According to the latest figures, breast cancer has surpassed lung cancer as the most commonly diagnosed disease in the world, with an anticipated 2.3 million new cases in 2020. It’s also the most significant cause of cancer-related fatalities in women all around the globe. Breast cancer is also the most often diagnosed cancer type in the Arab world, accounting for 17.7% to 19% of all new cancer cases (as per 2018 statistics).

Be First to Comment

Leave a Reply

Your email address will not be published. Required fields are marked *