Mammography is recommended for the early detection of breast cancer . It is also shown to decrease mortality by 20 to 40%. 1 However, higher rates of false negative and false positive results and inconsistent availability of experts are major challenges in mammography. Of late, deep learning (DL) technology is being applied to mammography to overcome these challenges. In such an effort, researchers from the USA have trained a DL model with a large set of mammogram data to improve the detection of breast cancer.
2 Study details Mammogram data were utilized from seven databases – five from the USA, one from the UK, and one from China. Databases with annotated data were selected to develop an efficient DL model to detect breast cancer. Similarly, a Chinese database was selected to generalize the results across the population. Scanned film mammography, diagnostic and screening digital…
