Artificial intelligence in breast imaging.
W. B. Saunders Co., Ltd.
MetadataShow full item record
Le, E., Wang, Y., Huang, Y., Hickman, S., & Gilbert, F. (2019). Artificial intelligence in breast imaging.. Clinical radiology, 74 (5), 357-366. https://doi.org/10.1016/j.crad.2019.02.006
Introduction Globally, breast cancer (BC) is the most common cancer amongst women1 and remains the second leading cause of cancer death2. The importance of mammography screening has been widely recognised3 and the early detection of breast cancer is associated with better outcomes4,5. The limitations of mammography screening include over-diagnosis6, overtreatment and false positive rates with associated negative psychological impact7,8 and unnecessary costs and biopsies3. Interpretation of mammograms varies with experience9, is subjective10 and prone to error due to the heterogeneous presentation of breast cancer and the masking effect with dense breast tissue. This contributes to interval cancers that are diagnosed between screening or cancers found in the subsequent screening round11,12. Although reading time for 2D mammography is less than 30-60 seconds, the huge volumes of mammograms and double-reading of each mammogram creates manpower problems and resource issues. Computer-aided detection (CAD) systems for mammography have been used extensively in the USA following initial promising results and reimbursement introduced in 2001. However more recently, CAD has been shown to adversely affect some radiologists’ performance, increase recalls without improvement in cancer detection rates13. This has resulted in some scepticism as to whether or not AI tools can reliably assist radiologists in breast cancer screening. This article reviews the current limitations and future opportunities for the application of CAD systems and artificial intelligence in breast imaging.
Breast, Humans, Breast Neoplasms, Mammography, Artificial Intelligence, Image Processing, Computer-Assisted
Elizabeth PV Le is undertaking a PhD funded by the Cambridge School of Clinical Medicine, Frank Edward Elmore Fund and the Medical Research Council’s Doctoral Training Partnership (Award Reference: 1966157).
Department of Health (via National Institute for Health Research (NIHR)) (NF-SI-0515-10067)
External DOI: https://doi.org/10.1016/j.crad.2019.02.006
This record's URL: https://www.repository.cam.ac.uk/handle/1810/290051