The Path to Implementation of Artificial Intelligence in Screening Mammography Is Not All That Clear
Menée à partir de 144 231 mammogrammes de dépistage provenant de 85 580 Américaines et à partir des résultats de 166 578 examens de dépistage réalisés sur 68 008 Suédoises, cette étude évalue la performance d'un algorithme d'apprentissage automatique, utilisant des données de clichés mammographiques, d'examens de dépistage ainsi que des données cliniques et démographiques, pour améliorer l'interprétation des mammographies de dépistage
Breast cancer is the most common non–skin-related cancer among women and the leading cause of cancer-related deaths among women worldwide. While mammography screening has been shown to reduce breast cancer morbidity and mortality, the intrinsic limitation of a mammogram, namely, it being a 2-dimensional projection of a 3-dimensional structure, increases the complexity of the cancer detection task. In the United States, a single radiologist interprets screening mammograms to carry out this task, whereas most of Europe and parts of Asia use 2 radiologists (double reading). In the single-radiologist reading scenario, false-negative rates range between 10% and 30%, and false-positive rates are such that 49% of women screened annually for 10 years will experience at least 1 false-positive mammogram result. Clearly, this is a task that can benefit from artificial intelligence (AI), and indeed AI applications in breast cancer compose 12% of the total applications of AI in radiology. In particular, deep learning applications in digital mammograms are on the rise. However, most of the studies to date have used small data sets, which could have resulted in algorithm overtraining and overenthusiastic predictions about the algorithms’ usability in the breast imaging clinic.
JAMA Network Open , commentaire en libre accès, 2019