Effect of Benign Biopsy Findings on an Artificial Intelligence-Based Cancer Detector in Screening Mammography: Retrospective Case-Control Study.
Athanasios ZouzosAleksandra MilovanovicKarin DembrowerFredrik StrandPublished in: JMIR AI (2023)
Compared to healthy women without a biopsy, the examined AI CAD system flagged a much larger proportion of women who had or would have a benign biopsy finding based on a radiologist's decision. However, the flagging rate was not higher than that for radiologists. Further research should be focused on training the AI CAD system taking prior biopsy information into account.
Keyphrases
- artificial intelligence
- ultrasound guided
- machine learning
- fine needle aspiration
- big data
- deep learning
- coronary artery disease
- polycystic ovary syndrome
- pregnancy outcomes
- papillary thyroid
- healthcare
- cervical cancer screening
- squamous cell carcinoma
- magnetic resonance imaging
- type diabetes
- magnetic resonance
- pregnant women
- cross sectional
- computed tomography
- skeletal muscle
- health information
- adipose tissue
- young adults
- social media
- childhood cancer