Advances in breast cancer risk modeling: integrating clinics, imaging, pathology and artificial intelligence for personalized risk assessment.
Filippo PesapaneOttavia BattagliaGiuseppe PellegrinoElisa MangioneSalvatore PetittoEliza Del Fiol MannaLaura CazzanigaLuca NicosiaMatteo LazzeroniGiovanni CorsoNicola FuscoEnrico CassanoPublished in: Future oncology (London, England) (2023)
Breast cancer risk models represent the likelihood of developing breast cancer based on risk factors. They enable personalized interventions to improve screening programs. Radiologists identify mammographic density as a significant risk factor and test new imaging techniques. Pathologists provide data for risk assessment. Clinicians conduct individual risk assessments and adopt prevention strategies for high-risk subjects. Tumor genetic testing guides personalized screening and treatment decisions. Artificial intelligence in mammography integrates imaging, clinical, genetic and pathological data to develop risk models. Emerging imaging technologies, genetic testing and molecular profiling improve risk model accuracy. The complexity of the disease, limited data availability and model inputs are discussed. A multidisciplinary approach is essential for earlier detection and improved outcomes.
Keyphrases
- artificial intelligence
- breast cancer risk
- big data
- risk assessment
- risk factors
- high resolution
- machine learning
- deep learning
- electronic health record
- primary care
- public health
- heavy metals
- gene expression
- magnetic resonance
- palliative care
- dna methylation
- single cell
- metabolic syndrome
- photodynamic therapy
- smoking cessation
- contrast enhanced
- loop mediated isothermal amplification