Solutions and Features
Breast Cancer Detection
Personalized Breast Screening
Breast Density Assessment
Breast AI uses deep learning technology that is intended to be used concurrently by radiologists while reading digital breast tomosynthesis (DBT) exams. The algorithm detects soft tissue densities (masses, architectural distortions and asymmetries) and calcifications in 3D DBT slices. The suspicious areas that are detected and highlighted and the unique certainty of finding and case scores assist radiologists in identifying and assessing soft tissue densities and calcifications that may be confirmed or dismissed by the radiologist.
Breast AI offers an equitable and inclusive approach to precision screening.1,4,5 It factors in clinically relevant global screening guidelines and more than 15 country incidence and mortality reference tables, for alignment with that country’s general population. Breast AI incorporates multiple risk factors found in a screening mammogram:
- Breast Density
- Subtle Mammographic Features
This solution offers the highest AUC available, 0.80 (95% CI: 0.76, 0.83), for providing a one-year future risk estimation based only on a screening mammogram.5 This advanced solution provides superior insights,1,2 that empower clinicians to tailor breast screening regimens and potentially identify cancers earlier, when they may be more easily treated.
Breast AI removes the challenges of subjectivity in breast density reporting. Using full field digital mammography (FFDM) or synthetic 2D images, it analyzes the dispersion and texture of breast tissue, delivering clinicians a consistent, accurate, and reliable patient-specific breast density assessment
Breast AI is a clinical decision support tool that provides a short-term, breast cancer risk estimation based on 2D or 3D mammograms with the highest AUC available, 0.80 (95% CI: 0.76, 0.83) offering greater accuracy compared to traditional risk assessment models1,4,5.
Breast AI automatically assesses breast density of 2D or 3D mammograms with the appropriate BI-RADS® density category and provides physicians with simplified and standardized breast density reporting and stratification, with accurate and reliable results1.
Increase Productivity and Decrease Reporting Time
Breast AI analyzes each individual image or slice and identifies potentially malignant lesions in digital breast tomosynthesis exams -- providing radiologists with superior clinical performance and crucial information, such as lesion Certainty of Finding and Case Scores, which assists in prioritizing caseload, clinical decision-making and reducing reading time by up to 52.7%1-3.
Breast AI does not require on-premises hardware and results are accessible through a single user-interface and an internet connection. It seamlessly integrates with existing PACS, EHR, worklist, notification, and dictation systems ensuring exams are read accordingly and consistently.
- iCAD data on file.
- iCAD ProfoundAI FDA filing: K203822.
- Conant E, Toledano A, Periaswamy S, et al. Improving Accuracy and Efficiency with Concurrent Use of Artificial Intelligence for Digital Breast Tomosynthesis. Radiol Artif Intell. 2019 Jul 31;1(4):e180096. doi: 10.1148/ryai.2019180096
- Eriksson M, Czene K, Strand F et al. Identification of Women at High Risk of Breast Cancer Who Need Supplemental Screening. Radiology. 2020, 297(2): 327-333. doi.org/10.1148/radiol.2020201620. Epub Sep 8.
- iCAD ProFound AI Risk for DBT 1-year AUC performance: 0.80 (95% CI: 0.76, 0.83); ProFound AI Risk for FFDM 2-year AUC performance 0.73 (95% CI: 0.68, 0.77). Performance varies by mammography system.