None listed
Conditions
Brief summary
This research study is investigating the safety and efficacy of using artificial intelligence (AI) in Australian breast cancer population screening by determining if using AI improves mammogram reading accuracy and timeliness and reduces reading workload. Who is it for? You may be eligible for this study if you are a woman aged 40 years and over who is eligible to participate in population-based mammography screening in Victoria and South Australia. Study details Participants will be randomly allocated to have their mammograms read by an AI-integrated system, or by the current mammogram reading standard of care (independent reading by two blinded radiologists and a third if discrepancy). The AI-integrated system will replace one of the independent radiologists with an AI reader (BRAIx AI Reader) while maintaining the arbitration radiologist reader if needed. Data will be collected on screen-detected breast cancer rates and radiologist workload. It is hoped that findings from this study will help researchers evaluate the clinical utility of implementing AI within breast cancer population screening systems in an Australian setting.
Interventions
Intervention: AI-integrated screening mammogram reading using investigational product; BRAIx AI Reader (Software as a Medical Device).
An AI reader (Deep Learning Classification Model) implemented to automatically analyse and assign a classification score to screening mammograms replacing the second radiologist reader in the independent double-reading of every mammogram, while maintaining the arbitration radiologist reader if needed. The first radiologist reader will not know the AI reader resul
Intervention: AI-integrated screening mammogram reading using investigational product; BRAIx AI Reader (Software as a Medical Device). An AI reader (Deep Learning Classification Model) implemented to automatically analyse and assign a classification score to screening mammograms replacing the second radiologist reader in the independent double-reading of every mammogram, while maintaining the arbitration radiologist reader if needed. The first radiologist reader will not know the AI reader result in accordance with the current clinical routine (BreastScreen Australia National Accreditation Standards). If arbitration is required, the arbitration radiologist reader will be unblinded to both the AI and radiologist reader’s decision and have access to image annotations indicating Region of Interest of suspicion according to current clinical practice. The intervention will be implemented in the context of breast cancer screening, accordingly all women aged 40 and above who are eligible to participate in population-based mammography screening. The approximate turnaround time for this mammogram double-reading procedure involving the AI reader, is 48 hours, which is well within the standard set by the BreastScreen Australia National Accreditation Standards, where screening reading results are provided to the client within 14 days. A data log file procedure will be implemented to monitor adherence to the intervention if applicable, i.e. audit of patient medical records.
Sponsors
ST VINCENT'S INSTITUTE OF MEDICAL RESEARCH
Study design
Allocation
Randomised controlled trial
Intervention model
Parallel
Primary purpose
Diagnosis
Masking
Blinded (masking used) (Subject)
Eligibility
Sex/Gender
All
Age
40 Years to No maximum
Healthy volunteers
Yes
Inclusion criteria
To be included in the study, subjects must meet the following criteria: - Women eligible to participate in population-based mammography screening in Victoria and South Australia.
Exclusion criteria
No exclusion criteria applied.
Outcome results
None listed