Multi-Reader Multi-Case, Retrospective Study to Evaluate Effectiveness of CadAI-B for Breast
- Conditions
- Breast Cancer
- Interventions
- Device: CadAI-B for Breast
- Registration Number
- NCT06352684
- Lead Sponsor
- BeamWorks Inc.
- Brief Summary
The purpose of this study is to evaluate the effectiveness of lesion detection and diagnosis-aiding software (CadAI-B for Breast) during ultrasound (US) examination
- Detailed Description
CadAI-B for Breast is a real-time AI diagnosis system designed to assist healthcare professionals in lesion detection and differential diagnosis during breast US examinations. The primary objective of the study is to evaluate the effectiveness of CadAI-B in the assistance of detection and diagnosis of breast cancer by comparing the clinical performance of physicians before and after using CadAI-B in their ultrasound reading. The secondary objective of this study is to evaluate the sensitivity and specificity using CadAI-B for US examinations.
Recruitment & Eligibility
- Status
- ACTIVE_NOT_RECRUITING
- Sex
- Female
- Target Recruitment
- 1000
- Women who underwent breast US examination
- Women with breast cancer (DCIS or invasive cancer) diagnosed via biopsy
- Women who had been followed for more than 2 years after initial US examination
- women who had breast implants
- women who had US images containing artifacts affecting the review of images
Study & Design
- Study Type
- OBSERVATIONAL
- Study Design
- Not specified
- Arm && Interventions
Group Intervention Description Benign group CadAI-B for Breast Either confirmed as a benign through the subsequent biopsy conducted within following 1 year of the ultrasound exam or showing stability on more than 2 years of imaging follow-up after initial diagnosis Cancer group CadAI-B for Breast confirmed as a breast cancer (DCIS or invasive cancer) through the subsequent biopsy conducted within following 1 year of the ultrasound exam. Normal group CadAI-B for Breast Interpreted as BI-RADS 1 (Negative) with no cancers on the ultrasound exam
- Primary Outcome Measures
Name Time Method Area Under the LROC Curve 6 weeks The area under the LROC curve (AUC_LROC) on the diagnosis of suspicious lesions was computed and compared between the aided and unaided sessions.
- Secondary Outcome Measures
Name Time Method Lesion detection sensitivity and specificity 6 weeks The mean sensitivity and specificity of 15 readers were calculated and compared between the aided and unaided sessions.
Trial Locations
- Locations (1)
Yonsei University Severance Hospital
🇰🇷Seoul, Korea, Republic of
Yonsei University Severance Hospital🇰🇷Seoul, Korea, Republic of