Effectiveness of CadAI-B Dx for Decision Support in Breast Ultrasound

NCT07287111 | Completed FDA Device

• 1 other identifier: IP0014-US-CAB-I
• Study Type: interventional
• Target: 797
• Locations: 1 country
• Sites: 1

Brief Summary

This is a retrospective, fully-crossed, multi-reader, multi-case (MRMC) study to evaluate the effectiveness of 'CadAI-B Dx' (CadAI-B) for decision support in breast ultrasound. The study compares the diagnostic performance of readers interpreting breast ultrasound images with and without the aid of CadAI-B. A total of 797 patient cases will be included, comprising 350 cases with a confirmed diagnosis of malignancy and 447 cases with a confirmed benign diagnosis. Sixteen readers will participate in the study to evaluate the device.

Conditions

Breast Cancer; Breast Neoplasms

Outcome Measures

Primary Outcomes (1)

• Area Under the Localization Receiver Operating Characteristic (LROC) Curve (AULROC)

  The difference in reader performance between the unaided and AI-aided sessions in breast ultrasound interpretation. LROC reflects both detection accuracy and localization precision. The primary hypothesis is that the mean AULROC of all readers for the AI-aided reading mode is greater than that for the unaided reading mode.

  Through study completion, approximately 2 months

Secondary Outcomes (6)

• Sensitivity

  Through study completion, approximately 2 months

• Positive Predictive Value (PPV)

  Through study completion, approximately 2 months

• Negative Predictive Value (NPV)

  Through study completion, approximately 2 months

• Inter-reader Agreement

  Through study completion, approximately 2 months

• Reading Time

  Through study completion, approximately 2 months

Study Arms (2)

CadAI- Dx(AI) Unaided Reading

NO INTERVENTION

Readers evaluate each ultrasound image without access to AI assistance. Readers use only the provided radiological images and their professional clinical expertise to determine their final diagnosis and relevant findings

CadAI-DX (AI)-aided Reading

EXPERIMENTAL

Readers have access to CadAI-B's decision-support outputs, which include a pixel-level heatmap (CadAI-Map), auto-segmented lesion boundary, BI-RADS lexicon descriptors, a suggested malignancy probability score (CadAI-Score), and BI-RADS category.

Device: CadAI-B Dx

Interventions

CadAI-B Dx DEVICE

CadAI-B Dx is a Software as a Medical Device (SaMD) designed to assist physicians by providing Computer-Aided Detection (CADe) and Diagnosis (CADx) capabilities in breast ultrasound interpretation. The software automatically processes the image to identify suspicious regions (Lesion Detection) and provides a quantitative malignancy score (CadAI-Score) mapped to a corresponding BI-RADS Category. It also analyzes lesion size and BI-RADS lexicon descriptors.

CadAI-DX (AI)-aided Reading

Eligibility Criteria

• Age: 22 Years+
• Sex: female
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Women aged 22 years or older at the time of the breast ultrasound examination.
• Standard B-mode breast ultrasound images available for analysis.
• Lesions must have a confirmed diagnosis based on one of the following reference standards:
• Malignant Cases: Diagnosis of breast cancer confirmed through biopsy or surgery.
• Benign Cases: Confirmed as benign through biopsy or surgical excision, or confirmed as having no evidence of malignancy for at least 2 years of follow-up.

You may not qualify if:

• mages containing modes other than standard B-mode ultrasound, such as Doppler, elastography, or other annotations/overlays.
• Patients who have breast implant(s).
• Patients suffering from significant breast trauma or mastitis at the time of the breast ultrasound examination.
• Images of post-surgical resection sites.
• Images where multiple lesions are present within a single 2D ultrasound image

Sponsors & Collaborators

• BeamWorks Inc.: lead

Study Sites (1)

Yonsei University Severance Hospital

Seoul, 03722, South Korea

Location

MeSH Terms

Conditions

Breast Neoplasms

Condition Hierarchy (Ancestors)

Neoplasms by Site; Neoplasms; Breast Diseases; Skin Diseases; Skin and Connective Tissue Diseases

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: QUADRUPLE
• Who Masked: PARTICIPANT, CARE PROVIDER, INVESTIGATOR, OUTCOMES ASSESSOR
• Purpose: DIAGNOSTIC
• Intervention Model: CROSSOVER
• Sponsor Type: INDUSTRY
• Responsible Party: SPONSOR

Model Details: Retrospective, fully-crossed, Multi-Reader Multi-Case (MRMC) study.

Study Record Dates

• First Submitted: December 11, 2025
• First Posted: December 17, 2025
• Study Start: August 30, 2025
• Primary Completion: October 7, 2025
• Study Completion: November 24, 2025
• Last Updated: December 17, 2025

Record last verified: 2025-12

Data Sharing

• IPD Sharing: Will not share

Locations

KR (1)