Human-AI Collaborative INSIGHT Diagnostic Workflow for in Breast Cancer With Extensive Intraductal Component

Launched by SUN YAT-SEN UNIVERSITY · Jul 1, 2025

Keywords

ClinConnect Summary

This clinical trial is studying a new way to help doctors find invasive breast cancer more accurately in a specific type of tumor called extensive intraductal carcinoma (EIC). This tumor can be hard to diagnose using regular methods. The study compares two approaches: one where doctors use an artificial intelligence (AI) tool that highlights suspicious areas on breast tissue samples, and another where doctors review the samples the usual way without AI help. The goal is to see if the AI-assisted method helps doctors find invasive cancer better, how long it takes them to review the samples, and whether fewer extra tests are needed.

Women who have had breast surgery for tumors mostly made up of a non-invasive form called ductal carcinoma in situ (DCIS), with tumors larger than 2 cm and extensive calcifications (small calcium deposits seen on imaging), may be eligible. The study uses breast tissue samples already taken during surgery—no new procedures are needed. If eligible, your stored tissue samples will be randomly assigned to be reviewed either with the AI tool or by standard methods. This helps researchers understand if AI can improve cancer diagnosis and support doctors in making the best treatment decisions.

Gender

FEMALE

Eligibility criteria

• Inclusion Criteria:
• • DCIS (ductal carcinoma in situ) with or without invasive carcinoma, as confirmed by core needle biopsy prior to surgery.
• • Tumor size \>2 cm (cT2-cT4 according to AJCC 8th edition staging) with extensive calcifications, as documented by ultrasound or MRI.
• • Undergone either mastectomy or breast-conserving surgery.
• • Histopathological examination showing DCIS comprising ≥80% of the total tumor volume in the surgical specimen.
• • DCIS (ductal carcinoma in situ) with or without invasive carcinoma, as confirmed by core needle biopsy prior to surgery.
• • - Minimum of 10 H\&E-stained slides available for each case, with adequate tissue quality for analysis.
• Exclusion Criteria:
• • Received neoadjuvant therapy (chemotherapy, endocrine therapy, or targeted therapy) before surgery.
• • History of vacuum-assisted biopsy (VAB) or other minimally invasive breast procedures that may alter tumor architecture.
• • Insufficient or degraded tissue samples (e.g., due to fixation artifacts, sectioning errors, or poor staining quality).
• • Tumors lacking a DCIS (ductal carcinoma in situ) component upon histological examination.