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

NCT07060599 | Not Yet Recruiting

• 1 other identifier: G2023-277-01
• Study Type: interventional
• Target: 480
• Locations: 1 country
• Sites: 1

Brief Summary

The goal of this clinical trial is to see if an artificial intelligence (AI)-assisted method helps doctors more accurately detect invasive breast cancer in people with a specific type of tumor called "extensive intraductal carcinoma" (EIC). This type of tumor is challenging to diagnose correctly using standard methods. The main question this study aims to answer is: Does the new AI-assisted method find more invasive breast cancer in EIC tumors compared to the standard method? Researchers will compare two groups:

• Group 1 (INSIGHT): Doctors review breast tissue samples using an AI tool that highlights suspicious areas needing closer attention.
• Group 2 (Conventional): Doctors review breast tissue samples without AI help, using the standard method. This comparison will show if the AI-assisted method works better at finding invasive cancer. What happens in the study?
• Researchers will use stored breast tissue samples already collected during the participant's surgery.
• Each sample will be randomly assigned to be reviewed using either the new AI-assisted method (Group 1) or the standard method (Group 2).
• In Group 1, an AI program will scan the tissue images first and point out areas that might contain invasive cancer for the doctor to check closely.
• In Group 2, doctors will review the tissue images without any AI help, using their standard process.
• Researchers will measure which method finds invasive cancer more accurately, how long the review takes, and how many additional tests (called IHC stains) are needed. No new procedures are required from participants; the study uses existing tissue samples.

Conditions

Artificial Intelligence (AI) in Diagnosis

Keywords

Extensive Intraductal Component; Breast Cancer; Pathology; Human-AI Collaborative Workflow; Artificial Intelligence; DCIS; Diagnosis

Outcome Measures

Primary Outcomes (1)

• Diagnostic sensitivity

  Diagnostic sensitivity for invasive carcinoma detection in breast cancer with extensive intraductal component

  through study completion, an average of 1 year

Secondary Outcomes (4)

• Diagnostic efficiency

  up to 24 weeks

• Immunohistochemical (IHC) stains utilization

  up to 24 weeks

• Diagnostic specificity

  through study completion, an average of 1 year

• Negative predictive value (NPV)

  through study completion, an average of 1 year

Study Arms (2)

Conventional Workflow

NO INTERVENTION

Pathologists review all WSIs without AI assistance; IHC stains ordered at pathologist's discretion.

INSIGHT Workflow

EXPERIMENTAL

AI pre-screening of WSIs; AI-generated ROI maps highlighting suspicious invasive cancer regions; Pathologist verifies AI-flagged ROIs and full slide review; IHC only triggered for uncertain ROIs if necessary.

Other: INvasion Screening with Intelligent Guidance for Histopathology Triage (INSIGHT) Workflow

Interventions

INvasion Screening with Intelligent Guidance for Histopathology Triage (INSIGHT) Workflow OTHER

An AI-generated segmentation model are refined through a post-processing pipeline: retaining only invasive carcinoma (IC) regions, filtering detections \<500 µm², grouping adjacent IC areas, and generating per-cluster bounding boxes (red boxes). This converted raw segmentations into clinically actionable ROI proposals, balancing sensitivity and specificity for pathologist review in external testing and clinical validation. The INSIGHT workflow addresses key diagnostic challenges in EIC cases by pre-screening whole-slide images (WSIs) and intelligently marking potential IC regions. This guides pathologists to prioritize diagnostically critical areas across multiple slides or within extensive DCIS - a task particularly valuable when IC is multifocal or presents as subtle micro-invasive foci easily overlooked during routine manual examination.

INSIGHT Workflow

Eligibility Criteria

• Healthy Volunteers: No
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)

You may qualify if:

• 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.

You may not qualify if:

• 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.

Sponsors & Collaborators

• Sun Yat-sen University: lead

Study Sites (1)

Sun Yat-sen University Cancer Center

Guangzhou, Guangdong, 510060, China

Location

MeSH Terms

Conditions

Breast Neoplasms; Carcinoma, Intraductal, Noninfiltrating; Disease

Condition Hierarchy (Ancestors)

Neoplasms by Site; Neoplasms; Breast Diseases; Skin Diseases; Skin and Connective Tissue Diseases; Adenocarcinoma; Carcinoma; Neoplasms, Glandular and Epithelial; Neoplasms by Histologic Type; Breast Carcinoma In Situ; Carcinoma in Situ; Neoplasms, Ductal, Lobular, and Medullary; Pathologic Processes; Pathological Conditions, Signs and Symptoms

Study Officials

• Peng Sun, MD, PhD.

  Sun Yat-sen University

  STUDY DIRECTOR

Central Study Contacts

Chen Jiang, MD, PhD.

CONTACT

+8613631417267; jiangchen@sysucc.org.cn

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: NONE
• Purpose: DIAGNOSTIC
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: MD, PhD

Study Record Dates

• First Submitted: June 24, 2025
• First Posted: July 11, 2025
• Study Start: August 1, 2025
• Primary Completion (Estimated): December 31, 2026
• Study Completion (Estimated): August 1, 2027
• Last Updated: July 11, 2025

Record last verified: 2025-07

Data Sharing

• IPD Sharing: Will not share

Locations

CN (1)