Artificial Intelligence (AI) in DiagnosisINSIGHT-EICNCT07060599
Human-AI Collaborative INSIGHT Diagnostic Workflow for in Breast Cancer With Extensive Intraductal Component
A study testing INvasion Screening with Intelligent Guidance for Histopathology Triage (INSIGHT) Workflow in people with Artificial Intelligence (AI) in Diagnosis, run by Sun Yat-sen University at 1 site in China.
Trial 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). Read more about this study
- Who is it for?
- Any age, women only
- Conditions the study is for
- Artificial Intelligence (AI) in Diagnosis
- What is being tested?
- INvasion Screening with Intelligent Guidance for Histopathology Triage (INSIGHT) Workflow
- Could I receive a placebo?
- No, everyone receives an active treatment
- How many people
- 480 participants
- Where
- 1 siteChina
- Study dates
- 1 Aug 2025to 1 Aug 2027
- Phase
- Interventional
- Are there results?
- Not yet: the study is under way
Key requirements
Who can take part, as listed by the sponsor. Only the study team can confirm whether you are eligible, so take this list to your doctor.
- Ages Any age
- Women only
- No healthy volunteers
- Child, Adult, Older adult
Who may be able to join
- 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.
Who cannot join
- 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.
Trial locations and contacts
1 site in 1 country. Contact the study team or a site near you to ask about taking part.
About this study
Official title: A Prospective Multicenter Randomized Trial Comparing the Human-AI Collaborative INSIGHT Workflow vs. Conventional Pathology Diagnosis for Detecting Invasive Carcinoma in Breast Cancer With Extensive Intraductal Component (EIC)
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:
Read more
- 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.
Read the detailed description
Breast cancer with extensive intraductal component (EIC) presents significant diagnostic challenges, characterized by widespread ductal carcinoma in situ (DCIS) frequently accompanied by small invasive foci (≤10 mm). Accurate identification of invasive carcinoma in EIC is critical for clinical staging and treatment decisions, yet conventional diagnostic methods face substantial limitations. Pathologists must manually screen extensive DCIS regions for minute invasive components, a labor-intensive process with reported miss rates reaching 20%, particularly for microinvasive foci (≤1 mm). Diagnostic uncertainty frequently leads to excessive immunohistochemical (IHC) staining (e.g., p63, CK5/6), with each stain costing ¥373.40, significantly increasing healthcare costs and prolonging turnaround times.
To address these challenges, we developed the INSIGHT (INvasion Screening with Intelligent Guidance for Histopathology Triage) human-AI collaborative workflow. This solution integrates four public datasets (TiGER, BRACS, BACH, CAS_PUIH) and employs weakly supervised pseudo-labeling to expand annotated pixels 22-fold to 25 billion, specifically improving representation of DCIS (3.14% to 12.53%) and benign tissue (0.65% to 10.9%). The AI model, based on a UperNet-VAN architecture, achieved Dice scores of 0.877 (training), 0.853 (validation), and 0.847 (testing). The system processes segmented invasive regions through size filtering (>500 µm²) and cluster grouping to generate actionable regions of interest (ROIs) for pathologist guidance.
In our preliminary retrospective study (576 whole slide images from 44 EIC patients), the INSIGHT workflow demonstrated superior diagnostic performance compared to conventional methods: sensitivity improved from 82.7% to 95.1% (p<0.001), with particularly notable gains in detecting ≤1 mm microinvasive foci (69.4% to 91.8%); negative predictive value (NPV) reached 96.7% versus 89.6% (p<0.001). The workflow reduced mean diagnostic time by 41.4% (102.6 to 60.1 seconds per slide, p<0.001) and decreased IHC usage by 40.4% (p=0.011). While standalone AI showed high sensitivity (95.6%), its specificity remained limited (76.6%), underscoring the necessity of human-AI collaboration.
This prospective clinical trial aims to validate the INSIGHT workflow's generalizability in real-world clinical settings, quantify its impact on patient stratification and treatment decisions, and establish standardized protocols for AI-assisted diagnosis to bridge critical gaps in computational pathology translation from research to clinical practice.
- Being tested
- INvasion Screening with Intelligent Guidance for Histopathology Triage (INSIGHT) Workflow
- Keywords
- Extensive Intraductal Component, Breast Cancer, Pathology, Human-AI Collaborative Workflow, Artificial Intelligence, DCIS, Diagnosis
- Medical subject headings
- Breast Neoplasms, Carcinoma, Intraductal, Noninfiltrating, Disease
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
INvasion Screening with Intelligent Guidance for Histopathology Triage (INSIGHT) WorkflowOther
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.
| Study group | Role | What they receive |
|---|---|---|
| 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. Receives: Other: INvasion Screening with Intelligent Guidance for Histopathology Triage (INSIGHT) Workflow |
What is being measured
The primary outcome is the main question the study is designed to answer.
Diagnostic sensitivity
Diagnostic sensitivity for invasive carcinoma detection in breast cancer with extensive intraductal component
Measured: through study completion, an average of 1 year
Secondary outcomes (4)
Diagnostic efficiency
Diagnostic time cost per case (minutes)
Measured: up to 24 weeks
Immunohistochemical (IHC) stains utilization
Immunohistochemical (IHC) stains utilization rate (stains/case)
Measured: up to 24 weeks
Diagnostic specificity
Diagnostic specificity for invasive carcinoma detection in breast cancer with extensive intraductal component
Measured: through study completion, an average of 1 year
Negative predictive value (NPV)
Negative predictive value (NPV) for invasive carcinoma detection in breast cancer with extensive intraductal component
Measured: through study completion, an average of 1 year
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted11 Jul 2025
- Study start1 Aug 2025 (estimated)
- Primary completion31 Dec 2026 (estimated)
- Study completion1 Aug 2027 (estimated)
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Other trials for Artificial Intelligence (AI) in DiagnosisStudies of the same condition, open and under way.
- More trials run by Sun Yat-sen UniversityThe sponsor's other registered studies.
- What the trial phases meanHow a treatment moves from first tests in people to approval.
More details
For doctors and researchers: how the study is designed, who runs it, and its registry IDs.
Study design
- Study type
- Interventional
- Phase
- Phase N/A
- Primary purpose
- Diagnosis
- Allocation
- Randomised
- Intervention model
- Parallel groups
- Masking
- None (open label)
- Enrolment
- 480 participants (estimated)
Sponsor and investigators
- Lead sponsor
- Sun Yat-sen University
- Sponsor type
- University, hospital or other
- Responsible party
- Principal investigator, Peng Sun, Sun Yat-sen University
- Investigators
- Peng Sun, MD, PhD., Study director, Sun Yat-sen University
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT07060599
- Sponsor's protocol ID
- G2023-277-01
- Acronym
- INSIGHT-EIC
- Status last verified
- Jul 2025
- First submitted
- 24 Jun 2025
- Last updated
- 11 Jul 2025
- Results posted
- No
- Data monitoring committee
- No
- FDA-regulated drug
- No
- FDA-regulated device
- No
- Individual data sharing
- No
Study at a glance
From the registry record, last updated by the sponsor on 11 Jul 2025. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- A Prospective Multicenter Randomized Trial Comparing the Human-AI Collaborative INSIGHT Workflow vs. Conventional Pathology Diagnosis for Detecting Invasive Carcinoma in Breast Cancer With Extensive Intraductal Component (EIC)
- ClinicalTrials.gov ID
- NCT07060599
- Acronym / sponsor ID
- INSIGHT-EIC / G2023-277-01
- Keywords
- Extensive Intraductal Component, Breast Cancer, Pathology, Human-AI Collaborative Workflow, Artificial Intelligence, DCIS, Diagnosis
- Study type
- Interventional
- Recruitment status
- Not yet recruiting
- Enrolment
- 480 participants (estimated)
- Lead sponsor
- Sun Yat-sen UniversityUniversity, hospital or other
- Study start
- 1 Aug 2025 (estimated)
- Primary completion
- 31 Dec 2026 (estimated)
- Study completion
- 1 Aug 2027 (estimated)
- First posted
- 11 Jul 2025 (actual)
- Results
- Not posted in the source record
Clinical summary
The research question as the sponsor registered it. This describes what the study plans to test, not what it found.
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.
Detailed description
Breast cancer with extensive intraductal component (EIC) presents significant diagnostic challenges, characterized by widespread ductal carcinoma in situ (DCIS) frequently accompanied by small invasive foci (≤10 mm). Accurate identification of invasive carcinoma in EIC is critical for clinical staging and treatment decisions, yet conventional diagnostic methods face substantial limitations. Pathologists must manually screen extensive DCIS regions for minute invasive components, a labor-intensive process with reported miss rates reaching 20%, particularly for microinvasive foci (≤1 mm). Diagnostic uncertainty frequently leads to excessive immunohistochemical (IHC) staining (e.g., p63, CK5/6), with each stain costing ¥373.40, significantly increasing healthcare costs and prolonging turnaround times.
To address these challenges, we developed the INSIGHT (INvasion Screening with Intelligent Guidance for Histopathology Triage) human-AI collaborative workflow. This solution integrates four public datasets (TiGER, BRACS, BACH, CAS_PUIH) and employs weakly supervised pseudo-labeling to expand annotated pixels 22-fold to 25 billion, specifically improving representation of DCIS (3.14% to 12.53%) and benign tissue (0.65% to 10.9%). The AI model, based on a UperNet-VAN architecture, achieved Dice scores of 0.877 (training), 0.853 (validation), and 0.847 (testing). The system processes segmented invasive regions through size filtering (>500 µm²) and cluster grouping to generate actionable regions of interest (ROIs) for pathologist guidance.
In our preliminary retrospective study (576 whole slide images from 44 EIC patients), the INSIGHT workflow demonstrated superior diagnostic performance compared to conventional methods: sensitivity improved from 82.7% to 95.1% (p<0.001), with particularly notable gains in detecting ≤1 mm microinvasive foci (69.4% to 91.8%); negative predictive value (NPV) reached 96.7% versus 89.6% (p<0.001). The workflow reduced mean diagnostic time by 41.4% (102.6 to 60.1 seconds per slide, p<0.001) and decreased IHC usage by 40.4% (p=0.011). While standalone AI showed high sensitivity (95.6%), its specificity remained limited (76.6%), underscoring the necessity of human-AI collaboration.
This prospective clinical trial aims to validate the INSIGHT workflow's generalizability in real-world clinical settings, quantify its impact on patient stratification and treatment decisions, and establish standardized protocols for AI-assisted diagnosis to bridge critical gaps in computational pathology translation from research to clinical practice.
Study design
- Primary purpose
- Diagnosis
- Allocation
- Randomised
- Intervention model
- Parallel groups
- Masking
- None (open label)
- Number of arms
- 2
| Arm | Type | Receives |
|---|---|---|
| Conventional Workflow | No intervention | –Pathologists review all WSIs without AI assistance; IHC stains ordered at pathologist's discretion. |
| INSIGHT Workflow | Experimental | Other: INvasion Screening with Intelligent Guidance for Histopathology Triage (INSIGHT) WorkflowAI 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. |
Who may qualify
- Sex
- Female only
- Healthy volunteers
- Not accepted
- Age groups
- Child, Adult, Older adult
Key inclusion criteria (6 listed)
- 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.
Key exclusion criteria (4 listed)
- 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.
Eligibility is decided by the study team after screening; this overview does not establish that a patient qualifies. Full inclusion and exclusion criteria.
Interventions
| Intervention | Type | Arms |
|---|---|---|
| INvasion Screening with Intelligent Guidance for Histopathology Triage (INSIGHT) WorkflowAn 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. | Other | INSIGHT Workflow |
Primary outcome
Diagnostic sensitivity
Time frame: through study completion, an average of 1 year
Diagnostic sensitivity for invasive carcinoma detection in breast cancer with extensive intraductal component
4 secondary outcomes
Diagnostic efficiency
Time frame: up to 24 weeks
Immunohistochemical (IHC) stains utilization
Time frame: up to 24 weeks
Diagnostic specificity
Time frame: through study completion, an average of 1 year
Negative predictive value (NPV)
Time frame: through study completion, an average of 1 year
Results and safety
This study is still under way. Results are not available in the source record yet.
Research links
- Official record on ClinicalTrials.govLast updated by the sponsor 11 Jul 2025.
- Individual participant dataSharing planned: No
Related trials for Artificial Intelligence (AI) in Diagnosis
Active, not recruitingObservational study
Accuracy and Time Efficiency of AI Versus Manual Segmentation in Adult Crowding Using Aligner Software
Dental Crowding
Active, not recruitingObservational study
A Multicenter Study in Bronchoscopy Combining Stimulated Raman Histology With Artificial Intelligence for Rapid Lung Cancer Detection - The ON-SITE Study
Lung Biopsy, Lung Cancer
Recruiting
AI-Assisted Interpretation of Cardiac CT in the Emergency Department
Chest Pain, Acute Coronary Syndrome
Active, not recruiting
AI-Supported Mobile High-Impact and Strengthening Exercise Program in Postmenopausal Women With Low Bone Density
Osteopenia
Active, not recruitingObservational study
Epigenetic Changes in Long COVID Patients
Long COVID-19 Syndrome, Long COVID Symptoms
Referral and contact
AzTrials does not enrol participants or take referrals. Contact the study team or a site listed below; they decide who can take part.
Peng Sun, MD, PhD. study director
Sun Yat-sen University
1 site in 1 country: see every site and its status.
Questions about this trial
What is this clinical trial studying?
A study testing INvasion Screening with Intelligent Guidance for Histopathology Triage (INSIGHT) Workflow in people with Artificial Intelligence (AI) in Diagnosis, run by Sun Yat-sen University at 1 site in China.
The full registered description is in the About this study section and the official record.
Who may be eligible to take part?
The sponsor lists 6 inclusion and 4 exclusion criteria. Eligibility is decided by the study team after screening, so read the full criteria and contact a listed site.
Is this clinical trial currently recruiting?
The record says: opening soon, as of the sponsor's last update on 11 Jul 2025. Status can change between updates, so confirm with the study contact before making plans.
Where is the study taking place?
The record lists 1 site in China. Whether a site is taking part right now should be confirmed with that site. See every site.
What are the possible benefits and risks?
They depend on the study and the treatment, and no study can promise a benefit. The study team explains the known risks during informed consent, before anyone joins; the record itself does not list them.
Are results available for this study?
This study is still under way. Results are not available in the source record yet.
How can a doctor refer a patient or contact the research team?
Contact Chen Jiang, MD, PhD. (+8613631417267, jiangchen@sysucc.org.cn), or a site near the patient. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
Diagnostic sensitivity (time frame: through study completion, an average of 1 year). It is what the study was designed to measure, not a finding.
Where can I read the original study information?
Does a listing mean the treatment is approved or proven to work?
No. A listing means the study is registered. It does not show that the treatment is safe, works, or is approved by a regulator.
How often is this information updated?
AzTrials copies changed records from ClinicalTrials.gov every night and reloads the whole registry every week. The sponsor last updated this record on 11 Jul 2025.