Using AI to help diagnose suspected lung and breast cancer
A Non-interventional Study Evaluating Samples From Patients With Suspected Non-small Lung Cancer or Breast Cancer to Describe Pathology Practices and to Evaluate Computational Pathology Plus Artificial Intelligence Algorithms.
AstraZeneca · NCT06827132
This project will test AI-powered pathology tools on tissue samples from adults suspected of having lung or breast cancer to see how they perform alongside routine lab review.
Quick facts
| Study type | Observational |
|---|---|
| Enrollment | 600 (estimated) |
| Sex | All |
| Sponsor | AstraZeneca (industry) |
| Locations | 1 site (Nairobi) |
| Trial ID | NCT06827132 on ClinicalTrials.gov |
What this trial studies
This non-interventional, retrospective study will implement computational pathology and AI algorithms in digital pathology laboratories to analyze samples from adults with suspected invasive breast cancer, ductal carcinoma in situ, or non-small cell lung cancer. The study is conducted in two parts (first breast, then lung) across sites in Australia, Brazil, Egypt, and Kenya, with additional lung centers to be selected later. Participating labs will run specified AI algorithms (Galen™ Breast in Australia and MindPeak Breast in Brazil, Egypt, and Kenya) on previously collected samples that were originally read by conventional pathology workflows. Approximately 150 samples per laboratory will be used for the primary objectives, and samples with poor technical quality or those previously used in AI training are excluded.
Who should consider this trial
Good fit: Ideal candidates are adults (≥18 years) whose tissue samples were taken for suspected non-small cell lung cancer or invasive breast cancer/DCIS and were processed in participating laboratories with adequate slide quality.
Not a fit: Patients whose samples are low-quality, taken by fine needle aspiration or sent for cytology, previously used in algorithm training, or who are under 18 are unlikely to benefit from this work.
Why it matters
Potential benefit: If successful, the AI tools could help pathologists detect cancers more accurately or more quickly, especially in regions with few pathologists.
How similar studies have performed: Previous research has shown promising results for AI in breast and lung pathology, but broader clinical adoption and validation across diverse settings remain limited.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria:Sample from adult patients (≥ 18 years) with suspected non-small cell lung cancer or invasive breast cancer or ductal carcinoma in situ. \- Exclusion Criteria: * Samples with the inadequate technical quality of slides (pre-analytics quality) or images, e.g., broken slides, large out-of-focus areas, slides with fixation artefacts. * Samples from cases that were included in the training or technical validation. * Sample taken by fine needle aspiration. * Sample sent for cytological evaluation.
Where this trial is running
Nairobi
- Research Site — Nairobi, Kenya (RECRUITING)
Study contacts
- Study coordinator: AstraZeneca Clinical Study Information Center
- Email: information.center@astrazeneca.com
- Phone: 1-877-240-9479
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.
Conditions: Lung Cancer, Breast Cancer, Artificial intelligence, Computational Pathology, Algorithm, Positive predictive value, Negative predictive value, Galen™ Breast application