Earlier answers from every scan.
BreastScan AI reads breast ultrasound images with deep learning to help clinicians classify tumours as benign or malignant, supporting earlier and more consistent diagnosis.
The problem
Breast cancer is the most common cancer in women.
Early detection dramatically improves survival, but reading ultrasound images takes specialist time and experience that are not always available.
women were diagnosed with breast cancer in 2022.
deaths from breast cancer worldwide in 2022.
accuracy of our best deep learning model (ConvNet).
Sources: WHO breast cancer fact sheet (2024); results from the founding research paper (2024).
How it works
How it works
A clear path from data to decision.
Scan
A standard breast ultrasound image is captured.
Analyse
Deep learning models examine the image.
Classify
The tumour is classified as benign or malignant.
Review
The radiologist reviews the AI result and decides next steps.
Product
What makes it different.
Every feature is grounded in the founding research.
Ultrasound-based
Uses widely available, radiation-free imaging.
Benchmarked models
DenseNet-169, U-Net and ConvNet compared.
91% accuracy
ConvNet led with 85% precision and 83% recall.
Clinician-first
Decision support that keeps doctors in control.
Who it's for
Who it's for.
Radiology departments
Faster, more consistent reading.
Breast screening programmes
Prioritise suspicious cases.
Clinics with limited specialists
Expert-level support where it's needed.
The research
Built on peer-reviewed research.
- Studies deep learning for automating breast cancer diagnosis from ultrasound images.
- Evaluates DenseNet-169, U-Net and ConvNet models.
- Classifies tumours as benign or malignant.
- ConvNet performed best: accuracy 91%, recall 83%, precision 85%, F1 83%.
Khaleefah, S. H., et al. (2024). Applying Deep Learning Models to Breast Ultrasound Images for Automating Breast Cancer Diagnosis. JOIV: International Journal on Informatics Visualization, 8(3-2), 1779.
Team
The team behind it.
Founded in 2024 by a student team from two faculties.
Faculty of Health & Medical Technologies
Medical imaging and clinical validation.
Faculty of Science (Computer Science)
Deep learning models and software.
FAQ
Questions we hear often.
Does it replace the radiologist?
No. It supports clinicians with a second opinion; the final diagnosis is always a doctor's.
What imaging does it need?
Standard breast ultrasound images.
Is this a finished commercial product?
It is a research-based student startup moving from validated prototype toward pilots with real users.
Can we partner or run a pilot?
Yes. We are looking for organisations willing to test the solution in real conditions and share feedback.
Bring BreastScan AI to your organisation.
We are onboarding pilot partners now. Read the research and get in touch.