Segmenting and classifying tuberculosis, pneumonia and COVID-19 in chest X-rays
A deep learning pipeline that first isolates the lungs in a chest X-ray, then classifies the image as normal, tuberculosis, pneumonia or COVID-19.
MedTech
AI for medical imaging and clinical risk, grounded in our published research.
Overview
Our MedTech work builds on peer-reviewed research in cardiovascular and stroke risk stratification, medical image segmentation and explainable AI. We design clinical AI to support clinicians with transparent reasoning, validated on the populations it will serve, and never to replace clinical judgement.
What we build
- Medical image segmentation
- Deep learning that outlines structures in ultrasound, IVUS, X-ray and CT images for measurement and review.
- Clinical risk stratification
- Models that estimate cardiovascular and stroke risk from imaging, labs and patient history.
- Explainable clinical AI
- Outputs that show the image regions and risk factors behind each result, so clinicians can verify them.
- Bias and validation studies
- Checks for bias across patient groups and validation designs suitable for clinical and regulatory review.
Use cases by industry
Where medtech makes the biggest difference for our clients.
MedTech: case studies & projects
Filter all case studiesTransformer models for coronary artery wall segmentation in intravascular ultrasound
A review of transformer and attention-based deep learning architectures for outlining coronary artery walls in IVUS images, and where they outperform earlier networks.
AI frameworks for cardiovascular and stroke risk in patients with comorbidities
A body of research on how AI can estimate cardiovascular and stroke risk in people with diabetes, Parkinson’s disease, rheumatoid arthritis, sleep apnoea and COVID-19.
How we deliver
Discover
A short workshop to understand the problem, the data and what success looks like.
Prototype
A working proof of concept on a sample of your data, so you can judge results early.
Build
The full solution, tested against your data and integrated with your systems.
Deploy and support
Production deployment on your cloud, with monitoring and continuous improvement.
Questions
Are your models approved for clinical use?
Clinical use depends on the specific product and regulatory pathway. We design studies and documentation to support approval, and say clearly when a tool is for research use only.
Can you work with our hospital’s data securely?
Yes. We work under data-sharing agreements, de-identify data and can train models inside your environment.
More technologies
Explore medtech for your organisation
Start with a free discovery call. We will tell you honestly what is possible with your data.