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.
For healthcare
BigHealth
AI for clinical risk assessment and medical imaging.
Overview
BigHealth brings our research in cardiovascular and stroke risk stratification and medical image analysis into a platform hospitals, diagnostic centres and researchers can use. Every result comes with the factors behind it, so clinicians can see why the model reached its view.
BigHealth supports clinical decisions; it does not replace a clinician’s judgement.
What BigHealth does
- Risk scoring with explanations
- Cardiovascular and stroke risk estimates that list the factors behind each score.
- Imaging support
- Segmentation and measurement support for ultrasound, IVUS and X-ray images.
- Record summaries
- Structured summaries of patient reports and records, linked to the source.
- Clinical dashboards
- Population views for clinical and research teams, with cohort filters.
How it works
Connect
Integrate with PACS and hospital systems, or upload de-identified data.
Analyse
Models process images and records and produce explained results.
Review
Clinicians review, accept or correct each result.
Improve
Corrections feed back into validation and model updates.
BigHealth in action
Filter all case studies
Transformer 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.
Clinical report summarisation for a hospital
An assistant that turns long reports and discharge notes into structured summaries for clinicians, with every statement linked to its source.
Other products
See BigHealth on your data
We run demos on a sample of your own data, so you can judge the results for yourself.