Skip to content
DIMECHAIN

Healthcare

Advanced Medical ImagingMaturity: concept

Image reconstruction, denoising, classification and diagnostic assistance.

concept An idea we find credible. Nothing has been built or measured.

What this is

The problem

Imaging volume grows faster than the radiology workforce. Reconstruction quality, denoising and triage all affect how much of a radiologist's day is spent on images that did not need their attention.

Where the current approach strains

Reconstruction from limited data is an inverse problem, and reducing dose or acquisition time makes it harder. Denoising can remove the artefact and the finding together, which is the failure mode nobody wants.

What we are exploring

Reconstruction, denoising and triage support, with uncertainty reported alongside every output. A tool that flags its own low confidence is usable; one that is uniformly confident is not.

What would have to be true

Reader studies with radiologists, on data from scanners other than the ones used to develop it. Generalisation across sites is where medical imaging models most often fail, and it is rarely the headline result.

This is development-stage research. Not a medical device, no regulatory clearance, and not for diagnostic use.

Where it applies

Related

Want to co-develop this?