Researchers from the Cambridge Cardiovascular network and their collaborators have created a system called CytoDiffusion that uses generative AI to study the shape and structure of blood cells. A tool that can analyse abnormalities in the shape and form of blood cells with greater accuracy and reliability than human experts could change the way some conditions are diagnosed. CytoDiffusion could accurately identify a wide range of normal blood cell appearances and spot unusual or rare cells that may indicate disease. Results are reported in the journal Nature Machine Intelligence.
The ability to spot subtle differences in blood cell size, shape and appearance requires years of training, and experienced doctors can disagree on difficult cases. While CytoDiffusion is not a replacement for trained clinicians, the new model can triage cases, highlighting anything unusual for human review.
To develop CytoDiffusion, the researchers trained the system on over half a million images of blood smears collected at Addenbrooke’s Hospital in Cambridge. The dataset – the largest of its kind – included both common blood cell types and rarer examples, as well as elements that can confuse automated systems. The AI became robust to differences between hospitals, microscopes and staining methods, and better able to recognise rare or abnormal cells.
“When we tested its accuracy, the system was slightly better than humans,” said first author Simon Deltadahl of Cambridge University’s Department of Applied Mathematics and Theoretical Physics. “Our model would never say it was certain and then be wrong, but that is something that humans sometimes do.”
“We evaluated our method against many of the challenges seen in real-world AI, such as never-before-seen images, images captured by different machines and the degree of uncertainty in the labels,” said co-senior author Professor Michael Roberts, also from Cambridge’s Department of Applied Mathematics and Theoretical Physics. “This framework gives a multi-faceted view of model performance, which we believe will be beneficial to researchers.”
As part of the project, the researchers are releasing what they say is the world’s largest publicly available dataset of peripheral blood smear images: more than half a million in total.
“By making this resource open, we hope to empower researchers worldwide to build and test new AI models, democratise access to high-quality medical data, and ultimately contribute to better patient care,” said Deltadahl.
Further work is needed to make the system faster and to test it across diverse patient populations to ensure fairness and accuracy.
Read a longer article on the Cambridge University research website.