20 May 2025
Microscopy and AI combine to observe clotting activity as it happens.
A project at the University of Tokyo has developed a new imaging technique designed to observe the development of potentially dangerous blood clots.A combination of frequency-division multiplexed (FDM) microscopy and AI image analysis allows platelet clumping to be tracked in patients with coronary artery disease, opening the door to safer and more personalized medical treatment.
"Platelets play a crucial role in heart disease, especially in coronary artery disease, because they are directly involved in forming blood clots," said Kazutoshi Hirose from the University of Tokyo Hospital.
"To prevent dangerous clots, patients with coronary artery disease are often treated with anti-platelet drugs. However, it's still challenging to accurately evaluate how well these drugs are working in each individual, which makes monitoring platelet activity an important goal for both doctors and researchers."
As described in Nature Communications, the project set out to develop a new way of studying platelets in motion. Although a number of flow cytometry and assay techniques have been applied to this task, blood flow dynamics and the presence of other blood cells have made the measurements challenging.
The team's solution involves an FDM approach, in which an optical frequency comb of multiple spatially distributed beams is used as the light source. This arrangement can reveal the spatial profile of a target object, such as individual platelets or accumulations beginning to form.
"A frequency-division multiplexed microscope works like a super high-speed camera that takes sharp pictures of blood cells in flow," commented team member Yuqi Zhou.
"Just like traffic cameras capture every car on the road, our microscope captures thousands of images of blood cells in motion every second. We then use artificial intelligence to analyze those images. The AI can tell whether it’s looking at a single platelet, a clump of platelets, or even a white blood cell tagging along."
Personalized treatment for effective therapy
In trials using blood samples from over 200 patients, the FDM images revealed that patients with acute coronary syndrome had more platelet aggregates than those with chronic symptoms, supporting the idea that this technology can track clotting risk in real time.
The technique also indicated a regimen-dependent reduction in these concentrations upon treatment with anti-platelet drugs, which suggests that it will allow the effects of therapeutic treatments to be directly assessed.
"Typically, if doctors want to understand what's happening in the arteries, especially the coronary arteries, they need to do invasive procedures to collect blood," said Kazutoshi Hirose. "What we found is that just taking a regular blood sample from a vein in the arm can still provide meaningful information about platelet activity in the arteries. That's exciting because it makes the process much easier, safer and more convenient."
The Tokyo team thinks that a clearer picture of platelet behavior could lead to personalized therapies more closely matched to the requirements of individual patients, accommodating the way that different individuals react differently to treatment.
"Some patients are affected by recurrent thrombosis and others are suffering from recurrences of bleeding events even on the same anti-platelet medications," said Hirose. "Our technology can help doctors see how each individual's platelets are behaving in real time. That means treatments could be adjusted to better match each person’s needs."
© 2025 SPIE Europe |
|