Event Date
Event Date
We developed a diffusion-model-based virtual staining (VS) technique that digitally generates histochemical staining from label-free imaging mass spectrometry (IMS) data. This VS approach introduces cellular morphological features and significantly enhances the effective spatial resolution of IMS images without requiring chemical staining. We validated our technique through blind testing on human kidney samples, successfully generated VS images presenting a good match to chemically stained tissue sections, despite using IMS data with ten-fold lower resolution. This approach has the potential to significantly expand the clinical and research applications of IMS by providing accurate, high-resolution histological context directly from label-free IMS data.
Presenter
UCLA Samueli School of Engineering (United States)
Yijie Zhang received his Bachelor of Science degree in Optical Science and Engineering from Zhejiang University in Hangzhou, China, in 2018. He earned his Master of Science degree in Electrical and Computer Engineering from UCLA in 2020. That same year, he joined Professor Aydogan Ozcan’s Bio- and Nano-Photonics Group in the Department of Electrical and Computer Engineering at UCLA to pursue his Ph.D. His research primarily focuses on computational imaging for virtual tissue staining and biosensing.