UCLA researchers in the Departments of Electrical Engineering and Computer Engineering have developed a novel method for automated image analysis of digital pathology slides.
Digital pathology is an extremely powerful imaging tool in cancer research and clinical practices Advancements in whole slide scanners has enabled complete digitization of pathology slides. However, tools for automatically detecting regions of interest in images have not yet been fully realized due to high computational cost, large image files and low contrast for features of interest. Improved methods for digitization of pathological analyses would offer important decision support for pathologists.
Professor Jalali and colleagues have developed a novel method for digitizing pathological analyses. The method relies on phase stretch transform (PST), a computational imaging algorithm for improved image feature detection. The image is processed in multiple steps, first using PST to create a feature library and then using machine learning to identify specific regions of interest (ROIs). The microscope stage is aligned with the desired ROI and the following quantitative analysis and tissue grading is carried out. The information is then stored for physician decision support. PST exhibits superior edge detection compared to previous best-in-class techniques in visually impaired images with high noise and low contrast.
digital microscopy, visually impaired image, phase stretch transform, quantitative analysis, decision support, smart microscopy