Abstract
Whole slide imaging (WSI) devices, i.e. robotic microscopes and scanners, provide the starting point for computer-based processing of microscopy image, providing a complete toolkit for computer-aided diagnosis (CAD). This include biopsy analysis, which is crucial to make an accurate diagnosis in some diseases such as prostate cancer. A fully automated approach to region of interest (ROI) segmentation in prostate biopsy images is proposed here.
Highlights
Despite significant improvements in computer vision and image processing techniques, there are few software tools that are able to analyze prostate biopsy images in a fully automated way in order to find ROIs in those images
We have focused on samples digitized with 10x magnification, our work could be adapted to be magnification-independent
The results of the algorithm were compared to the manual selection of ROIs done by pathologists from the Hospital General Universitario de Ciudad Real (HGUCR)
Summary
Despite significant improvements in computer vision and image processing techniques, there are few software tools that are able to analyze prostate biopsy images in a fully automated way in order to find ROIs in those images. The segmentation of the ROI mentioned above is a complex task that includes several challenges. The suppression of user interaction means that the system should be robust enough to deal with image irregularities by itself. Such irregularities may include stain intensity variations, tissue cuts, and even dust over the slide when it is digitized. The physical size and memory requirements of the images limit the processing algorithms that may be used, since we want our system to be used in personal computers (i.e. not clusters)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
