GloFlow: Global Image Alignment for Creation of Whole Slide Images for Pathology from Video
This addresses the bottleneck in pathology slide digitization by reducing reliance on expensive hardware, though it is incremental as it builds on known optical flow techniques.
The paper tackles the high cost of slide digitization for pathology by proposing GloFlow, a two-stage optical flow and graph-pruning method for creating whole slide images from video, which outperforms existing stitching approaches on simulated data.
The application of deep learning to pathology assumes the existence of digital whole slide images of pathology slides. However, slide digitization is bottlenecked by the high cost of precise motor stages in slide scanners that are needed for position information used for slide stitching. We propose GloFlow, a two-stage method for creating a whole slide image using optical flow-based image registration with global alignment using a computationally tractable graph-pruning approach. In the first stage, we train an optical flow predictor to predict pairwise translations between successive video frames to approximate a stitch. In the second stage, this approximate stitch is used to create a neighborhood graph to produce a corrected stitch. On a simulated dataset of video scans of WSIs, we find that our method outperforms known approaches to slide-stitching, and stitches WSIs resembling those produced by slide scanners.