GloFlow: Global Image Alignment for Creation of Whole Slide Images for Pathology from Video

TL;DR

GloFlow is a novel two-stage optical flow-based method that efficiently creates accurate whole slide images from video scans, reducing reliance on expensive slide scanner hardware.

Contribution

It introduces a global alignment approach with graph pruning for slide stitching, improving accuracy and computational efficiency over existing methods.

Findings

Outperforms existing slide-stitching approaches on simulated data.

Produces stitched images comparable to those from traditional slide scanners.

Demonstrates effectiveness of optical flow and graph-based correction in pathology imaging.

Abstract

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.