Developing image analysis pipelines of whole-slide images: Pre- and post-processing.

Byron Smith,Meyke Hermsen,Elizabeth Lesser,Walter Kremers,Deepak Ravichandar

doi:10.1017/cts.2020.531

Abstract

Deep learning has pushed the scope of digital pathology beyond simple digitization and telemedicine. The incorporation of these algorithms in routine workflow is on the horizon and maybe a disruptive technology, reducing processing time, and increasing detection of anomalies. While the newest computational methods enjoy much of the press, incorporating deep learning into standard laboratory workflow requires many more steps than simply training and testing a model. Image analysis using deep learning methods often requires substantial pre- and post-processing order to improve interpretation and prediction. Similar to any data processing pipeline, images must be prepared for modeling and the resultant predictions need further processing for interpretation. Examples include artifact detection, color normalization, image subsampling or tiling, removal of errant predictions, etc. Once processed, predictions are complicated by image file size - typically several gigabytes when unpacked. This forces images to be tiled, meaning that a series of subsamples from the whole-slide image (WSI) are used in modeling. Herein, we review many of these methods as they pertain to the analysis of biopsy slides and discuss the multitude of unique issues that are part of the analysis of very large images.

Highlights

Recent developments in hardware and software have expanded the opportunities for modeling and analysis of whole-slide images (WSIs) in pathology
Many methods described in this article can and have been used in standard image analysis, we focus on how they augment the deep learning model development process
The last decade’s evolutions in machine learning and whole-slide tissue scanners have changed the conversation around digital pathology and provided opportunities for increased accuracy and efficiency by the incorporation of computational pathology

Summary

Introduction

Recent developments in hardware and software have expanded the opportunities for modeling and analysis of whole-slide images (WSIs) in pathology. Analyzing images generated from a single center’s lab on an individual scanner may mitigate some of these issues, but variations may still exist across time as staining protocols and hardware changes To combat these sources of variability, preprocessing and post-processing are used in tandem with complex modeling to create a reliable diagnostic tool (Fig. 1). Networks (CNNs) to images as opposed to other machine learning algorithms such as support vector machines or random forest predictions To better understand this context, we briefly describe how deep learning is applied to images before moving on to the pre- and post-processing steps that improve output. Note that a general recommendation is to start with the simplest solution and expand on this solution with increasing complexity; examples of this will be included throughout

A Brief Overview of Deep Learning for Image Analysis

Findings

Discussion