Iterative annotation to ease neural network training: Specialized machine learning in medical image analysis

TL;DR

This paper introduces an iterative, human-in-the-loop annotation method using a familiar WSI viewer to improve neural network training for medical image segmentation, demonstrated on renal and prostate tissue images.

Contribution

It presents an intuitive annotation interface combined with iterative training to reduce annotation effort and enhance segmentation accuracy in medical imaging.

Findings

Network performance improves with each iteration.

Effective multi-class segmentation achieved in renal tissue.

Method adapts to different medical imaging modalities.

Abstract

Neural networks promise to bring robust, quantitative analysis to medical fields, but adoption is limited by the technicalities of training these networks. To address this translation gap between medical researchers and neural networks in the field of pathology, we have created an intuitive interface which utilizes the commonly used whole slide image (WSI) viewer, Aperio ImageScope (Leica Biosystems Imaging, Inc.), for the annotation and display of neural network predictions on WSIs. Leveraging this, we propose the use of a human-in-the-loop strategy to reduce the burden of WSI annotation. We track network performance improvements as a function of iteration and quantify the use of this pipeline for the segmentation of renal histologic findings on WSIs. More specifically, we present network performance when applied to segmentation of renal micro compartments, and demonstrate multi-class segmentation in human and mouse renal tissue slides. Finally, to show the adaptability of this technique to other medical imaging fields, we demonstrate its ability to iteratively segment human prostate glands from radiology imaging data.