A deep learning segmentation strategy that minimizes the amount of manually annotated images.

Thierry Pécot,Kristin Wallace,Alexander Alekseyenko

doi:10.12688/f1000research.52026.1

Thierry Pécot, Kristin Wallace + Show 1 more

Open Access

https://doi.org/10.12688/f1000research.52026.1

Copy DOI

Abstract

Deep learning has revolutionized the automatic processing of images. While deep convolutional neural networks have demonstrated astonishing segmentation results for many biological objects acquired with microscopy, this technology's good performance relies on large training datasets. In this paper, we present a strategy to minimize the amount of time spent in manually annotating images for segmentation. It involves using an efficient and open source annotation tool, the artificial increase of the training data set with data augmentation, the creation of an artificial data set with a conditional generative adversarial network and the combination of semantic and instance segmentations. We evaluate the impact of each of these approaches for the segmentation of nuclei in 2D widefield images of human precancerous polyp biopsies in order to define an optimal strategy.

Highlights

IntroductionDeep learning approaches have outperformed all existing methods for image segmentation[1,2,3,4]
Over the last decade, deep learning approaches have outperformed all existing methods for image segmentation[1,2,3,4]
We propose to use a high throughput chemical screen on U2OS cells dataset (CC) and a widefield mouse intestinal epithelium dataset (MIE)[12]

Summary

Introduction

Deep learning approaches have outperformed all existing methods for image segmentation[1,2,3,4]. The estimation of a label at each pixel, and instance segmentation, the identification of individual objects, were successfully applied to spatially characterize biological entities in microscopic images[5,6,7,8]. These powerful approaches rely on large annotated datasets. We propose a strategy to minimize the amount of time dedicated to manually annotate images and investigate several approaches to maximize accuracy when only using one annotated image We apply this strategy to segment nuclei stained with DAPI in widefield images of human colorectal adenomas (i.e. precancerous polyps) as follows. We combine U-Net[14,15], a semantic segmentation approach, and Mask R-CNN16, an instance segmentation approach, to improve the nuclear segmentation accuracy

Methods

Results

Conclusion