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

Thierry Pécot,Kristin Wallace,Alexander Alekseyenko

doi:10.12688/f1000research.52026.2

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 dataset with data augmentation, the creation of an artificial dataset 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

Deep learning has revolutionized the automatic processing of images
One image was used to train U-Net and Mask R-CNN as well as pix2pix for most of the study, in addition to publicly available datasets
We propose to train a U-Net model and a Mask R-CNN model with a high throughput chemical screen on U2OS cells dataset (CC) and a widefield mouse intestinal epithelium dataset (MIE)[12]

Summary

Introduction

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. 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 dataset with data augmentation, the creation of an artificial dataset 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

Methods

Results

Conclusion