Department of Biochemistry and Molecular Biology, Hollings Cancer Center, Medical University of South Carolina, Charleston, SC, 29407, USA.
Rennes 1 University, SFR Biosit (UMS 3480 - US 018), F-35000 Rennes, France.
F1000Res. 2021 Mar 30;10:256. doi: 10.12688/f1000research.52026.2. eCollection 2021.
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.
深度学习彻底改变了图像的自动处理方式。虽然深度卷积神经网络已经为使用显微镜获取的许多生物对象的分割展示了惊人的结果，但这项技术的良好性能依赖于大型训练数据集。在本文中，我们提出了一种策略，以最大限度地减少手动注释图像进行分割所需的时间。它涉及使用高效且开源的注释工具、使用数据增强来人工增加训练数据集、使用条件生成对抗网络创建人工数据集以及结合语义分割和实例分割。我们评估了这些方法中每一种方法对人类癌前息肉活检的 2D 宽场图像中核的分割的影响，以便定义一种最佳策略。
