Data Augmentation Using Generative Adversarial Networks for Multi-Class Segmentation of Lung Confocal IF Images
Open Access
- 20 March 2022
- journal article
- Published by Fuji Technology Press Ltd. in Journal of Advanced Computational Intelligence and Intelligent Informatics
- Vol. 26 (2), 138-146
- https://doi.org/10.20965/jaciii.2022.p0138
Abstract
The human lung is a complex organ with high cellular heterogeneity, and its development and maintenance require interactive gene networks and dynamic cross-talk among multiple cell types. We focus on the confocal immunofluorescent (IF) images of lung tissues from the LungMAP database to reveal lung development. Using the current state-of-the-art deep learning-based model, the authors consider obtaining accurate multi-class segmentation of lung confocal IF images. One of the primary bottlenecks in using deep Convolutional Neural Network (CNN) models is the lack of availability of large-scale training or ground-truth segmentation labels. Then, we implement the multi-class segmentation with Generative Adversarial Network (GAN) models to expand the training dataset, improve overall segmentation accuracy, and discuss the effectiveness of created synthetic images in the segmentation of IF images. Consequently, experimental results indicated that 15.1% increased the accuracy of six-class segmentation using Mask R-CNN. In particular, the accuracy of our few data was mainly improved by using our proposed method. Therefore, the synthetic dataset can moderate the imbalanced data and be used for expanding the dataset.Keywords
Funding Information
- National Heart, Lung, and Blood Institute
This publication has 14 references indexed in Scilit:
- Initiating Multiomics Approach to Understand Neonatal Chronic Lung DiseasePublished by Elsevier BV ,2019
- Multi-Class Segmentation of Lung Immunofluorescence Confocal Images Using Deep LearningPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2019
- Semantic Image Synthesis With Spatially-Adaptive NormalizationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2019
- High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2018
- Development of a Web Based Image Annotation Tool for Lung Immunofluorescent Confocal ImagesInternational Symposium on Affective Science and Engineering, 2018
- LungMAP: The Molecular Atlas of Lung Development ProgramAmerican Journal of Physiology-Lung Cellular and Molecular Physiology, 2017
- Mask R-CNNPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- Image-to-Image Translation with Conditional Adversarial NetworksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- Lung development: orchestrating the generation and regeneration of a complex organDevelopment, 2014
- Toward a Confocal Subcellular Atlas of the Human ProteomeMolecular & Cellular Proteomics, 2008