A New Color Augmentation Method for Deep Learning Segmentation of Histological Images
Authors:
- 1 April 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 886-890
Abstract
This paper addresses the problem of labeled data insufficiency in neural network training for semantic segmentation of color-stained histological images acquired via Whole Slide Imaging. It proposes an efficient image augmentation method to alleviate the demand for a large amount of labeled data and improve the network's generalization capacity. Typical image augmentation in bioimaging involves geometric transformation. Here, we propose a new image augmentation technique by combining the structure of one image with the color appearance of another image to construct augmented images on-the-fly for each training iteration. We show that it improves performance in the segmentation of histological images of human skin, and also offers better results when combined with geometric transformation.Keywords
This publication has 12 references indexed in Scilit:
- Adversarial Stain Transfer for Histopathology Image AnalysisIEEE Transactions on Medical Imaging, 2017
- Automatic Skin Lesion Segmentation Using Deep Fully Convolutional Networks With Jaccard DistanceIEEE Transactions on Medical Imaging, 2017
- Segmentation methods of H&E-stained histological images of lymphoma: A reviewInformatics in Medicine Unlocked, 2017
- Appearance normalization of histology slidesComputerized Medical Imaging and Graphics, 2015
- A Nonlinear Mapping Approach to Stain Normalization in Digital Histopathology Images Using Image-Specific Color DeconvolutionIEEE Transactions on Biomedical Engineering, 2014
- Segmentation of epidermal tissue with histopathological damage in images of haematoxylin and eosin stained human skinBMC Medical Imaging, 2014
- Color transfer between imagesIEEE Computer Graphics and Applications, 2001
- Backpropagation Applied to Handwritten Zip Code RecognitionNeural Computation, 1989
- Color Science: Concepts and Methods, Quantitative Data and Formulae, 2nd ed., by Gunter Wyszecki and W. S. Stiles, John Wiley and Sons, New York, 1982, 950 pp. Price: $75.00Color Research & Application, 1983
- Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in positionBiological Cybernetics, 1980