Conditional generative adversarial network for synthesizing hyperspectral images of breast cancer cells from digitized histology

• Type of Material: Article
• Authors: Martin Halicek, University of Texas Dallas; Samuel Ortega, University of Texas Dallas; Himar Fabelo, University of Las Palmas de Gran Canaria; Carlos Lopez, Hospital de Tortosa Verge de la Cinta; Marylene Lejaune, Hospital de Tortosa Verge de la Cinta; Gustavo M. Callico, University of Las Palmas de Gran Canaria; Baowei Fei, Emory University
• Language: English
• Date: 2021-01-01
• Publisher: SPIE-INT SOC OPTICAL ENGINEERING
• Publication Version: Author Accepted Manuscript (After Peer Review)
• Copyright Statement: Proc. of SPIE Vol. 11320 113200U-8
• Final Published Version (URL): http://dx.doi.org/10.1117/12.2549994
• Title of Journal or Parent Work: MEDICAL IMAGING 2020: DIGITAL PATHOLOGY
• Volume: 11320
• Grant/Funding Information: This research was supported in part by the U.S. National Institutes of Health (NIH) grants (R01CA156775, R01CA204254, R01HL140325, and R21CA231911) and by the Cancer Prevention and Research Institute of Texas (CPRIT) grant RP190588. Additionally, this research was supported in part by the Canary Islands Government through the ACIISI (Canarian Agency for Research, Innovation and the Information Society), ITHACA project under Grant Agreement ProID2017010164. This work was completed while Samuel Ortega was beneficiary of a pre-doctoral grant given by the “Agencia Canaria de Investigacion, Innovacion y Sociedad de la Información (ACIISI)” of the “Conserjería de Economía, Industria, Comercio y Conocimiento” of the “Gobierno de Canarias”, which is part-financed by the European Social Fund (FSE) (POC 2014-2020, Eje 3 Tema Prioritario 74 (85%)).
• Keywords: Engineering; Optics; Physical Sciences; Science & Technology; Radiology, Nuclear Medicine & Medical Imaging; Life Sciences & Biomedicine; Technology; Engineering, Biomedical
• Research Categories: Engineering, Biomedical; Engineering, Nuclear; Health Sciences, Radiology

Abstract

Hyperspectral imaging (HSI), which acquires up to hundreds of bands, has been proposed as a promising imaging modality for digitized histology beyond RGB imaging to provide more quantitative information to assist pathologists with disease detection in samples. While digitized RGB histology is quite standardized and easy to acquire, histological HSI often requires custom-made equipment and longer imaging times compared to RGB. In this work, we present a dataset of corresponding RGB digitized histology and histological HSI of breast cancer, and we develop a conditional generative adversarial network (GAN) to artificially synthesize HSI from standard RGB images of normal and cancer cells. The results of the GAN synthesized HSI are promising, showing structural similarity (SSIM) of approximately 80% and mean absolute error (MAE) of 6 to 11%. Further work is needed to establish the ability of generating HSI from RGB images on larger datasets.