@article{1cf7cc6d8db849b3b127ccf79bfc47e9,
title = "Classifying T cell activity in autofluorescence intensity images with convolutional neural networks",
abstract = "The importance of T cells in immunotherapy has motivated developing technologies to improve therapeutic efficacy. One objective is assessing antigen-induced T cell activation because only functionally active T cells are capable of killing the desired targets. Autofluorescence imaging can distinguish T cell activity states in a non-destructive manner by detecting endogenous changes in metabolic co-enzymes such as NAD(P)H. However, recognizing robust activity patterns is computationally challenging in the absence of exogenous labels. We demonstrate machine learning methods that can accurately classify T cell activity across human donors from NAD(P)H intensity images. Using 8260 cropped single-cell images from six donors, we evaluate classifiers ranging from traditional models that use previously-extracted image features to convolutional neural networks (CNNs) pre-trained on general non-biological images. Adapting pre-trained CNNs for the T cell activity classification task provides substantially better performance than traditional models or a simple CNN trained with the autofluorescence images alone. Visualizing the images with dimension reduction provides intuition into why the CNNs achieve higher accuracy than other approaches. Our image processing and classifier training software is available at https://github.com/gitter-lab/t-cell-classification.",
keywords = "NAD(P)H intensity, deep learning, label-free, transfer learning",
author = "Wang, {Zijie J.} and Walsh, {Alex J.} and Skala, {Melissa C.} and Anthony Gitter",
note = "Funding Information: We thank Tiffany Heaster for assistance with the T cell image processing; Quan Yin for CNN transfer learning advice; Shengchao Liu and Christine Walsh for general machine learning feedback; Katie Mueller, Steve Trier and Kelsey Tweed for discussion of the classification results; and Jaime Frey and Zach Miller for assistance with the Cooley cluster. This research was funded by NIH R01 CA205101, the UW Carbone Cancer Center Support Grant NIH P30 CA014520, the Morgridge Institute for Research and a UW-Madison L&S Honors Program Summer Senior Thesis Research Grant. In addition, this research benefited from GPU hardware from NVIDIA, resources of the Argonne Leadership Computing Facility, which is a DOE Office of Science User Facility supported under contract DE-AC02-06CH11357, the use of credits from the NIH Cloud Credits Model Pilot, a component of the NIH Big Data to Knowledge (BD2K) program, and the compute resources and assistance of the UW-Madison Center for High Throughput Computing (CHTC) in the Department of Computer Sciences. The CHTC is supported by UW-Madison, the Advanced Computing Initiative, the Wisconsin Alumni Research Foundation, the Wisconsin Institutes for Discovery and the National Science Foundation and is an active member of the Open Science Grid. Funding Information: We thank Tiffany Heaster for assistance with the T cell image processing; Quan Yin for CNN transfer learning advice; Shengchao Liu and Christine Walsh for general machine learning feedback; Katie Mueller, Steve Trier and Kelsey Tweed for discussion of the classification results; and Jaime Frey and Zach Miller for assistance with the Cooley cluster. This research was funded by NIH R01 CA205101, the UW Carbone Cancer Center Support Grant NIH P30 CA014520, the Morgridge Institute for Research and a UW‐Madison L&S Honors Program Summer Senior Thesis Research Grant. In addition, this research benefited from GPU hardware from NVIDIA, resources of the Argonne Leadership Computing Facility, which is a DOE Office of Science User Facility supported under contract DE‐AC02‐06CH11357, the use of credits from the NIH Cloud Credits Model Pilot, a component of the NIH Big Data to Knowledge (BD2K) program, and the compute resources and assistance of the UW‐Madison Center for High Throughput Computing (CHTC) in the Department of Computer Sciences. The CHTC is supported by UW‐Madison, the Advanced Computing Initiative, the Wisconsin Alumni Research Foundation, the Wisconsin Institutes for Discovery and the National Science Foundation and is an active member of the Open Science Grid. Publisher Copyright: {\textcopyright} 2019 The Authors. Journal of Biophotonics published by WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim Copyright: Copyright 2020 Elsevier B.V., All rights reserved.",
year = "2020",
month = mar,
day = "1",
doi = "10.1002/jbio.201960050",
language = "English (US)",
volume = "13",
journal = "Journal of Biophotonics",
issn = "1864-063X",
publisher = "Wiley",
number = "3",
}