Robust and accurate quantification of biomarkers of immune cells in lung cancer micro-environment using deep convolutional neural networks

Recent years have seen a growing awareness of the role the immune system plays in successful cancer treatment, especially in novel therapies like immunotherapy. The characterization of the immunological composition of tumors and their micro-environment is thus becoming a necessity. In this paper we...

Full description

Bibliographic Details
Main Authors: Lilija Aprupe, Geert Litjens, Titus J. Brinker, Jeroen van der Laak, Niels Grabe
Format: Article
Language:English
Published: PeerJ Inc. 2019-04-01
Series:PeerJ
Subjects:
Online Access:https://peerj.com/articles/6335.pdf
_version_ 1797424941026508800
author Lilija Aprupe
Geert Litjens
Titus J. Brinker
Jeroen van der Laak
Niels Grabe
author_facet Lilija Aprupe
Geert Litjens
Titus J. Brinker
Jeroen van der Laak
Niels Grabe
author_sort Lilija Aprupe
collection DOAJ
description Recent years have seen a growing awareness of the role the immune system plays in successful cancer treatment, especially in novel therapies like immunotherapy. The characterization of the immunological composition of tumors and their micro-environment is thus becoming a necessity. In this paper we introduce a deep learning-based immune cell detection and quantification method, which is based on supervised learning, i.e., the input data for training comprises labeled images. Our approach objectively deals with staining variation and staining artifacts in immunohistochemically stained lung cancer tissue and is as precise as humans. This is evidenced by the low cell count difference to humans of 0.033 cells on average. This method, which is based on convolutional neural networks, has the potential to provide a new quantitative basis for research on immunotherapy.
first_indexed 2024-03-09T08:08:55Z
format Article
id doaj.art-ba9a9355e95e4b6ebe9cbfbb801f66b0
institution Directory Open Access Journal
issn 2167-8359
language English
last_indexed 2024-03-09T08:08:55Z
publishDate 2019-04-01
publisher PeerJ Inc.
record_format Article
series PeerJ
spelling doaj.art-ba9a9355e95e4b6ebe9cbfbb801f66b02023-12-02T23:35:09ZengPeerJ Inc.PeerJ2167-83592019-04-017e633510.7717/peerj.6335Robust and accurate quantification of biomarkers of immune cells in lung cancer micro-environment using deep convolutional neural networksLilija Aprupe0Geert Litjens1Titus J. Brinker2Jeroen van der Laak3Niels Grabe4Hamamatsu Tissue Imaging and Analysis (TIGA) Center, BioQuant, Heidelberg University, Heidelberg, GermanyDepartment of Pathology, Radboud University Medical Center, Nijmegen, The NetherlandsDepartment of Dermatology and National Center for Tumor Diseases (NCT), University Hospital Heidelberg, Heidelberg, GermanyDepartment of Pathology, Radboud University Medical Center, Nijmegen, The NetherlandsHamamatsu Tissue Imaging and Analysis (TIGA) Center, BioQuant, Heidelberg University, Heidelberg, GermanyRecent years have seen a growing awareness of the role the immune system plays in successful cancer treatment, especially in novel therapies like immunotherapy. The characterization of the immunological composition of tumors and their micro-environment is thus becoming a necessity. In this paper we introduce a deep learning-based immune cell detection and quantification method, which is based on supervised learning, i.e., the input data for training comprises labeled images. Our approach objectively deals with staining variation and staining artifacts in immunohistochemically stained lung cancer tissue and is as precise as humans. This is evidenced by the low cell count difference to humans of 0.033 cells on average. This method, which is based on convolutional neural networks, has the potential to provide a new quantitative basis for research on immunotherapy.https://peerj.com/articles/6335.pdfLung cancerImmune cellsDeep learningCancer micro-environmentBiomarker quantification
spellingShingle Lilija Aprupe
Geert Litjens
Titus J. Brinker
Jeroen van der Laak
Niels Grabe
Robust and accurate quantification of biomarkers of immune cells in lung cancer micro-environment using deep convolutional neural networks
PeerJ
Lung cancer
Immune cells
Deep learning
Cancer micro-environment
Biomarker quantification
title Robust and accurate quantification of biomarkers of immune cells in lung cancer micro-environment using deep convolutional neural networks
title_full Robust and accurate quantification of biomarkers of immune cells in lung cancer micro-environment using deep convolutional neural networks
title_fullStr Robust and accurate quantification of biomarkers of immune cells in lung cancer micro-environment using deep convolutional neural networks
title_full_unstemmed Robust and accurate quantification of biomarkers of immune cells in lung cancer micro-environment using deep convolutional neural networks
title_short Robust and accurate quantification of biomarkers of immune cells in lung cancer micro-environment using deep convolutional neural networks
title_sort robust and accurate quantification of biomarkers of immune cells in lung cancer micro environment using deep convolutional neural networks
topic Lung cancer
Immune cells
Deep learning
Cancer micro-environment
Biomarker quantification
url https://peerj.com/articles/6335.pdf
work_keys_str_mv AT lilijaaprupe robustandaccuratequantificationofbiomarkersofimmunecellsinlungcancermicroenvironmentusingdeepconvolutionalneuralnetworks
AT geertlitjens robustandaccuratequantificationofbiomarkersofimmunecellsinlungcancermicroenvironmentusingdeepconvolutionalneuralnetworks
AT titusjbrinker robustandaccuratequantificationofbiomarkersofimmunecellsinlungcancermicroenvironmentusingdeepconvolutionalneuralnetworks
AT jeroenvanderlaak robustandaccuratequantificationofbiomarkersofimmunecellsinlungcancermicroenvironmentusingdeepconvolutionalneuralnetworks
AT nielsgrabe robustandaccuratequantificationofbiomarkersofimmunecellsinlungcancermicroenvironmentusingdeepconvolutionalneuralnetworks