Cargando…

TilGAN: GAN for Facilitating Tumor-Infiltrating Lymphocyte Pathology Image Synthesis With Improved Image Classification

Tumor-infiltrating lymphocytes (TILs) act as immune cells against cancer tissues. The manual assessment of TILs is usually erroneous, tedious, costly and subject to inter- and intraobserver variability. Machine learning approaches can solve these issues, but they require a large amount of labeled da...

Descripción completa

Detalles Bibliográficos
Autores principales: SAHA, MONJOY, GUO, XIAOYUAN, SHARMA, ASHISH
Formato: Online Artículo Texto
Lenguaje:English
Publicado: 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8224465/
https://www.ncbi.nlm.nih.gov/pubmed/34178560
http://dx.doi.org/10.1109/access.2021.3084597
_version_ 1783711894865969152
author SAHA, MONJOY
GUO, XIAOYUAN
SHARMA, ASHISH
author_facet SAHA, MONJOY
GUO, XIAOYUAN
SHARMA, ASHISH
author_sort SAHA, MONJOY
collection PubMed
description Tumor-infiltrating lymphocytes (TILs) act as immune cells against cancer tissues. The manual assessment of TILs is usually erroneous, tedious, costly and subject to inter- and intraobserver variability. Machine learning approaches can solve these issues, but they require a large amount of labeled data for model training, which is expensive and not readily available. In this study, we present an efficient generative adversarial network, TilGAN, to generate high-quality synthetic pathology images followed by classification of TIL and non-TIL regions. Our proposed architecture is constructed with a generator network and a discriminator network. The novelty exists in the TilGAN architecture, loss functions, and evaluation techniques. Our TilGAN-generated images achieved a higher Inception score than the real images (2.90 vs. 2.32, respectively). They also achieved a lower kernel Inception distance (1.44) and a lower Fréchet Inception distance (0.312). It also passed the Turing test performed by experienced pathologists and clinicians. We further extended our evaluation studies and used almost one million synthetic data, generated by TilGAN, to train a classification model. Our proposed classification model achieved a 97.83% accuracy, a 97.37% F1-score, and a 97% area under the curve. Our extensive experiments and superior outcomes show the efficiency and effectiveness of our proposed TilGAN architecture. This architecture can also be used for other types of images for image synthesis.
format Online
Article
Text
id pubmed-8224465
institution National Center for Biotechnology Information
language English
publishDate 2021
record_format MEDLINE/PubMed
spelling pubmed-82244652021-06-24 TilGAN: GAN for Facilitating Tumor-Infiltrating Lymphocyte Pathology Image Synthesis With Improved Image Classification SAHA, MONJOY GUO, XIAOYUAN SHARMA, ASHISH IEEE Access Article Tumor-infiltrating lymphocytes (TILs) act as immune cells against cancer tissues. The manual assessment of TILs is usually erroneous, tedious, costly and subject to inter- and intraobserver variability. Machine learning approaches can solve these issues, but they require a large amount of labeled data for model training, which is expensive and not readily available. In this study, we present an efficient generative adversarial network, TilGAN, to generate high-quality synthetic pathology images followed by classification of TIL and non-TIL regions. Our proposed architecture is constructed with a generator network and a discriminator network. The novelty exists in the TilGAN architecture, loss functions, and evaluation techniques. Our TilGAN-generated images achieved a higher Inception score than the real images (2.90 vs. 2.32, respectively). They also achieved a lower kernel Inception distance (1.44) and a lower Fréchet Inception distance (0.312). It also passed the Turing test performed by experienced pathologists and clinicians. We further extended our evaluation studies and used almost one million synthetic data, generated by TilGAN, to train a classification model. Our proposed classification model achieved a 97.83% accuracy, a 97.37% F1-score, and a 97% area under the curve. Our extensive experiments and superior outcomes show the efficiency and effectiveness of our proposed TilGAN architecture. This architecture can also be used for other types of images for image synthesis. 2021-05-28 2021 /pmc/articles/PMC8224465/ /pubmed/34178560 http://dx.doi.org/10.1109/access.2021.3084597 Text en https://creativecommons.org/licenses/by/4.0/This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
spellingShingle Article
SAHA, MONJOY
GUO, XIAOYUAN
SHARMA, ASHISH
TilGAN: GAN for Facilitating Tumor-Infiltrating Lymphocyte Pathology Image Synthesis With Improved Image Classification
title TilGAN: GAN for Facilitating Tumor-Infiltrating Lymphocyte Pathology Image Synthesis With Improved Image Classification
title_full TilGAN: GAN for Facilitating Tumor-Infiltrating Lymphocyte Pathology Image Synthesis With Improved Image Classification
title_fullStr TilGAN: GAN for Facilitating Tumor-Infiltrating Lymphocyte Pathology Image Synthesis With Improved Image Classification
title_full_unstemmed TilGAN: GAN for Facilitating Tumor-Infiltrating Lymphocyte Pathology Image Synthesis With Improved Image Classification
title_short TilGAN: GAN for Facilitating Tumor-Infiltrating Lymphocyte Pathology Image Synthesis With Improved Image Classification
title_sort tilgan: gan for facilitating tumor-infiltrating lymphocyte pathology image synthesis with improved image classification
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8224465/
https://www.ncbi.nlm.nih.gov/pubmed/34178560
http://dx.doi.org/10.1109/access.2021.3084597
work_keys_str_mv AT sahamonjoy tilganganforfacilitatingtumorinfiltratinglymphocytepathologyimagesynthesiswithimprovedimageclassification
AT guoxiaoyuan tilganganforfacilitatingtumorinfiltratinglymphocytepathologyimagesynthesiswithimprovedimageclassification
AT sharmaashish tilganganforfacilitatingtumorinfiltratinglymphocytepathologyimagesynthesiswithimprovedimageclassification