Automated Classification of Lung Cancer Types from Cytological Images Using Deep Convolutional Neural Networks

Atsushi Teramoto, Tetsuya Tsukamoto, Yuka Kiriyama, Hiroshi Fujita

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

Lung cancer is a leading cause of death worldwide. Currently, in differential diagnosis of lung cancer, accurate classification of cancer types (adenocarcinoma, squamous cell carcinoma, and small cell carcinoma) is required. However, improving the accuracy and stability of diagnosis is challenging. In this study, we developed an automated classification scheme for lung cancers presented in microscopic images using a deep convolutional neural network (DCNN), which is a major deep learning technique. The DCNN used for classification consists of three convolutional layers, three pooling layers, and two fully connected layers. In evaluation experiments conducted, the DCNN was trained using our original database with a graphics processing unit. Microscopic images were first cropped and resampled to obtain images with resolution of 256 × 256 pixels and, to prevent overfitting, collected images were augmented via rotation, flipping, and filtering. The probabilities of three types of cancers were estimated using the developed scheme and its classification accuracy was evaluated using threefold cross validation. In the results obtained, approximately 71% of the images were classified correctly, which is on par with the accuracy of cytotechnologists and pathologists. Thus, the developed scheme is useful for classification of lung cancers from microscopic images.

Original languageEnglish
Article number4067832
JournalBioMed Research International
Volume2017
DOIs
Publication statusPublished - 01-01-2017

Fingerprint

Lung Neoplasms
Neural networks
Small Cell Carcinoma
Cause of Death
Squamous Cell Carcinoma
Neoplasms
Adenocarcinoma
Differential Diagnosis
Pixels
Cells
Learning
Databases
Experiments

All Science Journal Classification (ASJC) codes

  • Biochemistry, Genetics and Molecular Biology(all)
  • Immunology and Microbiology(all)

Cite this

@article{68e3508ba58e46b68d3d53c320fa3dc4,
title = "Automated Classification of Lung Cancer Types from Cytological Images Using Deep Convolutional Neural Networks",
abstract = "Lung cancer is a leading cause of death worldwide. Currently, in differential diagnosis of lung cancer, accurate classification of cancer types (adenocarcinoma, squamous cell carcinoma, and small cell carcinoma) is required. However, improving the accuracy and stability of diagnosis is challenging. In this study, we developed an automated classification scheme for lung cancers presented in microscopic images using a deep convolutional neural network (DCNN), which is a major deep learning technique. The DCNN used for classification consists of three convolutional layers, three pooling layers, and two fully connected layers. In evaluation experiments conducted, the DCNN was trained using our original database with a graphics processing unit. Microscopic images were first cropped and resampled to obtain images with resolution of 256 × 256 pixels and, to prevent overfitting, collected images were augmented via rotation, flipping, and filtering. The probabilities of three types of cancers were estimated using the developed scheme and its classification accuracy was evaluated using threefold cross validation. In the results obtained, approximately 71{\%} of the images were classified correctly, which is on par with the accuracy of cytotechnologists and pathologists. Thus, the developed scheme is useful for classification of lung cancers from microscopic images.",
author = "Atsushi Teramoto and Tetsuya Tsukamoto and Yuka Kiriyama and Hiroshi Fujita",
year = "2017",
month = "1",
day = "1",
doi = "10.1155/2017/4067832",
language = "English",
volume = "2017",
journal = "BioMed Research International",
issn = "2314-6133",
publisher = "Hindawi Publishing Corporation",

}

Automated Classification of Lung Cancer Types from Cytological Images Using Deep Convolutional Neural Networks. / Teramoto, Atsushi; Tsukamoto, Tetsuya; Kiriyama, Yuka; Fujita, Hiroshi.

In: BioMed Research International, Vol. 2017, 4067832, 01.01.2017.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Automated Classification of Lung Cancer Types from Cytological Images Using Deep Convolutional Neural Networks

AU - Teramoto, Atsushi

AU - Tsukamoto, Tetsuya

AU - Kiriyama, Yuka

AU - Fujita, Hiroshi

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Lung cancer is a leading cause of death worldwide. Currently, in differential diagnosis of lung cancer, accurate classification of cancer types (adenocarcinoma, squamous cell carcinoma, and small cell carcinoma) is required. However, improving the accuracy and stability of diagnosis is challenging. In this study, we developed an automated classification scheme for lung cancers presented in microscopic images using a deep convolutional neural network (DCNN), which is a major deep learning technique. The DCNN used for classification consists of three convolutional layers, three pooling layers, and two fully connected layers. In evaluation experiments conducted, the DCNN was trained using our original database with a graphics processing unit. Microscopic images were first cropped and resampled to obtain images with resolution of 256 × 256 pixels and, to prevent overfitting, collected images were augmented via rotation, flipping, and filtering. The probabilities of three types of cancers were estimated using the developed scheme and its classification accuracy was evaluated using threefold cross validation. In the results obtained, approximately 71% of the images were classified correctly, which is on par with the accuracy of cytotechnologists and pathologists. Thus, the developed scheme is useful for classification of lung cancers from microscopic images.

AB - Lung cancer is a leading cause of death worldwide. Currently, in differential diagnosis of lung cancer, accurate classification of cancer types (adenocarcinoma, squamous cell carcinoma, and small cell carcinoma) is required. However, improving the accuracy and stability of diagnosis is challenging. In this study, we developed an automated classification scheme for lung cancers presented in microscopic images using a deep convolutional neural network (DCNN), which is a major deep learning technique. The DCNN used for classification consists of three convolutional layers, three pooling layers, and two fully connected layers. In evaluation experiments conducted, the DCNN was trained using our original database with a graphics processing unit. Microscopic images were first cropped and resampled to obtain images with resolution of 256 × 256 pixels and, to prevent overfitting, collected images were augmented via rotation, flipping, and filtering. The probabilities of three types of cancers were estimated using the developed scheme and its classification accuracy was evaluated using threefold cross validation. In the results obtained, approximately 71% of the images were classified correctly, which is on par with the accuracy of cytotechnologists and pathologists. Thus, the developed scheme is useful for classification of lung cancers from microscopic images.

UR - http://www.scopus.com/inward/record.url?scp=85028656667&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85028656667&partnerID=8YFLogxK

U2 - 10.1155/2017/4067832

DO - 10.1155/2017/4067832

M3 - Article

C2 - 28884120

AN - SCOPUS:85028656667

VL - 2017

JO - BioMed Research International

JF - BioMed Research International

SN - 2314-6133

M1 - 4067832

ER -