Application of Neural Networks to the Prediction of Lymph Node Metastasis in Oral Cancer

Toshiyuki Kawazu, Kazuyuki Araki, Kazunori Yoshiura, Eiji Nakayama, Shigenobu Kanda

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Neural networks are a new type of computing algorithm. They are especially useful in pattern recognition. In this study we applied neural networks to the prediction of lymph node metastasis of patients with oral cancer. A data set of 1,116 lymph nodes verified histopathologically was used to train and evaluate the neural networks. Various three-layer feed-forward networks with a back-propagation algorithm were employed in this study. Performance of the neural networks was compared with that of radiologists and discriminant analysis (Quantification theory type II). Neural networks had a sensitivity of 80.6% and a specificity of 94.6%. Diagnostic accuracy of the neural networks was 93.6%, which was comparable to those of discriminant analysis and clinical radiologists.

Original languageEnglish
Pages (from-to)137-142
Number of pages6
JournalOral Radiology
Volume19
Issue number2
Publication statusPublished - Dec 1 2003

Fingerprint

Mouth Neoplasms
Discriminant Analysis
Lymph Nodes
Neoplasm Metastasis
Radiologists
Datasets

All Science Journal Classification (ASJC) codes

  • Dentistry (miscellaneous)
  • Radiology Nuclear Medicine and imaging

Cite this

Application of Neural Networks to the Prediction of Lymph Node Metastasis in Oral Cancer. / Kawazu, Toshiyuki; Araki, Kazuyuki; Yoshiura, Kazunori; Nakayama, Eiji; Kanda, Shigenobu.

In: Oral Radiology, Vol. 19, No. 2, 01.12.2003, p. 137-142.

Research output: Contribution to journalArticle

Kawazu, T, Araki, K, Yoshiura, K, Nakayama, E & Kanda, S 2003, 'Application of Neural Networks to the Prediction of Lymph Node Metastasis in Oral Cancer', Oral Radiology, vol. 19, no. 2, pp. 137-142.
Kawazu, Toshiyuki ; Araki, Kazuyuki ; Yoshiura, Kazunori ; Nakayama, Eiji ; Kanda, Shigenobu. / Application of Neural Networks to the Prediction of Lymph Node Metastasis in Oral Cancer. In: Oral Radiology. 2003 ; Vol. 19, No. 2. pp. 137-142.
@article{6f3bc2edcf3b44bda62bf46dcc881990,
title = "Application of Neural Networks to the Prediction of Lymph Node Metastasis in Oral Cancer",
abstract = "Neural networks are a new type of computing algorithm. They are especially useful in pattern recognition. In this study we applied neural networks to the prediction of lymph node metastasis of patients with oral cancer. A data set of 1,116 lymph nodes verified histopathologically was used to train and evaluate the neural networks. Various three-layer feed-forward networks with a back-propagation algorithm were employed in this study. Performance of the neural networks was compared with that of radiologists and discriminant analysis (Quantification theory type II). Neural networks had a sensitivity of 80.6{\%} and a specificity of 94.6{\%}. Diagnostic accuracy of the neural networks was 93.6{\%}, which was comparable to those of discriminant analysis and clinical radiologists.",
author = "Toshiyuki Kawazu and Kazuyuki Araki and Kazunori Yoshiura and Eiji Nakayama and Shigenobu Kanda",
year = "2003",
month = "12",
day = "1",
language = "English",
volume = "19",
pages = "137--142",
journal = "Oral Radiology",
issn = "0911-6028",
publisher = "Springer Japan",
number = "2",

}

TY - JOUR

T1 - Application of Neural Networks to the Prediction of Lymph Node Metastasis in Oral Cancer

AU - Kawazu, Toshiyuki

AU - Araki, Kazuyuki

AU - Yoshiura, Kazunori

AU - Nakayama, Eiji

AU - Kanda, Shigenobu

PY - 2003/12/1

Y1 - 2003/12/1

N2 - Neural networks are a new type of computing algorithm. They are especially useful in pattern recognition. In this study we applied neural networks to the prediction of lymph node metastasis of patients with oral cancer. A data set of 1,116 lymph nodes verified histopathologically was used to train and evaluate the neural networks. Various three-layer feed-forward networks with a back-propagation algorithm were employed in this study. Performance of the neural networks was compared with that of radiologists and discriminant analysis (Quantification theory type II). Neural networks had a sensitivity of 80.6% and a specificity of 94.6%. Diagnostic accuracy of the neural networks was 93.6%, which was comparable to those of discriminant analysis and clinical radiologists.

AB - Neural networks are a new type of computing algorithm. They are especially useful in pattern recognition. In this study we applied neural networks to the prediction of lymph node metastasis of patients with oral cancer. A data set of 1,116 lymph nodes verified histopathologically was used to train and evaluate the neural networks. Various three-layer feed-forward networks with a back-propagation algorithm were employed in this study. Performance of the neural networks was compared with that of radiologists and discriminant analysis (Quantification theory type II). Neural networks had a sensitivity of 80.6% and a specificity of 94.6%. Diagnostic accuracy of the neural networks was 93.6%, which was comparable to those of discriminant analysis and clinical radiologists.

UR - http://www.scopus.com/inward/record.url?scp=0942276081&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0942276081&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0942276081

VL - 19

SP - 137

EP - 142

JO - Oral Radiology

JF - Oral Radiology

SN - 0911-6028

IS - 2

ER -