Neural network analysis of breast cancer from MRI findings

P. Abdolmaleki, L. D. Buadu, S. Murayama, J. Murakami, N. Hashiguchi, H. Yabuuchi, K. Masuda

Research output: Contribution to journalArticle

20 Citations (Scopus)

Abstract

Purpose: To evaluate how much the experience of radiologists affects the performance of an artificial neural network (ANN) trained by two highly experienced radiologists. Materials and Methods: Before biopsy two experienced radiologists reviewed the MR images of 100 adult patients with suspicious breast lesions and evaluated their findings based on six features. This database was then used to train a three-layered feed-forward neural network. The network's generalizing ability was then tested to predict the outcome of biopsy in 56 new patients' records which were extracted by 10 participating radiologists. The MRI findings of each reader were presented to the ANN to evaluate the effect of various levels of experience on the output of the ANN. The performance of the ANN was then compared with that of attendant physicians in terms of sensitivity, specificity, and accuracy as well as ROC analysis. Results: The best ANN outcome offered a correct diagnosis in 40 of 41 of the patients with malignant breast cancer and 10 of 15 with benign entity presented in the testing set. The output of the trained ANN outperformed the attendant radiologists with low levels of experience and showed comparable performance with radiologists with higher levels of experience. Conclusions: The ANN is able to work as a backup system to assist radiologists in the diagnosis of breast cancer.

Original languageEnglish
Pages (from-to)283-293
Number of pages11
JournalRadiation Medicine - Medical Imaging and Radiation Oncology
Volume15
Issue number5
Publication statusPublished - Dec 1 1997

Fingerprint

network analysis
breast
cancer
Breast Neoplasms
Biopsy
Radiologists
ROC Curve
physicians
output
backups
readers
Breast
lesions
Databases
Physicians
Sensitivity and Specificity

All Science Journal Classification (ASJC) codes

  • Radiation
  • Radiology Nuclear Medicine and imaging
  • Oncology

Cite this

Abdolmaleki, P., Buadu, L. D., Murayama, S., Murakami, J., Hashiguchi, N., Yabuuchi, H., & Masuda, K. (1997). Neural network analysis of breast cancer from MRI findings. Radiation Medicine - Medical Imaging and Radiation Oncology, 15(5), 283-293.

Neural network analysis of breast cancer from MRI findings. / Abdolmaleki, P.; Buadu, L. D.; Murayama, S.; Murakami, J.; Hashiguchi, N.; Yabuuchi, H.; Masuda, K.

In: Radiation Medicine - Medical Imaging and Radiation Oncology, Vol. 15, No. 5, 01.12.1997, p. 283-293.

Research output: Contribution to journalArticle

Abdolmaleki, P, Buadu, LD, Murayama, S, Murakami, J, Hashiguchi, N, Yabuuchi, H & Masuda, K 1997, 'Neural network analysis of breast cancer from MRI findings', Radiation Medicine - Medical Imaging and Radiation Oncology, vol. 15, no. 5, pp. 283-293.
Abdolmaleki P, Buadu LD, Murayama S, Murakami J, Hashiguchi N, Yabuuchi H et al. Neural network analysis of breast cancer from MRI findings. Radiation Medicine - Medical Imaging and Radiation Oncology. 1997 Dec 1;15(5):283-293.
Abdolmaleki, P. ; Buadu, L. D. ; Murayama, S. ; Murakami, J. ; Hashiguchi, N. ; Yabuuchi, H. ; Masuda, K. / Neural network analysis of breast cancer from MRI findings. In: Radiation Medicine - Medical Imaging and Radiation Oncology. 1997 ; Vol. 15, No. 5. pp. 283-293.
@article{0de2a7e63868481a9d98357c84b9b2e2,
title = "Neural network analysis of breast cancer from MRI findings",
abstract = "Purpose: To evaluate how much the experience of radiologists affects the performance of an artificial neural network (ANN) trained by two highly experienced radiologists. Materials and Methods: Before biopsy two experienced radiologists reviewed the MR images of 100 adult patients with suspicious breast lesions and evaluated their findings based on six features. This database was then used to train a three-layered feed-forward neural network. The network's generalizing ability was then tested to predict the outcome of biopsy in 56 new patients' records which were extracted by 10 participating radiologists. The MRI findings of each reader were presented to the ANN to evaluate the effect of various levels of experience on the output of the ANN. The performance of the ANN was then compared with that of attendant physicians in terms of sensitivity, specificity, and accuracy as well as ROC analysis. Results: The best ANN outcome offered a correct diagnosis in 40 of 41 of the patients with malignant breast cancer and 10 of 15 with benign entity presented in the testing set. The output of the trained ANN outperformed the attendant radiologists with low levels of experience and showed comparable performance with radiologists with higher levels of experience. Conclusions: The ANN is able to work as a backup system to assist radiologists in the diagnosis of breast cancer.",
author = "P. Abdolmaleki and Buadu, {L. D.} and S. Murayama and J. Murakami and N. Hashiguchi and H. Yabuuchi and K. Masuda",
year = "1997",
month = "12",
day = "1",
language = "English",
volume = "15",
pages = "283--293",
journal = "Japanese Journal of Radiology",
issn = "1867-1071",
publisher = "Springer Japan",
number = "5",

}

TY - JOUR

T1 - Neural network analysis of breast cancer from MRI findings

AU - Abdolmaleki, P.

AU - Buadu, L. D.

AU - Murayama, S.

AU - Murakami, J.

AU - Hashiguchi, N.

AU - Yabuuchi, H.

AU - Masuda, K.

PY - 1997/12/1

Y1 - 1997/12/1

N2 - Purpose: To evaluate how much the experience of radiologists affects the performance of an artificial neural network (ANN) trained by two highly experienced radiologists. Materials and Methods: Before biopsy two experienced radiologists reviewed the MR images of 100 adult patients with suspicious breast lesions and evaluated their findings based on six features. This database was then used to train a three-layered feed-forward neural network. The network's generalizing ability was then tested to predict the outcome of biopsy in 56 new patients' records which were extracted by 10 participating radiologists. The MRI findings of each reader were presented to the ANN to evaluate the effect of various levels of experience on the output of the ANN. The performance of the ANN was then compared with that of attendant physicians in terms of sensitivity, specificity, and accuracy as well as ROC analysis. Results: The best ANN outcome offered a correct diagnosis in 40 of 41 of the patients with malignant breast cancer and 10 of 15 with benign entity presented in the testing set. The output of the trained ANN outperformed the attendant radiologists with low levels of experience and showed comparable performance with radiologists with higher levels of experience. Conclusions: The ANN is able to work as a backup system to assist radiologists in the diagnosis of breast cancer.

AB - Purpose: To evaluate how much the experience of radiologists affects the performance of an artificial neural network (ANN) trained by two highly experienced radiologists. Materials and Methods: Before biopsy two experienced radiologists reviewed the MR images of 100 adult patients with suspicious breast lesions and evaluated their findings based on six features. This database was then used to train a three-layered feed-forward neural network. The network's generalizing ability was then tested to predict the outcome of biopsy in 56 new patients' records which were extracted by 10 participating radiologists. The MRI findings of each reader were presented to the ANN to evaluate the effect of various levels of experience on the output of the ANN. The performance of the ANN was then compared with that of attendant physicians in terms of sensitivity, specificity, and accuracy as well as ROC analysis. Results: The best ANN outcome offered a correct diagnosis in 40 of 41 of the patients with malignant breast cancer and 10 of 15 with benign entity presented in the testing set. The output of the trained ANN outperformed the attendant radiologists with low levels of experience and showed comparable performance with radiologists with higher levels of experience. Conclusions: The ANN is able to work as a backup system to assist radiologists in the diagnosis of breast cancer.

UR - http://www.scopus.com/inward/record.url?scp=0031442386&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031442386&partnerID=8YFLogxK

M3 - Article

C2 - 9445150

AN - SCOPUS:0031442386

VL - 15

SP - 283

EP - 293

JO - Japanese Journal of Radiology

JF - Japanese Journal of Radiology

SN - 1867-1071

IS - 5

ER -