A method for classifying medical images using transfer learning: A pilot study on histopathology of breast cancer

Jongwon Chang, Jisang Yu, Taehwa Han, Hyuk-Jae Chang, Eunjeong Park

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Citations (Scopus)

Abstract

The advance of deep learning has made huge changes in computer vision and produced various off-the-shelf trained models. Particularly, Convolutional Neural Network (CNN) has been widely used to build image classification model which allow researchers transfer the pre-trained learning model for other classifications. We propose a transfer learning method to detect breast cancer using histopathology images based on Google's Inception v3 model which were initially trained for the classification of non-medical images. The pilot study shows the feasibility of transfer learning in the detection of breast cancer with AUC of 0.93.

Original languageEnglish
Title of host publication2017 IEEE 19th International Conference on e-Health Networking, Applications and Services, Healthcom 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-4
Number of pages4
ISBN (Electronic)9781509067046
DOIs
Publication statusPublished - 2017 Dec 14
Event19th IEEE International Conference on e-Health Networking, Applications and Services, Healthcom 2017 - Dalian, China
Duration: 2017 Oct 122017 Oct 15

Publication series

Name2017 IEEE 19th International Conference on e-Health Networking, Applications and Services, Healthcom 2017
Volume2017-December

Other

Other19th IEEE International Conference on e-Health Networking, Applications and Services, Healthcom 2017
CountryChina
CityDalian
Period17/10/1217/10/15

Fingerprint

cancer
Breast Neoplasms
Learning
learning
Area Under Curve
Image classification
learning method
Research Personnel
neural network
search engine
Computer vision
Neural networks
Transfer (Psychology)

All Science Journal Classification (ASJC) codes

  • Health Informatics
  • Computer Networks and Communications
  • Computer Science Applications
  • Health(social science)

Cite this

Chang, J., Yu, J., Han, T., Chang, H-J., & Park, E. (2017). A method for classifying medical images using transfer learning: A pilot study on histopathology of breast cancer. In 2017 IEEE 19th International Conference on e-Health Networking, Applications and Services, Healthcom 2017 (pp. 1-4). (2017 IEEE 19th International Conference on e-Health Networking, Applications and Services, Healthcom 2017; Vol. 2017-December). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/HealthCom.2017.8210843
Chang, Jongwon ; Yu, Jisang ; Han, Taehwa ; Chang, Hyuk-Jae ; Park, Eunjeong. / A method for classifying medical images using transfer learning : A pilot study on histopathology of breast cancer. 2017 IEEE 19th International Conference on e-Health Networking, Applications and Services, Healthcom 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 1-4 (2017 IEEE 19th International Conference on e-Health Networking, Applications and Services, Healthcom 2017).
@inproceedings{ddf6f87e49104645a7e1be086945f6f4,
title = "A method for classifying medical images using transfer learning: A pilot study on histopathology of breast cancer",
abstract = "The advance of deep learning has made huge changes in computer vision and produced various off-the-shelf trained models. Particularly, Convolutional Neural Network (CNN) has been widely used to build image classification model which allow researchers transfer the pre-trained learning model for other classifications. We propose a transfer learning method to detect breast cancer using histopathology images based on Google's Inception v3 model which were initially trained for the classification of non-medical images. The pilot study shows the feasibility of transfer learning in the detection of breast cancer with AUC of 0.93.",
author = "Jongwon Chang and Jisang Yu and Taehwa Han and Hyuk-Jae Chang and Eunjeong Park",
year = "2017",
month = "12",
day = "14",
doi = "10.1109/HealthCom.2017.8210843",
language = "English",
series = "2017 IEEE 19th International Conference on e-Health Networking, Applications and Services, Healthcom 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1--4",
booktitle = "2017 IEEE 19th International Conference on e-Health Networking, Applications and Services, Healthcom 2017",
address = "United States",

}

Chang, J, Yu, J, Han, T, Chang, H-J & Park, E 2017, A method for classifying medical images using transfer learning: A pilot study on histopathology of breast cancer. in 2017 IEEE 19th International Conference on e-Health Networking, Applications and Services, Healthcom 2017. 2017 IEEE 19th International Conference on e-Health Networking, Applications and Services, Healthcom 2017, vol. 2017-December, Institute of Electrical and Electronics Engineers Inc., pp. 1-4, 19th IEEE International Conference on e-Health Networking, Applications and Services, Healthcom 2017, Dalian, China, 17/10/12. https://doi.org/10.1109/HealthCom.2017.8210843

A method for classifying medical images using transfer learning : A pilot study on histopathology of breast cancer. / Chang, Jongwon; Yu, Jisang; Han, Taehwa; Chang, Hyuk-Jae; Park, Eunjeong.

2017 IEEE 19th International Conference on e-Health Networking, Applications and Services, Healthcom 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 1-4 (2017 IEEE 19th International Conference on e-Health Networking, Applications and Services, Healthcom 2017; Vol. 2017-December).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A method for classifying medical images using transfer learning

T2 - A pilot study on histopathology of breast cancer

AU - Chang, Jongwon

AU - Yu, Jisang

AU - Han, Taehwa

AU - Chang, Hyuk-Jae

AU - Park, Eunjeong

PY - 2017/12/14

Y1 - 2017/12/14

N2 - The advance of deep learning has made huge changes in computer vision and produced various off-the-shelf trained models. Particularly, Convolutional Neural Network (CNN) has been widely used to build image classification model which allow researchers transfer the pre-trained learning model for other classifications. We propose a transfer learning method to detect breast cancer using histopathology images based on Google's Inception v3 model which were initially trained for the classification of non-medical images. The pilot study shows the feasibility of transfer learning in the detection of breast cancer with AUC of 0.93.

AB - The advance of deep learning has made huge changes in computer vision and produced various off-the-shelf trained models. Particularly, Convolutional Neural Network (CNN) has been widely used to build image classification model which allow researchers transfer the pre-trained learning model for other classifications. We propose a transfer learning method to detect breast cancer using histopathology images based on Google's Inception v3 model which were initially trained for the classification of non-medical images. The pilot study shows the feasibility of transfer learning in the detection of breast cancer with AUC of 0.93.

UR - http://www.scopus.com/inward/record.url?scp=85048566890&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048566890&partnerID=8YFLogxK

U2 - 10.1109/HealthCom.2017.8210843

DO - 10.1109/HealthCom.2017.8210843

M3 - Conference contribution

AN - SCOPUS:85048566890

T3 - 2017 IEEE 19th International Conference on e-Health Networking, Applications and Services, Healthcom 2017

SP - 1

EP - 4

BT - 2017 IEEE 19th International Conference on e-Health Networking, Applications and Services, Healthcom 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Chang J, Yu J, Han T, Chang H-J, Park E. A method for classifying medical images using transfer learning: A pilot study on histopathology of breast cancer. In 2017 IEEE 19th International Conference on e-Health Networking, Applications and Services, Healthcom 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 1-4. (2017 IEEE 19th International Conference on e-Health Networking, Applications and Services, Healthcom 2017). https://doi.org/10.1109/HealthCom.2017.8210843