Analysis of the effects of transfer learning on opacity classification of diffuse lung diseases using convolutional neural network

Ami Atsumo; Shingo Mabu; Shoji Kido; Yasushi Hirano; Takashi Kuremoto

doi:10.1117/12.2521229

27 March 2019 Analysis of the effects of transfer learning on opacity classification of diffuse lung diseases using convolutional neural network

Ami Atsumo, Shingo Mabu, Shoji Kido, Yasushi Hirano, Takashi Kuremoto

Author Affiliations +

Proceedings Volume 11050, International Forum on Medical Imaging in Asia 2019; 1105017 (2019) https://doi.org/10.1117/12.2521229
Event: 2019 Joint International Workshop on Advanced Image Technology (IWAIT) and International Forum on Medical Imaging in Asia (IFMIA), 2019, Singapore, Singapore

Abstract

Research on Computer-Aided Diagnosis (CAD), which discriminates the presence or absence of diseases by machine learning and supports doctors’ diagnosis, has been actively conducted. However, training of machine learning requires many training data with annotations. Since the annotations are done by radiologists manually, annotating hundreds to thousands of images is very hard work. This study proposes classifiers using convolutional neural network (CNN) with transfer learning for efficient opacity classification of diffuse lung diseases, and the effects of transfer learning are analyzed under various conditions. In detail, classifiers with nine different conditions of transfer learning and without transfer learning are compared to show the best conditions.

Citation Download Citation

Ami Atsumo, Shingo Mabu, Shoji Kido, Yasushi Hirano, and Takashi Kuremoto "Analysis of the effects of transfer learning on opacity classification of diffuse lung diseases using convolutional neural network", Proc. SPIE 11050, International Forum on Medical Imaging in Asia 2019, 1105017 (27 March 2019); https://doi.org/10.1117/12.2521229

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available