Pilot study to generate image features by deep autoencoder for computer-aided detection systems

Mitsutaka Nemoto; Kazuyuki Ushifusa; Atsuko Tanaka; Takahiro Yamada; Yuichi Kimura; Naoto Hayashi

doi:10.1117/12.2521289

27 March 2019 Pilot study to generate image features by deep autoencoder for computer-aided detection systems

Mitsutaka Nemoto, Kazuyuki Ushifusa, Atsuko Tanaka, Takahiro Yamada, Yuichi Kimura, Naoto Hayashi

Proceedings Volume 11050, International Forum on Medical Imaging in Asia 2019; 110501J (2019) https://doi.org/10.1117/12.2521289
Event: 2019 Joint International Workshop on Advanced Image Technology (IWAIT) and International Forum on Medical Imaging in Asia (IFMIA), 2019, Singapore, Singapore

Abstract

We propose an automatic feature generation by deep convolutional autoencoder (deep CAE) without lesion data. The main idea of the proposed method is based on anomaly detection. Deep CAE is trained by only normal volume patches. Trained deep CAE calculates low-dimensional features and reproduction error from 2.5 dimensional (2.5D) volume patch. The proposed method was evaluated experimentally with 150 chest CT cases. By using both previous features and the deep CAE based features, an improved classification performance was obtained; AUC=0.989 and ANODE=0.339.

Citation Download Citation

Mitsutaka Nemoto, Kazuyuki Ushifusa, Atsuko Tanaka, Takahiro Yamada, Yuichi Kimura, and Naoto Hayashi "Pilot study to generate image features by deep autoencoder for computer-aided detection systems", Proc. SPIE 11050, International Forum on Medical Imaging in Asia 2019, 110501J (27 March 2019); https://doi.org/10.1117/12.2521289

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