HUSCAP logo Hokkaido Univ. logo

Hokkaido University Collection of Scholarly and Academic Papers >
Graduate School of Information Science and Technology / Faculty of Information Science and Technology >
Peer-reviewed Journal Articles, etc >

Cardiac sarcoidosis classification with deep convolutional neural network-based features using polar maps

Creative Commons License

Files in This Item:
02CardiacSarcoidosisClassificationWithDeepConvolutionalNeuralNetwork-basedFeaturesUsingPolarMaps.pdf582.36 kBPDFView/Open
Please use this identifier to cite or link to this item:http://hdl.handle.net/2115/76454

Title: Cardiac sarcoidosis classification with deep convolutional neural network-based features using polar maps
Authors: Togo, Ren Browse this author
Hirata, Kenji Browse this author →KAKEN DB
Manabe, Osamu Browse this author →KAKEN DB
Ohira, Hiroshi Browse this author →KAKEN DB
Tsujino, Ichizo Browse this author →KAKEN DB
Magota, Keiichi Browse this author →KAKEN DB
Ogawa, Takahiro Browse this author →KAKEN DB
Haseyama, Miki Browse this author →KAKEN DB
Shiga, Tohru Browse this author →KAKEN DB
Keywords: Deep learning
Convolutional neural network (CNN)
Cardiac sarcoidosis (CS)
18F-FDG PET
Computer-aided diagnosis
Radiology
Machine learning
Feature extraction
Feature selection
Issue Date: Jan-2019
Publisher: Elsevier
Journal Title: Computers in Biology and Medicine
Volume: 104
Start Page: 81
End Page: 86
Publisher DOI: 10.1016/j.compbiomed.2018.11.008
Abstract: Aims: The aim of this study was to determine whether deep convolutional neural network (DCNN)-based features can represent the difference between cardiac sarcoidosis (CS) and non-CS using polar maps. Methods: A total of 85 patients (33 CS patients and 52 non-CS patients) were analyzed as our study subjects. One radiologist reviewed PET/CT images and defined the left ventricle region for the construction of polar maps. We extracted high-level features from the polar maps through the Inception-v3 network and evaluated their effectiveness by applying them to a CS classification task. Then we introduced the ReliefF algorithm in our method. The standardized uptake value (SUV)-based classification method and the coefficient of variance (CoV)-based classification method were used as comparative methods. Results: Sensitivity, specificity and the harmonic mean of sensitivity and specificity of our method with the ReliefF algorithm were 0.839, 0.870 and 0.854, respectively. Those of the SUVmax-based classification method were 0.468, 0.710 and 0.564, respectively, and those of the CoV-based classification method were 0.655, 0.750 and 0.699, respectively. Conclusion: The DCNN-based high-level features may be more effective than low-level features used in conventional quantitative analysis methods for CS classification.
Rights: © 2019. This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0/
https://creativecommons.org/licenses/by-nc-nd/4.0/
Type: article (author version)
URI: http://hdl.handle.net/2115/76454
Appears in Collections:情報科学院・情報科学研究院 (Graduate School of Information Science and Technology / Faculty of Information Science and Technology) > 雑誌発表論文等 (Peer-reviewed Journal Articles, etc)

Submitter: 藤後 廉

Export metadata:

OAI-PMH ( junii2 , jpcoar )

MathJax is now OFF:


 

Feedback - Hokkaido University