Journal
FRONTIERS IN PSYCHIATRY
Volume 10, Issue -, Pages -Publisher
FRONTIERS MEDIA SA
DOI: 10.3389/fpsyt.2019.00205
Keywords
alcoholism; transfer learning; AlexNet; data augmentation; convolutional neural network; dropout; local response normalization; magnetic resonance imaging
Categories
Funding
- Zhejiang Provincial Natural Science Foundation of China [LY17F010003, Y18F010018]
- National key research and development plan [2017YFB1103202]
- Open Fund of Guangxi Key Laboratory of Manufacturing System and Advanced Manufacturing Technology [17-259-05-011K]
- Natural Science Foundation of China [61602250, U1711263, U1811264]
- Henan Key Research and Development Project [182102310629]
Ask authors/readers for more resources
Aim: This paper proposes a novel alcoholism identification approach that can assist radiologists in patient diagnosis. Method: AlexNet was used as the basic transfer learning model. The global learning rate was small, at 10(-4), and the iteration epoch number was at 10. The learning rate factor of replaced layers was 10 times larger than that of the transferred layers. We tested five different replacement con figurations of transfer learning. Results: The experiment shows that the best performance was achieved by replacing the final fully connected layer. Our method yielded a sensitivity of 97.44% +/- 1.15%, a specificity of 97.41 +/- 1.51%, a precision of 97.34 +/- 1.49%, an accuracy of 97.42 +/- 0.95%, and an F1 score of 97.37 +/- 0.97% on the test set. Conclusion: This method can assist radiologists in their routine alcoholism screening of brain magnetic resonance images.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available