Abstract
Alcohol use disorder (AUD) is an important brain disease. It alters the brain structure. Recently, scholars tend to use computer vision based techniques to detect AUD. We collected 235 subjects, 114 alcoholic and 121 non-alcoholic. Among the 235 image, 100 images were used as training set, and data augmentation method was used. The rest 135 images were used as test set. Further, we chose the latest powerful technique—convolutional neural network (CNN) based on convolutional layer, rectified linear unit layer, pooling layer, fully connected layer, and softmax layer. We also compared three different pooling techniques: max pooling, average pooling, and stochastic pooling. The results showed that our method achieved a sensitivity of 96.88%, a specificity of 97.18%, and an accuracy of 97.04%. Our method was better than three state-of-the-art approaches. Besides, stochastic pooling performed better than other max pooling and average pooling. We validated CNN with five convolution layers and two fully connected layers performed the best. The GPU yielded a 149× acceleration in training and a 166× acceleration in test, compared to CPU.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Edwards, A.C., Lonn, S.L., Karriker-Jaffe, K.J., Sundquist, J., Kendler, K.S., and Sundquist, K., Time-specific and cumulative effects of exposure to parental externalizing behavior on risk for young adult alcohol use disorder. Addict. Behav. 72:8–13, 2017. https://doi.org/10.1016/j.addbeh.2017.03.002.
Wlodarczyk, O., Schwarze, M., Rumpf, H.J., Metzner, F., and Pawils, S., Protective mental health factors in children of parents with alcohol and drug use disorders: A systematic review. PLoS One. 12(6):15, 2017. Article ID e0179140. https://doi.org/10.1371/journal.pone.0179140.
Kobayashi, T., Monma, M., Baba, T., Ishimori, Y., Shiotani, S., Saitou, H., Kaga, K., Miyamoto, K., Hayakawa, H., and Homma, K., Optimization of inversion time for postmortem short-tau inversion recovery (STIR) MR imaging. Magn. Reson. Med. Sci. 13(2):67–72, 2014. https://doi.org/10.2463/mrms.2013-0046.
Murano, T., Koshimizu, H., Hagihara, H., and Miyakawa, T., Transcriptomic immaturity of the hippocampus and prefrontal cortex in patients with alcoholism. Sci. Rep. 7(8), 2017. Article ID 44531. https://doi.org/10.1038/srep44531.
Sawyer, K.S., Oscar-Berman, M., Ruiz, S.M., Galvez, D.A., Makris, N., Harris, G.J., and Valera, E.M., Associations between cerebellar subregional morphometry and alcoholism history in men and women. Alcoholism. 40(6):1262–1272, 2016. https://doi.org/10.1111/acer.13074.
Liao, X., Yin, J., Guo, S., Li, X., and Sangaiah, A.K., Medical JPEG image steganography based on preserving inter-block dependencies. Comput. Electr. Eng. https://doi.org/10.1016/j.compeleceng.2017.08.020.
Zhang, R., Shen, J., Wei, F., Li, X., and Sangaiah, A.K., Medical image classification based on multi-scale non-negative sparse coding. Artif. Intell. Med., 2017. https://doi.org/10.1016/j.artmed.2017.05.006.
Samuel, O.W., Zhou, H., Li, X., Wang, H., Zhang, H., Sangaiah, A.K., and Li, G., Pattern recognition of electromyography signals based on novel time domain features for amputees' limb motion classificationPattern recognition of electromyography signals based on novel time domain features for amputees' limb motion classification. Comput. Electr. Eng. 2017. https://doi.org/10.1016/j.compeleceng.2017.04.003.
Fisher, T., Hamed, A., Vartholomeos, P., Masamune, K., Tang, G.Y., Ren, H.L., and Tse, Z.T.H., Intraoperative magnetic resonance imaging-conditional robotic devices for therapy and diagnosis. Proc. Inst. Mech. Eng. Part H. J. Eng. Med. 228(3):303–318, 2014. https://doi.org/10.1177/0954411914524189.
Nayak, D.R., Dash, R., and Majhi, B., Brain MR image classification using two-dimensional discrete wavelet transform and AdaBoost with random forests. Neurocomputing. 177:188–197, 2016. https://doi.org/10.1016/j.neucom.2015.11.034.
Alweshah, M., and Abdullah, S., Hybridizing firefly algorithms with a probabilistic neural network for solving classification problems. Appl Soft Comput. 35:513–524, 2015. https://doi.org/10.1016/j.asoc.2015.06.018.
Lv, Y.-D., and Hou, X.-X., Alcoholism detection by medical robots based on Hu moment invariants and predator–prey adaptive-inertia chaotic particle swarm optimization. Comput. Electr. Eng. https://doi.org/10.1016/j.compeleceng.2017.04.009.
Monnig, M.A., Observed power and projected sample sizes to detect white matter atrophy in neuroimaging of alcohol use disorders. Alcoholism. 36:272A–272A, 2012.
Yang, J., Pathological brain detection in MRI scanning via Hu moment invariants and machine learning. J. Exp. Theor. Artif. Intell. 29(2):299–312, 2017. https://doi.org/10.1080/0952813X.2015.1132274.
Do, B.J., Park, I.Y., Rhee, S.Y., Song, J.K., Jang, M.K., Cho, S.J., Nam, E.S., and Yun, E.J., A case of multiple hypervascular hyperplastic liver nodules in a patient with no history of alcohol abuse or chronic liver diseases. Korean J. Gastroenterol. 65(5):321–325, 2015. https://doi.org/10.4166/kjg.2015.65.5.321.
Matsui, T., Sakurai, H., Toyama, T., Yoshimura, A., Matsushita, S., and Higuchi, S., Clinical application of neuroimaging to alcohol-related dementia. Jpn. J. Alcohol Stud. Drug Depend. 47(3):125–134, 2012.
Zahr, N.M., Kaufman, K.L., and Harper, C.G., Clinical and pathological features of alcohol-related brain damage. Nat. Rev. Neurol. 7(5):284–294, 2011. https://doi.org/10.1038/nrneurol.2011.42.
Bae, J., Cha, Y.J., Lee, H., Lee, B., Baek, S., Choi, S., and Jang, D., Social networks and inference about unknown events: A case of the match between Google's AlphaGo and Sedol Lee. PLoS One. 12(2):25, 2017. Article ID e0171472. https://doi.org/10.1371/journal.pone.0171472.
Barik, A., Rai, R.K., and Chowdhury, A., Alcohol use-related problems among a rural Indian population of West Bengal: An application of the alcohol use disorders identification test (AUDIT). Alcohol Alcohol. 51(2):215–223, 2016. https://doi.org/10.1093/alcalc/agv097.
Lakhani, P., Deep convolutional neural networks for endotracheal tube position and X-ray image classification: Challenges and opportunities. J. Digit. Imaging. 30(4):460–468, 2017. https://doi.org/10.1007/s10278-017-9980-7.
Chen, Y., and Jin, Z., Reconstructive discriminant analysis: A feature extraction method induced from linear regression classification. Neurocomputing. 87:41–50, 2012. https://doi.org/10.1016/j.neucom.2012.02.001.
Chen, Y., Li, Z.Z., and Jin, Z., Feature extraction based on maximum nearest subspace margin criterion. Neural. Process. Lett. 37(3):355–375, 2013. https://doi.org/10.1007/s11063-012-9252-y.
Barushka, A., and Hajek, P., Spam filtering using regularized neural networks with rectified linear units. In: Adorni, G., Cagnoni, S., Gori, M., Maratea, M., (Eds.), 15th International Conference of the Italian Association for Artificial Intelligence (AIIA), Genova, ITALY. Lecture Notes in Computer Science. Springer Int Publishing Ag, 2016, pp 65–75. https://doi.org/10.1007/978-3-319-49130-1_6.
Sun, M., Raju, A., Tucker, G., Panchapagesan, S., Fu, G. S., Mandal, A., Matsoukas, S., Strom, N., and Vitaladevuni, S., Max-pooling loss training of long short-term memory networks for small-footprint keyword spotting. In: IEEE workshop on spoken language technology (SLT), San Diego, CA, USA: IEEE, 2016, pp 474–480.
Zhu, S.G., and Du, J.P., Visual tracking using max-average pooling and weight-selection strategy. J. Appl. Math. Article ID 828907, 2014. https://doi.org/10.1155/2014/828907.
Zeiler, M. D., and Fergus, R., Stochastic pooling for regularization of deep convolutional neural networks, in: International Conference on Learning Representations (ICLR), Scottsdale, Arizona, USA,: IEEE, May 2, 2013, pp 1–7.
Fernando, B., and Gould, S., Discriminatively learned hierarchical rank pooling networks. Int. J. Comput. Vis. 124(3):335–355, 2017. https://doi.org/10.1007/s11263-017-1030-x.
Han, X.B., Zhong, Y.F., Cao, L.Q., and Zhang, L.P., Pre-Trained AlexNet Architecture with Pyramid Pooling and Supervision for High Spatial Resolution Remote Sensing Image Scene Classification. Remote Sens. 9(8):22, 2017. Article ID 848. https://doi.org/10.3390/rs9080848.
Zhan, T.M., and Chen, Y., Multiple sclerosis detection based on biorthogonal wavelet transform, RBF kernel principal component analysis, and logistic regression. IEEE Access. 4:7567–7576, 2016. https://doi.org/10.1109/ACCESS.2016.2620996.
Sahin, R., Cross-entropy measure on interval neutrosophic sets and its applications in multicriteria decision making. Neural Comput. Appl. 28(5):1177–1187, 2017. https://doi.org/10.1007/s00521-015-2131-5.
Chen, X.Q., and Wu, L.A., Nonlinear demodulation and channel coding in EBPSK scheme. Sci. World J. Article ID 180469, 2012. https://doi.org/10.1100/2012/180469.
Chen, X.Q., and Wu, L.N., A novel detection scheme for EBPSK system. Math Probl. Eng. Article ID 956191, 2012. https://doi.org/10.1155/2012/956191.
Acknowledgments
This paper is financially supported by Natural Science Foundation of China (61602250) and Natural Science Foundation of Jiangsu Province (BK20150983).
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Conflict of Interest
The authors declare there is no conflict of interest with regards to this submission.
Additional information
This article is part of the Topical Collection on Image & Signal Processing
Rights and permissions
About this article
Cite this article
Wang, SH., Lv, YD., Sui, Y. et al. Alcoholism Detection by Data Augmentation and Convolutional Neural Network with Stochastic Pooling. J Med Syst 42, 2 (2018). https://doi.org/10.1007/s10916-017-0845-x
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10916-017-0845-x