Semi-Supervised Representation Learning for Infants Biliary Atresia Screening Using Deep CNN-Based Variational Autoencoder
The challenge of convolutional networks (CNNs) for medical imaging analysis is to train the network model with limited well labeled dataset. Since a variational autoencoder (VAE) is able to learn the probability distribution on data for describing an observation in terms of its latent attributes by unsupervised manner, it has emerged as one of the most popular unsupervised learning technology in computer vision applications. In this paper, we presented a semi-supervised representation learning approach for screening infant’s biliary atresia using convolutional variational autoencoder (CVAE). Firstly, we leveraged a smartphone’s camera for infant’s stool images collection. Secondly, a pre-trained deep convolutional variation autoencoder was used to train the feature extractor for the infant’s stool image-features extraction, and finally we fine-tuned the last classification layers for identifying acholic from normal stools. We compared our screening approach with “tradition stool color card” method; the results demonstrated CVAE model has a higher accuracy rate 92.16%. Universal screening biliary atresia by semi-supervised representation learning may be a valuable technology to help parents identify acholic stools in the perinatal period, which may ultimately lead to improved native liver survival probabilities.
KeywordsVariational autoencoder Biliary atresia CNN
This study was financed partially by the National Natural Science Foundation of China (NSFC: 61501444), Shenzhen Technology Development Project Fund under Grant JSGG20160429192140681.
Guangdong province science and technology plan projects (Grant No.2015B020233004), Shenzhen basic technology research project (Grant No. JCYJ20160429174611494, JCYJ20170818160306270).
- 1.Hou, X., Shen, L., Sun, K., et al.: Deep feature consistent variational autoencoder. In: Applications of Computer Vision, pp. 1133–1141. IEEE (2017)Google Scholar
- 2.Pu, Y., Gan, Z., Henao, R., et al.: Variational autoencoder for deep learning of images, labels and captions (2016)Google Scholar
- 5.Logan, S., Stanton, A.: Screening for biliary atresia. Lancet 342(8874), 1–9 (1993)Google Scholar
- 6.Dilokthanakul, N., Mediano, P.A.M., Garnelo, M., et al.: Deep unsupervised clustering with gaussian mixture variational autoencoders (2016)Google Scholar
- 7.Santara, A., Maji, D., Tejas, D.P., et al.: Faster learning of deep stacked autoencoders on multi-core systems using synchronized layer-wise pre-training (2016)Google Scholar
- 8.Semeniuta, S., Severyn, A., Barth, E.: A hybrid convolutional variational autoencoder for text generation (2017)Google Scholar