Few-Shot Domain Adaptation for Identification of Clinical Image in Dermatology

被引：0
|
作者：
Jing H. [1 ]
Zhang Q. [2 ]
Chen M. [2 ]
Zhang L. [3 ]
Li Z. [2 ]
Zhu J. [1 ]
Li Z. [2 ]
机构：
[1] School of Software Engineering, Xi'an Jiaotong University, Xi'an
[2] The Second Affiliated Hospital of Xi'an Jiaotong University, Xi'an
[3] East Branch, The First Affiliated Hospital of Xi'an Jiaotong University, Xi'an
来源：
Hsi-An Chiao Tung Ta Hsueh/Journal of Xi'an Jiaotong University | 2020年 / 54卷 / 09期
关键词：
Convolutional neural network; Dermatological recognition; Domain adaption; Few-shot; Maximum correntropy criterion;
D O I：
10.7652/xjtuxb202009016
中图分类号：
学科分类号：
摘要：
Aiming at the problem that the model trained by public data set cannot be directly applied to the auxiliary diagnosis of different clinical devices and there is not sufficient manpower to label the clinical data, few-shot domain adaptation for the identification of clinical image in dermatology is proposed. The ISIC dermatological public data set is taken as the source domain with known label, and the actual clinical dataset is taken as the target domain to be predicted, small amount of clinical data are marked by the doctor to train few-shot domain adaptive model of feature extractor and classifier implemented by convolutional neural network. The maximum correntropy criterion is adopted to improve the accuracy and generalization ability of the recognition model. If there are only a small number of labeled target samples in each class, the distribution gap between different domains is reduced while extracting discriminative features by alternating maximum and minimum conditional entropy. The accuracy of the classifier in the new domain is improved, and the model is transferred across domains. The proposed method is experimentally verified in the classification of actinic keratosis and seborrheic keratosis. Compared with the non-domain adaptive method, the proposed method solves the difficulty of difference in data distribution caused by different collection devices and achieves higher recognition accuracy. Compared with the unsupervised domain adaptive method, the proposed method achieves domain adaptation by adding a small amount of labeled clinical data, and the recognition accuracy rate is 93.94%. © 2020, Editorial Office of Journal of Xi'an Jiaotong University. All right reserved.
引用
收藏
页码：142 / 148and156
相关论文
共 23 条
  • [11] DAUME H., Frustratingly easy domain adaptation
  • [12] SCHWEIKERT G, WIDMER C, SCHOLKOPF B, Et al., An empirical analysis of domain adaptation algorithms for genomic sequence analysis, Proceedings of the 2008 Advances in Neural Information Processing Systems, pp. 1433-1440, (2009)
  • [13] KAMNITSAS K, BAUMGARTNER C, LEDIG C, Et al., Unsupervised domain adaptation in brain lesion segmentation with adversarial networks, International Conference on Information Processing in Medical Imaging, pp. 597-609, (2017)
  • [14] SHI J, ZHOU S C, LIU X, Et al., Stacked deep polynomial network based representation learning for tumor classification with small ultrasound image dataset, Neurocomputing, 194, pp. 87-94, (2016)
  • [15] MONDAL A K, DOLZ J, DESROSIERS C., Few-shot 3D multi-modal medical image segmentation using generative adversarial learning
  • [16] MEDELA A, PICON A, SARATXAGA C L, Et al., Few shot learning in histopathological images: reducing the need of labeled data on biological datasets, 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI), pp. 1860-1864, (2019)
  • [17] YE D H, POHL K M, DAVATZIKOS C., Semi-supervised pattern classification: application to structural MRI of Alzheimer's disease, 2011 International Workshop on Pattern Recognition in NeuroImaging, pp. 1-4, (2011)
  • [18] RAHHAL M M A, BAZI Y, ALHICHRI H, Et al., Deep learning approach for active classification of electrocardiogram signals, Information Sciences, 345, pp. 340-354, (2016)
  • [19] BAI W, OKTAY O, SINCLAIR M, Et al., Semi-supervised learning for network-based cardiac MR image segmentation, 2017 International Conference on Medical Image Computing and Computer Assisted Intervention, pp. 253-260, (2017)
  • [20] CODELLA N, ROTEMBERG V, TSCHANDL P, Et al., Skin lesion analysis toward melanoma detection 2018: a challenge hosted by the International Skin Imaging Collaboration (ISIC)
123