期刊
PATTERN RECOGNITION AND IMAGE ANALYSIS (IBPRIA 2017)
卷 10255, 期 -, 页码 243-250出版社
SPRINGER INTERNATIONAL PUBLISHING AG
DOI: 10.1007/978-3-319-58838-4_27
关键词
Transfer learning; Regularization; Cervical cancer; Digital colposcopy
资金
- Project NanoSTIMA: Macro-to-Nano Human Sensing: Towards Integrated Multimodal Health Monitoring and Analytics - North Portugal Regional Operational Programme (NORTE), under the PORTUGAL Partnership Agreement [NORTE-01-0145-FEDER-000016]
- European Regional Development Fund (ERDF)
- Fundacao para a Ciencia e a Tecnologia (FCT) [SFRH/BD/93012/2013]
- Fundação para a Ciência e a Tecnologia [SFRH/BD/93012/2013] Funding Source: FCT
Cervical cancer remains a significant cause of mortality in low-income countries. As in many other diseases, the existence of several screening/diagnosis methods and subjective physician preferences creates a complex ecosystem for automated methods. In order to diminish the amount of labeled data from each modality/expert we propose a regularization-based transfer learning strategy that encourages source and target models to share the same coefficient signs. We instantiated the proposed framework to predict cross-modality individual risk and cross-expert subjective quality assessment of colposcopic images for different modalities. Thus, we are able to transfer knowledge gained from one expert/modality to another.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据