Transfer Learning with Partial Observability Applied to Cervical Cancer Screening

• Type: Article in International Conference Proceedings Book
• Date: 2017

Authors

Fernandes, K (Author) Other; Jaime S Cardoso (Author) FEUP; Fernandes, J (Author) Other

Conference proceedings International

Title: PATTERN RECOGNITION AND IMAGE ANALYSIS (IBPRIA 2017)

Pages: 243-250

8th Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA)

Univ Algarve, Faro, PORTUGAL, JUN 20-23, 2017

Indexing

ISI Web of Knowledge - 31 Citations

Scopus - 91 Citations

Other information

Authenticus ID: P-00N-9XR

DOI: 10.1007/978-3-319-58838-4_27

Abstract (EN): 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.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 8