Modeling clinician medical-knowledge in terms of med-level features for semantic content-based mammogram retrieval
作者：
Highlights：
• Generation of the computational clinician medical-knowledge models.
• Inferring semantic concepts from low-level features in terms of med-level ones.
• New variation of reduced shearlet coefficients for multi-resolution mammogram characterization.
• Creation of a ground-truth of MIAS dataset containing enriched Q/A radiologists.
• The proposed method outperforms compared CBMIR methods.
摘要
•Generation of the computational clinician medical-knowledge models.•Inferring semantic concepts from low-level features in terms of med-level ones.•New variation of reduced shearlet coefficients for multi-resolution mammogram characterization.•Creation of a ground-truth of MIAS dataset containing enriched Q/A radiologists.•The proposed method outperforms compared CBMIR methods.
论文关键词：Clinician medical-knowledge,Med-level model,CBMIR,Low-level features,Breast cancer diagnosis
论文评审过程：Received 13 June 2017, Revised 12 October 2017, Accepted 14 October 2017, Available online 18 October 2017, Version of Record 5 November 2017.
论文官网地址：https://doi.org/10.1016/j.eswa.2017.10.034
