An automatic BI-RADS description of mammographic masses by fusing multiresolution features

详细信息    查看全文

• 作者：Fabiá ; n Narvá ; ez^a ; ^{frnarvaeze@unal.edu.co} ; Gloria Dí ; az^b ; ^{gloriadiaz@itm.edu.co} ; Cesar Poveda^a ; ^c ; ^{capovedas@unal.edu.co} ; Eduardo Romero ; ^a ; ^{edromero@unal.edu.co}
• 关键词：BI-RADS mammographic lexicon ; Mammographic mass description ; Zernike moments ; Curvelet transform ; Multiple kernel learning
• 刊名：Expert Systems with Applications
• 出版年：2017
• 出版时间：15 May 2017
• 年：2017
• 卷：74
• 期：Complete
• 页码：82-95
• 全文大小：2402 K
• 卷排序：74

文摘

An automatic method that performs a BI-RADS description of mammographic masses. A multiple kernel learning strategy is proposed for combining two multiresolution features. Mass shape description is assigned by a hierarchical SVM classifier. The margin and density descriptions are assigned by a shape-based retrieval strategy. The method was evaluated on the datasets: DDSM and INBreast.