Segmentation information with attention integration for classification of breast tumor in ultrasound image

作者：

Highlights：

• A novel segmentation-to-classification framework is proposed for breast US diagnosis.

• The segmentation network is trained to obtain the segmentation enhanced images, and the features of the segmentation enhanced images and original images are extracted in parallel for classification.

• An attention-based method is proposed for feature aggregation of two parallel networks to enhance features useful for classification in a data-driven manner.

• Experimental results show the advantages of the proposed method.

摘要

•A novel segmentation-to-classification framework is proposed for breast US diagnosis.•The segmentation network is trained to obtain the segmentation enhanced images, and the features of the segmentation enhanced images and original images are extracted in parallel for classification.•An attention-based method is proposed for feature aggregation of two parallel networks to enhance features useful for classification in a data-driven manner.•Experimental results show the advantages of the proposed method.

论文关键词：Computer-aided diagnosis,Breast ultrasound,Deep convolution neural network,Feature combination

论文评审过程：Received 16 March 2021, Revised 25 October 2021, Accepted 8 November 2021, Available online 11 November 2021, Version of Record 28 February 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108427