Breast ultrasound region of interest detection and lesion localisation

作者：

Highlights：

• Automation of breast ultrasound region of interest detection with Faster-RCNN.

• We apply transfer learning approach and propose a new data augmentation method.

• We evaluate the proposed method within individual dataset and composite dataset.

• Faster-RCNN outperformed the state-of-the-art method in lesion localisation.

摘要

•Automation of breast ultrasound region of interest detection with Faster-RCNN.•We apply transfer learning approach and propose a new data augmentation method.•We evaluate the proposed method within individual dataset and composite dataset.•Faster-RCNN outperformed the state-of-the-art method in lesion localisation.

论文关键词：Breast ultrasound,Breast cancer,Object detection,Region of interests

论文评审过程：Received 6 August 2019, Revised 6 May 2020, Accepted 12 May 2020, Available online 29 May 2020, Version of Record 11 June 2020.

论文官网地址：https://doi.org/10.1016/j.artmed.2020.101880