Breast cancer diagnosis in DCE-MRI using mixture ensemble of convolutional neural networks
作者：
Highlights：
• A new method for breast cancer diagnosis in DCE-MRI is presented.
• We propose a mixture ensemble of convolutional neural networks for image classification.
• A convolutional gating network coordinates simultaneous, competitive learning of CNN experts.
• ME-CNN ensemble model is efficient for biomedical problems with a limited number of samples.
• The proposed model performs comparatively well on a DCE-MRI dataset of 112 patients.
摘要
•A new method for breast cancer diagnosis in DCE-MRI is presented.•We propose a mixture ensemble of convolutional neural networks for image classification.•A convolutional gating network coordinates simultaneous, competitive learning of CNN experts.•ME-CNN ensemble model is efficient for biomedical problems with a limited number of samples.•The proposed model performs comparatively well on a DCE-MRI dataset of 112 patients.
论文关键词：Breast cancer,DCE-MRI,Convolutional neural networks,Mixture ensemble of experts,CAD systems
论文评审过程：Received 19 February 2017, Revised 24 June 2017, Accepted 3 August 2017, Available online 4 August 2017, Version of Record 17 August 2017.
论文官网地址：https://doi.org/10.1016/j.patcog.2017.08.004
