Engineering Research Center of Learning-Based Intelligent System, Ministry of Education and the Key Laboratory of Computer Vision and System of Ministry of Education, Tianjin University of Technology, Tianjin, China
Auto-generated profile, based on publicly available information
Hongxia Yang
Engineering Research Center of Learning-Based Intelligent System, Ministry of Education and the Key Laboratory of Computer Vision and System of Ministry of Education, Tianjin University of Technology, Tianjin, China
The mainstream techniques to detect microaneurysm in medical images involve the use of stacked convolutional neural networks. But these techniques can not provide adequate detecting performance for the MA scenarios with limited information and different sizes. In this article, a hierarchical pyramid network with a ‘T’ structure is proposed to detect microaneurysms (MAs) in retinal fundus images, which can overcome the difficulties caused by the above scenarios.We design a data preparation technique that can adaptively compute the best receptive fields of MAs to generate various patch sizes, resulting in multi-size datasets for training. The ‘T’ network consists of two pyramid feature extractors, rather than a deep network to adequately extract features of MAs and avoid feature loss caused by deep layers. Experiments on five public retinal datasets demonstrate that our method achieves the state-of-the-art performance.