Article-Journal

STNet: shape and texture joint learning through two-stream network for knowledge-guided image recognition
The human brain processes shape and texture information separately through different neurons in the visual system. Inspired by that, we proposed a shape-and-texture-biased two-stream network to enhance the shape feature representation in knowledge-guided medical image analysis.
Xijing Wang, HAN Hongcheng, Mengrui Xu, Shengpeng Li, Dong Zhang, Shaoyi Du, Meifeng Xu
PDF Cite Source Document DOI
STNet: shape and texture joint learning through two-stream network for knowledge-guided image recognition
Coarse-to-fine feature representation based on deformable partition attention for melanoma identification
We propose a novel and efficient coarse-to-fine neural network for melanomas and nevi identification, which adopt a divide and conquer idea to overcome unbalanced inter-class spacing, and then leverages a fine sub-network to tackle the challenges of arduous training and unfavorable classification accuracy.
Dong Zhang, Jing Yang, Shaoyi Du*, HAN Hongcheng, Yuyan Ge, Longfei Zhu, Ce Li, Meifeng Xu, Nanning Zheng*
Cite Source Document DOI
MPMR: multi-scale feature and probability map for melanoma recognition
We propose a novel automatic melanoma recognition method based on the multi-scale features and probability map.
Dong Zhang, HAN Hongcheng, Shaoyi Du, Longfei Zhu, Jing Yang, Xijing Wang, Lin Wang, Meifeng Xu
PDF Cite Source Document DOI
MPMR: multi-scale feature and probability map for melanoma recognition
Multimodal orthodontic corpus construction based on semantic tag classification method
This paper proposes a new method for constructing a multimodal orthodontic corpus to tackle the situation that only using patients’ …
Yuping Lin, Yuting Chi, HAN Hongcheng, Mengqi Han, Yucheng Guo
Cite Source Document DOI