no code implementations • 23 May 2021 • Zhiqiang Shen, Chaonan Lin, Shaohua Zheng
Motivated by the detection transformer (DETR), COTR is constituted by a CNN for feature extraction, transformer encoder layers interleaved with convolutional layers for feature encoding and recalibration, transformer decoder layers for object querying, and a feed-forward network for detection prediction.
no code implementations • 22 Mar 2021 • Lin Pan, Yaoyong Zheng, Liqin Huang, Liuqing Chen, Zhen Zhang, Rongda Fu, Bin Zheng, Shaohua Zheng
We propose a novel method for automatic separation of pulmonary arteries and veins from chest CT images.
no code implementations • 25 Feb 2021 • Jinquan Guo, Rongda Fu, Lin Pan, Shaohua Zheng, Liqin Huang, Bin Zheng, Bingwei He
To improve the performance of the segmentation result, the CNN-based region growing method is designed to focus on obtaining small branches.
no code implementations • 22 Feb 2021 • Shaohua Zheng, Zhiqiang Shen, Chenhao Peia, Wangbin Ding, Haojin Lin, Jiepeng Zheng, Lin Pan, Bin Zheng, Liqin Huang
In addition, explanations of CDAM features proved that the shape and density of nodule regions were two critical factors that influence a nodule to be inferred as malignant, which conforms with the diagnosis cognition of experienced radiologists.