Advancing hierarchical neural networks with scale-aware pyramidal feature learning for medical image dense prediction

Xiang Liu, James Liang, Jianwei Zhang, Zihan Qian, Phoebe Xing, Taige Chen, Shanchieh Yang, Chijioke Chukwudi, Liang Qiu, Dongfang Liu, Junhan Zhao

Abstract: Highlights•INSPIRE over-performed popular baseline models for medical segmentation.•INSPIRE is generalizable for medical and natural image segmentation tasks.•INSPIRE can be integrated into any pyramidal network and their derivatives.