Difference-Deformable Convolution With Pseudo Scale Instance Map for Cell Localization

Cell localization still faces two unresolved challenges: 1) the dramatic variations in cell morphology, coupled with the heterogeneous intensity distribution of lightly stained cells; 2) existing cell location maps lack scale information, resulting in insufficient supervision for point maps and inaccurate supervision for density maps. 1) To address the first challenges, we introduce a novel gradient-aware and shape-adaptive Difference-Deformable Convolution (DDConv), which enhances the model's robustness to color by leveraging gradient information while adaptively adjusting the shape of the convolutional kernel to tackle the substantial variability in cell morphology. 2) To overcome the issue of unreasonable location maps, we propose the Pseudo-Scale Instance (PSI) map, which can adaptively provide the corresponding scale information for each cell to realize accurate supervision. We analyze and evaluate DDConv and the PSI map in three challenging cell localization tasks. In comparison to existing methods, our proposed approach significantly enhances localization performance, setting a new benchmark for the cell localization task.

Authors

• Chengyang Zhang
• Jie Chen
• Bo Li Department of Computing, The Hong Kong Polytechnic University
• Min Feng
• Yongquan Yang
• Qikui Zhu
• Hong Bu Bu

Keywords

• Location awareness
• Shape
• Convolution
• Morphology
• Computational modeling
• Adaptation models
• Information filters
• Local Map
• Cell Morphology
• Cells Stained
• Density Map
• Localization Performance
• Heterogeneous Distribution
• Convolution Kernel
• Map Points
• Gradient Information
• Information Of Cells
• Unresolved Challenges
• Cell Count
• Training Set
• Positive Cells
• Convolutional Neural Network
• Cell Size
• Cell Imaging
• Validation Set
• Feature Maps
• Cell Shape
• Deformable Convolution
• Negative Cells
• Instance Segmentation
• Image Instance
• Image Regions
• Cell Scale
• Feature Representation Learning
• You Only Look Once
• Shape Priors
• Detection Of Cells
• Cell localization
• location map
• deformable-difference convolution