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 inac...

Full description

Saved in:
Bibliographic Details
Published in:IEEE journal of biomedical and health informatics 2024-01, Vol.28 (1), p.355-366
Main Authors: Zhang, Chengyang, Chen, Jie, Li, Bo, Feng, Min, Yang, Yongquan, Zhu, Qikui, Bu, Hong Bu
Format: Article
Language:English
Subjects:
Adaptation models
Cell localization
Cell morphology
Computational modeling
Convolution
Cytology
deformable-difference convolution
Deformation
Formability
Information filters
Localization
Location awareness
location map
Morphology
Shape
Supervision
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2168-2194
2168-2208
DOI:10.1109/JBHI.2023.3329542