Directional And Topological Transformer With Topology Priors For 4D Cellular Image Segmentation

Zelin Li*, Zhaoke Huang, Zhen Zhu, Sicheng You, Zhongying Zhao, Hong Yan*

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

Abstract

Cellular segmentation is a crucial step in creating cell shape maps and morphological graphs for living embryos from time-lapse 3D fluorescence images (laser confocal). One reliable method for segmenting cell shapes through deep learning networks is to incorporate voxel distance and topology priors to model shapes in topological structures. However, automated and CNN-based segmentation methods often suffer from low signal-to-noise ratios and insufficient training data. Previous works on semantic segmentation have ignored directional distance and topological information. In this paper, we propose a 3D directional and topological transformer named DTTR (Directional distance mapping and Topological learning TRansformer), which uses topology priors to binarization, and demonstrates an effective directional latent space. We use attention calculation on directional distance maps and utilize topological loss and priors, along with an optimized Delaunay-clustering algorithm, to measure voxel predictions in higher dimensional topology space. DTTR outperforms other existing deep learning models and provides a reliable segmented cell instance dataset (22 new living C. elegans embryos) for establishing 4D cellular morphology map.
Original languageEnglish
Title of host publication2024 IEEE International Conference on Image Processing (ICIP)
PublisherIEEE
Pages2902-2908
Number of pages7
ISBN (Electronic)9798350349399
ISBN (Print)9798350349405
DOIs
Publication statusPublished - 30 Oct 2024
Event2024 IEEE International Conference on Image Processing (ICIP) - Abu Dhabi, United Arab Emirates
Duration: 27 Oct 202430 Oct 2024
https://ieeexplore.ieee.org/xpl/conhome/10647221/proceeding

Publication series

NameIEEE International Conference on Image Processing
ISSN (Print)1522-4880
ISSN (Electronic)2381-8549

Conference

Conference2024 IEEE International Conference on Image Processing (ICIP)
Country/TerritoryUnited Arab Emirates
CityAbu Dhabi
Period27/10/2430/10/24
Internet address

User-Defined Keywords

  • cell segmentation
  • 4D image
  • transformer
  • topological loss and priors
  • fluorescence imaging

Cite this