Preprint
CelloType: A Unified Model for Segmentation and Classification of Tissue Images
bioRxiv
09/19/2024
DOI: 10.1101/2024.09.15.613139
PMCID: PMC11429831
PMID: 39345491
Abstract
Cell segmentation and classification are critical tasks in spatial omics data analysis. We introduce CelloType, an end-to-end model designed for cell segmentation and classification of biomedical microscopy images. Unlike the traditional two-stage approach of segmentation followed by classification, CelloType adopts a multi-task learning approach that connects the segmentation and classification tasks and simultaneously boost the performance of both tasks. CelloType leverages Transformer-based deep learning techniques for enhanced accuracy of object detection, segmentation, and classification. It outperforms existing segmentation methods using ground-truths from public databases. In terms of classification, CelloType outperforms a baseline model comprised of state-of-the-art methods for individual tasks. Using multiplexed tissue images, we further demonstrate the utility of CelloType for multi-scale segmentation and classification of both cellular and non-cellular elements in a tissue. The enhanced accuracy and multi-task-learning ability of CelloType facilitate automated annotation of rapidly growing spatial omics data.Cell segmentation and classification are critical tasks in spatial omics data analysis. We introduce CelloType, an end-to-end model designed for cell segmentation and classification of biomedical microscopy images. Unlike the traditional two-stage approach of segmentation followed by classification, CelloType adopts a multi-task learning approach that connects the segmentation and classification tasks and simultaneously boost the performance of both tasks. CelloType leverages Transformer-based deep learning techniques for enhanced accuracy of object detection, segmentation, and classification. It outperforms existing segmentation methods using ground-truths from public databases. In terms of classification, CelloType outperforms a baseline model comprised of state-of-the-art methods for individual tasks. Using multiplexed tissue images, we further demonstrate the utility of CelloType for multi-scale segmentation and classification of both cellular and non-cellular elements in a tissue. The enhanced accuracy and multi-task-learning ability of CelloType facilitate automated annotation of rapidly growing spatial omics data.
Details
- Title: Subtitle
- CelloType: A Unified Model for Segmentation and Classification of Tissue Images
- Creators
- Minxing Pang - University of PennsylvaniaTarun Kanti Roy - University of IowaXiaodong Wu - University of IowaKai Tan - University of Pennsylvania
- Resource Type
- Preprint
- Publication Details
- bioRxiv
- DOI
- 10.1101/2024.09.15.613139
- PMID
- 39345491
- PMCID
- PMC11429831
- NLM abbreviation
- bioRxiv
- ISSN
- 2692-8205
- eISSN
- 2692-8205
- Language
- English
- Date posted
- 09/19/2024
- Academic Unit
- Electrical and Computer Engineering; Radiation Oncology; The Iowa Institute for Biomedical Imaging
- Record Identifier
- 9984721248902771
Metrics
21 Record Views