A generative benchmark for evaluating the performance of fluorescent cell image segmentation
Fluorescent cell imaging technology is fundamental in life science research, offering a rich source of image data crucial for understanding cell spatial positioning, differentiation, and decision-making mechanisms. As the volume of this data expands, precise image analysis becomes increasingly criti...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2024-12-01
|
| Series: | Synthetic and Systems Biotechnology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405805X24000802 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846122128051535872 |
|---|---|
| author | Jun Tang Wei Du Zhanpeng Shu Zhixing Cao |
| author_facet | Jun Tang Wei Du Zhanpeng Shu Zhixing Cao |
| author_sort | Jun Tang |
| collection | DOAJ |
| description | Fluorescent cell imaging technology is fundamental in life science research, offering a rich source of image data crucial for understanding cell spatial positioning, differentiation, and decision-making mechanisms. As the volume of this data expands, precise image analysis becomes increasingly critical. Cell segmentation, a key analysis step, significantly influences quantitative analysis outcomes. However, selecting the most effective segmentation method is challenging, hindered by existing evaluation methods' inaccuracies, lack of graded evaluation, and narrow assessment scope. Addressing this, we developed a novel framework with two modules: StyleGAN2-based contour generation and Pix2PixHD-based image rendering, producing diverse, graded-density cell images. Using this dataset, we evaluated three leading cell segmentation methods: DeepCell, CellProfiler, and CellPose. Our comprehensive comparison revealed CellProfiler's superior accuracy in segmenting cytoplasm and nuclei. Our framework diversifies cell image data generation and systematically addresses evaluation challenges in cell segmentation technologies, establishing a solid foundation for advancing research and applications in cell image analysis. |
| format | Article |
| id | doaj-art-b12795f8053f4a42877faff8c2475b6a |
| institution | Kabale University |
| issn | 2405-805X |
| language | English |
| publishDate | 2024-12-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | Synthetic and Systems Biotechnology |
| spelling | doaj-art-b12795f8053f4a42877faff8c2475b6a2024-12-15T06:16:00ZengKeAi Communications Co., Ltd.Synthetic and Systems Biotechnology2405-805X2024-12-0194627637A generative benchmark for evaluating the performance of fluorescent cell image segmentationJun Tang0Wei Du1Zhanpeng Shu2Zhixing Cao3State Key Laboratory of Bioreactor Engineering, East China University of Science and Technology, Shanghai, 200237, China; MOE Key Laboratory of Smart Manufacturing in Energy Chemical Process, East China University of Science and Technology, Shanghai, 200237, ChinaMOE Key Laboratory of Smart Manufacturing in Energy Chemical Process, East China University of Science and Technology, Shanghai, 200237, China; Corresponding author. East China University of Science and Technology, Shanghai, 200237, China.College of Electrical Engineering, Shanghai Dianji University, Shanghai, 201306, ChinaState Key Laboratory of Bioreactor Engineering, East China University of Science and Technology, Shanghai, 200237, China; Corresponding author. East China University of Science and Technology, Shanghai, 200237, China.Fluorescent cell imaging technology is fundamental in life science research, offering a rich source of image data crucial for understanding cell spatial positioning, differentiation, and decision-making mechanisms. As the volume of this data expands, precise image analysis becomes increasingly critical. Cell segmentation, a key analysis step, significantly influences quantitative analysis outcomes. However, selecting the most effective segmentation method is challenging, hindered by existing evaluation methods' inaccuracies, lack of graded evaluation, and narrow assessment scope. Addressing this, we developed a novel framework with two modules: StyleGAN2-based contour generation and Pix2PixHD-based image rendering, producing diverse, graded-density cell images. Using this dataset, we evaluated three leading cell segmentation methods: DeepCell, CellProfiler, and CellPose. Our comprehensive comparison revealed CellProfiler's superior accuracy in segmenting cytoplasm and nuclei. Our framework diversifies cell image data generation and systematically addresses evaluation challenges in cell segmentation technologies, establishing a solid foundation for advancing research and applications in cell image analysis.http://www.sciencedirect.com/science/article/pii/S2405805X24000802Fluorescent imagesGenerative adversarial networksBiological image analysisCell segmentation |
| spellingShingle | Jun Tang Wei Du Zhanpeng Shu Zhixing Cao A generative benchmark for evaluating the performance of fluorescent cell image segmentation Synthetic and Systems Biotechnology Fluorescent images Generative adversarial networks Biological image analysis Cell segmentation |
| title | A generative benchmark for evaluating the performance of fluorescent cell image segmentation |
| title_full | A generative benchmark for evaluating the performance of fluorescent cell image segmentation |
| title_fullStr | A generative benchmark for evaluating the performance of fluorescent cell image segmentation |
| title_full_unstemmed | A generative benchmark for evaluating the performance of fluorescent cell image segmentation |
| title_short | A generative benchmark for evaluating the performance of fluorescent cell image segmentation |
| title_sort | generative benchmark for evaluating the performance of fluorescent cell image segmentation |
| topic | Fluorescent images Generative adversarial networks Biological image analysis Cell segmentation |
| url | http://www.sciencedirect.com/science/article/pii/S2405805X24000802 |
| work_keys_str_mv | AT juntang agenerativebenchmarkforevaluatingtheperformanceoffluorescentcellimagesegmentation AT weidu agenerativebenchmarkforevaluatingtheperformanceoffluorescentcellimagesegmentation AT zhanpengshu agenerativebenchmarkforevaluatingtheperformanceoffluorescentcellimagesegmentation AT zhixingcao agenerativebenchmarkforevaluatingtheperformanceoffluorescentcellimagesegmentation AT juntang generativebenchmarkforevaluatingtheperformanceoffluorescentcellimagesegmentation AT weidu generativebenchmarkforevaluatingtheperformanceoffluorescentcellimagesegmentation AT zhanpengshu generativebenchmarkforevaluatingtheperformanceoffluorescentcellimagesegmentation AT zhixingcao generativebenchmarkforevaluatingtheperformanceoffluorescentcellimagesegmentation |