CodeCytos: AI-assisted spatial molecular imaging analysis via code-augmented agent action space
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913175025221632 |
|---|---|
| author | Vo, Hung Q. Vo, Huy Q. Ly, Son T. Wan, Zhihao Nguyen, Anh-Vu Zhao, Hong Sheng, Jianting Wong, Stephen T. C. Nguyen, Hien V. |
| author_facet | Vo, Hung Q. Vo, Huy Q. Ly, Son T. Wan, Zhihao Nguyen, Anh-Vu Zhao, Hong Sheng, Jianting Wong, Stephen T. C. Nguyen, Hien V. |
| contents | Conventional tissue image analysis software provides foundational capabilities for cellular analysis, including segmentation, basic morphological feature extraction, and spatial organization analysis. However, these tools often require manual intervention and are not well integrated with code-driven automation, limiting efficiency and scalability for complex spatial tissue studies. In addition, they offer limited flexibility for custom analyses, as they typically support only a fixed set of pre-implemented spatial cellular features. To address these limitations, we propose CodeCytos, a coding-based reasoning agent framework that enables dynamic, programmable interaction with spatial molecular imaging data to improve automation and customization. CodeCytos is designed to streamline the exploration of custom spatial cellular features and adapt to diverse research needs. We demonstrate its utility through case studies on four expert-curated datasets from distinct tissue types: frontal cortex, non-small-cell lung cancer, pancreas, and tonsil. We evaluate CodeCytos under a realistic minimal prompt setting, where bioscientists pose simple questions without task-specific instructions or contextual information about spatial cellular analysis, and benchmark multiple LLM backbones with strong coding capabilities. We further show that incorporating tailored, domain-agnostic few-shot in-context coding-reasoning examples (randomly sampled demonstrations outside the spatial analysis domain) can substantially improve performance without requiring costly, expert-crafted in-domain demonstrations. Overall, CodeCytos outperforms baseline approaches, highlighting the potential of code-action agents to assist with custom feature exploration in spatial molecular imaging and to accelerate biomarker discovery. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2606_00472 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CodeCytos: AI-assisted spatial molecular imaging analysis via code-augmented agent action space Vo, Hung Q. Vo, Huy Q. Ly, Son T. Wan, Zhihao Nguyen, Anh-Vu Zhao, Hong Sheng, Jianting Wong, Stephen T. C. Nguyen, Hien V. Computer Vision and Pattern Recognition Artificial Intelligence Human-Computer Interaction Machine Learning Conventional tissue image analysis software provides foundational capabilities for cellular analysis, including segmentation, basic morphological feature extraction, and spatial organization analysis. However, these tools often require manual intervention and are not well integrated with code-driven automation, limiting efficiency and scalability for complex spatial tissue studies. In addition, they offer limited flexibility for custom analyses, as they typically support only a fixed set of pre-implemented spatial cellular features. To address these limitations, we propose CodeCytos, a coding-based reasoning agent framework that enables dynamic, programmable interaction with spatial molecular imaging data to improve automation and customization. CodeCytos is designed to streamline the exploration of custom spatial cellular features and adapt to diverse research needs. We demonstrate its utility through case studies on four expert-curated datasets from distinct tissue types: frontal cortex, non-small-cell lung cancer, pancreas, and tonsil. We evaluate CodeCytos under a realistic minimal prompt setting, where bioscientists pose simple questions without task-specific instructions or contextual information about spatial cellular analysis, and benchmark multiple LLM backbones with strong coding capabilities. We further show that incorporating tailored, domain-agnostic few-shot in-context coding-reasoning examples (randomly sampled demonstrations outside the spatial analysis domain) can substantially improve performance without requiring costly, expert-crafted in-domain demonstrations. Overall, CodeCytos outperforms baseline approaches, highlighting the potential of code-action agents to assist with custom feature exploration in spatial molecular imaging and to accelerate biomarker discovery. |
| title | CodeCytos: AI-assisted spatial molecular imaging analysis via code-augmented agent action space |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Human-Computer Interaction Machine Learning |
| url | https://arxiv.org/abs/2606.00472 |