EUVIMEDEUVIMED entdecken
Open Access

OrgaCast: A Trustworthy Spatiotemporal Diffusion Model for Fluorescence Organoid Forecasting

Dawei Gao, Angello Huerta Gomez, Mingchen Li, Marcel El-Mokahal, Huaxiao Yang, Yunhe Feng

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (6) · 4104-4112

DOI: 10.1609/aaai.v40i6.42405 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Dawei Gao und 5 weiteren Autor:innen. Beteiligte Einrichtung: University of North Texas, Denton, TX, USA. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NICHD NIH HHS, NHLBI NIH HHS, NIGMS NIH HHS.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurately forecasting the spatiotemporal dynamics of biological systems, such as human pluripotent stem cell (hPSC)-derived cardiac organoids, from microscopy time-series is a critical challenge in biomedicine with profound implications for drug discovery. Existing generative models often fail to capture the intricate dynamics of organoid development, struggling with their irregular morphology, indistinct boundaries, and complex spatiotemporal patterns. To overcome these limitations, we introduce OrgaCast, a novel multimodal conditional diffusion model for high-fidelity organoid forecasting. OrgaCast uniquely conditions the generative process on three synergistic modalities: (i) historical image sequences, captured by a dedicated spatiotemporal control module; (ii) structured numerical metadata defining experimental conditions; and (iii) descriptive text captions summarizing the biological context. This comprehensive conditioning enables the generation of forecasts with high visual accuracy and biological plausibility. Furthermore, to enhance the model's utility in critical research settings, we introduce a post-hoc uncertainty quantification method that produces intuitive confidence maps, bolstering the interpretability and trustworthiness of predictions. Extensive experiments on a challenging cardiac organoid dataset demonstrate that OrgaCast outperforms baselines in metrics such as SSIM, PSNR, and LPIPS. Our framework presents a robust solution for biological forecasting, promising to accelerate research discovery while minimizing experimental costs and manual effort.

Autor:innen und Institutionen

  • University of North Texas, Denton, TX, USA.

Förderung

  • NICHD NIH HHS
  • NHLBI NIH HHS
  • NIGMS NIH HHS

Zitieren

APA

Gao, D., Gomez, A. H., Li, M., El-Mokahal, M., Yang, H., & Feng, Y. (2026). OrgaCast: A Trustworthy Spatiotemporal Diffusion Model for Fluorescence Organoid Forecasting. Proceedings of the AAAI Conference on Artificial Intelligence, 40(6), 4104-4112. https://doi.org/10.1609/aaai.v40i6.42405

Vancouver

Gao D, Gomez AH, Li M, El-Mokahal M, Yang H, Feng Y. OrgaCast: A Trustworthy Spatiotemporal Diffusion Model for Fluorescence Organoid Forecasting. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(6):4104-4112. doi:10.1609/aaai.v40i6.42405

BibTeX
@article{Gao2026,
  author = {Gao, Dawei and Gomez, Angello Huerta and Li, Mingchen and El-Mokahal, Marcel and Yang, Huaxiao and Feng, Yunhe},
  title = {OrgaCast: A Trustworthy Spatiotemporal Diffusion Model for Fluorescence Organoid Forecasting},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {6},
  pages = {4104--4112},
  doi = {10.1609/aaai.v40i6.42405}
}
Kostenlos starten →