Holotomography and artificial intelligence: label-free 3D imaging, classification, and inference of live cells, tissues, and organoids

Holotomography and artificial intelligence: label-free 3D imaging, classification, and inference of live cells, tissues, and organoids

🎙 Prof. YongKeun (Paul) Park 👥 71 📅 October 13, 2025 ⏱ 29 min 👁 153 📄 expert opinion 🧭 2026-08-16
Available in: English (current) Français

Keywords

holotomographyquantitative phase imagingrefractive indexlabel-freeAI3D imagingorganoidsvirtual stainingsegmentationclassification

Summary

In this plenary presentation at ICAPI 2025, Prof. YongKeun (Paul) Park introduces holotomography (HT), a label-free 3D imaging technique based on refractive index contrast, and its integration with artificial intelligence (AI). He explains the principle as an optical analog to X-ray CT, using multiple illumination angles to reconstruct 3D refractive index distributions. Key benefits include no labeling, high resolution (150 nm), fast acquisition, and long-term live cell imaging. He demonstrates applications in cell biology, organoids, and tissue imaging, and highlights AI’s role in segmentation, classification, and virtual staining. He also discusses extending the technique to X-ray and dielectric tensor tomography. The talk concludes with commercialization efforts and future directions.

109 words

Critical Evaluation

Value of the Information & Strength of the Argument

The presentation provides a comprehensive overview of holotomography, emphasizing its advantages over conventional techniques. The argumentation is solid, supported by numerous examples and demonstrations. The speaker effectively communicates the potential of combining HT with AI for advanced biomedical imaging and diagnostics. However, the talk is more of an overview than a detailed technical exposition, and some claims could benefit from more rigorous quantitative backing.

73 words

Title / Content Match

The title accurately reflects the content, which covers holotomography principles, applications, and AI integration.

Quality & Reliability

8/10

The presentation is by a leading expert in the field, with a strong track record of publications and commercialized technology. The content is technically sound, but as a conference talk, it lacks detailed methodological descriptions and peer-reviewed references are not explicitly cited in the talk.

Key Moments

Cited Sources

Concurring Sources

  • Tomocube — Commercial holotomography system co-founded by the speaker

Contribution & Novelties

The talk provides an expert overview of holotomography and its synergy with AI, highlighting recent advances and future directions. It emphasizes the potential of label-free 3D imaging for live cell and tissue analysis, and introduces novel applications such as virtual staining and extension to X-ray.

Pour aller plus loin :

  • Quantitative phase imaging — Overview of QPI techniques.
  • Optical diffraction tomography — Related technique.
  • Tomocube — Commercial system for holotomography.
  • Deep learning in microscopy — AI applications in imaging.

79 words

Radar Profile

The radar profile shows high scores across all dimensions, indicating a well-rounded and reliable presentation. The speaker demonstrates strong expertise, provides substantial information, and maintains a high technical level, making it a valuable resource for those interested in advanced imaging.

Reliability 8/10