ICTürkiye2025 International Brokerage Event

10 Apr 2025 | İstanbul, Türkiye

ProductUpdated on 27 March 2025

HistoNeRF

Kubilay Doğan Kılıç

Post Doctoral Researcher at Ege Üniversitesi

Izmir, Türkiye

About

HistoNeRF is an innovative software platform that transforms conventional 2D histological images into high-resolution 3D tissue reconstructions using Neural Radiance Fields (NeRF), a cutting-edge artificial intelligence technology. Developed through a multidisciplinary collaboration between histologists and computer engineers, HistoNeRF addresses a critical gap in medical imaging: the inability of 2D microscopy to represent the complex three-dimensional microarchitecture of biological tissues fully.

Traditional histology relies on thin tissue sections and 2D imaging, which often obscure spatial relationships, cellular layering, and volumetric pathology features—especially in complex structures like tumors, glands, or vascular systems. While advanced imaging techniques such as confocal microscopy or micro-CT offer 3D insights, they require expensive hardware, technical expertise, and time-consuming protocols. HistoNeRF eliminates these limitations by leveraging AI to create photorealistic, interactive, and hardware-independent 3D models directly from routine 2D slides.

The system integrates multiple advanced components:

  • Deep Learning-based 3D Reconstruction using NeRF to model light behavior and spatial structure from serial 2D images.

  • Automated Segmentation with U-Net architecture to highlight histologically relevant features (e.g., cell boundaries, vessels).

  • Interactive Visualization Interface (PyQt-based) with real-time rendering, slicing, zoom, and rotation.

  • GPU Acceleration via CUDA to ensure high performance and smooth user interaction.

  • User-oriented design with export options (STL, OBJ, PDF), metadata display, and accessibility features for pathology labs and educational use.

HistoNeRF is particularly useful in:

  • Medical Research: Enables detailed morphological analysis, quantitative comparisons, and 3D data integration in histopathological studies.

  • Medical Education: Facilitates student understanding of complex tissue structures through interactive 3D exploration, enhancing traditional microscopy training.

  • Digital Pathology & Diagnostics: Offers a scalable alternative to 3D imaging for hospitals and clinics, paving the way for integration with AI-assisted diagnostic systems.

This platform lowers the barrier to 3D histology, making it accessible even in settings with limited imaging infrastructure. By providing a cost-effective and intuitive tool, HistoNeRF democratizes access to spatially resolved histological analysis and opens the door for new clinical and research applications in oncology, developmental biology, and personalized medicine.

With its cross-platform compatibility (Windows, macOS, Linux), open-source core architecture, and future-ready design, HistoNeRF has strong potential for commercialization as a standalone software product or an integrated module within existing digital pathology systems. Upcoming developments include real-time anomaly detection via AI, cloud-based collaboration modules, and DICOM-standard clinical integration.

Applies to

  • Artificial Intelligence (AI)-based Tools and Technologies
  • Digital Solutions and Digitalization
  • Digital Health Data

Organisation

Ege Üniversitesi

University

Izmir, Türkiye

Similar opportunities

  • Expertise

    Metaverse Infrastructure and Co-Creation Tools

    • Virtual Worlds
    • Digital Health Data
    • Digital Solutions and Digitalization
    • Artificial Intelligence (AI)-based Tools and Technologies

    ertan toy

    Assoc. Prof. at Yildiz Technical University

    İstanbul, Türkiye

  • Project cooperation

    Mixed Reality for Medical Imaging

    • Technical Partner
    • Planning (Concept)
    • Digital Health Data
    • Digital Solutions and Digitalization
    • Innovative, Sustainable, and High-Quality Healthcare
    • Artificial Intelligence (AI) based Tools and Technologies

    Faraz Janan

    Senior Teaching Fellow (AI) at Imperial College London

    London, United Kingdom

  • Expertise

    Cardiovascular Engineering

    • Virtual Worlds
    • Digital Health Data
    • AI & Data & Robotics
    • Computing Technologies
    • Innovative, Sustainable, and High-Quality Healthcare
    • Artificial Intelligence (AI)-based Tools and Technologies

    İbrahim Başar Aka

    Assistant Professor at Bilgi University Mechatronics Engineering Program at İstanbul Bilgi Üniversitesi

    Istanbul, Türkiye