AI insights supercharging lab-grown brain research

Dr Anwaar Ulhaq stands in an office, wearing a blue suit and crossing his arms.

Key points

  • AI-powered image analysis is dramatically improving how scientists study lab-grown brain organoids, enabling faster, more consistent and more accurate analysis than traditional manual methods.
  • The research combines artificial intelligence with stem cell biology, helping scientists better understand brain development, cell division and disease progression while reducing reliance on animal models.
  • In collaboration with international partners, the project is advancing AI-driven biomedical imaging and laying foundations for future diagnostic and healthcare innovations. 

Our Research

Challenge

Understanding how the human brain develops—and how neurological diseases emerge—requires researchers to analyse enormous numbers of microscope images of brain cells.

Brain organoids, miniature three-dimensional brain-like structures grown from stem cells, have transformed neuroscience by providing realistic models of human brain development while reducing reliance on animal testing. However, analysing these complex images manually is slow, subjective and often inconsistent, limiting the speed of scientific discovery. 

As biomedical imaging datasets continue to grow, researchers need intelligent tools that can accurately interpret complex biological images, even when data is limited or highly variable.

Solution

CQUniversity researchers have developed advanced artificial intelligence systems that automatically analyse microscope images of brain organoids.

Unlike conventional image recognition tools, the AI combines computer vision with biological knowledge, enabling it to recognise subtle stages of cellular activity—such as different phases of cell division—that are critical to understanding brain growth and disease progression. 

The technology is specifically designed for real biomedical environments, where datasets are often small, imbalanced or visually complex. By automating image analysis, researchers can:

  • analyse significantly more samples
  • improve consistency and accuracy
  • identify patterns difficult to detect manually
  • accelerate biomedical discoveries. 

The research demonstrates how explainable, medically grounded AI can become an important decision-support tool for neuroscience and regenerative medicine. 

Impact

Accelerating brain research

Automated image analysis enables researchers to analyse brain organoids more quickly and consistently, helping scientists better understand how the brain develops and how neurological diseases progress. Faster analysis means new discoveries can be made more efficiently, supporting advances in neuroscience and stem cell research. 

Advancing AI for healthcare

The project represents an important step towards intelligent medical imaging systems that do more than recognise patterns—they interpret biological information in ways that support scientific decision-making.

The research contributes to the growing field of AI-driven biomedical imaging and has potential applications across medical diagnostics, disease modelling and future healthcare technologies. 

Strengthening global research collaboration

The project combines expertise from Australia, the United Kingdom and the United Arab Emirates, demonstrating how international collaboration can accelerate innovation while positioning CQUniversity as a leader in applied artificial intelligence for health research. 

  • Dr Anwaar Ulhaq
    Dr Ulhaq leads the development of AI-driven biomedical imaging systems, specialising in computer vision, explainable artificial intelligence and medical image analysis.
  • Researchers from the University of Oxford
  • Researchers from Khalifa University  
  • CQUniversity Australia
  • University of Oxford
  • Khalifa University

Subscribe to Impact Connections

Stay up to date with the latest CQUniversity research making a difference in communities across Australia and around the world. Subscribe to the Impact Connections newsletter.

Subscribe