PhD scholarship in Machine learning and AI to Improve Targeted Radionuclide Therapy

TRT leverages radiopharmaceuticals that home in on cancer cells, delivering a therapeutic radiation dose while minimising damage to surrounding healthy tissues. By combining vast datasets on radionuclide energy deposition, PET-captured spatio-temporal distribution, and immunohistochemistry (IHC) data, the project seeks to refine the accuracy of internal dosimetry. This integration addresses challenges such as heterogeneous radiopharmaceutical distribution within tumours and the spatial resolution limitations of current imaging methods.Key scientific objectives include mapping IHC data onto Monte Carlo simulation models to reflect true cellular-level distribution and creating transparent, explainable AI frameworks. These models are designed to incorporate a human-in-the-loop strategy, allowing clinicians to adjust parameters based on patient-specific anatomy and physiology. Validation studies will be conducted to ensure that AI-derived dosimetry aligns with actual patient outcomes, thereby enhancing clinical trust.Industry collaboration is a vital aspect of the project. In partnership with Cyclotek, one of the largest suppliers of PET radiopharmaceuticals in Australia and New Zealand, students will have the opportunity to engage in a six-month internship. This internship offers practical experience in understanding real-world applications of AI in PET imaging.