Dr Teddy Zhao PhD

• PhD, Cancer and Genomic Sciences, University of Birmingham, England
• maîtrise, électronique et télécommunications, Université de Rennes, France

Teddy studied biomedical engineering and medical imaging between 2010 and 2017. During his undergraduate studies, Teddy was interested in data science and mathematical modelling for biological and clinical questions. In his master studies, Teddy researched two topics, Fourier analysis for photoplethysmography signals and magnetic resonance spectroscopic imaging for Alzheimer’s disease.

Teddy moved to Birmingham, England in 2017 to research in vivo nuclear magnetic resonance spectroscopy for paediatric brain cancer diagnosis, supervised by Professor Andrew C Peet. Between 2020 and 2024, Teddy worked at Professor Dominik R Bach’s group in computational neuroscience at University College London as a part-time research assistant for developing neurophysiological data analysis tools.

Since 2022, Teddy continues his research in cancer imaging at Birmingham as a postdoctoral fellow, where he works closely with Professor Andrew C Peet and Dr John R Apps for developing a computerised clinical decision support system and designing explainable machine learning methods for rare cancer diagnosis.

Teddy provides supervision for postgraduate research students with expertise in data science and magnetic resonance spectroscopy.

Teddy’s main research interest is to design multidisciplinary machine learning for answering questions in cancer research with support from evidence in corresponding areas.

Teddy originally came from biomedical engineering before completing a PhD in cancer imaging. During his PhD, Teddy worked as a data scientist in a multidisciplinary research team and collaborated with researchers of clinical and natural sciences. Teddy’s PhD focused on understanding metabolism in childhood brain tumours through clinical cohorts and 1.5T/3T in vivo single-voxel proton nuclear magnetic resonance (NMR) spectroscopy, where he designed multiple computational models that translated spectroscopic biomarkers to cancer diagnosis with support from physics, computational science, and biochemistry. Teddy used machine learning to understand and overcome restrictions in in vivo proton NMR spectroscopy for answering clinical and scientific questions in cancer metabolism. 

Teddy’s research goal following his PhD is to support the translational use of in vivo NMR spectroscopy for cancer by harmonising and overcoming current challenges. Teddy uses machine learning as a tool to reveal precise cancer biomarkers from in vivo NMR spectroscopy and imaging for diagnosis by collaborating with clinicians. In detail, he focuses on (1) translating in vivo NMR spectroscopy and imaging into a computerised clinical decision support system by interpreting radiomic biomarkers for cancer diagnosis (Little Princess Trust) and (2) designing explainable machine learning methods for rare cancer diagnosis through utilising metabolic and cellular biomarkers (National Institute of Health Research).