Members

Dr Blackledge has been working in the field of quantitative MRI for over 10 years, having completed his PhD developing whole-body MRI for cancer response assessment in 2011. He has a track record of developing new mathematical and computational techniques in image analysis for the purposes of monitoring treatment response in cancer patients.

Sheng obtained his PhD in the field of Electronic Health Records and clinical data integration. His current research interests include identification of therapeutic markers in high throughput drug screens and predictive biomarkers of treatment toxicity with machine learning. He aims to integrate genomic and patient data with imaging using deep learning and radiomics.

Imogen's PhD combines AI with multi-parametric, quantitative MRI in soft-tissue sarcoma. Her main areas of study include extracting quantitative information from multiple MRI techniques including (dynamic contrast-enhanced, diffusion-weighted and elastography), and subsequently using cutting-edge machine learning to improve assessment of heterogeneous radiotherapy response.

Annemarie is a physics graduate from Warwick university, who joined the team in 2019. Her PhD project focusses on the development of novel image-processing techniques for whole-body MRI in order to monitor heterogeneous response in patients with advanced melanoma.

Reza's PhD focusses on the application of novel methods in deep-learning to automate the process of disease and healthy organ delineation from MRI scans in order to improve the radiotherapy treatment planning pathway. He is keen to harness recent breakthroughs in artificial intelligence and computer vision to improve analysis of large medical imaging datasets.

Konstantinos is developing techniques that combine digital histopathology with MRI to better understand the connection between imaging appearances and the biology of soft tissue tumours. He is also developing innovative deep-learning techniques that accelerate scanning times for whole-body MRI.

Dr Hindocha is a clinical oncology specialist registrar. He is among the first cohort of students to be awarded PhD funding by the prestigious UKRI AI for Healthcare Centre for Doctoral Training at Imperial College London. Dr Hindocha is leading the OCTAPUS-AI study which focuses on radiomics and deep-learning to develop prognostication models following curative intent radiotherapy for non-small cell lung cancer.

Anjus' PhD aims to develop an AI-based tool for predicting swallowing difficulties (dysphagia) following radiotherapy of the head and neck. She is building deep-learning techniques that can combine imaging, dosimetric and patient demographic data to drive discovery of predictive biomarkers, with an aim to optimize radiation dose in this population.

Megan's PhD, funded by the CRUK convergence science centre, focusses on combining super-resolution ultrasound (SRUS) with quantitative modelling of contrast-enhanced and diffusion-weighted MRI to improve characterisation of radiotherapy-induced changes to the microvasculature of patient with advanced breast cancers. She hopes to use this information to improve prediction of patient outcomes following treatment.

Timothy's PhD focusses on the application of deep-learning to develop novel predictive biomarkers of tumour response using real-world imaging data of soft-tissue sarcomas. His PhD is funded as part of the international Sarcoma Accelerator, funded by Cancer Research UK, which will collect one of the largest repositories of multi-center sarcoma datasets.

Antonio is developing fully automated tumour segmentation from whole-body MRI, with a focus on advanced prostate cancer. This deep-learning tool is being developed into a medical device for implementation of techniques into clinical practice. He is combining these tools to develop models of metastatic tumour response from systemic treatments of advanced disease.