Predicting response to cardiac resynchronisation therapy
Cardiac resynchronisation therapy (CRT) is a treatment for heart failure which involves implanting a pacemaker into the heart to restore electrical and mechanical synchrony. This procedure is invasive and not without risk, but approximately 30-50% of patients do not respond positively to the treatment. Therefore, there is interest in predicting which patients are likely to respond using pre-treatment imaging data. Over the years we have proposed a number of frameworks to address this problem, starting with classical machine learning approaches and progressing to the latest deep learning methods. Along the way, we have addressed the issues of interpretability and trust in the models with a view to developing an AI model for CRT response prediction which could act as a decision support tool for cardiologists.
E. Puyol-Antón, B. S. Sidhu, J. Gould, B. Porter, M. K. Elliott, V. Mehta, C. A. Rinaldi, A. P.King, "A Multimodal Deep Learning Model for Cardiac Resynchronisation Therapy Response Prediction", Medical Image Analysis, 79:102465, 2022. (open access paper)
T. Dawood, C. Chen, R. Andlauer, B. S. Sidhu, B. Ruijsink, J. Gould, B. Porter, M. Elliott, V. Mehta, C. A. Rinaldi, E. Puyol-Antón, R. Razavi, A. P. King, "Uncertainty-Aware Training for Cardiac Resynchronisation Therapy Response Prediction", Proceedings MICCAI STACOM, 2021. (paper, presentation)
E. Puyol-Antón, C. Chen, J. R. Clough, B. Ruijsink, B. S. Sidhu, J. Gould, B. Porter, M. Elliot, V. Mehta, D. Rueckert, C. A. Rinaldi, A. P. King, "Interpretable Deep Models for Cardiac Resynchronisation Therapy Response Prediction", Proceedings MICCAI, 2020. (paper)
D. Peressutti, M. Sinclair, W. Bai, T. Jackson, J. Ruijsink, D. Nordsletten, L. Asner, M. Hadjicharalambous, C. A. Rinaldi, D. Rueckert, A. P. King, "A Framework for Combining a Motion Atlas with Non-Motion Information to Learn Clinically Useful Biomarkers: Application to Cardiac Resynchronisation Therapy Response Prediction", Medical Image Analysis 35:669-684, 2017. (open access paper)
Multimodal deep learning based framework for prediction of response to CRT
Framework for predicting response to CRT using multiple kernel learning from imaging and non-imaging data
Radiotherapy dose map overlaid onto CT scan of mandible area
Predicting toxicity in radiotherapy
Mandible osteoradionecrosis (ORN) is one of the most severe toxicities in patients with head and neck cancer undergoing radiotherapy. Previous literature has focused on examining correlations between mandible ORN and clinical and dosimetric factors. In this work, for the first time we investigated the use of machine learning methods to make personalised predictions of mandible ORN incidence.
L. Humbert-Vidan, V. Patel, R. Andlauer, A. P King, T. G. Urbano, "Prediction of Mandibular ORN Incidence From 3D Radiation Dose Distribution Maps Using Deep Learning", Proceedings MICCAI AMAI, 2022. (paper)
L. Humbert-Vidan, V. Patel, I. Oksuz, A. P. King, T. Guerrero-Urbano, "Comparison of machine learning methods for prediction of osteoradionecrosis incidence in patients with head and neck cancer", British Journal of Radiology, 2021. (paper)