Automated tumour contouring of brain metastases for stereotactic radiosurgery planning and response prediction following treatment
Lead Research Organisation:
King's College London
Department Name: Imaging & Biomedical Engineering
Abstract
Metastatic brain tumours are the most common type of brain cancer. Patients with brain metastases require individualized patient management and may include surgery, radiation treatment and chemotherapy, either alone or in combination. This project aims to: 1) construct deep learning models to automatically detect and segment brain metastases using MRI; 2) design an interactive corrections module to facilitate the automatic initialisation of stereotactic radiosurgery (SRS) planning; and 3) create composite clinical and imaging biomarkers to predict tumour response and behaviour following stereotactic radiosurgery.
Modern learning-based image-registration methods will be utilised to provide robust spatial normalisation of the imaging dataset. The curated dataset will provide the foundation of an ambitious research programme aiming at translating such tools in clinical practice by making the AI tools flexible enough to seamlessly integrate into the clinical workflow. Deep learning interactive segmentation methods will be used and embedded within the MONAI Label software framework. Human factors analysis will evaluate changes to the clinical workflow of SRS planning through the integration of automated deep learning frameworks with support for user-driven corrections.
Modern learning-based image-registration methods will be utilised to provide robust spatial normalisation of the imaging dataset. The curated dataset will provide the foundation of an ambitious research programme aiming at translating such tools in clinical practice by making the AI tools flexible enough to seamlessly integrate into the clinical workflow. Deep learning interactive segmentation methods will be used and embedded within the MONAI Label software framework. Human factors analysis will evaluate changes to the clinical workflow of SRS planning through the integration of automated deep learning frameworks with support for user-driven corrections.
Organisations
People |
ORCID iD |
Jonathan Shapey (Primary Supervisor) | |
Marina Ivory (Student) |
Studentship Projects
Project Reference | Relationship | Related To | Start | End | Student Name |
---|---|---|---|---|---|
EP/Y035364/1 | 31/03/2024 | 29/09/2032 | |||
2930150 | Studentship | EP/Y035364/1 | 30/09/2024 | 29/09/2028 | Marina Ivory |