Deep learning segmentation of paediatric brain tumours using diffusion-weighted MRI: towards an early, <i>in vivo</i> classification pipeline.
Authors
Affiliations (6)
Affiliations (6)
- Aston Institute of Health and Neurodevelopment, College of Health and Life Sciences, Aston University, Birmingham B4 7TE, UK.
- Medical Physics and Clinical Engineering, Nottingham University Hospitals NHS Trust, Nottingham NG5 1PB, UK.
- College of Engineering and Physical Sci., Aston University, Birmingham B4 7TE, UK.
- Department of Oncology, Birmingham Children's Hospital, Birmingham B4 6NH, UK.
- Department of Cancer and Genomic Sciences, University of Birmingham, Birmingham B15 2TT, UK.
- School of Engineering, University of Birmingham, Birmingham B15 2TT, UK.
Abstract
Diffusion-weighted MRI (DWI) can offer vital quantitative biomarkers to understand paediatric brain tumours to benefit clinical management. However, extraction of these markers requires delineation of the tumour margins, which is time-consuming, requires expertise and can still be highly variable. Automated approaches using deep learning to generate these tumour regions exist, but to our knowledge, few exist using only DWI as an input modality, with none in paediatrics. This retrospective study develops an automated segmentation approach, leveraging transfer learning and multi-modal ensembling to tackle the issues specific to this DWI-only approach. Using the Imaging of Tumors study data, we analysed data from 107 paediatric brain tumour patients. Using a 3D convolutional neural network, namely DeepMedic, to perform automatic segmentations, we demonstrate the benefit of these approaches for this task. We assess the accuracy of these predicted segmentations in comparison to the 'ground truth' manual annotations, with a median Dice score of 0.63 achieved by the best-performing model. The current study highlights the potential of this approach to be implemented in future clinical decision support tools using DWI, but more work is needed to improve segmentation accuracy or establish current performance as 'sufficient' for the purposes that these segmentations are required.