Meeting Banner
Abstract #0258

Classification of Pediatric Brain Tumours using Apparent Diffusion Coefficient – a Multi-Centre Study

Jan Novak1,2, Niloufar Zarinabad1,2, Theodoros N Arvanitis3, Lesley MacPherson4, Daniel Rodriguez 5,6, Richard Grundy6, Dorothee Auer7,8, Tim Jaspan6, Shivaram Avula9, Laurence Abernethy9, Patrick Hales10, Ramneek Kaur10, Darren Hargrave11, Dipayan Mitra12, Simon Bailey13, Nigel Davies14, Christopher Clark10, and Andrew Peet2,15

1Institute of Cancer and Genomic Sciences, University of Birmingham, Birmingham, United Kingdom, 2Oncology, Birmingham Children's Hospital, Birmingham, United Kingdom, 3Institute of Digital Healthcare, University of Warwick, Coventry, United Kingdom, 4Radiology, Birmingham Children's Hospital, Birmingham, United Kingdom, 5Division of Clinical Neuroscience, University of Nottingham, Nottingham, United Kingdom, 6The Children‘s Brain Tumour Research Centre, University of Nottingham, Nottingham, United Kingdom, 7Sir Peter Mansfield Imaging Centre, University of Nottingham, Nottingham, United Kingdom, 8Department of Neuroradiology, Nottingham University Hospital Trusts, Nottingham, United Kingdom, 9Radiology, Alder Hey Children’s NHF Foundation Trust, Liverpool, United Kingdom, 10Developmental Imaging and Biophysics Section, University College London, London, United Kingdom, 11Haematology and Oncology Department, Great Ormond Street Children's Hospital, London, United Kingdom, 12The Newcastle upon Tyne Hospitals NHS Foundation Trust, Newcastle, United Kingdom, 13Sir James Spence Institute of Child Health, Royal Victoria Infirmary, Newcastle upon Tyne, United Kingdom, 14Radiation Protection Services, University Hospitals Birmingham NHS Foundation Trus, Birmingham, United Kingdom, 15Institute of Cancer and Genomic Sciences, University of Birmingham, BIRMINGHAM, United Kingdom

The purpose of the study was to investigate the potential of apparent diffusion coefficient (ADC) to discriminate between paediatric cerebellar tumours on a multicentre basis using histograms. A total of 117 paediatric patients with cerebellar tumours (55 Medulloblastomas, 36 Pilocytic Astrocytomas and 26 Ependymomas) were imaged using diffusion weighted imaging across 12 different hospitals using a total of 18 different scanners. Overall classification accuracies for the ADC histogram metrics were 86 % using Naïve Bayes and 84 % for Random Forest classifier.

This abstract and the presentation materials are available to members only; a login is required.

Join Here

Abstract