Automated Diffusion Analysis for Non-Invasive Prediction of IDH Genotype in WHO Grade 2-3 Gliomas.
Authors
Affiliations (1)
Affiliations (1)
- From the Centre for Medical Image Computing (CMIC), Department of Medical Physics and Biomedical Engineering, University College London, London, UK (JW, FPC, FB), Neuroradiological Academic Unit, UCL Queen Square Institute of Neurology, University College London, London, UK (JW, ST, SW, JM, FB), Radiological Sciences, Mental Health and Neurosciences, School of Medicine, University of Nottingham, Nottingham, UK (ST), Sir Peter Mansfield Imaging Centre, School of Physics and Astronomy, University of Nottingham, Nottingham, UK (ST), NIHR Nottingham Biomedical Research Center, Nottingham, UK (ST), Lysholm Department of Neuroradiology, National Hospital for Neurology and Neurosurgery, University College London Hospitals NHS Foundation Trust, London, UK (SW, GA, MB, JM, FB), Department of Neuroradiology, King's College Hospital NHS Foundation Trust, London, United Kingdom (GA), Department of Radiology, Mansoura University hospitals, Mansoura Faculty of Medicine, Egypt (GA), Department of Diagnostic Imaging and Radiotherapy, Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Rome, Italy (MB), Department of Radiology, Guy's and St Thomas' NHS Foundation Trust, London, UK (JM), Department of Neurodegenerative Disease, UCL Institute of Neurology and Division of Neuropathology, National Hospital for Neurology and Neurosurgery, University College London NHS Foundation Trust, London (SB), Department of Neuroinflammation, Faculty of Brain Sciences, Queen Square MS Center, UCL Institute of Neurology, University College London, London, UK (FPC), e-Health Center, Universitat Oberta de Catalunya, Barcelona, Spain (FPC), Radiology & Nuclear Medicine, VU University Medical Center, Amsterdam, the Netherlands (FB).
Abstract
Glioma molecular characterization is essential for risk stratification and treatment planning. Noninvasive imaging biomarkers such as apparent diffusion coefficient (ADC) values have shown potential for predicting glioma genotypes. However, manual segmentation of gliomas is time-consuming and operator-dependent. To address this limitation, we aimed to establish a single-sequence-derived automatic ADC extraction pipeline using T2-weighted imaging to support glioma isocitrate dehydrogenase (IDH) genotyping. Glioma volumes from a hospital data set (University College London Hospitals; n=247) were manually segmented on T2-weighted MRI scans using ITK-Snap Toolbox and co-registered to ADC maps sequences using the FMRIB Linear Image Registration Tool in FSL, followed by ADC histogram extraction (Python). Separately, a nnUNet deep learning algorithm was trained to segment glioma volumes using T2w only from BraTS 2021 data (n=500, 80% training, 5% validation and 15% test split). nnUnet was then applied to the University College London Hospitals (UCLH) data for segmentation and ADC read-outs. Univariable logistic regression was used to test the performance manual and nnUNet derived ADC metrics for IDH status prediction. Statistical equivalence was tested (paired two-sided t-test). nnUnet segmentation achieved a median Dice of 0.85 on BraTS data, and 0.83 on UCLH data. For the best performing metric (rADCmean) the area under the receiver operating characteristic curve (AUC) for differentiating IDH-mutant from IDHwildtype gliomas was 0.82 (95% CI: 0.78-0.88), compared to the manual segmentation AUC 0.84 (95% CI: 0.77-0.89). For all ADC metrics, manually and nnUNet extracted ADC were statistically equivalent (p<0.01). nnUNet identified one area of glioma infiltration missed by human observers. In 0.8% gliomas, nnUnet missed glioma components. In 6% of cases, over-segmentation of brain remote from the tumor occurred (e.g. temporal poles). The T2w trained nnUnet algorithm achieved ADC readouts for IDH genotyping with a performance statistically equivalent to human observers. This approach could support rapid ADC based identification of glioblastoma at an early disease stage, even with limited input data. AUC = Area under the receiver operating characteristic curve, BraTS = The brain tumor segmentation challenge held by MICCAI, Dice = Dice Similarity Coefficient, IDH = Isocitrate dehydrogenase, mGBM = Molecular glioblastoma, ADCmin = Fifth ADC histogram percentile, ADCmean = Mean ADC value, ADCNAWM = ADC in the contralateral centrum semiovale normal white matter, rADCmin = Normalized ADCmin, VOI rADCmean = Normalized ADCmean.