Yiping Lu1, Markand Patel2, Kal Natarajan3, Ismail Ughratdar4, Paul Sanghera5, Raj Jena6, Colin Watts7, Vijay Sawlani8. 1. Neuroradiology, Queen Elizabeth Hospital Birmingham, University Hospitals Birmingham NHS Foundation Trust, Mindelsohn Way, Edgbaston, Birmingham B15 2TH, UK; Radiology, Huashan Hospital, Fudan University, Wulumuqi Middle Road, Shanghai, China. 2. Neuroradiology, Queen Elizabeth Hospital Birmingham, University Hospitals Birmingham NHS Foundation Trust, Mindelsohn Way, Edgbaston, Birmingham B15 2TH, UK; University of Birmingham, Edgbaston, Birmingham B15 2TT, UK. 3. Medical Physics, Queen Elizabeth Hospital Birmingham, University Hospitals Birmingham NHS Foundation Trust, Mindelsohn Way, Edgbaston, Birmingham B15 2TH, UK. 4. Neurosurgery, Queen Elizabeth Hospital Birmingham, University Hospitals Birmingham NHS Foundation Trust, Mindelsohn Way, Edgbaston, Birmingham B15 2TH, UK. 5. Clinical Oncology, Queen Elizabeth Hospital Birmingham, University Hospitals Birmingham NHS Foundation Trust, Mindelsohn Way, Edgbaston, Birmingham B15 2TH, UK. 6. Oncology, Addenbrooke's Hospital, Cambridge University Hospitals NHS Foundation Trust, Hills Road, Cambridge CB2 0QQ, UK. 7. University of Birmingham, Edgbaston, Birmingham B15 2TT, UK; Neurosurgery, Queen Elizabeth Hospital Birmingham, University Hospitals Birmingham NHS Foundation Trust, Mindelsohn Way, Edgbaston, Birmingham B15 2TH, UK. 8. Neuroradiology, Queen Elizabeth Hospital Birmingham, University Hospitals Birmingham NHS Foundation Trust, Mindelsohn Way, Edgbaston, Birmingham B15 2TH, UK; University of Birmingham, Edgbaston, Birmingham B15 2TT, UK. Electronic address: Vijay.Sawlani@uhb.nhs.uk.
Abstract
INTRODUCTION: Survival varies in patients with glioblastoma due to intratumoral heterogeneity and radiomics/imaging biomarkers have potential to demonstrate heterogeneity. The objective was to combine radiomic, semantic and clinical features to improve prediction of overall survival (OS) and O6-methylguanine-DNA methyltransferase (MGMT) promoter methylation status from pre-operative MRI in patients with glioblastoma. METHODS: A retrospective study of 181 MRI studies (mean age 58 ± 13 years, mean OS 497 ± 354 days) performed in patients with histopathology-proven glioblastoma. Tumour mass, contrast-enhancement and necrosis were segmented from volumetric contrast-enhanced T1-weighted imaging (CE-T1WI). 333 radiomic features were extracted and 16 Visually Accessible Rembrandt Images (VASARI) features were evaluated by two experienced neuroradiologists. Top radiomic, VASARI and clinical features were used to build machine learning models to predict MGMT status, and all features including MGMT status were used to build Cox proportional hazards regression (Cox) and random survival forest (RSF) models for OS prediction. RESULTS: The optimal cut-off value for MGMT promoter methylation index was 12.75%; 42 radiomic features exhibited significant differences between high and low-methylation groups. However, model performance accuracy combining radiomic, VASARI and clinical features for MGMT status prediction varied between 45 and 67%. For OS predication, the RSF model based on clinical, VASARI and CE radiomic features achieved the best performance with an average iAUC of 96.2 ± 1.7 and C-index of 90.0 ± 0.3. CONCLUSIONS: VASARI features in combination with clinical and radiomic features from the enhancing tumour show promise for predicting OS with a high accuracy in patients with glioblastoma from pre-operative volumetric CE-T1WI.
INTRODUCTION: Survival varies in patients with glioblastoma due to intratumoral heterogeneity and radiomics/imaging biomarkers have potential to demonstrate heterogeneity. The objective was to combine radiomic, semantic and clinical features to improve prediction of overall survival (OS) and O6-methylguanine-DNA methyltransferase (MGMT) promoter methylation status from pre-operative MRI in patients with glioblastoma. METHODS: A retrospective study of 181 MRI studies (mean age 58 ± 13 years, mean OS 497 ± 354 days) performed in patients with histopathology-proven glioblastoma. Tumour mass, contrast-enhancement and necrosis were segmented from volumetric contrast-enhanced T1-weighted imaging (CE-T1WI). 333 radiomic features were extracted and 16 Visually Accessible Rembrandt Images (VASARI) features were evaluated by two experienced neuroradiologists. Top radiomic, VASARI and clinical features were used to build machine learning models to predict MGMT status, and all features including MGMT status were used to build Cox proportional hazards regression (Cox) and random survival forest (RSF) models for OS prediction. RESULTS: The optimal cut-off value for MGMT promoter methylation index was 12.75%; 42 radiomic features exhibited significant differences between high and low-methylation groups. However, model performance accuracy combining radiomic, VASARI and clinical features for MGMT status prediction varied between 45 and 67%. For OS predication, the RSF model based on clinical, VASARI and CE radiomic features achieved the best performance with an average iAUC of 96.2 ± 1.7 and C-index of 90.0 ± 0.3. CONCLUSIONS: VASARI features in combination with clinical and radiomic features from the enhancing tumour show promise for predicting OS with a high accuracy in patients with glioblastoma from pre-operative volumetric CE-T1WI.