1 August 2022 in Radiology
MRI-based machine learning designed with sequential decision steps reliably differentiated four unique medulloblastoma molecular subgroups. Background Radiogenomics of pediatric medulloblastoma (MB) offers an opportunity for MB risk stratification, which may aid therapeutic decision making, family counseling, and selection of patient g...
1 January 2021 in Neuro-Oncology Advances
Diffuse intrinsic pontine gliomas (DIPGs) are lethal pediatric brain tumors. Presently, MRI is the mainstay of disease diagnosis and surveillance. We identify clinically significant computational features from MRI and create a prognostic machine learning model. We isolated tumor volumes of T1-post-contrast (T1) and T2-weighted (T2) MRIs from 177 treatment-naïve DIPG patients from an international cohort for model training and testing. The Quantitative Image Feature Pipeline and PyRadiomics was used for feature extraction. Ten-fold cross-validation of least absolute shrinkage and selection operator Cox regression selected optimal features to predict overall survival in the training dataset and tested in the independent testing dataset. We analyzed model performance using clinical variables (age at diagnosis and sex) only, radiomics only, and radiomics plus clinical variables. All selected features were intensity and texture-based on the wavelet-filtered images (3 T1 gray-level co-occurrence matrix (GLCM) texture features, T2 GLCM texture feature, and T2 first-order mean). This multivariable Cox model demonstrated a concordance of 0.68 (95% CI: 0.61–0.74) in the training dataset, significantly outperforming the clinical-only model (C = 0.57 [95% CI: 0.49–0.64]). Adding clinical features to radiomics slightly improved performance (C = 0.70 [95% CI: 0.64–0.77]). The combined radiomics and clinical model was validated in the independent testing dataset (C = 0.59 [95% CI: 0.51–0.67], Noether’s test P = .02). In this international study, we demonstrate the use of radiomic signatures to create a machine learning model for DIPG prognostication. Standardized, quantitative approaches that objectively measure DIPG changes, including computational MRI evaluation, could offer new approaches to assessing tumor phenotype and serve a future role for optimizing clinical trial eligibility and tumor surveillance.
20 June 2018 in Child's Nervous System
Purpose To determine the value of structural magnetic resonance imaging (MRI) in predicting post-operative paediatric cerebellar mutism syndrome (pCMS) in children undergoing surgical treatment for medulloblastoma. Methods Retrospective cohort study design. Electronic/paper case note review of all children with medulloblastoma presenting to Great Ormond Street Hospital between 2003 and 2013. The diagnosis of pCMS was established through a scoring system incorporating mutism, ataxia, behavioural disturbance and cranial nerve deficits. MRI scans performed at three time points were assessed by neuroradiologists blinded to the diagnosis of pCMS. Results Of 56 children included, 12 (21.4%) developed pCMS as judged by a core symptom of mutism. pCMS was more common in those aged 5 or younger. There was no statistically significant difference in pre-operative distortion or signal change of the dentate or red nuclei or superior cerebellar peduncles (SCPs) between those who did and did not develop pCMS. In both early (median 5 days) and late (median 31 months) post-operative scans, T2-weighted signal change in SCPs was more common in the pCMS group (p = 0.040 and 0.046 respectively). Late scans also showed statistically significant signal change in the dentate nuclei (p = 0.024). Conclusions The development of pCMS could not be linked to any observable changes on pre-operative structural MRI scans. Post-operative T2-weighted signal change in the SCPs and dentate nuclei underlines the role of cerebellar efferent injury in pCMS. Further research using advanced quantitative MRI sequences is warranted given the inability of conventional pre-surgical MRI to predict pCMS.
25 November 2021 in Neuro-Oncology
The risk profile for posterior fossa ependymoma (EP) depends on surgical and molecular status [Group A (PFA) versus Group B (PFB)]. While subtotal tumor resection is known to confer worse prognosis, MRI-based EP risk-profiling is unexplored. We aimed to apply machine learning strategies to link MRI-based biomarkers of high-risk EP and also to distinguish PFA from PFB. We extracted 1800 quantitative features from presurgical T2-weighted (T2-MRI) and gadolinium-enhanced T1-weighted (T1-MRI) imaging of 157 EP patients. We implemented nested cross-validation to identify features for risk score calculations and apply a Cox model for survival analysis. We conducted additional feature selection for PFA versus PFB and examined performance across three candidate classifiers. For all EP patients with GTR, we identified four T2-MRI-based features and stratified patients into high- and low-risk groups, with 5-year overall survival rates of 62% and 100%, respectively (P < .0001). Among presumed PFA patients with GTR, four T1-MRI and five T2-MRI features predicted divergence of high- and low-risk groups, with 5-year overall survival rates of 62.7% and 96.7%, respectively (P = .002). T1-MRI-based features showed the best performance distinguishing PFA from PFB with an AUC of 0.86. We present machine learning strategies to identify MRI phenotypes that distinguish PFA from PFB, as well as high- and low-risk PFA. We also describe quantitative image predictors of aggressive EP tumors that might assist risk-profiling after surgery. Future studies could examine translating radiomics as an adjunct to EP risk assessment when considering therapy strategies or trial candidacy.
14 August 2021 in Neurosurgery
BACKGROUND: Clinicians and machine classifiers reliably diagnose pilocytic astrocytoma (PA) on magnetic resonance imaging (MRI) but less accurately distinguish medulloblastoma (MB) from ependymoma (EP). One strategy is to first rule out the most identifiable diagnosis. OBJECTIVE: To hypothesize a sequential machine-learning classifier could improve diagnostic performance by mimicking a clinician's strategy of excluding PA before distinguishing MB from EP. METHODS: We extracted 1800 total Image Biomarker Standardization Initiative (IBSI)-based features from T2- and gadolinium-enhanced T1-weighted images in a multinational cohort of 274 MB, 156 PA, and 97 EP. We designed a 2-step sequential classifier – first ruling out PA, and next distinguishing MB from EP. For each step, we selected the best performing model from 6-candidate classifier using a reduced feature set, and measured performance on a holdout test set with the microaveraged F1 score. RESULTS: Optimal diagnostic performance was achieved using 2 decision steps, each with its own distinct imaging features and classifier method. A 3-way logistic regression classifier first distinguished PA from non-PA, with T2 uniformity and T1 contrast as the most relevant IBSI features (F1 score 0.8809). A 2-way neural net classifier next distinguished MB from EP, with T2 sphericity and T1 flatness as most relevant (F1 score 0.9189). The combined, sequential classifier was with F1 score 0.9179. CONCLUSION: An MRI-based sequential machine-learning classifiers offer high-performance prediction of pediatric posterior fossa tumors across a large, multinational cohort. Optimization of this model with demographic, clinical, imaging, and molecular predictors could provide significant advantages for family counseling and surgical planning.
1 November 2018 in European Journal of Radiology
Post-operative paediatric cerebellar mutism syndrome (pCMS) occurs in around 25% of children undergoing surgery for cerebellar and fourth ventricular tumours. Reversible mutism is the hallmark of a syndrome which comprises severe motor, cognitive and linguistic deficits. Recent evidence from advanced neuroimaging studies has led to the current theoretical understanding of the condition as a form of diaschisis contingent on damage to efferent cerebellar circuitry. Tractography data derived from diffusion MRI studies have shown disruption of the dentato-rubro-thalamo-cortical tract in patients with pCMS, and perfusion studies have indicated widespread supratentorial regions which may give rise to the florid signs and symptoms of pCMS. Given the difficulties in predicting pCMS from standard structural MRI, this review discusses findings from quantitative MRI modalities which have contributed to our understanding of this debilitating syndrome, and considers the goals and challenges which lie ahead in the field.