Dataset Information

Combining multi-site magnetic resonance imaging with machine learning predicts survival in pediatric brain tumors.

ABSTRACT: Brain tumors represent the highest cause of mortality in the pediatric oncological population. Diagnosis is commonly performed with magnetic resonance imaging. Survival biomarkers are challenging to identify due to the relatively low numbers of individual tumor types. 69 children with biopsy-confirmed brain tumors were recruited into this study. All participants had perfusion and diffusion weighted imaging performed at diagnosis. Imaging data were processed using conventional methods, and a Bayesian survival analysis performed. Unsupervised and supervised machine learning were performed with the survival features, to determine novel sub-groups related to survival. Sub-group analysis was undertaken to understand differences in imaging features. Survival analysis showed that a combination of diffusion and perfusion imaging were able to determine two novel sub-groups of brain tumors with different survival characteristics (p < 0.01), which were subsequently classified with high accuracy (98%) by a neural network. Analysis of high-grade tumors showed a marked difference in survival (p = 0.029) between the two clusters with high risk and low risk imaging features. This study has developed a novel model of survival for pediatric brain tumors. Tumor perfusion plays a key role in determining survival and should be considered as a high priority for future imaging protocols.

SUBMITTER: Grist JT

PROVIDER: S-EPMC8460620 | biostudies-literature | 2021 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Combining multi-site magnetic resonance imaging with machine learning predicts survival in pediatric brain tumors.

Grist James T JT Withey Stephanie S Bennett Christopher C Rose Heather E L HEL MacPherson Lesley L Oates Adam A Powell Stephen S Novak Jan J Abernethy Laurence L Pizer Barry B Bailey Simon S Clifford Steven C SC Mitra Dipayan D Arvanitis Theodoros N TN Auer Dorothee P DP Avula Shivaram S Grundy Richard R Peet Andrew C AC

Scientific reports 20210923 1

Brain tumors represent the highest cause of mortality in the pediatric oncological population. Diagnosis is commonly performed with magnetic resonance imaging. Survival biomarkers are challenging to identify due to the relatively low numbers of individual tumor types. 69 children with biopsy-confirmed brain tumors were recruited into this study. All participants had perfusion and diffusion weighted imaging performed at diagnosis. Imaging data were processed using conventional methods, and a Baye ...[more]

PMID: 34556677

Similar Datasets

Project description:BackgroundThe hybrid imaging positron emission tomography/magnetic resonance (PET/MR) is an important tool in the management of pediatric oncology patients, particularly in malignant musculoskeletal pathologies, because it combines the functional and metabolic information of tumor provided by PET with the high soft-tissue contrast and the functional information offered by magnetic resonance imaging (MRI).MethodsWe performed an observational retrospective study that included pediatric patients diagnosed with primary bone or soft-tissue sarcomas in the Pediatric Hematology and Oncology Unit at the HM Montepríncipe University Hospital, Boadilla del Monte, Madrid (Spain) who underwent whole-body 18F-fluorodeoxyglucose (18F-FDG) PET/MRI as a staging study and for follow-up evaluation for treatment response from September 2017 to January 2023. This study explores the protocols, the practical application of the PET/MRI technique and our clinical experience at our center in the diagnosis and follow-up of primary bone tumors and soft-tissue sarcomas in children.ResultsSeventy-one 18F-PET/MR studies were performed on 39 patients. Most of them (55%) were initial extension studies and (45%) were follow-up studies. Most of the patients studied were male (74.4%) with a median age of 15 years. Of the 39 cases, 51% were primary bone tumors while 18% were Langerhans cell histiocytosis and 21% soft tissue tumors. Of the 71 studies, five showed metastases at the initial diagnosis, three presented lymph node involvement, one with local infiltration, and one with pulmonary metastasis.ConclusionsPET/MR has represented a significant advancement in the evaluation of pediatric malignant neoplasms, with specific applications in musculoskeletal tumors showing clear benefits over PET/CT. The primary advantage is the reduction in ionizing radiation doses and the assessment of soft tissues, making it an excellent option for malignant musculoskeletal pathologies in pediatric patients who often require long-term follow-up. It is particularly useful for early tumor detection and functional therapy monitoring in oncology. The development of new protocols is making studies increasingly faster and better tolerated, even without the need for anesthesia. PET/MRI has shown to increase diagnostic accuracy in primary bone and soft tissue tumors, as it allows for the comprehensive evaluation of their morpho-metabolic characteristics, locoregional, and distant involvement in a single study. It is also useful in surgical planning and post-treatment follow-up.

Project description:BackgroundRadiologists currently subjectively examine multi-parametric magnetic resonance imaging (MP-MRI) to determine prostate tumor aggressiveness using the Prostate Imaging Reporting and Data System scoring system (PI-RADS). Recent studies showed that modified signal to clutter ratio (SCR), tumor volume, and eccentricity (elongation or roundness) of prostate tumors correlated with Gleason score (GS). No previous studies have combined the prostate tumor's shape, SCR, tumor volume, in order to predict potential tumor aggressiveness and GS.MethodsMP-MRI (T1, T2, diffusion, dynamic contrast-enhanced images) were obtained, resized, translated, and stitched to form spatially registered multi-parametric cubes. Multi-parametric signatures that characterize prostate tumors were inserted into a target detection algorithm [adaptive cosine estimator (ACE)]. Pixel-based blobbing, and labeling were applied to the threshold ACE images. Eccentricity calculation used moments of inertia from the blobs. Tumor volume was computed by counting pixels within multi parametric MRI blobs and tumor outlines based on pathologist assessment of whole mount histology. Pathology assessment of GS was performed on whole mount prostatectomy. The covariance matrix and mean of normal tissue background was computed from normal prostate. Using signatures and normal tissue statistics, the z-score, noise corrected SCR [principal component (PC), modified regularization] from each patient was computed. Eccentricity, tumor volume, and SCR were fitted to GS. Analysis of variance assesses the relationship among the variables.ResultsA multivariate analysis generated correlation coefficient (0.60 to 0.784) and P value (0.00741 to <0.0001) from fitting two sets of independent variates, namely, tumor eccentricity (the eccentricity for the largest blob, weighted average for the eccentricity) and SCR (removing 3 PCs, removing 4 PCs, modified regularization, and z-score) to GS. The eccentricity t-statistic exceeded the SCR t-statistic. The three-variable fit to GS using tumor volume (histology, MRI) yielded correlation coefficients ranging from 0.724 to 0.819 (P value <<0.05). Tumor volumes generated from histology yielded higher correlation coefficients than MRI volumes. Adding volume to eccentricity and SCR adds little improvement for fitting GS due to higher correlation coefficients among independent variables and little additional, independent information.ConclusionsCombining prostate tumors eccentricity with SCR relatively highly correlates with GS.

Project description:IntroductionThe effects caused by differences in data acquisition can be substantial and may impact data interpretation in multi-site/scanner studies using magnetic resonance spectroscopy (MRS). Given the increasing use of multi-site studies, a better understanding of how to account for different scanners is needed. Using data from a concussion population, we compare ComBat harmonization with different statistical methods in controlling for site, vendor, and scanner as covariates to determine how to best control for multi-site data.MethodsThe data for the current study included 545 MRS datasets to measure tNAA, tCr, tCho, Glx, and mI to study the pediatric concussion acquired across five sites, six scanners, and two different MRI vendors. For each metabolite, the site and vendor were accounted for in seven different models of general linear models (GLM) or mixed-effects models while testing for group differences between the concussion and orthopedic injury. Models 1 and 2 controlled for vendor and site. Models 3 and 4 controlled for scanner. Models 5 and 6 controlled for site applied to data harmonized by vendor using ComBat. Model 7 controlled for scanner applied to data harmonized by scanner using ComBat. All the models controlled for age and sex as covariates.ResultsModels 1 and 2, controlling for site and vendor, showed no significant group effect in any metabolites, but the vendor and site were significant factors in the GLM. Model 3, which included a scanner, showed a significant group effect for tNAA and tCho, and the scanner was a significant factor. Model 4, controlling for the scanner, did not show a group effect in the mixed model. The data harmonized by the vendor using ComBat (Models 5 and 6) had no significant group effect in both the GLM and mixed models. Lastly, the data harmonized by the scanner using ComBat (Model 7) showed no significant group effect. The individual site data suggest there were no group differences.ConclusionUsing data from a large clinical concussion population, different analysis techniques to control for site, vendor, and scanner in MRS data yielded different results. The findings support the use of ComBat harmonization for clinical MRS data, as it removes the site and vendor effects.

Dataset Information

Combining multi-site magnetic resonance imaging with machine learning predicts survival in pediatric brain tumors.

Publications

Combining multi-site magnetic resonance imaging with machine learning predicts survival in pediatric brain tumors.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets