Combining multi-site magnetic resonance imaging with machine learning predicts survival in pediatric brain tumors.
Ontology highlight
ABSTRACT:
SUBMITTER: Grist JT
PROVIDER: S-EPMC8460620 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:The imaging and subsequent accurate diagnosis of paediatric brain tumours presents a radiological challenge, with magnetic resonance imaging playing a key role in providing tumour specific imaging information. Diffusion weighted and perfusion imaging are commonly used to aid the non-invasive diagnosis of children's brain tumours, but are usually evaluated by expert qualitative review. Quantitative studies are mainly single centre and single modality. The aim of this work was to combine multi-centre diffusion and perfusion imaging, with machine learning, to develop machine learning based classifiers to discriminate between three common paediatric tumour types. The results show that diffusion and perfusion weighted imaging of both the tumour and whole brain provide significant features which differ between tumour types, and that combining these features gives the optimal machine learning classifier with >80% predictive precision. This work represents a step forward to aid in the non-invasive diagnosis of paediatric brain tumours, using advanced clinical imaging.
| S-EPMC7005468 | biostudies-literature
Project description:Machine learning classifiers for psychiatric disorders using resting-state functional magnetic resonance imaging (rs-fMRI) have recently attracted attention as a method for directly examining relationships between neural circuits and psychiatric disorders. To develop accurate and generalizable classifiers, we compiled a large-scale, multi-site, multi-disorder neuroimaging database. The database comprises resting-state fMRI and structural images of the brain from 993 patients and 1,421 healthy individuals, as well as demographic information such as age, sex, and clinical rating scales. To harmonize the multi-site data, nine healthy participants ("traveling subjects") visited the sites from which the above datasets were obtained and underwent neuroimaging with 12 scanners. All participants consented to having their data shared and analyzed at multiple medical and research institutions participating in the project, and 706 patients and 1,122 healthy individuals consented to having their data disclosed. Finally, we have published four datasets: 1) the SRPBS Multi-disorder Connectivity Dataset 2), the SRPBS Multi-disorder MRI Dataset (restricted), 3) the SRPBS Multi-disorder MRI Dataset (unrestricted), and 4) the SRPBS Traveling Subject MRI Dataset.
| S-EPMC8405782 | biostudies-literature
Project description:Classification models are becoming useful tools for finding patterns in neuroimaging data sets that are not observable to the naked eye. Many of these models are applied to discriminating clinical groups such as schizophrenic patients from healthy controls or from patients with bipolar disorder. A more nuanced model might be to discriminate between levels of personality traits. Here, as a proof of concept, we take an initial step toward developing prediction models to differentiate individuals based on a personality disorder: psychopathy. We included three groups of adolescent participants: incarcerated youth with elevated psychopathic traits (i.e., callous and unemotional traits and conduct disordered traits; n=71), incarcerated youth with low psychopathic traits (n=72), and non-incarcerated youth as healthy controls (n=21). Support vector machine (SVM) learning models were developed to separate these groups using an out-of-sample cross-validation method on voxel-based morphometry (VBM) data. Regions of interest from the paralimbic system, identified in an independent forensic sample, were successful in differentiating youth groups. Models seeking to classify incarcerated individuals to have high or low psychopathic traits achieved 69.23% overall accuracy. As expected, accuracy increased in models differentiating healthy controls from individuals with high psychopathic traits (82.61%) and low psychopathic traits (80.65%). Here we have laid the foundation for using neural correlates of personality traits to identify group membership within and beyond psychopathy. This is only the first step, of many, toward prediction models using neural measures as a proxy for personality traits. As these methods are improved, prediction models with neural measures of personality traits could have far-reaching impact on diagnosis, treatment, and prediction of future behavior.
| S-EPMC4903946 | biostudies-literature
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.
| S-EPMC9246760 | biostudies-literature
Project description:BackgroundSuccessfully treating illicit drug use has become paramount, yet elusive. Devising specialized treatment interventions could increase positive outcomes, but it is necessary to identify risk factors of poor long-term outcomes to develop specialized, efficacious treatments. We investigated whether functional network connectivity (FNC) measures were predictive of substance abuse treatment completion using machine learning pattern classification of functional magnetic resonance imaging data.MethodsTreatment-seeking stimulant- or heroin-dependent incarcerated participants (n = 139; 89 women) volunteered for a 12-week substance abuse treatment program. Participants performed a response inhibition Go/NoGo functional magnetic resonance imaging task prior to onset of the substance abuse treatment. We tested whether FNC related to the anterior cingulate cortex would be predictive of those who would or would not complete a 12-week substance abuse treatment program.ResultsMachine learning pattern classification models using FNC between networks incorporating the anterior cingulate cortex, striatum, and insula predicted which individuals would (sensitivity: 81.31%) or would not (specificity: 78.13%) complete substance abuse treatment. FNC analyses predicted treatment completion above and beyond other clinical assessment measures, including age, sex, IQ, years of substance use, psychopathy, anxiety and depressive symptomatology, and motivation for change.ConclusionsAberrant neural network connections predicted substance abuse treatment outcomes, which could illuminate new targets for developing interventions designed to reduce or eliminate substance use while facilitating long-term outcomes. This work represents the first application of machine-learning models of FNC analyses of functional magnetic resonance imaging data to predict which substance abusers would or would not complete treatment.
| S-EPMC5851466 | biostudies-literature
Project description:BackgroundOptic pathway gliomas (OPGs) are low-grade tumors of the white matter of the visual system with a highly variable clinical course. The aim of the study was to generate a magnetic resonance imaging (MRI)-based predictive model of OPG tumor progression using advanced image analysis and machine learning techniques.MethodsWe performed a retrospective case-control study of OPG patients managed between 2009 and 2015 at an academic children's hospital. Progression was defined as radiographic tumor growth or vision decline. To generate the model, optic nerves were manually highlighted and optic radiations (ORs) were segmented using diffusion tractography tools. For each patient, intensity distributions were obtained from within the segmented regions on all imaging sequences, including derivatives of diffusion tensor imaging (DTI). A machine learning algorithm determined the combination of features most predictive of progression.ResultsNineteen OPG patients with progression were matched to 19 OPG patients without progression. The mean time between most recent follow-up and most recently analyzed MRI was 3.5 ± 1.7 years. Eighty-three MRI studies and 532 extracted features were included. The predictive model achieved an accuracy of 86%, sensitivity of 89%, and specificity of 81%. Fractional anisotropy of the ORs was among the most predictive features (area under the curve 0.83, P < 0.05).ConclusionsOur findings show that image analysis and machine learning can be applied to OPGs to generate a MRI-based predictive model with high accuracy. As OPGs grow along the visual pathway, the most predictive features relate to white matter changes as detected by DTI, especially within ORs.
| S-EPMC7455885 | biostudies-literature
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.
| S-EPMC10157208 | biostudies-literature
Project description:Structural variation heavily influences the molecular landscape of cancer, in part by impacting DNA methylation-mediated transcriptional regulation. Here, using multi-omic datasets involving >2400 pediatric brain and central nervous system tumors of diverse histologies from the Children's Brain Tumor Network, we report hundreds of genes and associated CpG islands (CGIs) for which the nearby presence of somatic structural variant (SV) breakpoints is recurrently associated with altered expression or DNA methylation, respectively, including tumor suppressor genes ATRX and CDKN2A. Altered DNA methylation near enhancers associates with nearby somatic SV breakpoints, including MYC and MYCN. A subset of genes with SV-CGI methylation associations also have expression associations with patient survival, including BCOR, TERT, RCOR2, and PDLIM4. DNA methylation changes in recurrent or progressive tumors compared to the initial tumor within the same patient can predict survival in pediatric and adult cancers. Our comprehensive and pan-histology genomic analyses reveal mechanisms of noncoding alterations impacting cancer genes.
| S-EPMC11310301 | biostudies-literature
Project description:BACKGROUND:It is still unknown that whether co-existing intracranial stenosis and extracranial carotid vulnerable plaques have higher predictive value for subsequent vascular events. This study aimed to determine the relationship between co-existing extracranial carotid vulnerable plaques and intracranial stenosis and subsequent vascular events utilizing cardiovascular magnetic resonance (CMR) vessel wall imaging. METHODS:Patients who had recent cerebrovascular symptoms in anterior circulation (<?2?weeks) were consecutively enrolled and underwent multi-contrast CMR vessel wall imaging for extracranial carotid arteries and 3D time-of flight CMR angiography for intracranial arteries at baseline. After baseline examination, all patients were followed-up for at least 1?year to determined recurrence of vascular events. The co-existing cerebrovascular atherosclerosis was defined as presence of both intracranial artery stenosis and at least one the following measures of extracranial artery atherosclerosis: plaque, calcification, lipid-rich necrotic core (LRNC), or intraplaque hemorrhage. Univariate and multivariate Cox regressions were used to calculate the hazard ratio (HR) and corresponding 95% confidence interval (CI) of co-existing plaques in predicting subsequent vascular events. RESULTS:In total, 150 patients (mean age: 61.8?±?11.9?years; 109 males) were recruited. During the median follow-up time of 12.1?months, 41 (27.3%) patients experienced vascular events. Co-existing intracranial artery stenosis and extracranial carotid plaque (HR, 3.57; 95% CI, 1.63-7.82; P?=?0.001) and co-existing intracranial artery stenosis and extracranial carotid LRNC (HR, 4.47; 95% CI, 2.15-9.27; P?<?0.001) were significantly associated with subsequent vascular events, respectively. After adjusted for confounding factors and carotid stenosis, these associations remained statistically significant (HR, 5.12; 95% CI, 1.36-19.24; P?=?0.016 and HR, 8.12; 95% CI, 2.41-27.31; P?=?0.001, respectively). CONCLUSIONS:The co-existing cerebrovascular atherosclerotic diseases, particularly co-existing carotid lipid-rich necrotic core and intracranial stenosis, are independent predictors for subsequent vascular events.
| S-EPMC6956475 | biostudies-literature
Project description:Magnetic resonance cholangiopancreatography (MRCP) has not been assessed as a surrogate biomarker in pediatrics. We aimed to determine the inter-rater reliability, prognostic utility, and construct validity of the modified Majoie endoscopic retrograde cholangiopancreatography classification applied to MRCP in a pediatric primary sclerosing cholangitis (PSC) cohort. This single-center, retrospective, cohort study included children with PSC undergoing diagnostic MRCP between 2008 and 2016. Six variations of the Majoie classification were examined: 1) intrahepatic duct (IHD) score, 2) extrahepatic duct (EHD) score (representing the worst intrahepatic and extrahepatic regions, respectively), 3) sum IHD-EHD score, 4) average IHD score, 5) average EHD score, and 6) sum average IHD-EHD score. Inter-rater reliability was assessed using weighted kappas and intraclass correlation coefficients (ICCs). Ability to predict time to PSC-related complications (ascites, esophageal varices, variceal bleed, liver transplant [LT], or cholangiocarcinoma) (primary outcome) and LT (secondary outcome) was assessed with Harrell's concordance statistic (c-statistic) and univariate/multivariable survival analysis. Construct validity was further assessed with Spearman correlations. Forty-five children were included (67% boys; median, 13.6 years). The inter-rater reliability of MRCP scores was substantial to excellent (kappas/ICCs, 0.78-0.82). The sum IHD-EHD score had the best predictive ability for time to PSC complication and LT (c-statistic, 0.80 and SE, 0.06; and c-statistic, 0.97 and SE, 0.01, respectively). Higher MRCP scores were independently associated with a higher rate of PSC-related complications, even after adjusting for the PSC Mayo risk score (hazard ratio, 1.74; 95% confidence interval, 1.14-2.). MRCP sum scores correlated significantly with METAVIR fibrosis stage, total bilirubin, and platelets (r = 0.42, r = 0.33, r = -0.31, respectively; P < 0.05). Conclusion: An MRCP score incorporating the worst affected intrahepatic and extrahepatic regions is reliable and predicts meaningful outcomes in pediatric PSC. Next steps include prospective validation and responsiveness assessment.
| S-EPMC6996389 | biostudies-literature