Dataset Information

Incremental prognostic value and underlying biological pathways of radiomics patterns in medulloblastoma.

ABSTRACT:

Background

To develop a radiomics signature for predicting overall survival (OS)/progression-free survival (PFS) in patients with medulloblastoma (MB), and to investigate the incremental prognostic value and biological pathways of the radiomics patterns.

Methods

A radiomics signature was constructed based on magnetic resonance imaging (MRI) from a training cohort (n = 83), and evaluated on a testing cohort (n = 83). Key pathways associated with the signature were identified by RNA-seq (GSE151519). Prognostic value of pathway genes was assessed in a public GSE85218 cohort.

Findings

The radiomics-clinicomolecular signature predicted OS (C-index 0.762) and PFS (C-index 0.697) better than either the radiomics signature (C-index: OS: 0.649; PFS: 0.593) or the clinicomolecular signature (C-index: OS: 0.725; PFS: 0.691) alone, with a better calibration and classification accuracy (net reclassification improvement: OS: 0.298, P = 0.022; PFS: 0.252, P = 0.026). Nine pathways were significantly correlated with the radiomics signature. Average expression value of pathway genes achieved significant risk stratification in GSE85218 cohort (log-rank P = 0.016).

Interpretation

This study demonstrated radiomics signature, which associated with dysregulated pathways, was an independent parameter conferring incremental value over clinicomolecular factors in survival predictions for MB patients.

Funding

A full list of funding bodies that contributed to this study can be found in the Acknowledgements section.

SUBMITTER: Yan J

PROVIDER: S-EPMC7581926 | biostudies-literature | 2020 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Incremental prognostic value and underlying biological pathways of radiomics patterns in medulloblastoma.

Yan Jing J Zhang Shenghai S Li Kay Ka-Wai KK Wang Weiwei W Li Ke K Duan Wenchao W Yuan Binke B Wang Li L Liu Lei L Zhan Yunbo Y Pei Dongling D Zhao Haibiao H Sun Tao T Sun Chen C Wang Wenqing W Liu Zhen Z Hong Xuanke X Wang Xiangxiang X Guo Yu Y Li Wencai W Cheng Jingliang J Liu Xianzhi X Ng Ho-Keung HK Li Zhicheng Z Zhang Zhenyu Z

EBioMedicine 20201021

<h4>Background</h4>To develop a radiomics signature for predicting overall survival (OS)/progression-free survival (PFS) in patients with medulloblastoma (MB), and to investigate the incremental prognostic value and biological pathways of the radiomics patterns.<h4>Methods</h4>A radiomics signature was constructed based on magnetic resonance imaging (MRI) from a training cohort (n = 83), and evaluated on a testing cohort (n = 83). Key pathways associated with the signature were identified by RNA ...[more]

PMID: 33096488

Similar Datasets

Project description:PurposeTo systematically evaluate the potential of radiomics coupled with machine-learning algorithms to improve the predictive power for overall survival (OS) of renal cell carcinoma (RCC).MethodsA total of 689 RCC patients (281 in the training cohort, 225 in the validation cohort 1 and 183 in the validation cohort 2) who underwent preoperative contrast-enhanced CT and surgical treatment were recruited from three independent databases and one institution. 851 radiomics features were screened using machine-learning algorithm, including Random Forest and Lasso-COX Regression, to establish radiomics signature. The clinical and radiomics nomogram were built by multivariate COX regression. The models were further assessed by Time-dependent receiver operator characteristic, concordance index, calibration curve, clinical impact curve and decision curve analysis.ResultThe radiomics signature comprised 11 prognosis-related features and was significantly correlated with OS in the training and two validation cohorts (Hazard Ratios: 2.718 (2.246,3.291)). Based on radiomics signature, WHOISUP, SSIGN, TNM Stage and clinical score, the radiomics nomogram has been developed. Compared with the existing prognostic models, the AUCs of 5 years OS prediction of the radiomics nomogram were superior to the TNM, WHOISUP and SSIGN model in the training cohort (0.841 vs 0.734, 0.707, 0.644) and validation cohort2 (0.917 vs 0.707, 0.773, 0.771). Stratification analysis suggested that the sensitivity of some drugs and pathways in cancer were observed different for RCC patients with high-and low-radiomics scores.ConclusionThis study showed the application of contrast-enhanced CT-based radiomics in RCC patients, creating novel radiomics nomogram that could be used to predict OS. Radiomics provided incremental prognostic value to the existing models and significantly improved the predictive power. The radiomics nomogram might be helpful for clinicians to evaluate the benefit of surgery or adjuvant therapy and make individualized therapeutic regimens for patients with renal cell carcinoma.

Project description:BackgroundUsing a pathway-focused approach, we aimed to provide a subgroup-specific basis for finding novel therapeutic strategies and further refinement of the risk stratification in pediatric medulloblastoma.MethodBased on genome-wide Cox regression and Gene Set Enrichment Analysis, we investigated prognosis-related signaling pathways and core genes in pediatric medulloblastoma subgroups using 530 patient data from Medulloblastoma Advanced Genomic International Consortium (MAGIC) project. We further examined the relationship between expression of the prognostic core genes and frequent chromosome aberrations using broad range copy number change data.ResultsIn SHH subgroup, relatively high expression of the core genes involved in p53, PLK1, FOXM1, and Aurora B signaling pathways are associated with poor prognosis, and their average expression synergistically increases with co-occurrence of losses of 17p, 14q, or 10q, or gain of 17q. In Group 3, in addition to high MYC expression, relatively elevated expression of PDGFRA, IGF1R, and FGF2 and their downstream genes in PI3K/AKT and MAPK/ERK pathways are related to poor survival outcome, and their average expression is increased with the presence of isochromosome 17q [i(17q)] and synergistically down-regulated with simultaneous losses of 16p, 8q, or 4q. In Group 4, up-regulation of the genes encoding various immune receptors and those involved in NOTCH, NF-κB, PI3K/AKT, or RHOA signaling pathways are associated with worse prognosis. Additionally, the expressions of Notch genes correlate with those of the prognostic immune receptors. Besides the Group 4 patients with previously known prognostic aberration, loss of chromosome 11, those with loss of 8q but without i(17q) show excellent survival outcomes and low average expression of the prognostic core genes whereas those harboring 10q loss, 1q gain, or 12q gain accompanied by i(17q) show bad outcomes. Finally, several metabolic pathways known to be reprogrammed in cancer cells are detected as prognostic pathways including glutamate metabolism in SHH subgroup, pentose phosphate pathway and TCA cycle in Group 3, and folate-mediated one carbon-metabolism in Group 4.ConclusionsThe results underscore several subgroup-specific pathways for potential therapeutic interventions: SHH-GLI-FOXM1 pathway in SHH subgroup, receptor tyrosine kinases and their downstream pathways in Group 3, and immune and inflammatory pathways in Group 4.

Project description:BackgroundThe 2019 arrhythmogenic right ventricular cardiomyopathy (ARVC) risk model has proved insufficient in the capability of predicting ventricular arrhythmia (VA) risk in non-classical arrhythmogenic cardiomyopathy (ACM). Furthermore, the prognostic value of ringlike late gadolinium enhancement (LGE) of the left ventricle in non-classical ACM remains unknown. We aimed to assess the incremental value of ringlike LGE over the 2019 ARVC risk model in predicting sustained VA in patients with non-classical ACM.MethodsIn this retrospective study, consecutive patients with non-classical ACM who underwent CMR from January 2011 to January 2022 were included. The pattern of LGE was categorized as no, non-ringlike, and ringlike LGE. The primary outcome was defined as the occurrence of sustained VA. Univariable and multivariable Cox regression analysis was used to evaluate the impact of LGE patterns on sustained VA and area under curve (AUC) was calculated for the incremental value of ringlike LGE.ResultsA total of 73 patients were collected in the final cohort (mean age, 39.3 ± 14.4 years, 51 male), of whom 10 (13.7%) had no LGE, 33 (45.2%) had non-ringlike LGE, and 30 (41.1%) had ringlike LGE. There was no statistically significant difference in the 5-year risk score among the three groups (P = 0.190). During a median follow-up of 34 (13-56) months, 34 (46.6%) patients experienced sustained VA, including 1 (10.0%), 13 (39.4%) and 20 (66.7%) of patients with no, non-ringlike and ringlike LGE, respectively. After multivariable adjustment, ringlike LGE remained independently associated with the presence of sustained VA (adjusted hazard ratio: 6.91, 95% confidence intervals: 1.89-54.60; P = 0.036). Adding ringlike LGE to the 2019 ARVC risk model showed significantly incremental prognostic value for sustained VA (AUC: 0.80 vs. 0.67; P = 0.024).ConclusionRinglike LGE provides independent and incremental prognostic value over the 2019 ARVC risk model in patients with non-classical ACM.

Dataset Information

Incremental prognostic value and underlying biological pathways of radiomics patterns in medulloblastoma.

Background

Methods

Findings

Interpretation

Funding

Publications

Incremental prognostic value and underlying biological pathways of radiomics patterns in medulloblastoma.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets