Dataset Information

A Multidimensional Connectomics- and Radiomics-Based Advanced Machine-Learning Framework to Distinguish Radiation Necrosis from True Progression in Brain Metastases.

ABSTRACT: We introduce tumor connectomics, a novel MRI-based complex graph theory framework that describes the intricate network of relationships within the tumor and surrounding tissue, and combine this with multiparametric radiomics (mpRad) in a machine-learning approach to distinguish radiation necrosis (RN) from true progression (TP). Pathologically confirmed cases of RN vs. TP in brain metastases treated with SRS were included from a single institution. The region of interest was manually segmented as the single largest diameter of the T1 post-contrast (T1C) lesion plus the corresponding area of T2 FLAIR hyperintensity. There were 40 mpRad features and 6 connectomics features extracted, as well as 5 clinical and treatment factors. We developed an Integrated Radiomics Informatics System (IRIS) based on an Isomap support vector machine (IsoSVM) model to distinguish TP from RN using leave-one-out cross-validation. Class imbalance was resolved with differential misclassification weighting during model training using the IRIS. In total, 135 lesions in 110 patients were analyzed, including 43 cases (31.9%) of pathologically proven RN and 92 cases (68.1%) of TP. The top-performing connectomics features were three centrality measures of degree, betweenness, and eigenvector centralities. Combining these with the 10 top-performing mpRad features, an optimized IsoSVM model was able to produce a sensitivity of 0.87, specificity of 0.84, AUC-ROC of 0.89 (95% CI: 0.82-0.94), and AUC-PR of 0.94 (95% CI: 0.87-0.97).

SUBMITTER: Cao Y

PROVIDER: S-EPMC10452423 | biostudies-literature | 2023 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A Multidimensional Connectomics- and Radiomics-Based Advanced Machine-Learning Framework to Distinguish Radiation Necrosis from True Progression in Brain Metastases.

Cao Yilin Y Parekh Vishwa S VS Lee Emerson E Chen Xuguang X Redmond Kristin J KJ Pillai Jay J JJ Peng Luke L Jacobs Michael A MA Kleinberg Lawrence R LR

Cancers 20230815 16

We introduce tumor connectomics, a novel MRI-based complex graph theory framework that describes the intricate network of relationships within the tumor and surrounding tissue, and combine this with multiparametric radiomics (mpRad) in a machine-learning approach to distinguish radiation necrosis (RN) from true progression (TP). Pathologically confirmed cases of RN vs. TP in brain metastases treated with SRS were included from a single institution. The region of interest was manually segmented a ...[more]

PMID: 37627141

Similar Datasets

Project description:PurposeTreatment effect or radiation necrosis after stereotactic radiosurgery (SRS) for brain metastases is a common phenomenon often indistinguishable from true progression. Radiomics is an emerging field that promises to improve on conventional imaging. In this study, we sought to apply a radiomics-based prediction model to the problem of diagnosing treatment effect after SRS.Methods and materialsWe included patients in the Johns Hopkins Health System who were treated with SRS for brain metastases who subsequently underwent resection for symptomatic growth. We also included cases of likely treatment effect in which lesions grew but subsequently regressed spontaneously. Lesions were segmented semiautomatically on preoperative T1 postcontrast and T2 fluid-attenuated inversion recovery magnetic resonance imaging, and radiomic features were extracted with software developed in-house. Top-performing features on univariate logistic regression were entered into a hybrid feature selection/classification model, IsoSVM, with parameter optimization and further feature selection performed using leave-one-out cross-validation. Final model performance was assessed by 10-fold cross-validation with 100 repeats. All cases were independently reviewed by a board-certified neuroradiologist for comparison.ResultsWe identified 82 treated lesions across 66 patients, with 77 lesions having pathologic confirmation. There were 51 radiomic features extracted per segmented lesion on each magnetic resonance imaging sequence. An optimized IsoSVM classifier based on top-ranked radiomic features had sensitivity and specificity of 65.38% and 86.67%, respectively, with an area under the curve of 0.81 on leave-one-out cross-validation. Only 73% of cases were classifiable by the neuroradiologist, with a sensitivity of 97% and specificity of 19%.ConclusionsRadiomics holds promise for differentiating between treatment effect and true progression in brain metastases treated with SRS. A predictive model built on radiomic features from an institutional cohort performed well on cross-validation testing. These results warrant further validation in independent datasets. Such work could prove invaluable for guiding management of individual patients and assessing outcomes of novel interventions.

Project description:Schizophrenia is a very complex syndrome that involves widespread brain multi-dysconnectivity. Neural circuits within specific brain regions and their links to corresponding regions are abnormal in the illness. Theoretical models of dysconnectivity and the investigation of connectomics and brain network organization have been examined in schizophrenia since the early nineteenth century. In more recent years, advancements have been achieved with the development of neuroimaging tools that have provided further clues to the structural and functional organization of the brain and global neural networks in the illness. Neural circuitry that extends across prefrontal, temporal and parietal areas of the cortex as well as limbic and other subcortical brain regions is disrupted in schizophrenia. As a result, many patients have a poor response to antipsychotic treatment and treatment failure is common. Treatment resistance that is specific to positive, negative, and cognitive domains of the illness may be related to distinct circuit phenotypes unique to treatment-refractory disease. Currently, there are no customized neural circuit-specific and targeted therapies that address this neural dysconnectivity. Investigation of targeted therapeutics that addresses particular areas of substantial regional dysconnectivity is an intriguing approach to precision medicine in schizophrenia. This review examines current findings of system and circuit-level brain dysconnectivity in treatment-resistant schizophrenia based on neuroimaging studies. Within a connectome context, on-off circuit connectivity synonymous with excitatory and inhibitory neuronal pathways is discussed. Mechanistic cellular, neurochemical and molecular studies are included with specific emphasis given to cell pathology and synaptic communication in glutamatergic and GABAergic systems. In this review we attempt to deconstruct how augmenting treatments may be applied within a circuit context to improve circuit integration and treatment response. Clinical studies that have used a variety of glutamate receptor and GABA interneuron modulators, nitric oxide-based therapies and a variety of other strategies as augmenting treatments with antipsychotic drugs are included. This review supports the idea that the methodical mapping of system-level networks to both on (excitatory) and off (inhibitory) cellular circuits specific to treatment-resistant disease may be a logical and productive approach in directing future research toward the advancement of targeted pharmacotherapeutics in schizophrenia.

Dataset Information

A Multidimensional Connectomics- and Radiomics-Based Advanced Machine-Learning Framework to Distinguish Radiation Necrosis from True Progression in Brain Metastases.

Publications

A Multidimensional Connectomics- and Radiomics-Based Advanced Machine-Learning Framework to Distinguish Radiation Necrosis from True Progression in Brain Metastases.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets