Radiomic signatures of meningiomas using the Ki-67 proliferation index as a prognostic marker of clinical outcomes.

OBJECTIVE: The clinical behavior of meningiomas is not entirely captured by its designated WHO grade, therefore other factors must be elucidated that portend increased tumor aggressiveness and associated risk of recurrence. In this study, the authors identify multiparametric MRI radiomic signatures of meningiomas using Ki-67 as a prognostic marker of clinical outcomes independent of WHO grade. METHODS: A retrospective analysis was conducted of all resected meningiomas between 2012 and 2018. Preoperative MR images were used for high-throughput radiomic feature extraction and subsequently used to develop a machine learning algorithm to stratify meningiomas based on Ki-67 indices < 5% and ≥ 5%, independent of WHO grade. Progression-free survival (PFS) was assessed based on machine learning prediction of Ki-67 strata and compared with outcomes based on histopathological Ki-67. RESULTS: Three hundred forty-three meningiomas were included: 291 with WHO grade I, 43 with grade II, and 9 with grade III. The overall rate of recurrence was 19.8% (15.1% in grade I, 44.2% in grade II, and 77.8% in grade III) over a median follow-up of 28.5 months. Grade II and III tumors had higher Ki-67 indices than grade I tumors, albeit tumor and peritumoral edema volumes had considerable variation independent of meningioma WHO grade. Forty-six high-performing radiomic features (1 morphological, 7 intensity-based, and 38 textural) were identified and used to build a support vector machine model to stratify tumors based on a Ki-67 cutoff of 5%, with resultant areas under the curve of 0.83 (95% CI 0.78-0.89) and 0.84 (95% CI 0.75-0.94) achieved for the discovery (n = 257) and validation (n = 86) data sets, respectively. Comparison of histopathological Ki-67 versus machine learning-predicted Ki-67 showed excellent performance (overall accuracy > 80%), with classification of grade I meningiomas exhibiting the greatest accuracy. Prediction of Ki-67 by machine learning classifier revealed shorter PFS for meningiomas with Ki-67 indices ≥ 5% compared with tumors with Ki-67 < 5% (p < 0.0001, log-rank test), which corroborates divergent patient outcomes observed using histopathological Ki-67. CONCLUSIONS: The Ki-67 proliferation index may serve as a surrogate marker of increased meningioma aggressiveness independent of WHO grade. Machine learning using radiomic feature analysis may be used for the preoperative prediction of meningioma Ki-67, which provides enhanced analytical insights to help improve diagnostic classification and guide patient-specific treatment strategies.

Imaging signatures of glioblastoma molecular characteristics: A radiogenomics review.

Over the past few decades, the advent and development of genomic assessment methods and computational approaches have raised the hopes for identifying therapeutic targets that may aid in the treatment of glioblastoma. However, the targeted therapies have barely been successful in their effort to cure glioblastoma patients, leaving them with a grim prognosis. Glioblastoma exhibits high heterogeneity, both spatially and temporally. The existence of different genetic subpopulations in glioblastoma allows this tumor to adapt itself to environmental forces. Therefore, patients with glioblastoma respond poorly to the prescribed therapies, as treatments are directed towards the whole tumor and not to the specific genetic subregions. Genomic alterations within the tumor develop distinct radiographic phenotypes. In this regard, MRI plays a key role in characterizing molecular signatures of glioblastoma, based on regional variations and phenotypic presentation of the tumor. Radiogenomics has emerged as a (relatively) new field of research to explore the connections between genetic alterations and imaging features. Radiogenomics offers numerous advantages, including noninvasive and global assessment of the tumor and its response to therapies. In this review, we summarize the potential role of radiogenomic techniques to stratify patients according to their specific tumor characteristics with the goal of designing patient-specific therapies. Level of Evidence: 5 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2020;52:54-69.

Diffusion MRI for Assessment of Bone Quality; A Review of Findings in Healthy Aging and Osteoporosis.

Diffusion MRI (dMRI) is a growing imaging technique with the potential to provide biomarkers of tissue variation, such as cellular density, tissue anisotropy, and microvascular perfusion. However, the role of dMRI in characterizing different aspects of bone quality, especially in aging and osteoporosis, has not yet been fully established, particularly in clinical applications. The reason lies in the complications accompanied with implementation of dMRI in assessment of human bone structure, in terms of acquisition and quantification. Bone is a composite tissue comprising different elements, each contributing to the overall quality and functional competence of bone. As diffusion is a critical biophysical process in biological tissues, early changes of tissue microstructure and function can affect diffusive properties of the tissue. While there are multiple MRI methods to detect variations of individual properties of bone quality due to aging and osteoporosis, dMRI has potential to serve as a superior method for characterizing different aspects of bone quality within the same framework but with higher sensitivity to early alterations. This is mainly because several properties of the tissue including directionality and anisotropy of trabecular bone and cell density can be collected using only dMRI. In this review article, we first describe components of human bone that can be potentially detected by their diffusivity properties and contribute to variations in bone quality during aging and osteoporosis. Then we discuss considerations and challenges of dMRI in bone imaging, current status, and suggestions for development of dMRI in research studies and clinics to segregate different contributing components of bone quality in an integrated acquisition. Level of Evidence: 5 Technical Efficacy Stage: 2 J. Magn. Reson. Imaging 2020;51:975-992.

A one-step biomarker quantification methodology for DCE-MRI of adnexal masses: Capturing kinetic pattern from early to late enhancement.

PURPOSE: To develop a one-step quantification approach that accounts for joint preprocessing and quantification of whole-range kinetics (early and late-phase washout) of dynamic contrast-enhanced (DCE) MRI of indeterminate adnexal masses. METHODS: Preoperative DCE-MRI of 43 (24 benign, 19 malignant) sonographically indeterminate adnexal masses were analyzed prospectively. A five-parameter sigmoid function was implemented to model the enhancement curves calculated within regions of interest. Diagnostic performance of five-parameter sigmoid model parameters (P1 through P5 ) was compared with pharmacokinetic (PK) modeling, semiquantitative analysis, and three-parameter sigmoid. Statistical analysis was performed using two-tailed student's t-test. RESULTS: The results revealed that P2 , representing the enhancement amplitude, is significantly higher, and P5 , indicating the terminal phase, is generally negative in malignant lesions (P < 0.001). P2 (sensitivity = 79%, specificity = 87.5%, accuracy = 84%, area under the receiver operating characteristic curve = 91%) outperforms classification performances of PK and semiquantitative parameters. A combination of P2 and P5 shows comparable performance (sensitivity = 79%, specificity = 87.5%, accuracy = 84%, area under the receiver operating characteristic curve = 92%) to that of the combination of PK parameters, whereas the five-parameter sigmoid function maintains fewer assumptions than PK. CONCLUSIONS: The presented one-step quantification approach is helpful for accurate discrimination of benign from malignant indeterminate adnexal masses. Accordingly, P2 has considerably high diagnostic performance and terminal slope (P5 ), as a previously overlooked feature, contributes more than widely accepted early-enhancement kinetic features. Magn Reson Med 79:1165-1171, 2018. © 2017 International Society for Magnetic Resonance in Medicine.

ADC-derived spatial features can accurately classify adnexal lesions.

BACKGROUND: The role of quantitative apparent diffusion coefficient (ADC) maps in differentiating adnexal masses is unresolved. PURPOSE/HYPOTHESIS: To propose an objective diagnostic method devised based on spatial features for predicting benignity/malignancy of adnexal masses in ADC maps. STUDY TYPE: Prospective. POPULATION: In all, 70 women with sonographically indeterminate and histopathologically confirmed adnexal masses (38 benign, 3 borderline, and 29 malignant) were considered for this study. FIELD STRENGTH/SEQUENCE: Conventional and diffusion-weighted magnetic resonance (MR) images (b-values = 50, 400, 1000 s/mm2 ) were acquired on a 3T scanner. ASSESSMENT: For each patient, two radiologists in consensus manually delineated lesion borders in whole ADC map volumes, which were consequently analyzed using spatial models (first-order histogram [FOH], gray-level co-occurrence matrix [GLCM], run-length matrix [RLM], and Gabor filters). Two independent radiologists were asked to identify the attributed (benign/malignant) classes of adnexal masses based on morphological features on conventional MRI. STATISTICAL TESTS: Leave-one-out cross-validated feature selection followed by cross-validated classification were applied to the feature space to choose the spatial models that best discriminate benign from malignant adnexal lesions. Two schemes of feature selection/classification were evaluated: 1) including all benign and malignant masses, and 2) scheme 1 after excluding endometrioma, hemorrhagic cysts, and teratoma (14 benign, 29 malignant masses). The constructed feature subspaces for benign/malignant lesion differentiation were tested for classification of benign/borderline/malignant and also borderline/malignant adnexal lesions. RESULTS: The selected feature subspace consisting of RLM features differentiated benign from malignant adnexal masses with a classification accuracy of ∼92%. The same model discriminated benign, borderline, and malignant lesions with 87% and borderline from malignant with 100% accuracy. Qualitative assessment of the radiologists based on conventional MRI features reached an accuracy of 80%. DATA CONCLUSION: The spatial quantification methodology proposed in this study, which works based on cellular distributions within ADC maps of adnexal masses, may provide a helpful computer-aided strategy for objective characterization of adnexal masses. LEVEL OF EVIDENCE: 1 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2018;47:1061-1071.

Characterization of active and infiltrative tumorous subregions from normal tissue in brain gliomas using multiparametric MRI.

BACKGROUND: Targeted localized biopsies and treatments for diffuse gliomas rely on accurate identification of tissue subregions, for which current MRI techniques lack specificity. PURPOSE: To explore the complementary and competitive roles of a variety of conventional and quantitative MRI methods for distinguishing subregions of brain gliomas. STUDY TYPE: Prospective. POPULATION: Fifty-one tissue specimens were collected using image-guided localized biopsy surgery from 10 patients with newly diagnosed gliomas. FIELD STRENGTH/SEQUENCE: Conventional and quantitative MR images consisting of pre- and postcontrast T1 w, T2 w, T2 -FLAIR, T2 -relaxometry, DWI, DTI, IVIM, and DSC-MRI were acquired preoperatively at 3T. ASSESSMENT: Biopsy specimens were histopathologically attributed to glioma tissue subregion categories of active tumor (AT), infiltrative edema (IE), and normal tissue (NT) subregions. For each tissue sample, a feature vector comprising 15 MRI-based parameters was derived from preoperative images and assessed by a machine learning algorithm to determine the best multiparametric feature combination for characterizing the tissue subregions. STATISTICAL TESTS: For discrimination of AT, IE, and NT subregions, a one-way analysis of variance (ANOVA) test and for pairwise tissue subregion differentiation, Tukey honest significant difference, and Games-Howell tests were applied (P < 0.05). Cross-validated feature selection and classification methods were implemented for identification of accurate multiparametric MRI parameter combination. RESULTS: After exclusion of 17 tissue specimens, 34 samples (AT = 6, IE = 20, and NT = 8) were considered for analysis. Highest accuracies and statistically significant differences for discrimination of IE from NT and AT from NT were observed for diffusion-based parameters (AUCs >90%), and the perfusion-derived parameter as the most accurate feature in distinguishing IE from AT. A combination of "CBV, MD, T2 _ISO, FLAIR" parameters showed high diagnostic performance for identification of the three subregions (AUC ∼90%). DATA CONCLUSION: Integration of a few quantitative along with conventional MRI parameters may provide a potential multiparametric imaging biomarker for predicting the histopathologically proven glioma tissue subregions. LEVEL OF EVIDENCE: 2 Technical Efficacy: Stage 3 J. Magn. Reson. Imaging 2018;48:938-950.

Multi-parametric (ADC/PWI/T2-w) image fusion approach for accurate semi-automatic segmentation of tumorous regions in glioblastoma multiforme.

OBJECT: Glioblastoma multiforme (GBM) brain tumor is heterogeneous in nature, so its quantification depends on how to accurately segment different parts of the tumor, i.e. viable tumor, edema and necrosis. This procedure becomes more effective when metabolic and functional information, provided by physiological magnetic resonance (MR) imaging modalities, like diffusion-weighted-imaging (DWI) and perfusion-weighted-imaging (PWI), is incorporated with the anatomical magnetic resonance imaging (MRI). In this preliminary tumor quantification work, the idea is to characterize different regions of GBM tumors in an MRI-based semi-automatic multi-parametric approach to achieve more accurate characterization of pathogenic regions. MATERIALS AND METHODS: For this purpose, three MR sequences, namely T2-weighted imaging (anatomical MR imaging), PWI and DWI of thirteen GBM patients, were acquired. To enhance the delineation of the boundaries of each pathogenic region (peri-tumoral edema, viable tumor and necrosis), the spatial fuzzy C-means algorithm is combined with the region growing method. RESULTS: The results show that exploiting the multi-parametric approach along with the proposed semi-automatic segmentation method can differentiate various tumorous regions with over 80 % sensitivity, specificity and dice score. CONCLUSION: The proposed MRI-based multi-parametric segmentation approach has the potential to accurately segment tumorous regions, leading to an efficient design of the pre-surgical treatment planning.

Training and Comparison of nnU-Net and DeepMedic Methods for Autosegmentation of Pediatric Brain Tumors.

BACKGROUND AND PURPOSE: Tumor segmentation is essential in surgical and treatment planning and response assessment and monitoring in pediatric brain tumors, the leading cause of cancer-related death among children. However, manual segmentation is time-consuming and has high interoperator variability, underscoring the need for more efficient methods. After training, we compared 2 deep-learning-based 3D segmentation models, DeepMedic and nnU-Net, with pediatric-specific multi-institutional brain tumor data based on multiparametric MR images. MATERIALS AND METHODS: Multiparametric preoperative MR imaging scans of 339 pediatric patients (n = 293 internal and n = 46 external cohorts) with a variety of tumor subtypes were preprocessed and manually segmented into 4 tumor subregions, ie, enhancing tumor, nonenhancing tumor, cystic components, and peritumoral edema. After training, performances of the 2 models on internal and external test sets were evaluated with reference to ground truth manual segmentations. Additionally, concordance was assessed by comparing the volume of the subregions as a percentage of the whole tumor between model predictions and ground truth segmentations using the Pearson or Spearman correlation coefficients and the Bland-Altman method. RESULTS: The mean Dice score for nnU-Net internal test set was 0.9 (SD, 0.07) (median, 0.94) for whole tumor; 0.77 (SD, 0.29) for enhancing tumor; 0.66 (SD, 0.32) for nonenhancing tumor; 0.71 (SD, 0.33) for cystic components, and 0.71 (SD, 0.40) for peritumoral edema, respectively. For DeepMedic, the mean Dice scores were 0.82 (SD, 0.16) for whole tumor; 0.66 (SD, 0.32) for enhancing tumor; 0.48 (SD, 0.27) for nonenhancing tumor; 0.48 (SD, 0.36) for cystic components, and 0.19 (SD, 0.33) for peritumoral edema, respectively. Dice scores were significantly higher for nnU-Net (P ≤ .01). Correlation coefficients for tumor subregion percentage volumes were higher (0.98 versus 0.91 for enhancing tumor, 0.97 versus 0.75 for nonenhancing tumor, 0.98 versus 0.80 for cystic components, 0.95 versus 0.33 for peritumoral edema in the internal test set). Bland-Altman plots were better for nnU-Net compared with DeepMedic. External validation of the trained nnU-Net model on the multi-institutional Brain Tumor Segmentation Challenge in Pediatrics (BraTS-PEDs) 2023 data set revealed high generalization capability in the segmentation of whole tumor, tumor core (a combination of enhancing tumor, nonenhancing tumor, and cystic components), and enhancing tumor with mean Dice scores of 0.87 (SD, 0.13) (median, 0.91), 0.83 (SD, 0.18) (median, 0.89), and 0.48 (SD, 0.38) (median, 0.58), respectively. CONCLUSIONS: The pediatric-specific data-trained nnU-Net model is superior to DeepMedic for whole tumor and subregion segmentation of pediatric brain tumors.

Integrating imaging and genomic data for the discovery of distinct glioblastoma subtypes: a joint learning approach.

Glioblastoma is a highly heterogeneous disease, with variations observed at both phenotypical and molecular levels. Personalized therapies would be facilitated by non-invasive in vivo approaches for characterizing this heterogeneity. In this study, we developed unsupervised joint machine learning between radiomic and genomic data, thereby identifying distinct glioblastoma subtypes. A retrospective cohort of 571 IDH-wildtype glioblastoma patients were included in the study, and pre-operative multi-parametric MRI scans and targeted next-generation sequencing (NGS) data were collected. L21-norm minimization was used to select a subset of 12 radiomic features from the MRI scans, and 13 key driver genes from the five main signal pathways most affected in glioblastoma were selected from the genomic data. Subtypes were identified using a joint learning approach called Anchor-based Partial Multi-modal Clustering on both radiomic and genomic modalities. Kaplan-Meier analysis identified three distinct glioblastoma subtypes: high-risk, medium-risk, and low-risk, based on overall survival outcome (p < 0.05, log-rank test; Hazard Ratio = 1.64, 95% CI 1.17-2.31, Cox proportional hazard model on high-risk and low-risk subtypes). The three subtypes displayed different phenotypical and molecular characteristics in terms of imaging histogram, co-occurrence of genes, and correlation between the two modalities. Our findings demonstrate the synergistic value of integrated radiomic signatures and molecular characteristics for glioblastoma subtyping. Joint learning on both modalities can aid in better understanding the molecular basis of phenotypical signatures of glioblastoma, and provide insights into the biological underpinnings of tumor formation and progression.

Comparison of volumetric and 2D-based response methods in the PNOC-001 pediatric low-grade glioma clinical trial.

Background: Although response in pediatric low-grade glioma (pLGG) includes volumetric assessment, more simplified 2D-based methods are often used in clinical trials. The study's purpose was to compare volumetric to 2D methods. Methods: An expert neuroradiologist performed solid and whole tumor (including cyst and edema) volumetric measurements on MR images using a PACS-based manual segmentation tool in 43 pLGG participants (213 total follow-up images) from the Pacific Pediatric Neuro-Oncology Consortium (PNOC-001) trial. Classification based on changes in volumetric and 2D measurements of solid tumor were compared to neuroradiologist visual response assessment using the Brain Tumor Reporting and Data System (BT-RADS) criteria for a subset of 65 images using receiver operating characteristic (ROC) analysis. Longitudinal modeling of solid tumor volume was used to predict BT-RADS classification in 54 of the 65 images. Results: There was a significant difference in ROC area under the curve between 3D solid tumor volume and 2D area (0.96 vs 0.78, P = .005) and between 3D solid and 3D whole volume (0.96 vs 0.84, P = .006) when classifying BT-RADS progressive disease (PD). Thresholds of 15-25% increase in 3D solid tumor volume had an 80% sensitivity in classifying BT-RADS PD included in their 95% confidence intervals. The longitudinal model of solid volume response had a sensitivity of 82% and a positive predictive value of 67% for detecting BT-RADS PD. Conclusions: Volumetric analysis of solid tumor was significantly better than 2D measurements in classifying tumor progression as determined by BT-RADS criteria and will enable more comprehensive clinical management.

Towards Consistency in Pediatric Brain Tumor Measurements: Challenges, Solutions, and the Role of AI-Based Segmentation.

MR imaging is central to the assessment of tumor burden and changes over time in neuro-oncology. Several response assessment guidelines have been set forth by the Response Assessment in Pediatric Neuro-Oncology (RAPNO) working groups in different tumor histologies; however, the visual delineation of tumor components using MRIs is not always straightforward, and complexities not currently addressed by these criteria can introduce inter- and intra-observer variability in manual assessments. Differentiation of non-enhancing tumor from peritumoral edema, mild enhancement from absence of enhancement, and various cystic components can be challenging; particularly given a lack of sufficient and uniform imaging protocols in clinical practice. Automated tumor segmentation with artificial intelligence (AI) may be able to provide more objective delineations, but rely on accurate and consistent training data created manually (ground truth). Herein, this paper reviews existing challenges and potential solutions to identifying and defining subregions of pediatric brain tumors (PBTs) that are not explicitly addressed by current guidelines. The goal is to assert the importance of defining and adopting criteria for addressing these challenges, as it will be critical to achieving standardized tumor measurements and reproducible response assessment in PBTs, ultimately leading to more precise outcome metrics and accurate comparisons among clinical studies.

Quantification of Multi-Parametric Magnetic Resonance Imaging Based on Radiomics Analysis for Differentiation of Benign and Malignant Lesions of Prostate.

Background: The most common cancer (non-cutaneous) malignancy among men is prostate cancer. Management of prostate cancer, including staging and treatment, playing an important role in decreasing mortality rates. Among all current diagnostic tools, multiparametric MRI (mp-MRI) has shown high potential in localizing and staging prostate cancer. Quantification of mp-MRI helps to decrease the dependency of diagnosis on readers' opinions. Objective: The aim of this research is to set a method based on quantification of mp-MRI images for discrimination between benign and malignant prostatic lesions with fusion-guided MR imaging/transrectal ultrasonography biopsy as a pathology validation reference. Material and Methods: It is an analytical research that 27 patients underwent the mp-MRI examination, including T1- and T2- weighted and diffusion weighted imaging (DWI). Quantification was done by calculating radiomic features from mp-MRI images. Receiver-operating-characteristic curve was done for each feature to evaluate the discriminatory capacity and linear discriminant analysis (LDA) and leave-one-out cross-validation for feature filtering to estimate the sensitivity, specificity and accuracy of the benign and malignant lesion differentiation process is used. Results: An accuracy, sensitivity and specificity of 92.6%, 95.2% and 83.3%, respectively, were achieved from a subset of radiomics features obtained from T2-weighted images and apparent diffusion coefficient (ADC) maps for distinguishing benign and malignant prostate lesions. Conclusion: Quantification of mp-MRI (T2-weighted images and ADC-maps) based on radiomics feature has potential to distinguish benign with appropriate accuracy from malignant prostate lesions. This technique is helpful in preventing needless biopsies in patients and provides an assisted diagnosis for classifications of prostate lesions.

Adding Value to Liquid Biopsy for Brain Tumors: The Role of Imaging.

Clinical management in neuro-oncology has changed to an integrative approach that incorporates molecular profiles alongside histopathology and imaging findings. While the World Health Organization (WHO) guideline recommends the genotyping of informative alterations as a routine clinical practice for central nervous system (CNS) tumors, the acquisition of tumor tissue in the CNS is invasive and not always possible. Liquid biopsy is a non-invasive approach that provides the opportunity to capture the complex molecular heterogeneity of the whole tumor through the detection of circulating tumor biomarkers in body fluids, such as blood or cerebrospinal fluid (CSF). Despite all of the advantages, the low abundance of tumor-derived biomarkers, particularly in CNS tumors, as well as their short half-life has limited the application of liquid biopsy in clinical practice. Thus, it is crucial to identify the factors associated with the presence of these biomarkers and explore possible strategies that can increase the shedding of these tumoral components into biological fluids. In this review, we first describe the clinical applications of liquid biopsy in CNS tumors, including its roles in the early detection of recurrence and monitoring of treatment response. We then discuss the utilization of imaging in identifying the factors that affect the detection of circulating biomarkers as well as how image-guided interventions such as focused ultrasound can help enhance the presence of tumor biomarkers through blood-brain barrier (BBB) disruption.

Radio-pathomic approaches in pediatric neuro-oncology: Opportunities and challenges.

With medical software platforms moving to cloud environments with scalable storage and computing, the translation of predictive artificial intelligence (AI) models to aid in clinical decision-making and facilitate personalized medicine for cancer patients is becoming a reality. Medical imaging, namely radiologic and histologic images, has immense analytical potential in neuro-oncology, and models utilizing integrated radiomic and pathomic data may yield a synergistic effect and provide a new modality for precision medicine. At the same time, the ability to harness multi-modal data is met with challenges in aggregating data across medical departments and institutions, as well as significant complexity in modeling the phenotypic and genotypic heterogeneity of pediatric brain tumors. In this paper, we review recent pathomic and integrated pathomic, radiomic, and genomic studies with clinical applications. We discuss current challenges limiting translational research on pediatric brain tumors and outline technical and analytical solutions. Overall, we propose that to empower the potential residing in radio-pathomics, systemic changes in cross-discipline data management and end-to-end software platforms to handle multi-modal data sets are needed, in addition to embracing modern AI-powered approaches. These changes can improve the performance of predictive models, and ultimately the ability to advance brain cancer treatments and patient outcomes through the development of such models.

Automated tumor segmentation and brain tissue extraction from multiparametric MRI of pediatric brain tumors: A multi-institutional study.

Background: Brain tumors are the most common solid tumors and the leading cause of cancer-related death among all childhood cancers. Tumor segmentation is essential in surgical and treatment planning, and response assessment and monitoring. However, manual segmentation is time-consuming and has high interoperator variability. We present a multi-institutional deep learning-based method for automated brain extraction and segmentation of pediatric brain tumors based on multi-parametric MRI scans. Methods: Multi-parametric scans (T1w, T1w-CE, T2, and T2-FLAIR) of 244 pediatric patients ( n = 215 internal and n = 29 external cohorts) with de novo brain tumors, including a variety of tumor subtypes, were preprocessed and manually segmented to identify the brain tissue and tumor subregions into four tumor subregions, i.e., enhancing tumor (ET), non-enhancing tumor (NET), cystic components (CC), and peritumoral edema (ED). The internal cohort was split into training ( n = 151), validation ( n = 43), and withheld internal test ( n = 21) subsets. DeepMedic, a three-dimensional convolutional neural network, was trained and the model parameters were tuned. Finally, the network was evaluated on the withheld internal and external test cohorts. Results: Dice similarity score (median ± SD) was 0.91 ± 0.10/0.88 ± 0.16 for the whole tumor, 0.73 ± 0.27/0.84 ± 0.29 for ET, 0.79 ± 19/0.74 ± 0.27 for union of all non-enhancing components (i.e., NET, CC, ED), and 0.98 ± 0.02 for brain tissue in both internal/external test sets. Conclusions: Our proposed automated brain extraction and tumor subregion segmentation models demonstrated accurate performance on segmentation of the brain tissue and whole tumor regions in pediatric brain tumors and can facilitate detection of abnormal regions for further clinical measurements.

Radiomic Analysis of Multi-parametric MR Images (MRI) for Classification of Parotid Tumors.

Background: Characterization of parotid tumors before surgery using multi-parametric magnetic resonance imaging (MRI) scans can support clinical decision making about the best-suited therapeutic strategy for each patient. Objective: This study aims to differentiate benign from malignant parotid tumors through radiomics analysis of multi-parametric MR images, incorporating T2-w images with ADC-map and parametric maps generated from Dynamic Contrast Enhanced MRI (DCE-MRI). Material and Methods: MRI scans of 31 patients with histopathologically-confirmed parotid gland tumors (23 benign, 8 malignant) were included in this retrospective study. For DCE-MRI, semi-quantitative analysis, Tofts pharmacokinetic (PK) modeling, and five-parameter sigmoid modeling were performed and parametric maps were generated. For each patient, borders of the tumors were delineated on whole tumor slices of T2-w image, ADC-map, and the late-enhancement dynamic series of DCE-MRI, creating regions-of-interest (ROIs). Radiomic analysis was performed for the specified ROIs. Results: Among the DCE-MRI-derived parametric maps, wash-in rate (WIR) and PK-derived Ktrans parameters surpassed the accuracy of other parameters based on support vector machine (SVM) classifier. Radiomics analysis of ADC-map outperformed the T2-w and DCE-MRI techniques using the simpler classifier, suggestive of its inherently high sensitivity and specificity. Radiomics analysis of the combination of T2-w image, ADC-map, and DCE-MRI parametric maps resulted in accuracy of 100% with both classifiers with fewer numbers of selected texture features than individual images. Conclusion: In conclusion, radiomics analysis is a reliable quantitative approach for discrimination of parotid tumors and can be employed as a computer-aided approach for pre-operative diagnosis and treatment planning of the patients.

Radiomics and radiogenomics in pediatric neuro-oncology: A review.

The current era of advanced computing has allowed for the development and implementation of the field of radiomics. In pediatric neuro-oncology, radiomics has been applied in determination of tumor histology, identification of disseminated disease, prognostication, and molecular classification of tumors (ie, radiogenomics). The field also comes with many challenges, such as limitations in study sample sizes, class imbalance, generalizability of the methods, and data harmonization across imaging centers. The aim of this review paper is twofold: first, to summarize existing literature in radiomics of pediatric neuro-oncology; second, to distill the themes and challenges of the field and discuss future directions in both a clinical and technical context.