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.

Heterogeneity analysis of diffusion-weighted MRI for prediction and assessment of microstructural changes early after one cycle of induction chemotherapy in nasopharyngeal cancer patients.

PURPOSE: To evaluate whether the pretreatment apparent diffusion coefficient (ADC) heterogeneity parameters and their alterations, after one cycle of induction chemotherapy, can be used as reliable markers of treatment response to induction chemotherapy in patients with nasopharyngeal cancer. MATERIALS AND METHODS: Ten patients were recruited and received induction chemotherapy (IC). Diffusion-weighted imaging was performed prior to, during, and after IC. The first-order ADC histogram parameters at the intra-treatment time-point were compared to the baseline time-point in the metastatic lymph nodes (LNs). Some ADC pretreatment parameters were combined with each other, employing discriminant analysis to achieve a feasible model to separate the complete response (CR) from the partial response (PR) groups. RESULTS: For ten patients, significant rise in Mean and Txt1Mean (p = 0.048 and 0.015, respectively) was observed in the metastatic nodes following one cycle of IC. Txt5Energy significantly decreased (p = 0.002). Discriminant analysis on pretreatment parameters illustrated that Txt5Energypre was the best parameter to use to correctly classify CR and PR patients. This was followed by Txt9Percentile75pre, Txt1Meanpre, and Txt2Standard Deviationpre. CONCLUSIONS: Our results suggest that heterogeneity metrics extracted from ADC-maps in metastatic lymph nodes, before and after IC, can be used as supplementary IC response indicators.

Semiquantitative dynamic contrast-enhanced MRI for accurate classification of complex adnexal masses.

PURPOSE: To identify the best dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) descriptive parameters in predicting malignancy of complex ovarian masses, and develop an optimal decision tree for accurate classification of benign and malignant complex ovarian masses. MATERIALS AND METHODS: Preoperative DCE-MR images of 55 sonographically indeterminate ovarian masses (27 benign and 28 malignant) were analyzed prospectively. Four descriptive parameters of the dynamic curve, namely, time-to-peak (TTP), wash-in-rate (WIR), relative signal intensity (SIrel ), and the initial area under the curve (IAUC60 ) were calculated on the normalized curves of specified regions-of-interest (ROIs). A two-tailed Student's t-test and two automated classifiers, linear discriminant analysis (LDA) and support vector machines (SVMs), were used to compare the performance of the mentioned parameters individually and in combination with each other. RESULTS: TTP (P = 6.15E-8) and WIR (P = 5.65E-5) parameters induced the highest sensitivity (89% for LDA, and 97% for SVM) and specificity (93% for LDA, and 100% for SVM), respectively. Regarding the high sensitivity of TTP and high specificity of WIR and through their combination, an accurate and simple decision-tree classifier was designed using the line equation obtained by LDA classification model. The proposed classifier achieved an accuracy of 89% and area under the ROC curve of 93%. CONCLUSION: In this study an accurate decision-tree classifier based on a combination of TTP and WIR parameters was proposed, which provides a clinically flexible framework to aid radiologists/clinicians to reach a conclusive preoperative diagnosis and patient-specific therapy plan for distinguishing malignant from benign complex ovarian masses. LEVEL OF EVIDENCE: 2 J. Magn. Reson. Imaging 2017;45:418-427.

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.

Physics-Informed Discretization for Reproducible and Robust Radiomic Feature Extraction Using Quantitative MRI.

OBJECTIVE: Given the limited repeatability and reproducibility of radiomic features derived from weighted magnetic resonance imaging (MRI), there may be significant advantages to using radiomics in conjunction with quantitative MRI. This study introduces a novel physics-informed discretization (PID) method for reproducible radiomic feature extraction and evaluates its performance using quantitative MRI sequences including magnetic resonance fingerprinting (MRF) and apparent diffusion coefficient (ADC) mapping. MATERIALS AND METHODS: A multiscanner, scan-rescan dataset comprising whole-brain 3D quantitative (MRF T1, MRF T2, and ADC) and weighted MRI (T1w MPRAGE, T2w SPACE, and T2w FLAIR) from 5 healthy subjects was prospectively acquired. Subjects underwent 2 repeated acquisitions on 3 distinct 3 T scanners each, for a total of 6 scans per subject (30 total scans). First-order statistical (n = 23) and second-order texture (n = 74) radiomic features were extracted from 56 brain tissue regions of interest using the proposed PID method (for quantitative MRI) and conventional fixed bin number (FBN) discretization (for quantitative MRI and weighted MRI). Interscanner radiomic feature reproducibility was measured using the intraclass correlation coefficient (ICC), and the effect of image sequence (eg, MRF T1 vs T1w MPRAGE), as well as image discretization method (ie, PID vs FBN), on radiomic feature reproducibility was assessed using repeated measures analysis of variance. The robustness of PID and FBN discretization to segmentation error was evaluated by simulating segmentation differences in brainstem regions of interest. Radiomic features with ICCs greater than 0.75 following simulated segmentation were determined to be robust to segmentation. RESULTS: First-order features demonstrated higher reproducibility in quantitative MRI than weighted MRI sequences, with 30% (n = 7/23) features being more reproducible in MRF T1 and MRF T2 than weighted MRI. Gray level co-occurrence matrix (GLCM) texture features extracted from MRF T1 and MRF T2 were significantly more reproducible using PID compared with FBN discretization; for all quantitative MRI sequences, PID yielded the highest number of texture features with excellent reproducibility (ICC > 0.9). Comparing texture reproducibility of quantitative and weighted MRI, a greater proportion of MRF T1 (n = 225/370, 61%) and MRF T2 (n = 150/370, 41%) texture features had excellent reproducibility (ICC > 0.9) compared with T1w MPRAGE (n = 148/370, 40%), ADC (n = 115/370, 32%), T2w SPACE (n = 98/370, 27%), and FLAIR (n = 102/370, 28%). Physics-informed discretization was also more robust than FBN discretization to segmentation error, as 46% (n = 103/222, 46%) of texture features extracted from quantitative MRI using PID were robust to simulated 6 mm segmentation shift compared with 19% (n = 42/222, 19%) of weighted MRI texture features extracted using FBN discretization. CONCLUSIONS: The proposed PID method yields radiomic features extracted from quantitative MRI sequences that are more reproducible and robust than radiomic features extracted from weighted MRI using conventional (FBN) discretization approaches. Quantitative MRI sequences also demonstrated greater scan-rescan robustness and first-order feature reproducibility than weighted MRI.

Early prognostication of overall survival for pediatric diffuse midline gliomas using MRI radiomics and machine learning: a two-center study.

Background: Diffuse midline gliomas (DMG) are aggressive pediatric brain tumors that are diagnosed and monitored through MRI. We developed an automatic pipeline to segment subregions of DMG and select radiomic features that predict patient overall survival (OS). Methods: We acquired diagnostic and post-radiation therapy (RT) multisequence MRI (T1, T1ce, T2, T2 FLAIR) and manual segmentations from two centers of 53 (internal cohort) and 16 (external cohort) DMG patients. We pretrained a deep learning model on a public adult brain tumor dataset, and finetuned it to automatically segment tumor core (TC) and whole tumor (WT) volumes. PyRadiomics and sequential feature selection were used for feature extraction and selection based on the segmented volumes. Two machine learning models were trained on our internal cohort to predict patient 1-year survival from diagnosis. One model used only diagnostic tumor features and the other used both diagnostic and post-RT features. Results: For segmentation, Dice score (mean [median]±SD) was 0.91 (0.94)±0.12 and 0.74 (0.83)±0.32 for TC, and 0.88 (0.91)±0.07 and 0.86 (0.89)±0.06 for WT for internal and external cohorts, respectively. For OS prediction, accuracy was 77% and 81% at time of diagnosis, and 85% and 78% post-RT for internal and external cohorts, respectively. Homogeneous WT intensity in baseline T2 FLAIR and larger post-RT TC/WT volume ratio indicate shorter OS. Conclusions: Machine learning analysis of MRI radiomics has potential to accurately and non-invasively predict which pediatric patients with DMG will survive less than one year from the time of diagnosis to provide patient stratification and guide therapy.

Active Learning in Brain Tumor Segmentation with Uncertainty Sampling and Annotation Redundancy Restriction.

Deep learning models have demonstrated great potential in medical imaging but are limited by the expensive, large volume of annotations required. To address this, we compared different active learning strategies by training models on subsets of the most informative images using real-world clinical datasets for brain tumor segmentation and proposing a framework that minimizes the data needed while maintaining performance. Then, 638 multi-institutional brain tumor magnetic resonance imaging scans were used to train three-dimensional U-net models and compare active learning strategies. Uncertainty estimation techniques including Bayesian estimation with dropout, bootstrapping, and margins sampling were compared to random query. Strategies to avoid annotating similar images were also considered. We determined the minimum data necessary to achieve performance equivalent to the model trained on the full dataset (α = 0.05). Bayesian approximation with dropout at training and testing showed results equivalent to that of the full data model (target) with around 30% of the training data needed by random query to achieve target performance (p = 0.018). Annotation redundancy restriction techniques can reduce the training data needed by random query to achieve target performance by 20%. We investigated various active learning strategies to minimize the annotation burden for three-dimensional brain tumor segmentation. Dropout uncertainty estimation achieved target performance with the least annotated data.

Early prognostication of overall survival for pediatric diffuse midline gliomas using MRI radiomics and machine learning: A two-center study.

Background: Diffuse midline gliomas (DMG) are aggressive pediatric brain tumors that are diagnosed and monitored through MRI. We developed an automatic pipeline to segment subregions of DMG and select radiomic features that predict patient overall survival (OS). Methods: We acquired diagnostic and post-radiation therapy (RT) multisequence MRI (T1, T1ce, T2, and T2 FLAIR) and manual segmentations from 2 centers: 53 from 1 center formed the internal cohort and 16 from the other center formed the external cohort. We pretrained a deep learning model on a public adult brain tumor data set (BraTS 2021), and finetuned it to automatically segment tumor core (TC) and whole tumor (WT) volumes. PyRadiomics and sequential feature selection were used for feature extraction and selection based on the segmented volumes. Two machine learning models were trained on our internal cohort to predict patient 12-month survival from diagnosis. One model used only data obtained at diagnosis prior to any therapy (baseline study) and the other used data at both diagnosis and post-RT (post-RT study). Results: Overall survival prediction accuracy was 77% and 81% for the baseline study, and 85% and 78% for the post-RT study, for internal and external cohorts, respectively. Homogeneous WT intensity in baseline T2 FLAIR and larger post-RT TC/WT volume ratio indicate shorter OS. Conclusions: Machine learning analysis of MRI radiomics has potential to accurately and noninvasively predict which pediatric patients with DMG will survive less than 12 months from the time of diagnosis to provide patient stratification and guide therapy.

Comparison of Volumetric and 2D Measurements and Longitudinal Trajectories in the Response Assessment of BRAF V600E-Mutant Pediatric Gliomas in the Pacific Pediatric Neuro-Oncology Consortium Clinical Trial.

BACKGROUND AND PURPOSE: Response on imaging is widely used to evaluate treatment efficacy in clinical trials of pediatric gliomas. While conventional criteria rely on 2D measurements, volumetric analysis may provide a more comprehensive response assessment. There is sparse research on the role of volumetrics in pediatric gliomas. Our purpose was to compare 2D and volumetric analysis with the assessment of neuroradiologists using the Brain Tumor Reporting and Data System (BT-RADS) in BRAF V600E-mutant pediatric gliomas. MATERIALS AND METHODS: Manual volumetric segmentations of whole and solid tumors were compared with 2D measurements in 31 participants (292 follow-up studies) in the Pacific Pediatric Neuro-Oncology Consortium 002 trial (NCT01748149). Two neuroradiologists evaluated responses using BT-RADS. Receiver operating characteristic analysis compared classification performance of 2D and volumetrics for partial response. Agreement between volumetric and 2D mathematically modeled longitudinal trajectories for 25 participants was determined using the model-estimated time to best response. RESULTS: Of 31 participants, 20 had partial responses according to BT-RADS criteria. Receiver operating characteristic curves for the classification of partial responders at the time of first detection (median = 2 months) yielded an area under the curve of 0.84 (95% CI, 0.69-0.99) for 2D area, 0.91 (95% CI, 0.80-1.00) for whole-volume, and 0.92 (95% CI, 0.82-1.00) for solid volume change. There was no significant difference in the area under the curve between 2D and solid (P = .34) or whole volume (P = .39). There was no significant correlation in model-estimated time to best response (ρ = 0.39, P >.05) between 2D and whole-volume trajectories. Eight of the 25 participants had a difference of ≥90 days in transition from partial response to stable disease between their 2D and whole-volume modeled trajectories. CONCLUSIONS: Although there was no overall difference between volumetrics and 2D in classifying partial response assessment using BT-RADS, further prospective studies will be critical to elucidate how the observed differences in tumor 2D and volumetric trajectories affect clinical decision-making and outcomes in some individuals.

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.