Evaluation of Standard Response Assessment in Neuro-Oncology, Modified Response Assessment in Neuro-Oncology, and Immunotherapy Response Assessment in Neuro-Oncology in Newly Diagnosed and Recurrent Glioblastoma.

PURPOSE: The Response Assessment in Neuro-Oncology (RANO) criteria are widely used in high-grade glioma clinical trials. We compared the RANO criteria with updated modifications (modified RANO [mRANO] and immunotherapy RANO [iRANO] criteria) in patients with newly diagnosed glioblastoma (nGBM) and recurrent GBM (rGBM) to evaluate the performance of each set of criteria and inform the development of the planned RANO 2.0 update. MATERIALS AND METHODS: Evaluation of tumor measurements and fluid-attenuated inversion recovery (FLAIR) sequences were performed by blinded readers to determine disease progression using RANO, mRANO, iRANO, and other response assessment criteria. Spearman's correlations between progression-free survival (PFS) and overall survival (OS) were calculated. RESULTS: Five hundred twenty-six nGBM and 580 rGBM cases were included. Spearman's correlations were similar between RANO and mRANO (0.69 [95% CI, 0.62 to 0.75] v 0.67 [95% CI, 0.60 to 0.73]) in nGBM and rGBM (0.48 [95% CI, 0.40 to 0.55] v 0.50 [95% CI, 0.42 to 0.57]). In nGBM, requirement of a confirmation scan within 12 weeks of completion of radiotherapy to determine progression was associated with improved correlations. Use of the postradiation magnetic resonance imaging (MRI) as baseline scan was associated with improved correlation compared with use of the pre-radiation MRI (0.67 [95% CI, 0.60 to 0.73] v 0.53 [95% CI, 0.42 to 0.62]). Evaluation of FLAIR sequences did not improve the correlation. Among patients who received immunotherapy, Spearman's correlations were similar among RANO, mRANO, and iRANO. CONCLUSION: RANO and mRANO demonstrated similar correlations between PFS and OS. Confirmation scans were only beneficial in nGBM within 12 weeks of completion of radiotherapy, and there was a trend in favor of the use of postradiation MRI as the baseline scan in nGBM. Evaluation of FLAIR can be omitted. The iRANO criteria did not add significant benefit in patients who received immune checkpoint inhibitors.

Deep Learning for Noninvasive Assessment of H3 K27M Mutation Status in Diffuse Midline Gliomas Using MR Imaging.

BACKGROUND: Determination of H3 K27M mutation in diffuse midline glioma (DMG) is key for prognostic assessment and stratifying patient subgroups for clinical trials. MRI can noninvasively depict morphological and metabolic characteristics of H3 K27M mutant DMG. PURPOSE: This study aimed to develop a deep learning (DL) approach to noninvasively predict H3 K27M mutation in DMG using T2-weighted images. STUDY TYPE: Retrospective and prospective. POPULATION: For diffuse midline brain gliomas, 341 patients from Center-1 (27 ± 19 years, 184 males), 42 patients from Center-2 (33 ± 19 years, 27 males) and 35 patients (37 ± 18 years, 24 males). For diffuse spinal cord gliomas, 133 patients from Center-1 (30 ± 15 years, 80 males). FIELD STRENGTH/SEQUENCE: 5T and 3T, T2-weighted turbo spin echo imaging. ASSESSMENT: Conventional radiological features were independently reviewed by two neuroradiologists. H3 K27M status was determined by histopathological examination. The Dice coefficient was used to evaluate segmentation performance. Classification performance was evaluated using accuracy, sensitivity, specificity, and area under the curve. STATISTICAL TESTS: Pearson's Chi-squared test, Fisher's exact test, two-sample Student's t-test and Mann-Whitney U test. A two-sided P value <0.05 was considered statistically significant. RESULTS: In the testing cohort, Dice coefficients of tumor segmentation using DL were 0.87 for diffuse midline brain and 0.81 for spinal cord gliomas. In the internal prospective testing dataset, the predictive accuracies, sensitivities, and specificities of H3 K27M mutation status were 92.1%, 98.2%, 82.9% in diffuse midline brain gliomas and 85.4%, 88.9%, 82.6% in spinal cord gliomas. Furthermore, this study showed that the performance generalizes to external institutions, with predictive accuracies of 85.7%-90.5%, sensitivities of 90.9%-96.0%, and specificities of 82.4%-83.3%. DATA CONCLUSION: In this study, an automatic DL framework was developed and validated for accurately predicting H3 K27M mutation using T2-weighted images, which could contribute to the noninvasive determination of H3 K27M status for clinical decision-making. EVIDENCE LEVEL: 2 Technical Efficacy: Stage 2.

Artificial intelligence (AI)-based decision support improves reproducibility of tumor response assessment in neuro-oncology: An international multi-reader study.

BACKGROUND: To assess whether artificial intelligence (AI)-based decision support allows more reproducible and standardized assessment of treatment response on MRI in neuro-oncology as compared to manual 2-dimensional measurements of tumor burden using the Response Assessment in Neuro-Oncology (RANO) criteria. METHODS: A series of 30 patients (15 lower-grade gliomas, 15 glioblastoma) with availability of consecutive MRI scans was selected. The time to progression (TTP) on MRI was separately evaluated for each patient by 15 investigators over two rounds. In the first round the TTP was evaluated based on the RANO criteria, whereas in the second round the TTP was evaluated by incorporating additional information from AI-enhanced MRI sequences depicting the longitudinal changes in tumor volumes. The agreement of the TTP measurements between investigators was evaluated using concordance correlation coefficients (CCC) with confidence intervals (CI) and P-values obtained using bootstrap resampling. RESULTS: The CCC of TTP-measurements between investigators was 0.77 (95% CI = 0.69,0.88) with RANO alone and increased to 0.91 (95% CI = 0.82,0.95) with AI-based decision support (P = .005). This effect was significantly greater (P = .008) for patients with lower-grade gliomas (CCC = 0.70 [95% CI = 0.56,0.85] without vs. 0.90 [95% CI = 0.76,0.95] with AI-based decision support) as compared to glioblastoma (CCC = 0.83 [95% CI = 0.75,0.92] without vs. 0.86 [95% CI = 0.78,0.93] with AI-based decision support). Investigators with less years of experience judged the AI-based decision as more helpful (P = .02). CONCLUSIONS: AI-based decision support has the potential to yield more reproducible and standardized assessment of treatment response in neuro-oncology as compared to manual 2-dimensional measurements of tumor burden, particularly in patients with lower-grade gliomas. A fully-functional version of this AI-based processing pipeline is provided as open-source (https://github.com/NeuroAI-HD/HD-GLIO-XNAT).

Deep learning-based automatic tumor burden assessment of pediatric high-grade gliomas, medulloblastomas, and other leptomeningeal seeding tumors.

BACKGROUND: Longitudinal measurement of tumor burden with magnetic resonance imaging (MRI) is an essential component of response assessment in pediatric brain tumors. We developed a fully automated pipeline for the segmentation of tumors in pediatric high-grade gliomas, medulloblastomas, and leptomeningeal seeding tumors. We further developed an algorithm for automatic 2D and volumetric size measurement of tumors. METHODS: The preoperative and postoperative cohorts were randomly split into training and testing sets in a 4:1 ratio. A 3D U-Net neural network was trained to automatically segment the tumor on T1 contrast-enhanced and T2/FLAIR images. The product of the maximum bidimensional diameters according to the RAPNO (Response Assessment in Pediatric Neuro-Oncology) criteria (AutoRAPNO) was determined. Performance was compared to that of 2 expert human raters who performed assessments independently. Volumetric measurements of predicted and expert segmentations were computationally derived and compared. RESULTS: A total of 794 preoperative MRIs from 794 patients and 1003 postoperative MRIs from 122 patients were included. There was excellent agreement of volumes between preoperative and postoperative predicted and manual segmentations, with intraclass correlation coefficients (ICCs) of 0.912 and 0.960 for the 2 preoperative and 0.947 and 0.896 for the 2 postoperative models. There was high agreement between AutoRAPNO scores on predicted segmentations and manually calculated scores based on manual segmentations (Rater 2 ICC = 0.909; Rater 3 ICC = 0.851). Lastly, the performance of AutoRAPNO was superior in repeatability to that of human raters for MRIs with multiple lesions. CONCLUSIONS: Our automated deep learning pipeline demonstrates potential utility for response assessment in pediatric brain tumors. The tool should be further validated in prospective studies.

Automatic assessment of glioma burden: a deep learning algorithm for fully automated volumetric and bidimensional measurement.

BACKGROUND: Longitudinal measurement of glioma burden with MRI is the basis for treatment response assessment. In this study, we developed a deep learning algorithm that automatically segments abnormal fluid attenuated inversion recovery (FLAIR) hyperintensity and contrast-enhancing tumor, quantitating tumor volumes as well as the product of maximum bidimensional diameters according to the Response Assessment in Neuro-Oncology (RANO) criteria (AutoRANO). METHODS: Two cohorts of patients were used for this study. One consisted of 843 preoperative MRIs from 843 patients with low- or high-grade gliomas from 4 institutions and the second consisted of 713 longitudinal postoperative MRI visits from 54 patients with newly diagnosed glioblastomas (each with 2 pretreatment "baseline" MRIs) from 1 institution. RESULTS: The automatically generated FLAIR hyperintensity volume, contrast-enhancing tumor volume, and AutoRANO were highly repeatable for the double-baseline visits, with an intraclass correlation coefficient (ICC) of 0.986, 0.991, and 0.977, respectively, on the cohort of postoperative GBM patients. Furthermore, there was high agreement between manually and automatically measured tumor volumes, with ICC values of 0.915, 0.924, and 0.965 for preoperative FLAIR hyperintensity, postoperative FLAIR hyperintensity, and postoperative contrast-enhancing tumor volumes, respectively. Lastly, the ICCs for comparing manually and automatically derived longitudinal changes in tumor burden were 0.917, 0.966, and 0.850 for FLAIR hyperintensity volume, contrast-enhancing tumor volume, and RANO measures, respectively. CONCLUSIONS: Our automated algorithm demonstrates potential utility for evaluating tumor burden in complex posttreatment settings, although further validation in multicenter clinical trials will be needed prior to widespread implementation.

Imaging and diagnostic advances for intracranial meningiomas.

The archetypal imaging characteristics of meningiomas are among the most stereotypic of all central nervous system (CNS) tumors. In the era of plain film and ventriculography, imaging was only performed if a mass was suspected, and their results were more suggestive than definitive. Following more than a century of technological development, we can now rely on imaging to non-invasively diagnose meningioma with great confidence and precisely delineate the locations of these tumors relative to their surrounding structures to inform treatment planning. Asymptomatic meningiomas may be identified and their growth monitored over time; moreover, imaging routinely serves as an essential tool to survey tumor burden at various stages during the course of treatment, thereby providing guidance on their effectiveness or the need for further intervention. Modern radiological techniques are expanding the power of imaging from tumor detection and monitoring to include extraction of biologic information from advanced analysis of radiological parameters. These contemporary approaches have led to promising attempts to predict tumor grade and, in turn, contribute prognostic data. In this supplement article, we review important current and future aspects of imaging in the diagnosis and management of meningioma, including conventional and advanced imaging techniques using CT, MRI, and nuclear medicine.

Proposed response assessment and endpoints for meningioma clinical trials: report from the Response Assessment in Neuro-Oncology Working Group.

No standard criteria exist for assessing response and progression in clinical trials involving patients with meningioma, and there is no consensus on the optimal endpoints for trials currently under way. As a result, there is substantial variation in the design and response criteria of meningioma trials, making comparison between trials difficult. In addition, future trials should be designed with accepted standardized endpoints. The Response Assessment in Neuro-Oncology Meningioma Working Group is an international effort to develop standardized radiologic criteria for treatment response for meningioma clinical trials. In this proposal, we present the recommendations for response criteria and endpoints for clinical trials involving patients with meningiomas.

Response assessment of meningioma: 1D, 2D, and volumetric criteria for treatment response and tumor progression.

BACKGROUND: Meningiomas are the most common primary brain tumors in adults. Due to their variable growth rates and irregular tumor shapes, response assessment in clinical trials remains challenging and no standard criteria have been defined. We evaluated 1D, 2D, and volume imaging criteria to assess whether a volumetric approach might be a superior surrogate for overall survival (OS). METHODS: In this retrospective multicenter study, we evaluated the clinical and imaging data of 93 patients with recurrent meningiomas treated with pharmacotherapy. One-dimensional (1D), 2D, and volumetric measurements of enhancing tumor on pre- and post-treatment MRI were compared at 6 and 12 months after treatment initiation. Cox proportional hazards models were used to examine the relationship between each imaging criterion and OS. RESULTS: The median age of the patient cohort is 51 years (range 12-88), with 14 World Health Organization (WHO) grade I, 53 WHO grade II, and 26 WHO grade III meningiomas. Volumetric increase of 40% and unidimensional increase by 10 mm at 6 months and 12 months provided the strongest association with overall survival (HR = 2.58 and 3.24 respectively, p<0.01). Setting a volume change threshold above 40% did not correlate with survival. The interobserver agreement of 1D, 2D, and volume criteria is only moderate (kappa = 0.49, 0.46, 0.52, respectively). None of the criteria based on tumor size reduction were associated with OS (P > 0.09). CONCLUSION: Compared with 1D (Response Evaluation Criteria In Solid Tumors 1.1) and 2D (Response Assessment in Neuro-Oncology) approaches, volumetric criteria for tumor progression has a stronger association with OS, although the differences were only modest. The interobserver variability is moderate for all 3 methods. Further validation of these findings in an independent patient cohort is needed.

Voxel-Wise Analysis of Fluoroethyltyrosine PET and MRI in the Assessment of Recurrent Glioblastoma During Antiangiogenic Therapy.

OBJECTIVE: In MRI of patients with recurrent glioblastoma, bevacizumab-induced normalization of tumor vascularity can be difficult to differentiate from antitumor effects. The aim of this study was to assess the utility of 18F-fluoroethyl-L-tyrosine (FET) PET in the evaluation of recurrent glioblastoma treated with bevacizumab. SUBJECTS AND METHODS: MRI and FET PET were performed before and after administration of two doses of bevacizumab to 11 patients with recurrent glioblastoma. The ratio between normalized FET uptake at follow-up and baseline of the entire (volume of T2 FLAIR abnormality) and enhancing tumor were assessed for prediction of progression-free survival (PFS) and overall survival (OS). Voxel-wise Spearman correlation between normalized FET uptake and contrast-enhanced T1 signal intensity was assessed and tested as a predictor of PFS and OS. RESULTS: Mean Spearman correlation between FET uptake and contrast-enhanced T1 signal intensity before therapy was 0.65 and after therapy was 0.61 (p = 0.256). The median PFS after initiation of bevacizumab therapy was 111 days, and the OS was 223 days. A post-treatment to pretreatment PET uptake ratio (mean and 90th percentile) greater than 0.7 for both entire and enhancing tumor was associated with lower PFS and OS (p < 0.001-0.049). The increase in correlation between PET uptake and contrast-enhanced T1 intensity after treatment was associated with lower PFS (p < 0.001) and OS (p = 0.049). CONCLUSION: There is only a moderate correlation between FET PET uptake and contrast-enhanced T1 signal intensity. High posttreatment-to-pretreatment FET PET uptake ratio and increase in correlation between PET uptake and contrast-enhanced T1 signal intensity after bevacizumab treatment are associated with poor PFS and OS.

Response Assessment in Neuro-Oncology Criteria and Clinical Endpoints.

The Response Assessment in Neuro-Oncology (RANO) Working Group is an international multidisciplinary group whose goal is to improve response criteria and define endpoints for neuro-oncology trials. The RANO criteria for high-grade gliomas attempt to address the issues of pseudoprogression, pseudoresponse, and nonenhancing tumor progression. Incorporation of advanced MR imaging may eventually help improve the ability of these criteria to define enhancing and nonenhancing disease better. The RANO group has also developed criteria for neurologic response and evaluation of patients receiving immunologic therapies. RANO criteria have been developed for brain metastases and are in progress for meningiomas, leptomeningeal disease, spinal tumors, and pediatric tumors.

The Impact of T2/FLAIR Evaluation per RANO Criteria on Response Assessment of Recurrent Glioblastoma Patients Treated with Bevacizumab.

PURPOSE: The RANO criteria have not been assessed using outcome data from prospective trials. We examined the radiologic data of patients with recurrent glioblastoma from the randomized phase II trial (AVF3708g) to determine the effect of including T2/FLAIR evaluation as per RANO criteria on measurements of objective response rates (ORRs) and progression-free survival (PFS) compared with assessment based on contrast enhancement (Macdonald criteria). EXPERIMENTAL DESIGN: The ORRs and median PFS were determined using the RANO criteria and compared with those obtained using the Macdonald criteria. Landmark analyses were performed at 2, 4, and 6 months, and Cox proportional hazard models were used to determine the associations between OR and progression with subsequent survival. RESULTS: The ORRs were 0.331 [95% confidence interval (CI), 0.260-0.409] and 0.393 (95% CI, 0.317-0.472) by RANO and Macdonald criteria, respectively (P < 0.0001). The median PFS was 4.6 months (95% CI, 4.1-5.5) using RANO criteria, compared with 6.4 months (95% CI, 5.5-7.1) as determined by Macdonald criteria (P = 0.01). At 2-, 4-, and 6-month landmarks, both OR status and PFS determined by either RANO or Macdonald criteria were predictive of overall survival [OS; hazard ratios for 4-month landmark (OR HR = 1.93, P = 0.0012; PFS HR, 4.23, P < 0.0001)]. CONCLUSIONS: The inclusion of T2/FLAIR assessment resulted in statistically significant differences in median PFS and ORRs compared with assessment of solely enhancing tumor (Macdonald criteria), although OR and PFS determined by both RANO and Macdonald criteria correlated with OS.

Recurrent glioblastoma: volumetric assessment and stratification of patient survival with early posttreatment magnetic resonance imaging in patients treated with bevacizumab.

BACKGROUND: Despite a high radiographic response rate in patients with recurrent glioblastoma following bevacizumab therapy, survival benefit has been relatively modest. We assess whether tumor volume measurements based on baseline and early posttreatment MRI can stratify patients in terms of progression-free survival (PFS) and overall survival (OS). METHODS: Baseline (-4 +/- 4 days) and posttreatment (30 +/- 6 days) MRI exams of 91 patients with recurrent glioblastoma treated with bevacizumab were retrospectively evaluated for volume of enhancing tumor as well as volume of the T2/FLAIR hyperintensity. Overall survival (OS) and progression-free survival (PFS) were assessed using volume parameters in a Cox regression model adjusted for significant clinical parameters. RESULTS: In univariable analysis, residual tumor volume, percentage change in tumor volume, steroid change from baseline to posttreatment scan, and number of recurrences were associated with both OS and PFS. With dichotomization by sample median of 52% change of enhancing volume can stratify OS (52 weeks vs. 31 weeks, P = .013) and PFS (21 weeks vs. 12 weeks, P = .009). Residual enhancing volume, dichotomized by sample median of 7.8 cm(3) , can also stratify for OS (64 weeks vs. 28 weeks, P < .001) and PFS (21 weeks vs. 12 weeks, P = .036). CONCLUSIONS: Volumetric percentage change and absolute early posttreatment volume of enhancing tumor can stratify survival for patients with recurrent glioblastoma receiving bevacizumab therapy.