Generation and applications of synthetic computed tomography images for neurosurgical planning

OBJECTIVE

CT and MRI are synergistic in the information provided for neurosurgical planning. While obtaining both types of images lends unique data from each, doing so adds to cost and exposes patients to additional ionizing radiation after MRI has been performed. Cross-modal synthesis of high-resolution CT images from MRI sequences offers an appealing solution. The authors therefore sought to develop a deep learning conditional generative adversarial network (cGAN) which performs this synthesis.

METHODS

Preoperative paired CT and contrast-enhanced MR images were collected for patients with meningioma, pituitary tumor, vestibular schwannoma, and cerebrovascular disease. CT and MR images were denoised, field corrected, and coregistered. MR images were fed to a cGAN that exported a "synthetic" CT scan. The accuracy of synthetic CT images was assessed objectively using the quantitative similarity metrics as well as by clinical features such as sella and internal auditory canal (IAC) dimensions and mastoid/clinoid/sphenoid aeration.

RESULTS

A total of 92,981 paired CT/MR images obtained in 80 patients were used for training/testing, and 10,068 paired images from 10 patients were used for external validation. Synthetic CT images reconstructed the bony skull base and convexity with relatively high accuracy. Measurements of the sella and IAC showed a median relative error between synthetic CT scans and ground truth images of 6%, with greater variability in IAC reconstruction compared with the sella. Aerations in the mastoid, clinoid, and sphenoid regions were generally captured, although there was heterogeneity in finer air cell septations. Performance varied based on pathology studied, with the highest limitation observed in evaluating meningiomas with intratumoral calcifications or calvarial invasion.

CONCLUSIONS

The generation of high-resolution CT scans from MR images through cGAN offers promise for a wide range of applications in cranial and spinal neurosurgery, especially as an adjunct for preoperative evaluation. Optimizing cGAN performance on specific anatomical regions may increase its clinical viability.

Clinical and Genomic Predictors of Adverse Events in Newly Diagnosed Glioblastoma

PURPOSE

Adverse clinical events cause significant morbidity in patients with GBM (GBM). We examined whether genomic alterations were associated with AE (AE) in patients with GBM.

EXPERIMENTAL DESIGN

We identified adults with histologically confirmed IDH-wild-type GBM with targeted next-generation sequencing (OncoPanel) at Dana Farber Cancer Institute from 2013 to 2019. Seizure at presentation, lymphopenia, thromboembolic events, pseudoprogression, and early progression (within 6 months of diagnosis) were identified as AE. The biologic function of genetic variants was categorized as loss-of-function (LoF), no change in function, or gain-of-function (GoF) using a somatic tumor mutation knowledge base (OncoKB) and consensus protein function predictions. Associations between functional genomic alterations and AE were examined using univariate logistic regressions and multivariable regressions adjusted for additional clinical predictors.

RESULTS

Our study included 470 patients diagnosed with GBM who met the study criteria. We focused on 105 genes that had sequencing data available for ≥ 90% of the patients and were altered in ≥10% of the cohort. Following false-discovery rate (FDR) correction and multivariable adjustment, the TP53, RB1, IGF1R, and DIS3 LoF alterations were associated with lower odds of seizures, while EGFR, SMARCA4, GNA11, BRD4, and TCF3 GoF and SETD2 LoF alterations were associated with higher odds of seizures. For all other AE of interest, no significant associations were found with genomic alterations following FDR correction.

CONCLUSIONS

Genomic biomarkers based on functional variant analysis of a routine clinical panel may help identify AE in GBM, particularly seizures. Identifying these risk factors could improve the management of patients through better supportive care and consideration of prophylactic therapies.

Improved optic nerve visualization and treatment planning through a dedicated optic nerve MRI protocol

OBJECTIVE

This study describes an innovative optic nerve MRI protocol for better delineating optic nerve anatomy from neighboring pathology.

METHODS

Twenty-two patients undergoing MRI examination of the optic nerve with the dedicated protocol were identified and included for analysis of imaging, surgical strategy, and outcomes. T2-weighted and fat-suppressed T1-weighted gadolinium-enhanced images were acquired perpendicular and parallel to the long axis of the optic nerve to achieve en face and in-line views along the course of the nerve.

RESULTS

Dedicated optic nerve MRI sequences provided enhanced visualization of the nerve, CSF within the nerve sheath, and local pathology. Optic nerve sequences leveraged the "CSF ring" within the optic nerve sheath to create contrast between pathology and normal tissue, highlighting areas of compression. Tumor was readily tracked along the longitudinal axis of the nerve by images obtained parallel to the nerve. The findings augmented treatment planning.

CONCLUSIONS

The authors present a dedicated optic nerve MRI protocol that is simple to use and affords improved cross-sectional and longitudinal visualization of the nerve, surrounding CSF, and pathology. This improved visualization enhances radiological evaluation and treatment planning for optic nerve lesions.

Auto-segmentation of Adult-Type Diffuse Gliomas: Comparison of Transfer Learning-Based Convolutional Neural Network Model vs. Radiologists

Segmentation of glioma is crucial for quantitative brain tumor assessment, to guide therapeutic research and clinical management, but very time-consuming. Fully automated tools for the segmentation of multi-sequence MRI are needed. We developed and pretrained a deep learning (DL) model using publicly available datasets A (n = 210) and B (n = 369) containing FLAIR, T2WI, and contrast-enhanced (CE)-T1WI. This was then fine-tuned with our institutional dataset (n = 197) containing ADC, T2WI, and CE-T1WI, manually annotated by radiologists, and split into training (n = 100) and testing (n = 97) sets. The Dice similarity coefficient (DSC) was used to compare model outputs and manual labels. A third independent radiologist assessed segmentation quality on a semi-quantitative 5-scale score. Differences in DSC between new and recurrent gliomas, and between uni or multifocal gliomas were analyzed using the Mann-Whitney test. Semi-quantitative analyses were compared using the chi-square test. We found that there was good agreement between segmentations from the fine-tuned DL model and ground truth manual segmentations (median DSC: 0.729, std-dev: 0.134). DSC was higher for newly diagnosed (0.807) than recurrent (0.698) (p < 0.001), and higher for unifocal (0.747) than multi-focal (0.613) cases (p = 0.001). Semi-quantitative scores of DL and manual segmentation were not significantly different (mean: 3.567 vs. 3.639; 93.8% vs. 97.9% scoring ≥ 3, p = 0.107). In conclusion, the proposed transfer learning DL performed similarly to human radiologists in glioma segmentation on both structural and ADC sequences. Further improvement in segmenting challenging postoperative and multifocal glioma cases is needed.

Expert-centered Evaluation of Deep Learning Algorithms for Brain Tumor Segmentation

Purpose To present results from a literature survey on practices in deep learning segmentation algorithm evaluation and perform a study on expert quality perception of brain tumor segmentation. Materials and Methods A total of 180 articles reporting on brain tumor segmentation algorithms were surveyed for the reported quality evaluation. Additionally, ratings of segmentation quality on a four-point scale were collected from medical professionals for 60 brain tumor segmentation cases. Results Of the surveyed articles, Dice score, sensitivity, and Hausdorff distance were the most popular metrics to report segmentation performance. Notably, only 2.8% of the articles included clinical experts' evaluation of segmentation quality. The experimental results revealed a low interrater agreement (Krippendorff α, 0.34) in experts' segmentation quality perception. Furthermore, the correlations between the ratings and commonly used quantitative quality metrics were low (Kendall tau between Dice score and mean rating, 0.23; Kendall tau between Hausdorff distance and mean rating, 0.51), with large variability among the experts. Conclusion The results demonstrate that quality ratings are prone to variability due to the ambiguity of tumor boundaries and individual perceptual differences, and existing metrics do not capture the clinical perception of segmentation quality. Keywords: Brain Tumor Segmentation, Deep Learning Algorithms, Glioblastoma, Cancer, Machine Learning Clinical trial registration nos. NCT00756106 and NCT00662506 Supplemental material is available for this article. © RSNA, 2023.

Artificial intelligence in neuroimaging of brain tumors: reality or still promise?

PURPOSE OF REVIEW

To provide an updated overview of artificial intelligence (AI) applications in neuro-oncologic imaging and discuss current barriers to wider clinical adoption.

RECENT FINDINGS

A wide variety of AI applications in neuro-oncologic imaging have been developed and researched, spanning tasks from pretreatment brain tumor classification and segmentation, preoperative planning, radiogenomics, prognostication and survival prediction, posttreatment surveillance, and differentiating between pseudoprogression and true disease progression. While earlier studies were largely based on data from a single institution, more recent studies have demonstrated that the performance of these algorithms are also effective on external data from other institutions. Nevertheless, most of these algorithms have yet to see widespread clinical adoption, given the lack of prospective studies demonstrating their efficacy and the logistical difficulties involved in clinical implementation.

SUMMARY

While there has been significant progress in AI and neuro-oncologic imaging, clinical utility remains to be demonstrated. The next wave of progress in this area will be driven by prospective studies measuring outcomes relevant to clinical practice and go beyond retrospective studies which primarily aim to demonstrate high performance.

A framework for standardised tissue sampling and processing during resection of diffuse intracranial glioma: joint recommendations from four RANO groups

Surgical resection represents the standard of care for people with newly diagnosed diffuse gliomas, and the neuropathological and molecular profile of the resected tissue guides clinical management and forms the basis for research. The Response Assessment in Neuro-Oncology (RANO) consortium is an international, multidisciplinary effort that aims to standardise research practice in neuro-oncology. These recommendations represent a multidisciplinary consensus from the four RANO groups: RANO resect, RANO recurrent glioblastoma, RANO radiotherapy, and RANO/PET for a standardised workflow to achieve a representative tumour evaluation in a disease characterised by intratumoural heterogeneity, including recommendations on which tumour regions should be surgically sampled, how to define those regions on the basis of preoperative imaging, and the optimal sample volume. Practical recommendations for tissue sampling are given for people with low-grade and high-grade gliomas, as well as for people with newly diagnosed and recurrent disease. Sampling of liquid biopsies is also addressed. A standardised workflow for subsequent handling of the resected tissue is proposed to avoid information loss due to decreasing tissue quality or insufficient clinical information. The recommendations offer a framework for prospective biobanking studies.

Revealing tumor microstructure with oscillating diffusion encoding MRI in pre-surgical and post-treatment glioma patients

PURPOSE

We hypothesized that the time-dependent diffusivity at short diffusion times, as measured by oscillating gradient spin echo (OGSE) diffusion MRI, can characterize tissue microstructures in glioma patients.

THEORY AND METHODS

Five adult patients with known diffuse glioma, including two pre-surgical and three with new enhancing lesions after treatment for high-grade glioma, were scanned in an ultra-high-performance gradient 3.0T MRI system. OGSE diffusion MRI at 30-100 Hz and pulsed gradient spin echo diffusion imaging (approximated as 0 Hz) were obtained. The ADC and trace-diffusion-weighted image at each acquired frequency were calculated, that is, ADC (f) and TraceDWI (f).

RESULTS

In pre-surgical patients, biopsy-confirmed solid enhancing tumor in a high-grade glioblastoma showed higherADC ( f ) ADC ( 0 Hz ) $$ \frac{\mathrm{ADC}\ (f)}{\mathrm{ADC}\ \left(0\ \mathrm{Hz}\right)} $$ and lowerTraceDWI ( f ) TraceDWI ( 0 Hz ) $$ \frac{\mathrm{TraceDWI}\ (f)}{\mathrm{TraceDWI}\ \left(0\ \mathrm{Hz}\right)} $$ , compared to that at same OGSE frequency in a low-grade astrocytoma. In post-treatment patients, the enhancing lesions of two patients who were diagnosed with tumor progression contained more voxels with highADC ( f ) ADC ( 0 Hz ) $$ \frac{\mathrm{ADC}\ (f)}{\mathrm{ADC}\ \left(0\ \mathrm{Hz}\right)} $$ and lowTraceDWI ( f ) TraceDWI ( 0 Hz ) $$ \frac{\mathrm{TraceDWI}\left(\mathrm{f}\right)}{\mathrm{TraceDWI}\left(0\ \mathrm{Hz}\right)} $$ , compared to the enhancing lesions of a patient who was diagnosed with treatment effect. Non-enhancing T2 signal abnormality lesions in both the pre-surgical high-grade glioblastoma and post-treatment tumor progressions showed regions with highADC ( f ) ADC ( 0 Hz ) $$ \frac{\mathrm{ADC}\ (f)}{\mathrm{ADC}\ \left(0\ \mathrm{Hz}\right)} $$ and lowTraceDWI ( f ) TraceDWI ( 0 Hz ) $$ \frac{\mathrm{TraceDWI}\ \left(\mathrm{f}\right)}{\mathrm{TraceDWI}\ \left(0\ \mathrm{Hz}\right)} $$ , consistent with infiltrative tumor. The solid tumor of the glioblastoma, the enhancing lesions of post-treatment tumor progressions, and the suspected infiltrative tumors showed high diffusion time-dependency from 30 to 100 Hz, consistent with high intra-tumoral volume fraction (cellular density).

CONCLUSION

Different characteristics of OGSE-based time-dependent diffusivity can reveal heterogenous tissue microstructures that indicate cellular density in glioma patients.

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.

Advanced Meningioma Imaging

Noninvasive imaging methods are used to accurately diagnose meningiomas and track their growth and location. These techniques, including computed tomography, MRI, and nuclear medicine, are also being used to gather more information about the biology of the tumors and potentially predict their grade and impact on prognosis. In this article, we will discuss the current and developing uses of these imaging techniques including additional analysis using radiomics in the diagnosis and treatment of meningiomas, including treatment planning and prediction of tumor behavior.

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.

Application of radiomics to meningiomas: A systematic review

BACKGROUND

Quantitative imaging analysis through radiomics is a powerful technology to non-invasively assess molecular correlates and guide clinical decision-making. There has been growing interest in image-based phenotyping for meningiomas given the complexities in management.

METHODS

We systematically reviewed meningioma radiomics analyses published in PubMed, Embase, and Web of Science until December 20, 2021. We compiled performance data and assessed publication quality using the radiomics quality score (RQS).

RESULTS

A total of 170 publications were grouped into 5 categories of radiomics applications to meningiomas: Tumor detection and segmentation (21%), classification across neurologic diseases (54%), grading (14%), feature correlation (3%), and prognostication (8%). A majority focused on technical model development (73%) versus clinical applications (27%), with increasing adoption of deep learning. Studies utilized either private institutional (50%) or public (49%) datasets, with only 68% using a validation dataset. For detection and segmentation, radiomic models had a mean accuracy of 93.1 ± 8.1% and a dice coefficient of 88.8 ± 7.9%. Meningioma classification had a mean accuracy of 95.2 ± 4.0%. Tumor grading had a mean area-under-the-curve (AUC) of 0.85 ± 0.08. Correlation with meningioma biological features had a mean AUC of 0.89 ± 0.07. Prognostication of the clinical course had a mean AUC of 0.83 ± 0.08. While clinical studies had a higher mean RQS compared to technical studies, quality was low overall with a mean RQS of 6.7 ± 5.9 (possible range -8 to 36).

CONCLUSIONS

There has been global growth in meningioma radiomics, driven by data accessibility and novel computational methodology. Translatability toward complex tasks such as prognostication requires studies that improve quality, develop comprehensive patient datasets, and engage in prospective trials.

Diagnostic performance of computed tomography features in detecting oropharyngeal squamous cell carcinoma extranodal extension

OBJECTIVES

Accurate pre-treatment imaging determination of extranodal extension (ENE) could facilitate the selection of appropriate initial therapy for HPV-positive oropharyngeal squamous cell carcinoma (HPV + OPSCC). Small studies have associated 7 CT features with ENE with varied results and agreement. This article seeks to determine the replicable diagnostic performance of these CT features for ENE.

METHODS

Five expert academic head/neck neuroradiologists from 5 institutions evaluate a single academic cancer center cohort of 75 consecutive HPV + OPSCC patients. In a web-based virtual laboratory for imaging research and education, the experts performed training on 7 published CT features associated with ENE and then independently identified the "single most (if any) suspicious" lymph node and presence/absence of each of the features. Inter-rater agreement was assessed using percentage agreement, Gwet's AC1, and Fleiss' kappa. Sensitivity, specificity, and positive and negative predictive values were calculated for each CT feature based on histologic ENE.

RESULTS

All 5 raters identified the same node in 52 cases (69%). In 15 cases (20%), at least one rater selected a node and at least one rater did not. In 8 cases (11%), all raters selected a node, but at least one rater selected a different node. Percentage agreement and Gwet's AC1 coefficients were > 0.80 for lesion identification, matted/conglomerated nodes, and central necrosis. Fleiss' kappa was always < 0.6. CT sensitivity for histologically confirmed ENE ranged 0.18-0.94, specificity 0.41-0.88, PPV 0.26-0.36, and NPV 0.78-0.96.

CONCLUSIONS

Previously described CT features appear to have poor reproducibility among expert head/neck neuroradiologists and poor predictive value for histologic ENE.

KEY POINTS

• Previously described CT imaging features appear to have poor reproducibility among expert head and neck subspecialized neuroradiologists as well as poor predictive value for histologic ENE. • Although it may still be appropriate to comment on the presence or absence of these CT features in imaging reports, the evidence indicates that caution is warranted when incorporating these features into clinical decision-making regarding the likelihood of ENE.

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).

Losartan controls immune checkpoint blocker-induced edema and improves survival in glioblastoma mouse models

Immune checkpoint blockers (ICBs) have failed in all phase III glioblastoma trials. Here, we found that ICBs induce cerebral edema in some patients and mice with glioblastoma. Through single-cell RNA sequencing, intravital imaging, and CD8+ T cell blocking studies in mice, we demonstrated that this edema results from an inflammatory response following antiprogrammed death 1 (PD1) antibody treatment that disrupts the blood-tumor barrier. Used in lieu of immunosuppressive corticosteroids, the angiotensin receptor blocker losartan prevented this ICB-induced edema and reprogrammed the tumor microenvironment, curing 20% of mice which increased to 40% in combination with standard of care treatment. Using a bihemispheric tumor model, we identified a "hot" tumor immune signature prior to losartan+anti-PD1 therapy that predicted long-term survival. Our findings provide the rationale and associated biomarkers to test losartan with ICBs in glioblastoma patients.

Isocitrate dehydrogenase (IDH) mutant gliomas: A Society for Neuro-Oncology (SNO) consensus review on diagnosis, management, and future directions

Isocitrate dehydrogenase (IDH) mutant gliomas are the most common adult, malignant primary brain tumors diagnosed in patients younger than 50, constituting an important cause of morbidity and mortality. In recent years, there has been significant progress in understanding the molecular pathogenesis and biology of these tumors, sparking multiple efforts to improve their diagnosis and treatment. In this consensus review from the Society for Neuro-Oncology (SNO), the current diagnosis and management of IDH-mutant gliomas will be discussed. In addition, novel therapies, such as targeted molecular therapies and immunotherapies, will be reviewed. Current challenges and future directions for research will be discussed.

Federated learning enables big data for rare cancer boundary detection

Although machine learning (ML) has shown promise across disciplines, out-of-sample generalizability is concerning. This is currently addressed by sharing multi-site data, but such centralization is challenging/infeasible to scale due to various limitations. Federated ML (FL) provides an alternative paradigm for accurate and generalizable ML, by only sharing numerical model updates. Here we present the largest FL study to-date, involving data from 71 sites across 6 continents, to generate an automatic tumor boundary detector for the rare disease of glioblastoma, reporting the largest such dataset in the literature (n = 6, 314). We demonstrate a 33% delineation improvement for the surgically targetable tumor, and 23% for the complete tumor extent, over a publicly trained model. We anticipate our study to: 1) enable more healthcare studies informed by large diverse data, ensuring meaningful results for rare diseases and underrepresented populations, 2) facilitate further analyses for glioblastoma by releasing our consensus model, and 3) demonstrate the FL effectiveness at such scale and task-complexity as a paradigm shift for multi-site collaborations, alleviating the need for data-sharing.

Brain metastases: A Society for Neuro-Oncology (SNO) consensus review on current management and future directions

Brain metastases occur commonly in patients with advanced solid malignancies. Yet, less is known about brain metastases than cancer-related entities of similar incidence. Advances in oncologic care have heightened the importance of intracranial management. Here, in this consensus review supported by the Society for Neuro-Oncology (SNO), we review the landscape of brain metastases with particular attention to management approaches and ongoing efforts with potential to shape future paradigms of care. Each coauthor carried an area of expertise within the field of brain metastases and initially composed, edited, or reviewed their specific subsection of interest. After each subsection was accordingly written, multiple drafts of the manuscript were circulated to the entire list of authors for group discussion and feedback. The hope is that the these consensus guidelines will accelerate progress in the understanding and management of patients with brain metastases, and highlight key areas in need of further exploration that will lead to dedicated trials and other research investigations designed to advance the field.

Circulating Immune Cell and Outcome Analysis from the Phase II Study of PD-L1 Blockade with Durvalumab for Newly Diagnosed and Recurrent Glioblastoma

PURPOSE

PD-L1 is upregulated in glioblastoma and supports immunosuppression. We evaluated PD-L1 blockade with durvalumab among glioblastoma cohorts and investigated potential biomarkers.

PATIENTS AND METHODS

MGMT unmethylated newly diagnosed patients received radiotherapy plus durvalumab (cohort A; n = 40). Bevacizumab-naïve, recurrent patients received durvalumab alone (cohort B; n = 31) or in combination with standard bevacizumab (cohort B2; n = 33) or low-dose bevacizumab (cohort B3; n = 33). Bevacizumab-refractory patients received durvalumab plus bevacizumab (cohort C; n = 22). Primary endpoints were: OS-12 (A), PFS-6 (B, B2, B3), and OS-6 (C). Exploratory biomarkers included: a systematic, quantitative, and phenotypic evaluation of circulating immune cells; tumor mutational burden (TMB); and tumor immune activation signature (IAS).

RESULTS

No cohort achieved the primary efficacy endpoint. Outcome was comparable among recurrent, bevacizumab-naïve cohorts. No unexpected toxicities were observed. A widespread reduction of effector immune cell subsets was noted among recurrent patients compared with newly diagnosed patients that was partially due to dexamethasone use. A trend of increased CD8+Ki67+ T cells at day 15 was noted among patients who achieved the primary endpoint and were not on dexamethasone. Neither TMB nor IAS predicted outcome.

CONCLUSIONS

Patients with recurrent glioblastoma have markedly lower baseline levels of multiple circulating immune cell subsets compared with newly diagnosed patients. An early increase in systemic Ki67+CD8+ cells may warrant further evaluation as a potential biomarker of therapeutic benefit among patients with glioblastoma undergoing checkpoint therapy. Dexamethasone decreased immune cell subsets. PD-L1 blockade and combination with standard or reduced dose bevacizumab was ineffective.

Radiomics-Based Machine Learning for Outcome Prediction in a Multicenter Phase II Study of Programmed Death-Ligand 1 Inhibition Immunotherapy for Glioblastoma

BACKGROUND AND PURPOSE

Imaging assessment of an immunotherapy response in glioblastoma is challenging due to overlap in the appearance of treatment-related changes with tumor progression. Our purpose was to determine whether MR imaging radiomics-based machine learning can predict progression-free survival and overall survival in patients with glioblastoma on programmed death-ligand 1 inhibition immunotherapy.

MATERIALS AND METHODS

Post hoc analysis was performed of a multicenter trial on the efficacy of durvalumab in glioblastoma (n = 113). Radiomics tumor features on pretreatment and first on-treatment time point MR imaging were extracted. The random survival forest algorithm was applied to clinical and radiomics features from pretreatment and first on-treatment MR imaging from a subset of trial sites (n = 60-74) to train a model to predict long overall survival and progression-free survival and was tested externally on data from the remaining sites (n = 29-43). Model performance was assessed using the concordance index and dynamic area under the curve from different time points.

RESULTS

The mean age was 55.2 (SD, 11.5) years, and 69% of patients were male. Pretreatment MR imaging features had a poor predictive value for overall survival and progression-free survival (concordance index  = 0.472-0.524). First on-treatment MR imaging features had high predictive value for overall survival (concordance index = 0.692-0.750) and progression-free survival (concordance index = 0.680-0.715).

CONCLUSIONS

A radiomics-based machine learning model from first on-treatment MR imaging predicts survival in patients with glioblastoma on programmed death-ligand 1 inhibition immunotherapy.

Imaging diagnosis and treatment selection for brain tumors in the era of molecular therapeutics

Currently, most CNS tumors require tissue sampling to discern their molecular/genomic landscape. However, growing research has shown the powerful role imaging can play in non-invasively and accurately detecting the molecular signature of these tumors. The overarching theme of this review article is to provide neuroradiologists and neurooncologists with a framework of several important molecular markers, their associated imaging features and the accuracy of those features. A particular emphasis is placed on those tumors and mutations that have specific or promising imaging correlates as well as their respective therapeutic potentials.

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.

An automated COVID-19 triage pipeline using artificial intelligence based on chest radiographs and clinical data

While COVID-19 diagnosis and prognosis artificial intelligence models exist, very few can be implemented for practical use given their high risk of bias. We aimed to develop a diagnosis model that addresses notable shortcomings of prior studies, integrating it into a fully automated triage pipeline that examines chest radiographs for the presence, severity, and progression of COVID-19 pneumonia. Scans were collected using the DICOM Image Analysis and Archive, a system that communicates with a hospital’s image repository. The authors collected over 6,500 non-public chest X-rays comprising diverse COVID-19 severities, along with radiology reports and RT-PCR data. The authors provisioned one internally held-out and two external test sets to assess model generalizability and compare performance to traditional radiologist interpretation. The pipeline was evaluated on a prospective cohort of 80 radiographs, reporting a 95% diagnostic accuracy. The study mitigates bias in AI model development and demonstrates the value of an end-to-end COVID-19 triage platform.

Body CT and PET/CT Detection of Extracranial Lymphoma in Patients with Newly Diagnosed Central Nervous System Lymphoma

BACKGROUND

We aimed to investigate the detection rate of body CT or PET/CT for sites of extracranial disease in patients with a new pathological diagnosis of CNS DLBCL and to identify factors associated with sites of extracranial disease.

METHODS

An international multicenter cohort study of consecutive immunocompetent patients with a new diagnosis of CNS DLBCL confirmed by brain biopsy who underwent CT and/or PET/CT to evaluate for sites of extracranial disease between 1998 and 2019. The primary outcome was the detection rate of extracranial lymphoma by CT or PET/CT. Subgroup analyses according to age and EBV status were also performed. Logistic regression analyses were performed to determine factors related to sites of extracranial disease. Detection rates of CT and PET/CT were compared.

RESULTS

1043 patients were included. The overall detection rate of CT or PET/CT was 2.6% (27/1043). The treatment approach was adjusted in 74% of these patients. Multivariable analysis demonstrated that age>61-years (OR, 3.10; P=.016) and EBV positivity (OR, 3.78; P=.045) were associated with greater odds of extracranial lymphoma. There was no statistically significant difference in detection rate between CT and PET/CT (P=.802). In patients≤61 years old, the false-referral rates were significantly higher than the detection rates (P<.001).

CONCLUSION

Our results showed increased odds of extracranial lymphoma in patients with older age or EBV-positive lymphoma. Treatment was adjusted in a majority of patients diagnosed with extracranial lymphoma, thereby supporting the current guidelines for the use contrast-enhanced body CT or PET/CT in patients with newly diagnosed CNS DLBCL.

Imaging Advances for Central Nervous System Tumors

This article reviews recent advances in the use of standard and advanced imaging techniques for diagnosis and treatment of central nervous system (CNS) tumors, including glioma and brain metastasis. Following the recent transition from a histology-based approach in classifying CNS tumors to one that integrates histology with the molecular information of tumor, the approaches for imaging CNS tumors have also been adapted to this new framework. Some challenges related to the diagnosis and treatment of CNS tumors, such as differentiating tumor from treatment-related imaging changes, require further progress to implement advanced imaging for clinical use.

Standardized Classification of Lumbar Spine Degeneration on Magnetic Resonance Imaging Reduces Intra- and Inter-subspecialty Variability

BACKGROUND AND PURPOSE

To determine the efficacy of standardized definitions of degenerative change in reducing variability in interpretation of lumbar spine magnetic resonance imaging within and between groups of subspecialty-trained neuroradiologists (NR) and musculoskeletal radiologists (MSK).

MATERIALS AND METHODS

Six radiologists, three from both NR and MSK groups were trained on a standardized classification system of degenerative change. After an 11-month washout period, they independently re-interpreted fifty exams at the L4-L5 and L5-S1 levels. Responses were converted to a six-point ordinal scale for the assessment of neural foraminal stenosis and spinal canal stenosis (SCS), three-point scale for lateral recess stenosis, and four-point scale for facet osteoarthritis (FO). Intra-subspecialty and inter-subspecialty analysis was performed using the weighted Cohen's kappa with a binary matrix of all reader pairs.

RESULTS

Inter-subspecialty agreement improved from k=0.527 (moderate) to k=0.602 (substantial) for neural foraminal stenosis, from k=0.540 (moderate) to k=0.652 (substantial) for SCS, from k=0.0818 (slight) to k=0.337 (fair) for lateral recess stenosis, and from k=0.176 (slight) to k=0.495 (moderate) for FO. The NR group demonstrated improved intra-subspecialty agreement for the assessment of SCS, from k=0.368 (fair) to k=0.638 (substantial). The MSK group demonstrated improved intra-subspecialty agreement for the assessment of FO, from k=0.134 (slight) to k=0.413 (moderate). Intra-subspecialty agreement was similar for other parameters before and after training.

CONCLUSIONS

As result of the standardized definitions training, the NR and MSK groups each improved in one of the four parameters, while inter-subspecialty variability improved in all four parameters. These definitions may be useful in clinical practice across radiology subspecialties.

Analysis of morphological characteristics of IDH-mutant/wildtype brain tumors using whole-lesion phenotype analysis

Background

Although IDH-mutant tumors aggregate to the frontotemporal regions, the clustering pattern of IDH-wildtype tumors is less clear. As voxel-based lesion-symptom mapping (VLSM) has several limitations for solid lesion mapping, a new technique, whole-lesion phenotype analysis (WLPA), is developed. We utilize WLPA to assess spatial clustering of tumors with IDH mutation from The Cancer Genome Atlas and The Cancer Imaging Archive.

Methods

The degree of tumor clustering segmented from T1 weighted images is measured to every other tumor by a function of lesion similarity to each other via the Hausdorff distance. Each tumor is ranked according to the degree to which its neighboring tumors show identical phenotypes, and through a permutation technique, significant tumors are determined. VLSM was applied through a previously described method.

Results

A total of 244 patients of mixed-grade gliomas (WHO II-IV) are analyzed, of which 150 were IDH-wildtype and 139 were glioblastomas. VLSM identifies frontal lobe regions that are more likely associated with the presence of IDH mutation but no regions where IDH-wildtype was more likely to be present. WLPA identifies both IDH-mutant and -wildtype tumors exhibit statistically significant spatial clustering.

Conclusion

WLPA may provide additional statistical power when compared with VLSM without making several potentially erroneous assumptions. WLPA identifies tumors most likely to exhibit particular phenotypes, rather than producing anatomical maps, and may be used in conjunction with VLSM to understand the relationship between tumor morphology and biologically relevant tumor phenotypes.

The Incidence and Treatment Response of Double Expression of MYC and BCL2 in Patients with Diffuse Large B-Cell Lymphoma: A Systematic Review and Meta-Analysis

MYC/BCL2 protein co-expression (i.e., double expressor) has been shown to be a negative predictor of outcome in diffuse large B-cell lymphoma (DLBCL). We aimed to establish the incidence of double expressor status in patients with de novo DLBCL and identify the predictive value of this biomarker on treatment response through systematic review and meta-analysis. PubMed and Embase were searched for studies published through December 2019 that reported proportions of double expressor DLBCL. The pooled proportions of MYC and BCL2 expression, both alone and in combination, were computed using the inverse variance method for calculating weights and by the DerSimonian-Laird method. The pooled odds ratios (ORs) of complete remission (CR) rate were calculated, and meta-regression analysis was conducted to explore heterogeneity. Forty-one studies (7054 patients) were included. The pooled incidence of double expressor status in DLBCL was 23% (95% confidence interval [CI], 20-26%), with an adjusted estimate of 31% (95% CI, 27-36%). Neither MYC/BCL2 protein cutoff values, race, mean, or median age of included patients, or overall study quality was a significant factor of heterogeneity (p ≥ 0.20). Cases without double expressor status demonstrated a higher probability of CR to rituximab, cyclophosphamide, doxorubicin, vincristine, and prednisone treatment (OR, 2.69; 95% CI, 1.55-4.67). Our results reaffirm the predictive power of this important biomarker.

Artificial intelligence for prediction of COVID-19 progression using CT imaging and clinical data

OBJECTIVES

Early recognition of coronavirus disease 2019 (COVID-19) severity can guide patient management. However, it is challenging to predict when COVID-19 patients will progress to critical illness. This study aimed to develop an artificial intelligence system to predict future deterioration to critical illness in COVID-19 patients.

METHODS

An artificial intelligence (AI) system in a time-to-event analysis framework was developed to integrate chest CT and clinical data for risk prediction of future deterioration to critical illness in patients with COVID-19.

RESULTS

A multi-institutional international cohort of 1,051 patients with RT-PCR confirmed COVID-19 and chest CT was included in this study. Of them, 282 patients developed critical illness, which was defined as requiring ICU admission and/or mechanical ventilation and/or reaching death during their hospital stay. The AI system achieved a C-index of 0.80 for predicting individual COVID-19 patients' to critical illness. The AI system successfully stratified the patients into high-risk and low-risk groups with distinct progression risks (p < 0.0001).

CONCLUSIONS

Using CT imaging and clinical data, the AI system successfully predicted time to critical illness for individual patients and identified patients with high risk. AI has the potential to accurately triage patients and facilitate personalized treatment.

KEY POINT

• AI system can predict time to critical illness for patients with COVID-19 by using CT imaging and clinical data.

Encephalopathy at admission predicts adverse outcomes in patients with SARS-CoV-2 infection

Aims

To determine if neurologic symptoms at admission can predict adverse outcomes in patients with severe acute respiratory syndrome coronavirus 2 (SARS‐CoV‐2).

Methods

Electronic medical records of 1053 consecutively hospitalized patients with laboratory‐confirmed infection of SARS‐CoV‐2 from one large medical center in the USA were retrospectively analyzed. Univariable and multivariable Cox regression analyses were performed with the calculation of areas under the curve (AUC) and concordance index (C‐index). Patients were stratified into subgroups based on the presence of encephalopathy and its severity using survival statistics. In sensitivity analyses, patients with mild/moderate and severe encephalopathy (defined as coma) were separately considered.

Results

Of 1053 patients (mean age 52.4 years, 48.0% men [n = 505]), 35.1% (n = 370) had neurologic manifestations at admission, including 10.3% (n = 108) with encephalopathy. Encephalopathy was an independent predictor for death (hazard ratio [HR] 2.617, 95% confidence interval [CI] 1.481–4.625) in multivariable Cox regression. The addition of encephalopathy to multivariable models comprising other predictors for adverse outcomes increased AUCs (mortality: 0.84–0.86, ventilation/ intensive care unit [ICU]: 0.76–0.78) and C‐index (mortality: 0.78 to 0.81, ventilation/ICU: 0.85–0.86). In sensitivity analyses, risk stratification survival curves for mortality and ventilation/ICU based on severe encephalopathy (n = 15) versus mild/moderate encephalopathy (n = 93) versus no encephalopathy (n = 945) at admission were discriminative (p < 0.001).

Conclusions

Encephalopathy at admission predicts later progression to death in SARS‐CoV‐2 infection, which may have important implications for risk stratification in clinical practice.

Activity of PD-1 blockade with Nivolumab among patients with recurrent atypical/anaplastic meningioma: Phase II trial results

BACKGROUND

Programmed death-1 ligand (PD-L1) contributes to tumor immunosuppression and is upregulated in aggressive meningiomas. We performed a phase II study of nivolumab, a programmed death-1 (PD-1) blocking antibody among patients with grade ≥2 meningioma that recurred after surgery and radiation therapy.

METHODS

Twenty-five patients received nivolumab (240 mg biweekly) until progression, voluntary withdrawal, unacceptable toxicity, or death. Tumor mutational burden (TMB) and quantification of tumor infiltrating lymphocytes (TIL) were evaluated as potential immunocorrelative biomarkers. Change in neurologic function was prospectively assessed using the Neurologic Assessment in Neuro-Oncology (NANO) scale.

RESULTS

Enrolled patients had multiple recurrences including ≥3 prior surgeries and ≥2 prior courses of radiation in 60% and 72%, respectively. Nivolumab was well tolerated with no unexpected AEs. PFS-6 was 42.4% (95% CI: 22.8, 60.7) and the median OS was 30.9 months (95% CI: 17.6, NA). One patient achieved radiographic response (ongoing at 4.5 years). TMB was > 10/Mb in 2 of 15 profiled tumors (13.3%). Baseline TIL density was low but increased post-treatment in 3 patients including both patients with elevated TMB. Most patients who achieved PFS-6 maintained neurologic function prior to progression as assessed by NANO.

CONCLUSION

Nivolumab was well tolerated but failed to improve PFS-6, although a subset of patients appeared to derive benefit. Low levels of TMB and TIL density were typically observed. NANO assessment of neurologic function contributed to outcome assessment. Future studies may consider rationally designed combinatorial regimens.

Evaluation of RAPNO criteria in medulloblastoma and other leptomeningeal seeding tumors using MRI and clinical data

BACKGROUND

Although the Response Assessment in Pediatric Neuro-Oncology (RAPNO) working group has made recommendations for response assessment in patients with medulloblastoma (MBL) and leptomeningeal seeding tumors, these criteria have yet to be evaluated.

METHODS

We examined MR imaging and clinical data in a multicenter retrospective cohort of 269 patients with MBL diagnoses, high grade glioma, embryonal tumor, germ cell tumor, or choroid plexus papilloma. Interobserver agreement, objective response (OR) rates, and progression-free survival (PFS) were calculated. Landmark analyses were performed for OR and progression status at 0.5, 1.0, and 1.5 years after treatment initiation. Cox proportional hazards models were used to determine the associations between OR and progression with overall survival (OS). Subgroup analyses based on tumor subgroup and treatment modality were performed.

RESULTS

The median follow-up time was 4.0 years. In all patients, the OR rate was .0.565 (95% CI: 0.505-0.625) by RAPNO. The interobserver agreement of OR determination between 2 raters (a neuroradiologist and a neuro-oncologist) for the RAPNO criteria in all patients was 83.8% (k statistic = 0.815; P < 0.001). At 0.5-, 1.0-, and 1.5-year landmarks, both OR status and PFS determined by RAPNO were predictive of OS (hazard ratios [HRs] for 1-year landmark: OR HR = 0.079, P < 0.001; PFS HR = 10.192, P < 0.001). In subgroup analysis, OR status and PFS were predictive of OS for all tumor subtypes and treatment modalities.

CONCLUSION

RAPNO criteria showed excellent consistency in the treatment response evaluation of MBL and other leptomeningeal seeding tumors. OR and PFS determined by RAPNO criteria correlated with OS.

Volumetric analysis of IDH-mutant lower-grade glioma: a natural history study of tumor growth rates before and after treatment

BACKGROUND

Lower-grade gliomas (LGGs) with isocitrate dehydrogenase 1 and/or 2 (IDH1/2) mutations have long survival times, making evaluation of treatment efficacy difficult. We investigated the volumetric growth rate of IDH mutant gliomas before and after treatment with established glioma therapies to determine whether a significant change in growth rate could be documented and perhaps be used in the future to evaluate treatment response to investigational agents in LGG trials.

METHODS

In this multicenter retrospective study, 230 adult patients with IDH1/2 mutated LGGs (World Health Organization grade II or III) undergoing surgery, radiation, or chemotherapy for progressive non-enhancing tumor were identified. Subjects were required to have 3 MRI scans containing T2/fluid attenuated inversion recovery imaging spanning a minimum of 6 months prior to treatment. A mixed-effect model was used to estimate tumor growth prior to treatment. A subset of 95 patients who received chemotherapy, radiotherapy, or chemoradiotherapy and had 2 posttreatment imaging time points available were evaluated for change in pre- and posttreatment volumetric growth rates using a piecewise mixed model.

RESULTS

The pretreatment volumetric growth rate across all 230 patients was 27.37%/180 days (95% CI: [23.36%, 31.51%]). In the 95 patients with both pre- and posttreatment scans available, there was a significant difference in volumetric growth rates before (26.63%/180 days, 95% CI: [19.31%, 34.40%]) and after treatment (-15.24% /180 days, 95% CI: [-21.37%, -8.62%]) (P < 0.0001). The growth rates for patient subgroup with 1p/19q codeletion (N = 118) was significantly slower than the rate of the 1p/19q non-codeleted group (N = 68) (22.84% vs 35.49%, P = 0.0108).

CONCLUSION

In this study, we evaluated the growth rates of IDH mutant gliomas before and after standard therapy. Further study is needed to establish whether a change in growth rate is associated with patient survival and its use as a surrogate endpoint in clinical trials for IDH mutant LGGs.

Standardization of imaging methods for machine learning in neuro-oncology

Radiomics is a novel technique in which quantitative phenotypes or features are extracted from medical images. Machine learning enables analysis of large quantities of medical imaging data generated by radiomic feature extraction. A growing number of studies based on these methods have developed tools for neuro-oncology applications. Despite the initial promises, many of these imaging tools remain far from clinical implementation. One major limitation hindering the use of these models is their lack of reproducibility when applied across different institutions and clinical settings. In this article, we discuss the importance of standardization of methodology and reporting in our effort to improve reproducibility. Ongoing efforts of standardization for neuro-oncological imaging are reviewed. Challenges related to standardization and potential disadvantages in over-standardization are also described. Ultimately, greater multi-institutional collaborative effort is needed to provide and implement standards for data acquisition and analysis methods to facilitate research results to be interoperable and reliable for integration into different practice environments.

The T2-FLAIR mismatch sign as a predictor of IDH-mutant, 1p/19q-noncodeleted lower-grade gliomas: a systematic review and diagnostic meta-analysis

OBJECTIVES

To evaluate the diagnostic performance of the T2-FLAIR mismatch sign for prediction of isocitrate dehydrogenase (IDH)-mutant, 1p/19q-noncodeleted lower-grade gliomas (LGGs) and review studies with false positive results.

METHODS

The MEDLINE and EMBASE databases were searched up to March 13, 2020, to identify articles reporting the diagnostic performance of the T2-FLAIR mismatch sign for prediction of IDH-mutant, 1p/19q-noncodeleted LGGs (IDHmut-Noncodel) using the search terms (T2 FLAIR mismatch). Pooled sensitivity, specificity, and correlation coefficient for interobserver agreement were calculated.

RESULTS

Twelve studies including a total of 1053 patients were included. The median age was 43 (median; range, 14-56). The pooled sensitivity and specificity were 42% (95% CI, 28-58%) and 100% (95% CI, 88-100%), respectively. According to the HSROC curve, the area under the curve was 0.77 (95% CI, 0.73-0.80). Considerable heterogeneity was possible among the studies in terms of both sensitivity and specificity. A threshold effect was suggested and was considered to explain most of the heterogeneity. Four studies reported false positive results for the T2-FLAIR mismatch sign, including dysembryoplastic neuroepithelial tumor, pediatric-type gliomas, and non-neoplastic lesions. The 2 original articles with false positive results showed the highest sensitivities among the 10 studies included in the quantitative analysis, supporting the probability of the threshold effect. The pooled correlation coefficient was 0.87 (95% CI, 0.73-0.94).

CONCLUSIONS

The T2-FLAIR mismatch sign had a high specificity and interobserver agreement for the prediction of IDHmut-Noncodel. However, the sign demonstrated low sensitivity, and a few studies with false positive cases were also reported.

KEY POINTS

• The pooled sensitivity and specificity of the T2-FLAIR mismatch sign for prediction of IDH-mutant, 1p/19q-noncodeleted lower-grade gliomas were 42% and 100%, respectively. • Four studies reported false positive results. • The pooled correlation coefficient was 0.87, suggesting almost perfect interobserver agreement.

Frequency and Evolution of New Postoperative Enhancement on 3 Tesla Intraoperative and Early Postoperative Magnetic Resonance Imaging

BACKGROUND

Intraoperative magnetic resonance imaging (IO-MRI) provides real-time assessment of extent of resection of brain tumor. Development of new enhancement during IO-MRI can confound interpretation of residual enhancing tumor, although the incidence of this finding is unknown.

OBJECTIVE

To determine the frequency of new enhancement during brain tumor resection on intraoperative 3 Tesla (3T) MRI. To optimize the postoperative imaging window after brain tumor resection using 1.5 and 3T MRI.

METHODS

We retrospectively evaluated 64 IO-MRI performed for patients with enhancing brain lesions referred for biopsy or resection as well as a subset with an early postoperative MRI (EP-MRI) within 72 h of surgery (N = 42), and a subset with a late postoperative MRI (LP-MRI) performed between 120 h and 8 wk postsurgery (N = 34). Three radiologists assessed for new enhancement on IO-MRI, and change in enhancement on available EP-MRI and LP-MRI. Consensus was determined by majority response. Inter-rater agreement was assessed using percentage agreement.

RESULTS

A total of 10 out of 64 (16%) of the IO-MRI demonstrated new enhancement. Seven of 10 patients with available EP-MRI demonstrated decreased/resolved enhancement. One out of 42 (2%) of the EP-MRI demonstrated new enhancement, which decreased on LP-MRI. Agreement was 74% for the assessment of new enhancement on IO-MRI and 81% for the assessment of new enhancement on the EP-MRI.

CONCLUSION

New enhancement occurs in intraoperative 3T MRI in 16% of patients after brain tumor resection, which decreases or resolves on subsequent MRI within 72 h of surgery. Our findings indicate the opportunity for further study to optimize the postoperative imaging window.

Immune Checkpoint Inhibitor with or without Radiotherapy in Melanoma Patients with Brain Metastases: A Systematic Review and Meta-Analysis

Objective

Immune checkpoint inhibitor (ICI) therapy has shown activity against melanoma brain metastases. Recently, promising results have also been reported for ICI combination therapy and ICI combined with radiotherapy. We aimed to evaluate radiologic response and adverse event rates of these therapeutic options by a systematic review and meta-analysis.

Materials and Methods

A systematic literature search of Ovid-MEDLINE and EMBASE was performed up to October 12, 2019 and included studies evaluating the intracranial objective response rates (ORRs) and/or disease control rates (DCRs) of ICI with or without radiotherapy for treating melanoma brain metastases. We also evaluated safety-associated outcomes.

Results

Eleven studies with 14 cohorts (3 with ICI combination therapy; 5 with ICI combined with radiotherapy; 6 with ICI monotherapy) were included. ICI combination therapy {pooled ORR, 53% (95% confidence interval [CI], 44–61%); DCR, 57% (95% CI, 49–66%)} and ICI combined with radiotherapy (pooled ORR, 42% [95% CI, 31–54%]; DCR, 85% [95% CI, 63–95%]) showed higher local efficacy compared to ICI monotherapy (pooled ORR, 15% [95% CI, 11–20%]; DCR, 26% [95% CI, 21–32%]). The grade 3 or 4 adverse event rate was significantly higher with ICI combination therapy (60%; 95% CI, 52–67%) compared to ICI monotherapy (11%; 95% CI, 8–17%) and ICI combined with radiotherapy (4%; 95% CI, 1–19%). Grade 3 or 4 central nervous system (CNS)-related adverse event rates were not different (9% in ICI combination therapy; 8% in ICI combined with radiotherapy; 5% in ICI monotherapy).

Conclusion

ICI combination therapy or ICI combined with radiotherapy showed better local efficacy than ICI monotherapy for treating melanoma brain metastasis. The grade 3 or 4 adverse event rate was highest with ICI combination therapy, and the CNS-related grade 3 or 4 event rate was similar. Prospective trials will be necessary to compare the efficacy of ICI combination therapy and ICI combined with radiotherapy.

Immune checkpoint inhibitor therapy may increase the incidence of treatment-related necrosis after stereotactic radiosurgery for brain metastases: a systematic review and meta-analysis

OBJECTIVES

To compare the incidence of treatment-related necrosis between combination SRS+ICI therapy and SRS therapy alone in patients with brain metastases from melanoma and non-small cell lung cancer (NSCLC).

METHODS

A systematic literature search of Ovid-MEDLINE and EMBASE was performed up to August 10, 2020. The difference in the pooled incidence of treatment-related necrosis after SRS+ICI or SRS alone was evaluated. The cumulative incidence of treatment-related necrosis at the specific time point after the treatment was calculated and plotted. Subgroup and meta-regression analyses were additionally performed.

RESULTS

Sixteen studies (14 on melanoma, 2 on NSCLC) were included. In NSCLC brain metastasis, the reported incidences of treatment-related necrosis in SRS+ICI and SRS alone ranged 2.9-3.4% and 0-2.9%, respectively. Meta-analysis was conducted including 14 studies on melanoma brain metastasis. The incidence of treatment-related necrosis was higher in SRS+ICI than SRS alone (16.0% vs. 6.5%; p = 0.065; OR, 2.35). The incidence showed rapid increase until 12 months after the SRS when combined with ICI therapy (14%; 95% CI, 8-22%) and its pace of increase slowed thereafter. Histopathologic diagnosis as the reference standard for treatment-related necrosis and inclusion of only symptomatic cases were the source of heterogeneity in SRS+ICI.

CONCLUSIONS

Treatment-related necrosis tended to occur 2.4 times more frequently in the setting of combination SRS+ICI therapy compared with SRS alone in melanoma brain metastasis showing high cumulative incidence within the first year. Treatment-related necrosis should be considered when SRS+ICI combination therapy is used for melanoma brain metastasis, especially in the first year.

KEY POINTS

• Treatment-related necrosis occurred 2.4 times more frequently in the setting of combination SRS+ICI therapy compared with SRS alone in melanoma brain metastasis. • Treatment-related necrosis more frequently occurred in brain metastases from melanoma than NSCLC. • Reference standard for treatment-related necrosis and inclusion of only symptomatic treatment-related necrosis were a significant source of heterogeneity, indicating varying definitions of treatment-related necrosis in the literature need to be unified.

Evaluation of a convolutional neural network for ovarian tumor differentiation based on magnetic resonance imaging

OBJECTIVES

There currently lacks a noninvasive and accurate method to distinguish benign and malignant ovarian lesion prior to treatment. This study developed a deep learning algorithm that distinguishes benign from malignant ovarian lesion by applying a convolutional neural network on routine MR imaging.

METHODS

Five hundred forty-five lesions (379 benign and 166 malignant) from 451 patients from a single institution were divided into training, validation, and testing set in a 7:2:1 ratio. Model performance was compared with four junior and three senior radiologists on the test set.

RESULTS

Compared with junior radiologists averaged, the final ensemble model combining MR imaging and clinical variables had a higher test accuracy (0.87 vs 0.64, p < 0.001) and specificity (0.92 vs 0.64, p < 0.001) with comparable sensitivity (0.75 vs 0.63, p = 0.407). Against the senior radiologists averaged, the final ensemble model also had a higher test accuracy (0.87 vs 0.74, p = 0.033) and specificity (0.92 vs 0.70, p < 0.001) with comparable sensitivity (0.75 vs 0.83, p = 0.557). Assisted by the model's probabilities, the junior radiologists achieved a higher average test accuracy (0.77 vs 0.64, Δ = 0.13, p < 0.001) and specificity (0.81 vs 0.64, Δ = 0.17, p < 0.001) with unchanged sensitivity (0.69 vs 0.63, Δ = 0.06, p = 0.302). With the AI probabilities, the junior radiologists had higher specificity (0.81 vs 0.70, Δ = 0.11, p = 0.005) but similar accuracy (0.77 vs 0.74, Δ = 0.03, p = 0.409) and sensitivity (0.69 vs 0.83, Δ = -0.146, p = 0.097) when compared with the senior radiologists.

CONCLUSIONS

These results demonstrate that artificial intelligence based on deep learning can assist radiologists in assessing the nature of ovarian lesions and improve their performance.

KEY POINTS

• Artificial Intelligence based on deep learning can assess the nature of ovarian lesions on routine MRI with higher accuracy and specificity than radiologists. • Assisted by the deep learning model's probabilities, junior radiologists achieved better performance that matched those of senior radiologists.

Artificial Intelligence Augmentation of Radiologist Performance in Distinguishing COVID-19 from Pneumonia of Other Origin at Chest CT

Background Coronavirus disease 2019 (COVID-19) and pneumonia of other diseases share similar CT characteristics, which contributes to the challenges in differentiating them with high accuracy. Purpose To establish and evaluate an artificial intelligence (AI) system for differentiating COVID-19 and other pneumonia at chest CT and assessing radiologist performance without and with AI assistance. Materials and Methods A total of 521 patients with positive reverse transcription polymerase chain reaction results for COVID-19 and abnormal chest CT findings were retrospectively identified from 10 hospitals from January 2020 to April 2020. A total of 665 patients with non-COVID-19 pneumonia and definite evidence of pneumonia at chest CT were retrospectively selected from three hospitals between 2017 and 2019. To classify COVID-19 versus other pneumonia for each patient, abnormal CT slices were input into the EfficientNet B4 deep neural network architecture after lung segmentation, followed by a two-layer fully connected neural network to pool slices together. The final cohort of 1186 patients (132 583 CT slices) was divided into training, validation, and test sets in a 7:2:1 and equal ratio. Independent testing was performed by evaluating model performance in separate hospitals. Studies were blindly reviewed by six radiologists without and then with AI assistance. Results The final model achieved a test accuracy of 96% (95% confidence interval [CI]: 90%, 98%), a sensitivity of 95% (95% CI: 83%, 100%), and a specificity of 96% (95% CI: 88%, 99%) with area under the receiver operating characteristic curve of 0.95 and area under the precision-recall curve of 0.90. On independent testing, this model achieved an accuracy of 87% (95% CI: 82%, 90%), a sensitivity of 89% (95% CI: 81%, 94%), and a specificity of 86% (95% CI: 80%, 90%) with area under the receiver operating characteristic curve of 0.90 and area under the precision-recall curve of 0.87. Assisted by the probabilities of the model, the radiologists achieved a higher average test accuracy (90% vs 85%, Δ = 5, P < .001), sensitivity (88% vs 79%, Δ = 9, P < .001), and specificity (91% vs 88%, Δ = 3, P = .001). Conclusion Artificial intelligence assistance improved radiologists' performance in distinguishing coronavirus disease 2019 pneumonia from non-coronavirus disease 2019 pneumonia at chest CT. © RSNA, 2020 Online supplemental material is available for this article.

Diagnostic Yield of Staging Brain MRI in Patients with Newly Diagnosed Non-Small Cell Lung Cancer

Background Existing guidelines are inconsistent regarding the indications for staging brain MRI in patients with newly diagnosed, early-stage non-small cell lung cancer (NSCLC). Purpose To evaluate the diagnostic yield of staging brain MRI in the initial evaluation of lung cancer. Materials and Methods This retrospective, observational, single-institution study included patients with newly diagnosed NSCLC who underwent staging chest CT and staging brain MRI from November 2017 to October 2018. Diagnostic yield was defined as the proportion of patients with brain metastases among all patients. Yield was stratified into clinical stage groups per the eighth edition of the American Joint Committee on Cancer staging guidelines, based on staging chest CT and in adenocarcinoma with epidermal growth factor receptor (EGFR) gene mutation and anaplastic lymphoma kinase (ALK) gene rearrangement. Subgroup analyses were performed on the basis of cell types and molecular markers. The χ² test was performed to compare the diagnostic yields, and Bonferroni correction was used to account for multiple testing between stage groups. Results A total of 1712 patients (mean age, 64 years ± 10 [standard deviation]; 1035 men) were included. The diagnostic yield of staging brain MRI in newly diagnosed NSCLC was 11.9% (203 of 1712; 95% confidence interval [CI]: 10.4%, 13.5%). In clinical stage IA, IB, and II disease, the diagnostic yields were 0.3% (two of 615; 95% CI: 0.0%, 1.2%), 3.8% (seven of 186; 95% CI: 1.5%, 7.6%), and 4.7% (eight of 171; 95% CI: 2.0%, 9.0%), respectively. The diagnostic yield was higher in patients with adenocarcinoma (13.6%; 176 of 1297; 95% CI: 11.8%, 15.6%) than squamous cell carcinoma (5.9%; 21 of 354; 95% CI: 3.7%, 8.9%) and in patients with EGFR mutation-positive adenocarcinoma (17.5%; 85 of 487; 95% CI: 14.2%, 21.1%) than with EGFR mutation-negative adenocarcinoma (10.6%; 68 of 639; 95% CI: 8.4%, 13.3%) (P < .001 for both). Conclusion The diagnostic yield of staging brain MRI in clinical stage IA non-small cell lung cancer was low, but staging brain MRI had a higher diagnostic yield in clinical stage IB and epidermal growth factor receptor mutation-positive adenocarcinoma. © RSNA, 2020 Online supplemental material is available for this article.