Two-Stage Training Framework Using Multicontrast MRI Radiomics for IDH Mutation Status Prediction in Glioma.

Purpose To develop a radiomics framework for preoperative MRI-based prediction of isocitrate dehydrogenase (IDH) mutation status, a crucial glioma prognostic indicator. Materials and Methods Radiomics features (shape, first-order statistics, and texture) were extracted from the whole tumor or the combination of nonenhancing, necrosis, and edema regions. Segmentation masks were obtained via the federated tumor segmentation tool or the original data source. Boruta, a wrapper-based feature selection algorithm, identified relevant features. Addressing the imbalance between mutated and wild-type cases, multiple prediction models were trained on balanced data subsets using random forest or XGBoost and assembled to build the final classifier. The framework was evaluated using retrospective MRI scans from three public datasets (The Cancer Imaging Archive [TCIA, 227 patients], the University of California San Francisco Preoperative Diffuse Glioma MRI dataset [UCSF, 495 patients], and the Erasmus Glioma Database [EGD, 456 patients]) and internal datasets collected from the University of Texas Southwestern Medical Center (UTSW, 356 patients), New York University (NYU, 136 patients), and University of Wisconsin-Madison (UWM, 174 patients). TCIA and UTSW served as separate training sets, while the remaining data constituted the test set (1617 or 1488 testing cases, respectively). Results The best performing models trained on the TCIA dataset achieved area under the receiver operating characteristic curve (AUC) values of 0.89 for UTSW, 0.86 for NYU, 0.93 for UWM, 0.94 for UCSF, and 0.88 for EGD test sets. The best performing models trained on the UTSW dataset achieved slightly higher AUCs: 0.92 for TCIA, 0.88 for NYU, 0.96 for UWM, 0.93 for UCSF, and 0.90 for EGD. Conclusion This MRI radiomics-based framework shows promise for accurate preoperative prediction of IDH mutation status in patients with glioma. Keywords: Glioma, Isocitrate Dehydrogenase Mutation, IDH Mutation, Radiomics, MRI Supplemental material is available for this article. Published under a CC BY 4.0 license. See also commentary by Moassefi and Erickson in this issue.

Synthesizing 3D Multi-Contrast Brain Tumor MRIs Using Tumor Mask Conditioning.

Data scarcity and data imbalance are two major challenges in training deep learning models on medical images, such as brain tumor MRI data. The recent advancements in generative artificial intelligence have opened new possibilities for synthetically generating MRI data, including brain tumor MRI scans. This approach can be a potential solution to mitigate the data scarcity problem and enhance training data availability. This work focused on adapting the 2D latent diffusion models to generate 3D multi-contrast brain tumor MRI data with a tumor mask as the condition. The framework comprises two components: a 3D autoencoder model for perceptual compression and a conditional 3D Diffusion Probabilistic Model (DPM) for generating high-quality and diverse multi-contrast brain tumor MRI samples, guided by a conditional tumor mask. Unlike existing works that focused on generating either 2D multi-contrast or 3D single-contrast MRI samples, our models generate multi-contrast 3D MRI samples. We also integrated a conditional module within the UNet backbone of the DPM to capture the semantic class-dependent data distribution driven by the provided tumor mask to generate MRI brain tumor samples based on a specific brain tumor mask. We trained our models using two brain tumor datasets: The Cancer Genome Atlas (TCGA) public dataset and an internal dataset from the University of Texas Southwestern Medical Center (UTSW). The models were able to generate high-quality 3D multi-contrast brain tumor MRI samples with the tumor location aligned by the input condition mask. The quality of the generated images was evaluated using the Fréchet Inception Distance (FID) score. This work has the potential to mitigate the scarcity of brain tumor data and improve the performance of deep learning models involving brain tumor MRI data.

MRI-Based Deep Learning Method for Classification of IDH Mutation Status.

Isocitrate dehydrogenase (IDH) mutation status has emerged as an important prognostic marker in gliomas. This study sought to develop deep learning networks for non-invasive IDH classification using T2w MR images while comparing their performance to a multi-contrast network. Methods: Multi-contrast brain tumor MRI and genomic data were obtained from The Cancer Imaging Archive (TCIA) and The Erasmus Glioma Database (EGD). Two separate 2D networks were developed using nnU-Net, a T2w-image-only network (T2-net) and a multi-contrast network (MC-net). Each network was separately trained using TCIA (227 subjects) or TCIA + EGD data (683 subjects combined). The networks were trained to classify IDH mutation status and implement single-label tumor segmentation simultaneously. The trained networks were tested on over 1100 held-out datasets including 360 cases from UT Southwestern Medical Center, 136 cases from New York University, 175 cases from the University of Wisconsin-Madison, 456 cases from EGD (for the TCIA-trained network), and 495 cases from the University of California, San Francisco public database. A receiver operating characteristic curve (ROC) was drawn to calculate the AUC value to determine classifier performance. Results: T2-net trained on TCIA and TCIA + EGD datasets achieved an overall accuracy of 85.4% and 87.6% with AUCs of 0.86 and 0.89, respectively. MC-net trained on TCIA and TCIA + EGD datasets achieved an overall accuracy of 91.0% and 92.8% with AUCs of 0.94 and 0.96, respectively. We developed reliable, high-performing deep learning algorithms for IDH classification using both a T2-image-only and a multi-contrast approach. The networks were tested on more than 1100 subjects from diverse databases, making this the largest study on image-based IDH classification to date.

Deep-learning-enabled brain hemodynamic mapping using resting-state fMRI.

Cerebrovascular disease is a leading cause of death globally. Prevention and early intervention are known to be the most effective forms of its management. Non-invasive imaging methods hold great promises for early stratification, but at present lack the sensitivity for personalized prognosis. Resting-state functional magnetic resonance imaging (rs-fMRI), a powerful tool previously used for mapping neural activity, is available in most hospitals. Here we show that rs-fMRI can be used to map cerebral hemodynamic function and delineate impairment. By exploiting time variations in breathing pattern during rs-fMRI, deep learning enables reproducible mapping of cerebrovascular reactivity (CVR) and bolus arrival time (BAT) of the human brain using resting-state CO2 fluctuations as a natural "contrast media". The deep-learning network is trained with CVR and BAT maps obtained with a reference method of CO2-inhalation MRI, which includes data from young and older healthy subjects and patients with Moyamoya disease and brain tumors. We demonstrate the performance of deep-learning cerebrovascular mapping in the detection of vascular abnormalities, evaluation of revascularization effects, and vascular alterations in normal aging. In addition, cerebrovascular maps obtained with the proposed method exhibit excellent reproducibility in both healthy volunteers and stroke patients. Deep-learning resting-state vascular imaging has the potential to become a useful tool in clinical cerebrovascular imaging.

Errata: Brain tumor IDH, 1p/19q, and MGMT molecular classification using MRI-based deep learning: an initial study on the effect of motion and motion correction.

[This corrects the article DOI: 10.1117/1.JMI.9.1.016001.].

Corrigendum to: A novel fully automated MRI-based deep-learning method for classification of 1p/19q co-deletion status in brain gliomas.

[This corrects the article DOI: 10.1093/noajnl/vdaa066.].

Imaging characteristics of 4th ventricle subependymoma.

PURPOSE: Subependymomas located within the 4th ventricle are rare, and the literature describing imaging characteristics is sparse. Here, we describe the clinical and radiological characteristics of 29 patients with 4th ventricle subependymoma. METHODS: This is a retrospective multi-center study performed after Institutional Review Board (IRB) approval. Patients diagnosed with suspected 4th ventricle subependymoma were identified. A review of clinical, radiology, and pathology reports along with magnetic resonance imaging (MRI) images was performed. RESULTS: Twenty-nine patients, including 6 females, were identified. Eighteen patients underwent surgery with histopathological confirmation of subependymoma. The median age at diagnosis was 52 years. Median tumor volume for the operative cohort was 9.87 cm3, while for the non-operative cohort, it was 0.96 cm3. Thirteen patients in the operative group exhibited symptoms at diagnosis. For the total cohort, the majority of subependymomas (n = 22) were isointense on T1, hyperintense (n = 22) on T2, and enhanced (n = 24). All tumors were located just below the body of the 4th ventricle, terminating near the level of the obex. Fourteen cases demonstrated extension of tumor into foramen of Magendie or Luschka. CONCLUSION: To the best of our knowledge, this is the largest collection of 4th ventricular subependymomas with imaging findings reported to date. All patients in this cohort had tumors originating between the bottom of the body of the 4th ventricle and the obex. This uniform and specific site of origin aids with imaging diagnosis and may infer possible theories of origin.

Adverse Radiation Therapy Effects in the Treatment of Head and Neck Tumors.

Whether used as a single modality or as part of a combined approach, radiation therapy (RT) plays an essential role in the treatment of several head and neck malignancies. Despite the improvement in radiation delivery techniques, normal structures in the vicinity of the target area remain susceptible to a wide range of adverse effects. Given their high incidence, some of these effects are referred to as expected postradiation changes (eg, mucositis, sialadenitis, and edema), while others are considered true complications, meaning they should not be expected and can even represent life-threatening conditions (eg, radionecrosis, fistulas, and radiation-induced neoplasms). Also, according to their timing of onset, these deleterious effects can be divided into four groups: acute (during RT), subacute (within weeks to months), delayed onset (within months to years), and very delayed onset (after several years).The authors provide a comprehensive review of the most important radiation-induced changes related to distinct head and neck sites, focusing on their typical cross-sectional imaging features and correlating them with the time elapsed after treatment. Radiologists should not only be familiar with these imaging findings but also actively seek essential clinical data at the time of interpretation (including knowledge of the RT dose and time, target site, and manifesting symptoms) to better recognize imaging findings, avoid pitfalls and help guide appropriate management. © RSNA, 2022.

Brain tumor IDH, 1p/19q, and MGMT molecular classification using MRI-based deep learning: an initial study on the effect of motion and motion correction.

Purpose: Deep learning has shown promise for predicting the molecular profiles of gliomas using MR images. Prior to clinical implementation, ensuring robustness to real-world problems, such as patient motion, is crucial. The purpose of this study is to perform a preliminary evaluation on the effects of simulated motion artifact on glioma marker classifier performance and determine if motion correction can restore classification accuracies. Approach: T2w images and molecular information were retrieved from the TCIA and TCGA databases. Simulated motion was added in the k-space domain along the phase encoding direction. Classifier performance for IDH mutation, 1p/19q co-deletion, and MGMT methylation was assessed over the range of 0% to 100% corrupted k-space lines. Rudimentary motion correction networks were trained on the motion-corrupted images. The performance of the three glioma marker classifiers was then evaluated on the motion-corrected images. Results: Glioma marker classifier performance decreased markedly with increasing motion corruption. Applying motion correction effectively restored classification accuracy for even the most motion-corrupted images. For isocitrate dehydrogenase (IDH) classification, 99% accuracy was achieved, exceeding the original performance of the network and representing a new benchmark in non-invasive MRI-based IDH classification. Conclusions: Robust motion correction can facilitate highly accurate deep learning MRI-based molecular marker classification, rivaling invasive tissue-based characterization methods. Motion correction may be able to increase classification accuracy even in the absence of a visible artifact, representing a new strategy for boosting classifier performance.

Alterations in the RB Pathway With Inactivation of RB1 Characterize Glioblastomas With a Primitive Neuronal Component.

A primitive neuronal component is a feature of some glioblastomas but defining molecular alterations of this histologic variant remains uncertain. We performed next-generation sequencing of 1500 tumor related genes on tissue from 9 patients with glioblastoma with a primitive component (G/PN) and analyzed 27 similar cases from the Cancer Genome Atlas (TCGA) dataset. Alterations in the RB pathway were identified in all of our patients' tumors and 81% of TCGA tumors with the retinoblastoma tumor suppressor gene (RB1) commonly affected. Although RB1 mutations were observed in some conventional glioblastomas, the allelic fractions of these mutations were significantly higher in tumors with a primitive neuronal component in both our and TCGA cohorts (median, 72% vs 25%, p < 0.001 and 80% vs 40%, p < 0.02, respectively). Further, in 78% of patients in our cohort, RB expression was lost by immunohistochemistry. Our findings indicate that alterations in the RB pathway are common in G/PNs and suggest that inactivation of RB1 may be a driving mechanism for the phenotype.

Preoperative imaging of glioblastoma patients using hyperpolarized 13C pyruvate: Potential role in clinical decision making.

BACKGROUND: Glioblastoma remains incurable despite treatment with surgery, radiation therapy, and cytotoxic chemotherapy, prompting the search for a metabolic pathway unique to glioblastoma cells.13C MR spectroscopic imaging with hyperpolarized pyruvate can demonstrate alterations in pyruvate metabolism in these tumors. METHODS: Three patients with diagnostic MRI suggestive of a glioblastoma were scanned at 3 T 1-2 days prior to tumor resection using a 13C/1H dual-frequency RF coil and a 13C/1H-integrated MR protocol, which consists of a series of 1H MR sequences (T2 FLAIR, arterial spin labeling and contrast-enhanced [CE] T1) and 13C spectroscopic imaging with hyperpolarized [1-13C]pyruvate. Dynamic spiral chemical shift imaging was used for 13C data acquisition. Surgical navigation was used to correlate the locations of tissue samples submitted for histology with the changes seen on the diagnostic MR scans and the 13C spectroscopic images. RESULTS: Each tumor was histologically confirmed to be a WHO grade IV glioblastoma with isocitrate dehydrogenase wild type. Total hyperpolarized 13C signals detected near the tumor mass reflected altered tissue perfusion near the tumor. For each tumor, a hyperintense [1-13C]lactate signal was detected both within CE and T2-FLAIR regions on the 1H diagnostic images (P = .008). [13C]bicarbonate signal was maintained or decreased in the lesion but the observation was not significant (P = .3). CONCLUSIONS: Prior to surgical resection, 13C MR spectroscopic imaging with hyperpolarized pyruvate reveals increased lactate production in regions of histologically confirmed glioblastoma.

Radiomics Repeatability Pitfalls in a Scan-Rescan MRI Study of Glioblastoma.

PURPOSE: To determine the influence of preprocessing on the repeatability and redundancy of radiomics features extracted using a popular open-source radiomics software package in a scan-rescan glioblastoma MRI study. MATERIALS AND METHODS: In this study, a secondary analysis of T2-weighted fluid-attenuated inversion recovery (FLAIR) and T1-weighted postcontrast images from 48 patients (mean age, 56 years [range, 22-77 years]) diagnosed with glioblastoma were included from two prospective studies (ClinicalTrials.gov NCT00662506 [2009-2011] and NCT00756106 [2008-2011]). All patients underwent two baseline scans 2-6 days apart using identical imaging protocols on 3-T MRI systems. No treatment occurred between scan and rescan, and tumors were essentially unchanged visually. Radiomic features were extracted by using PyRadiomics (https://pyradiomics.readthedocs.io/) under varying conditions, including normalization strategies and intensity quantization. Subsequently, intraclass correlation coefficients were determined between feature values of the scan and rescan. RESULTS: Shape features showed a higher repeatability than intensity (adjusted P < .001) and texture features (adjusted P < .001) for both T2-weighted FLAIR and T1-weighted postcontrast images. Normalization improved the overlap between the region of interest intensity histograms of scan and rescan (adjusted P < .001 for both T2-weighted FLAIR and T1-weighted postcontrast images), except in scans where brain extraction fails. As such, normalization significantly improves the repeatability of intensity features from T2-weighted FLAIR scans (adjusted P = .003 [z score normalization] and adjusted P = .002 [histogram matching]). The use of a relative intensity binning strategy as opposed to default absolute intensity binning reduces correlation between gray-level co-occurrence matrix features after normalization. CONCLUSION: Both normalization and intensity quantization have an effect on the level of repeatability and redundancy of features, emphasizing the importance of both accurate reporting of methodology in radiomics articles and understanding the limitations of choices made in pipeline design. Supplemental material is available for this article. © RSNA, 2020See also the commentary by Tiwari and Verma in this issue.

Cerebrovascular Reactivity Mapping Using Resting-State BOLD Functional MRI in Healthy Adults and Patients with Moyamoya Disease.

Background Cerebrovascular reserve, the potential capacity of brain tissue to receive more blood flow when needed, is a desirable marker in evaluating ischemic risk. However, current measurement methods require acetazolamide injection or hypercapnia challenge, prompting a clinical need for resting-state (RS) blood oxygen level-dependent (BOLD) functional MRI data to measure cerebrovascular reactivity (CVR). Purpose To optimize and evaluate an RS CVR MRI technique and demonstrate its relationship to neurosurgical treatment. Materials and Methods In this HIPAA-compliant study, RS BOLD functional MRI data collected in 170 healthy controls between December 2008 and September 2010 were retrospectively evaluated to identify the optimal frequency range of temporal filtering on the basis of spatial correlation with the reference standard CVR map obtained with CO2 inhalation. Next, the optimized RS method was applied in a new, prospective cohort of 50 participants with Moyamoya disease who underwent imaging between June 2014 and August 2019. Finally, CVR values were compared between brain hemispheres with and brain hemispheres without revascularization surgery by using Mann-Whitney U test. Results A total of 170 healthy controls (mean age ± standard deviation, 51 years ± 20; 105 women) and 100 brain hemispheres of 50 participants with Moyamoya disease (mean age, 41 years ± 12; 43 women) were evaluated. RS CVR maps based on a temporal filtering frequency of [0, 0.1164 Hz] yielded the highest spatial correlation (r = 0.74) with the CO2 inhalation CVR results. In patients with Moyamoya disease, 77 middle cerebral arteries (MCAs) had stenosis. RS CVR in the MCA territory was lower in the group that did not undergo surgery (n = 30) than in the group that underwent surgery (n = 47) (mean, 0.407 relative units [ru] ± 0.208 vs 0.532 ru ± 0.182, respectively; P = .006), which is corroborated with the CO2 inhalation CVR data (mean, 0.242 ru ± 0.273 vs 0.437 ru ± 0.200; P = .003). Conclusion Cerebrovascular reactivity mapping performed by using resting-state blood oxygen level-dependent functional MRI provided a task-free method to measure cerebrovascular reserve and depicted treatment effect of revascularization surgery in patients with Moyamoya disease comparable to that with the reference standard of CO2 inhalation MRI. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Wolf and Ware in this issue.

Phase II trial of carboplatin and bevacizumab in patients with breast cancer brain metastases.

BACKGROUND: We aimed to examine the safety and efficacy of bevacizumab and carboplatin in patients with breast cancer brain metastases. METHODS: We enrolled patients with breast cancer and > 1 measurable new or progressive brain metastasis. Patients received bevacizumab 15 mg/kg intravenously (IV) on cycle 1 day 1 and carboplatin IV AUC = 5 on cycle 1 day 8. Patients with HER2-positive disease also received trastuzumab. In subsequent cycles, all drugs were administered on day 1 of each cycle. Contrast-enhanced brain MRI was performed at baseline, 24-96 h after the first bevacizumab dose (day + 1), and every 2 cycles. The primary endpoint was objective response rate in the central nervous system (CNS ORR) by composite criteria. Associations between germline VEGF single nucleotide polymorphisms (rs699947, rs2019063, rs1570360, rs833061) and progression-free survival (PFS) and overall survival (OS) were explored, as were associations between early (day + 1) MRI changes and outcomes. RESULTS: Thirty-eight patients were enrolled (29 HER2-positive, 9 HER2-negative); all were evaluable for response. The CNS ORR was 63% (95% CI, 46-78). Median PFS was 5.62 months and median OS was 14.10 months. As compared with an Eastern Cooperative Oncology Group performance status (ECOG PS) of 0, patients with ECOG PS 1-2 had significantly worse PFS and OS (all P < 0.01). No significant associations between VEGF genotypes or early MRI changes and clinical outcomes were observed. CONCLUSIONS: The combination of bevacizumab and carboplatin results in a high rate of durable objective response in patients with brain metastases from breast cancer. This regimen warrants further investigation. TRIAL REGISTRATION: NCT01004172 . Registered 28 October 2009.

A novel fully automated MRI-based deep-learning method for classification of 1p/19q co-deletion status in brain gliomas.

BACKGROUND: One of the most important recent discoveries in brain glioma biology has been the identification of the isocitrate dehydrogenase (IDH) mutation and 1p/19q co-deletion status as markers for therapy and prognosis. 1p/19q co-deletion is the defining genomic marker for oligodendrogliomas and confers a better prognosis and treatment response than gliomas without it. Our group has previously developed a highly accurate deep-learning network for determining IDH mutation status using T2-weighted (T2w) MRI only. The purpose of this study was to develop a similar 1p/19q deep-learning classification network. METHODS: Multiparametric brain MRI and corresponding genomic information were obtained for 368 subjects from The Cancer Imaging Archive and The Cancer Genome Atlas. 1p/19 co-deletions were present in 130 subjects. Two-hundred and thirty-eight subjects were non-co-deleted. A T2w image-only network (1p/19q-net) was developed to perform 1p/19q co-deletion status classification and simultaneous single-label tumor segmentation using 3D-Dense-UNets. Three-fold cross-validation was performed to generalize the network performance. Receiver operating characteristic analysis was also performed. Dice scores were computed to determine tumor segmentation accuracy. RESULTS: 1p/19q-net demonstrated a mean cross-validation accuracy of 93.46% across the 3 folds (93.4%, 94.35%, and 92.62%, SD = 0.8) in predicting 1p/19q co-deletion status with a sensitivity and specificity of 0.90 ± 0.003 and 0.95 ± 0.01, respectively and a mean area under the curve of 0.95 ± 0.01. The whole tumor segmentation mean Dice score was 0.80 ± 0.007. CONCLUSION: We demonstrate high 1p/19q co-deletion classification accuracy using only T2w MR images. This represents an important milestone toward using MRI to predict glioma histology, prognosis, and response to treatment.

Intrasession Reliability of Arterial Spin-Labeled MRI-Measured Noncontrast Perfusion in Glioblastoma at 3 T.

Arterial spin-labeled magnetic resonance imaging can provide quantitative perfusion measurements in the brain and can be potentially used to evaluate therapy response assessment in glioblastoma (GBM). The reliability and reproducibility of this method to measure noncontrast perfusion in GBM, however, are lacking. We evaluated the intrasession reliability of brain and tumor perfusion in both healthy volunteers and patients with GBM at 3 T using pseudocontinuous labeling (pCASL) and 3D turbo spin echo (TSE) using Cartesian acquisition with spiral profile reordering (CASPR). Two healthy volunteers at a single time point and 6 newly diagnosed patients with GBM at multiple time points (before, during, and after chemoradiation) underwent scanning (total, 14 sessions). Compared with 3D GraSE, 3D TSE-CASPR generated cerebral blood flow maps with better tumor-to-normal background tissue contrast and reduced image distortions. The intraclass correlation coefficient between the 2 runs of 3D pCASL with TSE-CASPR was consistently high (≥0.90) across all normal-appearing gray matter (NAGM) regions of interest (ROIs), and was particularly high in tumors (0.98 with 95% confidence interval [CI]: 0.97-0.99). The within-subject coefficients of variation were relatively low in all normal-appearing gray matter regions of interest (3.40%-7.12%), and in tumors (4.91%). Noncontrast perfusion measured using 3D pCASL with TSE-CASPR provided robust cerebral blood flow maps in both healthy volunteers and patients with GBM with high intrasession repeatability at 3 T. This approach can be an appropriate noncontrast and noninvasive quantitative perfusion imaging method for longitudinal assessment of therapy response and management of patients with GBM.

A Fully Automated Deep Learning Network for Brain Tumor Segmentation.

We developed a fully automated method for brain tumor segmentation using deep learning; 285 brain tumor cases with multiparametric magnetic resonance images from the BraTS2018 data set were used. We designed 3 separate 3D-Dense-UNets to simplify the complex multiclass segmentation problem into individual binary-segmentation problems for each subcomponent. We implemented a 3-fold cross-validation to generalize the network's performance. The mean cross-validation Dice-scores for whole tumor (WT), tumor core (TC), and enhancing tumor (ET) segmentations were 0.92, 0.84, and 0.80, respectively. We then retrained the individual binary-segmentation networks using 265 of the 285 cases, with 20 cases held-out for testing. We also tested the network on 46 cases from the BraTS2017 validation data set, 66 cases from the BraTS2018 validation data set, and 52 cases from an independent clinical data set. The average Dice-scores for WT, TC, and ET were 0.90, 0.84, and 0.80, respectively, on the 20 held-out testing cases. The average Dice-scores for WT, TC, and ET on the BraTS2017 validation data set, the BraTS2018 validation data set, and the clinical data set were as follows: 0.90, 0.80, and 0.78; 0.90, 0.82, and 0.80; and 0.85, 0.80, and 0.77, respectively. A fully automated deep learning method was developed to segment brain tumors into their subcomponents, which achieved high prediction accuracy on the BraTS data set and on the independent clinical data set. This method is promising for implementation into a clinical workflow.

Glycine by MR spectroscopy is an imaging biomarker of glioma aggressiveness.

BACKGROUND: High-grade gliomas likely remodel the metabolic machinery to meet the increased demands for amino acids and nucleotides during rapid cell proliferation. Glycine, a non-essential amino acid and intermediate of nucleotide biosynthesis, may increase with proliferation. Non-invasive measurement of glycine by magnetic resonance spectroscopy (MRS) was evaluated as an imaging biomarker for assessment of tumor aggressiveness. METHODS: We measured glycine, 2-hydroxyglutarate (2HG), and other tumor-related metabolites in 35 glioma patients using an MRS sequence tailored for co-detection of glycine and 2HG in gadolinium-enhancing and non-enhancing tumor regions on 3T MRI. Glycine and 2HG concentrations as measured by MRS were correlated with tumor cell proliferation (MIB-1 labeling index), expression of mitochondrial serine hydroxymethyltransferase (SHMT2), and glycine decarboxylase (GLDC) enzymes, and patient overall survival. RESULTS: Elevated glycine was strongly associated with presence of gadolinium enhancement, indicating more rapidly proliferative disease. Glycine concentration was positively correlated with MIB-1, and levels higher than 2.5 mM showed significant association with shorter patient survival, irrespective of isocitrate dehydrogenase status. Concentration of 2HG did not correlate with MIB-1 index. A high glycine/2HG concentration ratio, >2.5, was strongly associated with shorter survival (P < 0.0001). GLDC and SHMT2 expression were detectable in all tumors with glycine concentration, demonstrating an inverse correlation with GLDC. CONCLUSIONS: The data suggest that aggressive gliomas reprogram glycine-mediated one-carbon metabolism to meet the biosynthetic demands for rapid cell proliferation. MRS evaluation of glycine provides a non-invasive metabolic imaging biomarker that is predictive of tumor progression and clinical outcome. KEY POINTS: 1. Glycine and 2-hydroxyglutarate in glioma patients are precisely co-detected using MRS at 3T.2. Tumors with elevated glycine proliferate and progress rapidly.3. A high glycine/2HG ratio is predictive of shortened patient survival.

A novel fully automated MRI-based deep-learning method for classification of IDH mutation status in brain gliomas.

BACKGROUND: Isocitrate dehydrogenase (IDH) mutation status has emerged as an important prognostic marker in gliomas. Currently, reliable IDH mutation determination requires invasive surgical procedures. The purpose of this study was to develop a highly accurate, MRI-based, voxelwise deep-learning IDH classification network using T2-weighted (T2w) MR images and compare its performance to a multicontrast network. METHODS: Multiparametric brain MRI data and corresponding genomic information were obtained for 214 subjects (94 IDH-mutated, 120 IDH wild-type) from The Cancer Imaging Archive and The Cancer Genome Atlas. Two separate networks were developed, including a T2w image-only network (T2-net) and a multicontrast (T2w, fluid attenuated inversion recovery, and T1 postcontrast) network (TS-net) to perform IDH classification and simultaneous single label tumor segmentation. The networks were trained using 3D Dense-UNets. Three-fold cross-validation was performed to generalize the networks' performance. Receiver operating characteristic analysis was also performed. Dice scores were computed to determine tumor segmentation accuracy. RESULTS: T2-net demonstrated a mean cross-validation accuracy of 97.14% ± 0.04 in predicting IDH mutation status, with a sensitivity of 0.97 ± 0.03, specificity of 0.98 ± 0.01, and an area under the curve (AUC) of 0.98 ± 0.01. TS-net achieved a mean cross-validation accuracy of 97.12% ± 0.09, with a sensitivity of 0.98 ± 0.02, specificity of 0.97 ± 0.001, and an AUC of 0.99 ± 0.01. The mean whole tumor segmentation Dice scores were 0.85 ± 0.009 for T2-net and 0.89 ± 0.006 for TS-net. CONCLUSION: We demonstrate high IDH classification accuracy using only T2-weighted MR images. This represents an important milestone toward clinical translation.