Optimal approaches to analyzing functional MRI data in glioma patients.

BACKGROUND: Resting-state fMRI is increasingly used to study the effects of gliomas on the functional organization of the brain. A variety of preprocessing techniques and functional connectivity analyses are represented in the literature. However, there so far has been no systematic comparison of how alternative methods impact observed results. NEW METHOD: We first surveyed current literature and identified alternative analytical approaches commonly used in the field. Following, we systematically compared alternative approaches to atlas registration, parcellation scheme, and choice of graph-theoretical measure as regards differentiating glioma patients (N = 59) from age-matched reference subjects (N = 163). RESULTS: Our results suggest that non-linear, as opposed to affine registration, improves structural match to an atlas, as well as measures of functional connectivity. Functionally- as opposed to anatomically-derived parcellation schemes maximized the contrast between glioma patients and reference subjects. We also demonstrate that graph-theoretic measures strongly depend on parcellation granularity, parcellation scheme, and graph density. COMPARISON WITH EXISTING METHODS AND CONCLUSIONS: Our current work primarily focuses on technical optimization of rs-fMRI analysis in glioma patients and, therefore, is fundamentally different from the bulk of papers discussing glioma-induced functional network changes. We report that the evaluation of glioma-induced alterations in the functional connectome strongly depends on analytical approaches including atlas registration, choice of parcellation scheme, and graph-theoretical measures.

The Brain Tumor Segmentation (BraTS) Challenge 2023: Brain MR Image Synthesis for Tumor Segmentation (BraSyn).

Automated brain tumor segmentation methods have become well-established and reached performance levels offering clear clinical utility. These methods typically rely on four input magnetic resonance imaging (MRI) modalities: T1-weighted images with and without contrast enhancement, T2-weighted images, and FLAIR images. However, some sequences are often missing in clinical practice due to time constraints or image artifacts, such as patient motion. Consequently, the ability to substitute missing modalities and gain segmentation performance is highly desirable and necessary for the broader adoption of these algorithms in the clinical routine. In this work, we present the establishment of the Brain MR Image Synthesis Benchmark (BraSyn) in conjunction with the Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2023. The primary objective of this challenge is to evaluate image synthesis methods that can realistically generate missing MRI modalities when multiple available images are provided. The ultimate aim is to facilitate automated brain tumor segmentation pipelines. The image dataset used in the benchmark is diverse and multi-modal, created through collaboration with various hospitals and research institutions.

MRI-based Identification and Classification of Major Intracranial Tumor Types by Using a 3D Convolutional Neural Network: A Retrospective Multi-institutional Analysis.

PURPOSE: To develop an algorithm to classify postcontrast T1-weighted MRI scans by tumor classes (high-grade glioma, low-grade glioma [LGG], brain metastasis, meningioma, pituitary adenoma, and acoustic neuroma) and a healthy tissue (HLTH) class. MATERIALS AND METHODS: In this retrospective study, preoperative postcontrast T1-weighted MR scans from four publicly available datasets-the Brain Tumor Image Segmentation dataset (n = 378), the LGG-1p19q dataset (n = 145), The Cancer Genome Atlas Glioblastoma Multiforme dataset (n = 141), and The Cancer Genome Atlas Low Grade Glioma dataset (n = 68)-and an internal clinical dataset (n = 1373) were used. In all, a total of 2105 images were split into a training dataset (n = 1396), an internal test set (n = 361), and an external test dataset (n = 348). A convolutional neural network was trained to classify the tumor type and to discriminate between images depicting HLTH and images depicting tumors. The performance of the model was evaluated by using cross-validation, internal testing, and external testing. Feature maps were plotted to visualize network attention. The accuracy, positive predictive value (PPV), negative predictive value, sensitivity, specificity, F1 score, area under the receiver operating characteristic curve (AUC), and area under the precision-recall curve (AUPRC) were calculated. RESULTS: On the internal test dataset, across the seven different classes, the sensitivities, PPVs, AUCs, and AUPRCs ranged from 87% to 100%, 85% to 100%, 0.98 to 1.00, and 0.91 to 1.00, respectively. On the external data, they ranged from 91% to 97%, 73% to 99%, 0.97 to 0.98, and 0.9 to 1.0, respectively. CONCLUSION: The developed model was capable of classifying postcontrast T1-weighted MRI scans of different intracranial tumor types and discriminating images depicting pathologic conditions from images depicting HLTH.Keywords MR-Imaging, CNS, Brain/Brain Stem, Diagnosis/Classification/Application Domain, Supervised Learning, Convolutional Neural Network, Deep Learning Algorithms, Machine Learning Algorithms Supplemental material is available for this article. © RSNA, 2021.

A feasibility study to evaluate early treatment response of brain metastases one week after stereotactic radiosurgery using perfusion weighted imaging.

BACKGROUND: To explore if early perfusion-weighted magnetic resonance imaging (PWI) may be a promising imaging biomarker to predict local recurrence (LR) of brain metastases after stereotactic radiosurgery (SRS). METHODS: This is a prospective pilot study of adult brain metastasis patients who were treated with SRS and imaged with PWI before and 1 week later. Relative cerebral blood volume (rCBV) parameter maps were calculated by normalizing to the mean value of the contralateral white matter on PWI. Cox regression was conducted to explore factors associated with time to LR, with Bonferroni adjusted p<0.0006 for multiple testing correction. LR rates were estimated with the Kaplan-Meier method and compared using the log-rank test. RESULTS: Twenty-three patients were enrolled from 2013 through 2016, with 22 evaluable lesions from 16 patients. After a median follow-up of 13.1 months (range: 3.0-53.7), 5 lesions (21%) developed LR after a median of 3.4 months (range: 2.3-5.7). On univariable analysis, larger tumor volume (HR 1.48, 95% CI 1.02-2.15, p = 0.04), lower SRS dose (HR 0.45, 95% CI 0.21-0.97, p = 0.04), and higher rCBV at week 1 (HR 1.07, 95% CI 1.003-1.14, p = 0.04) had borderline association with shorter time to LR. Tumors >2.0cm3 had significantly higher LR than if ≤2.0cm3: 54% vs 0% at 1 year, respectively, p = 0.008. A future study to confirm the association of early PWI and LR of the high-risk cohort of lesions >2.0cm3 is estimated to require 258 patients. CONCLUSIONS: PWI at week 1 after SRS may have borderline association with LR. Tumors <2.0cm3 have low risk of LR after SRS and may be low-yield for predictive biomarker studies. Information regarding sample size and potential challenges for future imaging biomarker studies may be gleaned from this pilot study.

Mapping language function with task-based vs. resting-state functional MRI.

BACKGROUND: Use of functional MRI (fMRI) in pre-surgical planning is a non-invasive method for pre-operative functional mapping for patients with brain tumors, especially tumors located near eloquent cortex. Currently, this practice predominantly involves task-based fMRI (T-fMRI). Resting state fMRI (RS-fMRI) offers an alternative with several methodological advantages. Here, we compare group-level analyses of RS-fMRI vs. T-fMRI as methods for language localization. PURPOSE: To contrast RS-fMRI vs. T-fMRI as techniques for localization of language function. METHODS: We analyzed data obtained in 35 patients who had both T-fMRI and RS-fMRI scans during the course of pre-surgical evaluation. The RS-fMRI data were analyzed using a previously trained resting-state network classifier. The T-fMRI data were analyzed using conventional techniques. Group-level results obtained by both methods were evaluated in terms of two outcome measures: (1) inter-subject variability of response magnitude and (2) sensitivity/specificity analysis of response topography, taking as ground truth previously reported maps of the language system based on intraoperative cortical mapping as well as meta-analytic maps of language task fMRI responses. RESULTS: Both fMRI methods localized major components of the language system (areas of Broca and Wernicke) although not with equal inter-subject consistency. Word-stem completion T-fMRI strongly activated Broca's area but also several task-general areas not specific to language. RS-fMRI provided a more specific representation of the language system. CONCLUSION: We demonstrate several advantages of classifier-based mapping of language representation in the brain. Language T-fMRI activated task-general (i.e., not language-specific) functional systems in addition to areas of Broca and Wernicke. In contrast, classifier-based analysis of RS-fMRI data generated maps confined to language-specific regions of the brain.

Brain extraction on MRI scans in presence of diffuse glioma: Multi-institutional performance evaluation of deep learning methods and robust modality-agnostic training.

Brain extraction, or skull-stripping, is an essential pre-processing step in neuro-imaging that has a direct impact on the quality of all subsequent processing and analyses steps. It is also a key requirement in multi-institutional collaborations to comply with privacy-preserving regulations. Existing automated methods, including Deep Learning (DL) based methods that have obtained state-of-the-art results in recent years, have primarily targeted brain extraction without considering pathologically-affected brains. Accordingly, they perform sub-optimally when applied on magnetic resonance imaging (MRI) brain scans with apparent pathologies such as brain tumors. Furthermore, existing methods focus on using only T1-weighted MRI scans, even though multi-parametric MRI (mpMRI) scans are routinely acquired for patients with suspected brain tumors. In this study, we present a comprehensive performance evaluation of recent deep learning architectures for brain extraction, training models on mpMRI scans of pathologically-affected brains, with a particular focus on seeking a practically-applicable, low computational footprint approach, generalizable across multiple institutions, further facilitating collaborations. We identified a large retrospective multi-institutional dataset of n=3340 mpMRI brain tumor scans, with manually-inspected and approved gold-standard segmentations, acquired during standard clinical practice under varying acquisition protocols, both from private institutional data and public (TCIA) collections. To facilitate optimal utilization of rich mpMRI data, we further introduce and evaluate a novel ''modality-agnostic training'' technique that can be applied using any available modality, without need for model retraining. Our results indicate that the modality-agnostic approach1 obtains accurate results, providing a generic and practical tool for brain extraction on scans with brain tumors.

Heterogeneity Diffusion Imaging of gliomas: Initial experience and validation.

OBJECTIVES: Primary brain tumors are composed of tumor cells, neural/glial tissues, edema, and vasculature tissue. Conventional MRI has a limited ability to evaluate heterogeneous tumor pathologies. We developed a novel diffusion MRI-based method-Heterogeneity Diffusion Imaging (HDI)-to simultaneously detect and characterize multiple tumor pathologies and capillary blood perfusion using a single diffusion MRI scan. METHODS: Seven adult patients with primary brain tumors underwent standard-of-care MRI protocols and HDI protocol before planned surgical resection and/or stereotactic biopsy. Twelve tumor sampling sites were identified using a neuronavigational system and recorded for imaging data quantification. Metrics from both protocols were compared between World Health Organization (WHO) II and III tumor groups. Cerebral blood volume (CBV) derived from dynamic susceptibility contrast (DSC) perfusion imaging was also compared with the HDI-derived perfusion fraction. RESULTS: The conventional apparent diffusion coefficient did not identify differences between WHO II and III tumor groups. HDI-derived slow hindered diffusion fraction was significantly elevated in the WHO III group as compared with the WHO II group. There was a non-significantly increasing trend of HDI-derived tumor cellularity fraction in the WHO III group, and both HDI-derived perfusion fraction and DSC-derived CBV were found to be significantly higher in the WHO III group. Both HDI-derived perfusion fraction and slow hindered diffusion fraction strongly correlated with DSC-derived CBV. Neither HDI-derived cellularity fraction nor HDI-derived fast hindered diffusion fraction correlated with DSC-derived CBV. CONCLUSIONS: Conventional apparent diffusion coefficient, which measures averaged pathology properties of brain tumors, has compromised accuracy and specificity. HDI holds great promise to accurately separate and quantify the tumor cell fraction, the tumor cell packing density, edema, and capillary blood perfusion, thereby leading to an improved microenvironment characterization of primary brain tumors. Larger studies will further establish HDI's clinical value and use for facilitating biopsy planning, treatment evaluation, and noninvasive tumor grading.

Integration of resting state functional MRI into clinical practice - A large single institution experience.

Functional magnetic resonance imaging (fMRI) is an important tool for pre-surgical evaluation of eloquent cortex. Classic task-based paradigms require patient participation and individual imaging sequence acquisitions for each functional domain that is being assessed. Resting state fMRI (rs-fMRI), however, enables functional localization without patient participation and can evaluate numerous functional domains with a single imaging session. To date, post-processing of this resting state data has been resource intensive, which limits its widespread application for routine clinical use. Through a novel automated algorithm and advanced imaging IT structure, we report the clinical application and the large-scale integration of rs-fMRI into routine neurosurgical practice. One hundred and ninety one consecutive patients underwent a 3T rs-fMRI, 83 of whom also underwent both motor and language task-based fMRI. Data were processed using a novel, automated, multi-layer perceptron algorithm and integrated into stereotactic navigation using a streamlined IT imaging pipeline. One hundred eighty-five studies were performed for intracranial neoplasm, 14 for refractory epilepsy and 33 for vascular malformations or other neurological disorders. Failure rate of rs-fMRI of 13% was significantly better than that for task-based fMRI (38.5%,) (p <0.001). In conclusion, at Washington University in St. Louis, rs-fMRI has become an integral part of standard imaging for neurosurgical planning. Resting state fMRI can be used in all patients, and due to its lower failure rate than task-based fMRI, it is useful for patients who are unable to cooperate with task-based studies.

Resting-state Functional Magnetic Resonance Imaging in Presurgical Functional Mapping: Sensorimotor Localization.

This article compares resting-state functional magnetic resonance (fMR) imaging with task fMR imaging for presurgical functional mapping of the sensorimotor (SM) region. Before tumor resection, 38 patients were scanned using both methods. The SM area was anatomically defined using 2 different software tools. Overlap of anatomic regions of interest with task activation maps and resting-state networks was measured in the SM region. A paired t-test showed higher overlap between resting-state maps and anatomic references compared with task activation when using a maximal overlap criterion. Resting state-derived maps are more comprehensive than those derived from task fMR imaging.

Heterogeneous Optimization Framework: Reproducible Preprocessing of Multi-Spectral Clinical MRI for Neuro-Oncology Imaging Research.

Neuroimaging research often relies on clinically acquired magnetic resonance imaging (MRI) datasets that can originate from multiple institutions. Such datasets are characterized by high heterogeneity of modalities and variability of sequence parameters. This heterogeneity complicates the automation of image processing tasks such as spatial co-registration and physiological or functional image analysis. Given this heterogeneity, conventional processing workflows developed for research purposes are not optimal for clinical data. In this work, we describe an approach called Heterogeneous Optimization Framework (HOF) for developing image analysis pipelines that can handle the high degree of clinical data non-uniformity. HOF provides a set of guidelines for configuration, algorithm development, deployment, interpretation of results and quality control for such pipelines. At each step, we illustrate the HOF approach using the implementation of an automated pipeline for Multimodal Glioma Analysis (MGA) as an example. The MGA pipeline computes tissue diffusion characteristics of diffusion tensor imaging (DTI) acquisitions, hemodynamic characteristics using a perfusion model of susceptibility contrast (DSC) MRI, and spatial cross-modal co-registration of available anatomical, physiological and derived patient images. Developing MGA within HOF enabled the processing of neuro-oncology MR imaging studies to be fully automated. MGA has been successfully used to analyze over 160 clinical tumor studies to date within several research projects. Introduction of the MGA pipeline improved image processing throughput and, most importantly, effectively produced co-registered datasets that were suitable for advanced analysis despite high heterogeneity in acquisition protocols.

Comparison of perfusion- and diffusion-weighted imaging parameters in brain tumor studies processed using different software platforms.

RATIONALE AND OBJECTIVES: To compare quantitative imaging parameter measures from diffusion- and perfusion-weighted imaging magnetic resonance imaging (MRI) sequences in subjects with brain tumors that have been processed with different software platforms. MATERIALS AND METHODS: Scans from 20 subjects with primary brain tumors were selected from the Comprehensive Neuro-oncology Data Repository at Washington University School of Medicine (WUSM) and the Swedish Neuroscience Institute. MR images were coregistered, and each subject's data set was processed by three software packages: 1) vendor-specific scanner software, 2) research software developed at WUSM, and 3) a commercially available, Food and Drug Administration-approved, processing platform (Nordic Ice). Regions of interest (ROIs) were chosen within the brain tumor and normal nontumor tissue. The results obtained using these methods were compared. RESULTS: For diffusion parameters, including mean diffusivity and fractional anisotropy, concordance was high when comparing different processing methods. For perfusion-imaging parameters, a significant variance in cerebral blood volume, cerebral blood flow, and mean transit time (MTT) values was seen when comparing the same raw data processed using different software platforms. Correlation was better with larger ROIs (radii ≥ 5 mm). Greatest variance was observed in MTT. CONCLUSIONS: Diffusion parameter values were consistent across different software processing platforms. Perfusion parameter values were more variable and were influenced by the software used. Variation in the MTT was especially large suggesting that MTT estimation may be unreliable in tumor tissues using current MRI perfusion methods.

The comprehensive neuro-oncology data repository (CONDR): a research infrastructure to develop and validate imaging biomarkers.

BACKGROUND: Advanced imaging methods have the potential to serve as quantitative biomarkers in neuro-oncology research. However, a lack of standardization of image acquisition, processing, and analysis limits their application in clinical research. Standardization of these methods and an organized archival platform are required to better validate and apply these markers in research settings and, ultimately, in clinical practice. OBJECTIVE: The primary objective of the Comprehensive Neuro-oncology Data Repository (CONDR) is to develop a data set for assessing and validating advanced imaging methods in patients diagnosed with brain tumors. As a secondary objective, informatics resources will be developed to facilitate the integrated collection, processing, and analysis of imaging, tissue, and clinical data in multicenter clinical trials. Finally, CONDR data and informatics resources will be shared with the research community for further analysis. METHODS: CONDR will enroll 200 patients diagnosed with primary brain tumors. Clinical, imaging, and tissue-based data are obtained from patients serially, beginning with diagnosis and continuing over the course of their treatment. The CONDR imaging protocol includes structural and functional sequences, including diffusion- and perfusion-weighted imaging. All data are managed within an XNAT-based informatics platform. Imaging markers are assessed by correlating image and spatially aligned pathological markers and a variety of clinical markers. EXPECTED OUTCOMES: CONDR will generate data for developing and validating imaging markers of primary brain tumors, including multispectral and probabilistic maps. DISCUSSION: CONDR implements a novel, open-research model that will provide the research community with both open-access data and open-source informatics resources.

Predicting a multi-parametric probability map of active tumor extent using random forests.

Glioblastoma Mulitforme is highly infiltrative, making precise delineation of tumor margin difficult. Multimodality or multi-parametric MR imaging sequences promise an advantage over anatomic sequences such as post contrast enhancement as methods for determining the spatial extent of tumor involvement. In considering multi-parametric imaging sequences however, manual image segmentation and classification is time-consuming and prone to error. As a preliminary step toward integration of multi-parametric imaging into clinical assessments of primary brain tumors, we propose a machine-learning based multi-parametric approach that uses radiologist generated labels to train a classifier that is able to classify tissue on a voxel-wise basis and automatically generate a tumor segmentation. A random forests classifier was trained using a leave-one-out experimental paradigm. A simple linear classifier was also trained for comparison. The random forests classifier accurately predicted radiologist generated segmentations and tumor extent.