Martin Rozycki

Advancing The Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features

Gliomas belong to a group of central nervous system tumors, and consist of various sub-regions. Gold standard labeling of these sub-regions in radiographic imaging is essential for both clinical and computational studies, including radiomic and radiogenomic analyses. Towards this end, we release segmentation labels and radiomic features for all pre-operative multimodal magnetic resonance imaging (MRI) (n=243) of the multi-institutional glioma collections of The Cancer Genome Atlas (TCGA), publicly available in The Cancer Imaging Archive (TCIA). Pre-operative scans were identified in both glioblastoma (TCGA-GBM, n=135) and low-grade-glioma (TCGA-LGG, n=108) collections via radiological assessment. The glioma sub-region labels were produced by an automated state-of-the-art method and manually revised by an expert board-certified neuroradiologist. An extensive panel of radiomic features was extracted based on the manually-revised labels. This set of labels and features should enable i) direct utilization of the TCGA/TCIA glioma collections towards repeatable, reproducible and comparative quantitative studies leading to new predictive, prognostic, and diagnostic assessments, as well as ii) performance evaluation of computer-aided segmentation methods, and comparison to our state-of-the-art method.

Memory, executive, and multidomain subtle cognitive impairment: Clinical and biomarker findings

Objective: We studied the biomarker signatures and prognoses of 3 different subtle cognitive impairment (SCI) groups (executive, memory, and multidomain) as well as the subjective memory complaints (SMC) group. Methods: We studied 522 healthy controls in the Alzheimers Disease Neuroimaging Initiative (ADNI). Cutoffs for executive, memory, and multidomain SCI were defined using participants who remained cognitively normal (CN) for 7 years. CSF Alzheimer disease (AD) biomarkers, composite and region-of-interest (ROI) MRI, and fluorodeoxyglucose-PET measures were compared in these participants. Results: Using a stringent cutoff (fifth percentile), 27.6% of the ADNI participants were classified as SCI. Most single ROI or global-based measures were not sensitive to detect differences between groups. Only MRI-SPARE-AD (Spatial Pattern of Abnormalities for Recognition of Early AD), a quantitative MRI pattern-based global index, showed differences between all groups, excluding the executive SCI group. Atrophy patterns differed in memory SCI and SMC. The CN and the SMC groups presented a similar distribution of preclinical dementia stages. Fifty percent of the participants with executive, memory, and multidomain SCI progressed to mild cognitive impairment or dementia at 7, 5, and 2 years, respectively. Conclusions: Our results indicate that (1) the different SCI categories have different clinical prognoses and biomarker signatures, (2) longitudinally followed CN subjects are needed to establish clinical cutoffs, (3) subjects with SMC show a frontal pattern of brain atrophy, and (4) pattern-based analyses outperform commonly used single ROI-based neuroimaging biomarkers and are needed to detect initial stages of cognitive impairment.

GLISTRboost: Combining Multimodal MRI Segmentation, Registration, and Biophysical Tumor Growth Modeling with Gradient Boosting Machines for Glioma Segmentation

We present an approach for segmenting low- and high-grade gliomas in multimodal magnetic resonance imaging volumes. The proposed approach is based on a hybrid generative-discriminative model. Firstly, a generative approach based on an Expectation-Maximization framework that incorporates a glioma growth model is used to segment the brain scans into tumor, as well as healthy tissue labels. Secondly, a gradient boosting multi-class classification scheme is used to refine tumor labels based on information from multiple patients. Lastly, a probabilistic Bayesian strategy is employed to further refine and finalize the tumor segmentation based on patient-specific intensity statistics from the multiple modalities. We evaluated our approach in 186 cases during the training phase of the BRAin Tumor Segmentation (BRATS) 2015 challenge and report promising results. During the testing phase, the algorithm was additionally evaluated in 53 unseen cases, achieving the best performance among the competing methods.

Multisite Machine Learning Analysis Provides a Robust Structural Imaging Signature of Schizophrenia Detectable Across Diverse Patient Populations and Within Individuals

Past work on relatively small, single-site studies using regional volumetry, and more recently machine learning methods, has shown that widespread structural brain abnormalities are prominent in schizophrenia. However, to be clinically useful, structural imaging biomarkers must integrate high-dimensional data and provide reproducible results across clinical populations and on an individual person basis. Using advanced multi-variate analysis tools and pooled data from case-control imaging studies conducted at 5 sites (941 adult participants, including 440 patients with schizophrenia), a neuroanatomical signature of patients with schizophrenia was found, and its robustness and reproducibility across sites, populations, and scanners, was established for single-patient classification. Analyses were conducted at multiple scales, including regional volumes, voxelwise measures, and complex distributed patterns. Single-subject classification was tested for single-site, pooled-site, and leave-site-out generalizability. Regional and voxelwise analyses revealed a pattern of widespread reduced regional gray matter volume, particularly in the medial prefrontal, temporolimbic and peri-Sylvian cortex, along with ventricular and pallidum enlargement. Multivariate classification using pooled data achieved a cross-validated prediction accuracy of 76% (AUC = 0.84). Critically, the leave-site-out validation of the detected schizophrenia signature showed accuracy/AUC range of 72-77%/0.73-0.91, suggesting a robust generalizability across sites and patient cohorts. Finally, individualized patient classifications displayed significant correlations with clinical measures of negative, but not positive, symptoms. Taken together, these results emphasize the potential for structural neuroimaging data to provide a robust and reproducible imaging signature of schizophrenia. A web-accessible portal is offered to allow the community to obtain individualized classifications of magnetic resonance imaging scans using the methods described herein.

In vivo detection of EGFRvIII in glioblastoma via perfusion magnetic resonance imaging signature consistent with deep peritumoral infiltration: the φ index

Purpose: The epidermal growth factor receptor variant III (EGFRvIII) mutation has been considered a driver mutation and therapeutic target in glioblastoma, the most common and aggressive brain cancer. Currently, detecting EGFRvIII requires postoperative tissue analyses, which are ex vivo and unable to capture the tumors spatial heterogeneity. Considering the increasing evidence of in vivo imaging signatures capturing molecular characteristics of cancer, this study aims to detect EGFRvIII in primary glioblastoma noninvasively, using routine clinically acquired imaging. Experimental Design: We found peritumoral infiltration and vascularization patterns being related to EGFRvIII status. We therefore constructed a quantitative within-patient peritumoral heterogeneity index (PHI/ϕ-index), by contrasting perfusion patterns of immediate and distant peritumoral edema. Application of ϕ-index in preoperative perfusion scans of independent discovery (n = 64) and validation (n = 78) cohorts, revealed the generalizability of this EGFRvIII imaging signature. Results: Analysis in both cohorts demonstrated that the obtained signature is highly accurate (89.92%), specific (92.35%), and sensitive (83.77%), with significantly distinctive ability (P = 4.0033 × 10−10, AUC = 0.8869). Findings indicated a highly infiltrative-migratory phenotype for EGFRvIII+ tumors, which displayed similar perfusion patterns throughout peritumoral edema. Contrarily, EGFRvIII− tumors displayed perfusion dynamics consistent with peritumorally confined vascularization, suggesting potential benefit from extensive peritumoral resection/radiation. Conclusions: This EGFRvIII signature is potentially suitable for clinical translation, since obtained from analysis of clinically acquired images. Use of within-patient heterogeneity measures, rather than population-based associations, renders ϕ-index potentially resistant to inter-scanner variations. Overall, our findings enable noninvasive evaluation of EGFRvIII for patient selection for targeted therapy, stratification into clinical trials, personalized treatment planning, and potentially treatment-response evaluation. Clin Cancer Res; 23(16); 4724–34. ©2017 AACR.

Segmentation of gliomas in pre-operative and post-operative multimodal magnetic resonance imaging volumes based on a hybrid generative-discriminative framework

We present an approach for segmenting both low- and high-grade gliomas in multimodal magnetic resonance imaging volumes. The proposed framework is an extension of our previous work [6,7], with an additional component for segmenting post-operative scans. The proposed approach is based on a hybrid generative-discriminative model. Firstly, a generative model based on a joint segmentation-registration framework is used to segment the brain scans into cancerous and healthy tissues. Secondly, a gradient boosting classification scheme is used to refine tumor segmentation based on information from multiple patients. We evaluated our approach in 218 cases during the training phase of the BRAin Tumor Segmentation (BRATS) 2016 challenge and report promising results. During the testing phase, the proposed approach was ranked among the top performing methods, after being additionally evaluated in 191 unseen cases.

Correlations of atrial diameter and frontooccipital horn ratio with ventricle size in fetal ventriculomegaly

OBJECTIVE Fetal ventriculomegaly (FV), or enlarged cerebral ventricles in utero, is defined in fetal studies as an atrial diameter (AD) greater than 10 mm. In postnatal studies, the frontooccipital horn ratio (FOHR) is commonly used as a proxy for ventricle size (VS); however, its role in FV has not been assessed. Using image analysis techniques to quantify VS on fetal MR images, authors of the present study examined correlations between linear measures (AD and FOHR) and VS in patients with FV. METHODS The authors performed a cross-sectional study using fetal MR images to measure AD in the axial plane at the level of the atria of the lateral ventricles and to calculate FOHR as the average of the frontal and occipital horn diameters divided by the biparietal distance. Computer software was used to separately segment and measure the area of the ventricle and the ventricle plus the subarachnoid space in 2 dimensions. Segmentation was performed on axial slices 3 above and 3 below the slice used to measure AD, and measurements for each slice were combined to yield a volume, or 3D VS. The VS was expressed as the absolute number of voxels (non-normalized) and as the number of voxels divided by intracranial size (normalized). A Pearson correlation coefficient was used to measure the strength of the relationships between the linear measures and the size of segmented regions in 2 and 3 dimensions and over various gestational ages (GAs). Differences between correlations were compared using Steigers z-test. RESULTS Fifty FV patients who had undergone fetal MRI between 2008 and 2014 were included in the study. The mean GA was 26.3 ± 5.4 weeks. The mean AD was 18.1 ± 8.3 mm, and the mean FOHR was 0.49 ± 0.11. When using absolute VS, the correlation between AD and 3D VS (r = 0.844, p < 0.0001) was significantly higher than that between FOHR and 3D VS (r = 0.668, p < 0.0001; p = 0.0004, Steigers z-test). However, when VS was normalized, correlations were not significantly different between AD and 3D VS (r = 0.830, p < 0.0001) or FOHR and 3D VS (r = 0.842, p < 0.0001; p = 0.8, Steigers z-test). For GAs of 24 weeks or earlier, AD correlated more strongly with normalized 3D VS (r = 0.902, p < 0.0001) than with FOHR (r = 0.674, p < 0.0001; p < 0.0001, Steigers z-test). After 24 weeks, there was no difference in correlations between linear measures (AD or FOHR) and 3D VS (r > 0.9). Correlations of linear measures with VS in 2 and 3 dimensions were similar, and inclusion of the subarachnoid space did not significantly alter results. CONCLUSIONS Findings in the study support the use of AD as a measure of VS in fetal studies as it correlates highly with both absolute and relative VS, especially at early GAs, and captures the preferential dilation of the occipital horns in patients with FV. Compared with AD, FOHR similarly correlates with normalized VS and, after a GA of 24 weeks, can be reported in fetal studies to provide continuity with postnatal monitoring.

Use of Fetal Magnetic Resonance Image Analysis and Machine Learning to Predict the Need for Postnatal Cerebrospinal Fluid Diversion in Fetal Ventriculomegaly

Importance Which children with fetal ventriculomegaly, or enlargement of the cerebral ventricles in utero, will develop hydrocephalus requiring treatment after birth is unclear. Objective To determine whether extraction of multiple imaging features from fetal magnetic resonance imaging (MRI) and integration using machine learning techniques can predict which patients require postnatal cerebrospinal fluid (CSF) diversion after birth. Design, Setting, and Patients This retrospective case-control study used an institutional database of 253 patients with fetal ventriculomegaly from January 1, 2008, through December 31, 2014, to generate a predictive model. Data were analyzed from January 1, 2008, through December 31, 2015. All 25 patients who required postnatal CSF diversion were selected and matched by gestational age with 25 patients with fetal ventriculomegaly who did not require CSF diversion (discovery cohort). The model was applied to a sample of 24 consecutive patients with fetal ventriculomegaly who underwent evaluation at a separate institution (replication cohort) from January 1, 1998, through December 31, 2007. Data were analyzed from January 1, 1998, through December 31, 2009. Exposures To generate the model, linear measurements, area, volume, and morphologic features were extracted from the fetal MRI, and a machine learning algorithm analyzed multiple features simultaneously to find the combination that was most predictive of the need for postnatal CSF diversion. Main Outcomes and Measures Accuracy, sensitivity, and specificity of the model in correctly classifying patients requiring postnatal CSF diversion. Results A total of 74 patients (41 girls [55%] and 33 boys [45%]; mean [SD] gestational age, 27.0 [5.6] months) were included from both cohorts. In the discovery cohort, median time to CSF diversion was 6 days (interquartile range [IQR], 2-51 days), and patients with fetal ventriculomegaly who did not develop symptoms were followed up for a median of 29 months (IQR, 9-46 months). The model correctly classified patients who required CSF diversion with 82% accuracy, 80% sensitivity, and 84% specificity. In the replication cohort, the model achieved 91% accuracy, 75% sensitivity, and 95% specificity. Conclusion and Relevance Image analysis and machine learning can be applied to fetal MRI findings to predict the need for postnatal CSF diversion. The model provides prognostic information that may guide clinical management and select candidates for potential fetal surgical intervention.

Radiomic MRI signature reveals three distinct subtypes of glioblastoma with different clinical and molecular characteristics, offering prognostic value beyond IDH1

The remarkable heterogeneity of glioblastoma, across patients and over time, is one of the main challenges in precision diagnostics and treatment planning. Non-invasive in vivo characterization of this heterogeneity using imaging could assist in understanding disease subtypes, as well as in risk-stratification and treatment planning of glioblastoma. The current study leveraged advanced imaging analytics and radiomic approaches applied to multi-parametric MRI of de novo glioblastoma patients (n = 208 discovery, n = 53 replication), and discovered three distinct and reproducible imaging subtypes of glioblastoma, with differential clinical outcome and underlying molecular characteristics, including isocitrate dehydrogenase-1 (IDH1), O6-methylguanine–DNA methyltransferase, epidermal growth factor receptor variant III (EGFRvIII), and transcriptomic subtype composition. The subtypes provided risk-stratification substantially beyond that provided by WHO classifications. Within IDH1-wildtype tumors, our subtypes revealed different survival (p < 0.001), thereby highlighting the synergistic consideration of molecular and imaging measures for prognostication. Moreover, the imaging characteristics suggest that subtype-specific treatment of peritumoral infiltrated brain tissue might be more effective than current uniform standard-of-care. Finally, our analysis found subtype-specific radiogenomic signatures of EGFRvIII-mutated tumors. The identified subtypes and their clinical and molecular correlates provide an in vivo portrait of phenotypic heterogeneity in glioblastoma, which points to the need for precision diagnostics and personalized treatment.

In vivo evaluation of EGFRvIII mutation in primary glioblastoma patients via complex multiparametric MRI signature

Background Epidermal growth factor receptor variant III (EGFRvIII) is a driver mutation and potential therapeutic target in glioblastoma. Non-invasive in vivo EGFRvIII determination, using clinically acquired multiparametric MRI sequences, could assist in assessing spatial heterogeneity related to EGFRvIII, currently not captured via single-specimen analyses. We hypothesize that integration of subtle, yet distinctive, quantitative imaging/radiomic patterns using machine learning may lead to non-invasively determining molecular characteristics, and particularly the EGFRvIII mutation. Methods We integrated diverse imaging features, including the tumors spatial distribution pattern, via support vector machines, to construct an imaging signature of EGFRvIII. This signature was evaluated in independent discovery (n = 75) and replication (n = 54) cohorts of de novo glioblastoma, and compared with the EGFRvIII status obtained through an assay based on next-generation sequencing. Results The cross-validated accuracy of the EGFRvIII signature in classifying the mutation status in individual patients of the independent discovery and replication cohorts was 85.3% (specificity = 86.3%, sensitivity = 83.3%, area under the curve [AUC] = 0.85) and 87% (specificity = 90%, sensitivity = 78.6%, AUC = 0.86), respectively. The signature was consistent with EGFRvIII+ tumors having increased neovascularization and cell density, as well as a distinctive spatial pattern involving relatively more frontal and parietal regions compared with EGFRvIII- tumors. Conclusions An imaging signature of EGFRvIII was found, revealing a complex, yet distinct macroscopic glioblastoma phenotype. By non-invasively capturing the tumor in its entirety, the proposed methodology can assist in evaluating the tumors spatial heterogeneity, hence overcoming common spatial sampling limitations of tissue-based analyses. This signature can preoperatively stratify patients for EGFRvIII-targeted therapies, and potentially monitor dynamic mutational changes during treatment.