Showing papers by "Kristin R. Swanson published in 2020"

Progress and Opportunities to Advance Clinical Cancer Therapeutics Using Tumor Dynamic Models.

Abstract: There is a need for new approaches and endpoints in oncology drug development, particularly with the advent of immunotherapies and the multiple drug combinations under investigation. Tumor dynamics modeling, a key component to oncology "model-informed drug development," has shown a growing number of applications and a broader adoption by drug developers and regulatory agencies in the past years to support drug development and approval in a variety of ways. Tumor dynamics modeling is also being investigated in personalized cancer therapy approaches. These models and applications are reviewed and discussed, as well as the limitations and issues open for further investigations. A close collaboration between stakeholders like clinical investigators, statisticians, and pharmacometricians is warranted to advance clinical cancer therapeutics.

From cells to tissue: How cell scale heterogeneity impacts glioblastoma growth and treatment response

Abstract: Glioblastomas are aggressive primary brain tumors known for their inter- and intratumor heterogeneity. This disease is uniformly fatal, with intratumor heterogeneity the major reason for treatment failure and recurrence. Just like the nature vs nurture debate, heterogeneity can arise from intrinsic or environmental influences. Whilst it is impossible to clinically separate observed behavior of cells from their environmental context, using a mathematical framework combined with multiscale data gives us insight into the relative roles of variation from different sources. To better understand the implications of intratumor heterogeneity on therapeutic outcomes, we created a hybrid agent-based mathematical model that captures both the overall tumor kinetics and the individual cellular behavior. We track single cells as agents, cell density on a coarser scale, and growth factor diffusion and dynamics on a finer scale over time and space. Our model parameters were fit utilizing serial MRI imaging and cell tracking data from ex vivo tissue slices acquired from a growth-factor driven glioblastoma murine model. When fitting our model to serial imaging only, there was a spectrum of equally-good parameter fits corresponding to a wide range of phenotypic behaviors. When fitting our model using imaging and cell scale data, we determined that environmental heterogeneity alone is insufficient to match the single cell data, and intrinsic heterogeneity is required to fully capture the migration behavior. The wide spectrum of in silico tumors also had a wide variety of responses to an application of an anti-proliferative treatment. Recurrent tumors were generally less proliferative than pre-treatment tumors as measured via the model simulations and validated from human GBM patient histology. Further, we found that all tumors continued to grow with an anti-migratory treatment alone, but the anti-proliferative/anti-migratory combination generally showed improvement over an anti-proliferative treatment alone. Together our results emphasize the need to better understand the underlying phenotypes and tumor heterogeneity present in a tumor when designing therapeutic regimens.

A Deep Convolutional Neural Network for Annotation of Magnetic Resonance Imaging Sequence Type

Abstract: The explosion of medical imaging data along with the advent of big data analytics has launched an exciting era for clinical research. One factor affecting the ability to aggregate large medical image collections for research is the lack of infrastructure for automated data annotation. Among all imaging modalities, annotation of magnetic resonance (MR) images is particularly challenging due to the non-standard labeling of MR image types. In this work, we aimed to train a deep neural network to annotate MR image sequence type for scans of brain tumor patients. We focused on the four most common MR sequence types within neuroimaging: T1-weighted (T1W), T1-weighted post-gadolinium contrast (T1Gd), T2-weighted (T2W), and T2-weighted fluid-attenuated inversion recovery (FLAIR). Our repository contains images acquired using a variety of pulse sequences, sequence parameters, field strengths, and scanner manufacturers. Image selection was agnostic to patient demographics, diagnosis, and the presence of tumor in the imaging field of view. We used a total of 14,400 two-dimensional images, each visualizing a different part of the brain. Data was split into train, validation, and test sets (9600, 2400, and 2400 images, respectively) and sets consisted of equal-sized groups of image types. Overall, the model reached an accuracy of 99% on the test set. Our results showed excellent performance of deep learning techniques in predicting sequence types for brain tumor MR images. We conclude deep learning models can serve as tools to support clinical research and facilitate efficient database management.

Performance of Standardized Relative CBV for Quantifying Regional Histologic Tumor Burden in Recurrent High-Grade Glioma: Comparison against Normalized Relative CBV Using Image-Localized Stereotactic Biopsies

Abstract: BACKGROUND AND PURPOSE: Perfusion MR imaging measures of relative CBV can distinguish recurrent tumor from posttreatment radiation effects in high-grade gliomas. Currently, relative CBV measurement requires normalization based on user-defined reference tissues. A recently proposed method of relative CBV standardization eliminates the need for user input. This study compares the predictive performance of relative CBV standardization against relative CBV normalization for quantifying recurrent tumor burden in high-grade gliomas relative to posttreatment radiation effects. MATERIALS AND METHODS: We recruited 38 previously treated patients with high-grade gliomas (World Health Organization grades III or IV) undergoing surgical re-resection for new contrast-enhancing lesions concerning for recurrent tumor versus posttreatment radiation effects. We recovered 112 image-localized biopsies and quantified the percentage of histologic tumor content versus posttreatment radiation effects for each sample. We measured spatially matched normalized and standardized relative CBV metrics (mean, median) and fractional tumor burden for each biopsy. We compared relative CBV performance to predict tumor content, including the Pearson correlation (r), against histologic tumor content (0%–100%) and the receiver operating characteristic area under the curve for predicting high-versus-low tumor content using binary histologic cutoffs (≥50%; ≥80% tumor). RESULTS: Across relative CBV metrics, fractional tumor burden showed the highest correlations with tumor content (0%–100%) for normalized (r = 0.63, P CONCLUSIONS: Standardization of relative CBV achieves similar performance compared with normalized relative CBV and offers an important step toward workflow optimization and consensus methodology.

Sex-specific impact of patterns of imageable tumor growth on survival of primary glioblastoma patients

Abstract: Sex is recognized as a significant determinant of outcome among glioblastoma patients, but the relative prognostic importance of glioblastoma features has not been thoroughly explored for sex differences. Combining multi-modal MR images, biomathematical models, and patient clinical information, this investigation assesses which pretreatment variables have a sex-specific impact on the survival of glioblastoma patients (299 males and 195 females). Among males, tumor (T1Gd) radius was a predictor of overall survival (HR = 1.027, p = 0.044). Among females, higher tumor cell net invasion rate was a significant detriment to overall survival (HR = 1.011, p < 0.001). Female extreme survivors had significantly smaller tumors (T1Gd) (p = 0.010 t-test), but tumor size was not correlated with female overall survival (p = 0.955 CPH). Both male and female extreme survivors had significantly lower tumor cell net proliferation rates than other patients (M p = 0.004, F p = 0.001, t-test). Despite similar distributions of the MR imaging parameters between males and females, there was a sex-specific difference in how these parameters related to outcomes.

Image-based metric of invasiveness predicts response to adjuvant temozolomide for primary glioblastoma.

Abstract: Background Temozolomide (TMZ) has been the standard-of-care chemotherapy for glioblastoma (GBM) patients for more than a decade. Despite this long time in use, significant questions remain regarding how best to optimize TMZ therapy for individual patients. Understanding the relationship between TMZ response and factors such as number of adjuvant TMZ cycles, patient age, patient sex, and image–based tumor features, might help predict which GBM patients would benefit most from TMZ, particularly for those whose tumors lack O6–methylguanine–DNA methyltransferase (MGMT) promoter methylation. Methods and findings Using a cohort of 90 newly–diagnosed GBM patients treated according to the standard of care, we examined the relationships between several patient and tumor characteristics and volumetric and survival outcomes during adjuvant chemotherapy. Volumetric changes in MR imaging abnormalities during adjuvant therapy were used to assess TMZ response. T1Gd volumetric response is associated with younger patient age, increased number of TMZ cycles, longer time to nadir volume, and decreased tumor invasiveness. Moreover, increased adjuvant TMZ cycles corresponded with improved volumetric response only among more nodular tumors, and this volumetric response was associated with improved survival outcomes. Finally, in a subcohort of patients with known MGMT methylation status, methylated tumors were more diffusely invasive than unmethylated tumors, suggesting the improved response in nodular tumors is not driven by a preponderance of MGMT methylated tumors. Conclusions Our finding that less diffusely invasive tumors are associated with greater volumetric response to TMZ suggests patients with these tumors may benefit from additional adjuvant TMZ cycles, even for those without MGMT methylation.

Deep neural network to locate and segment brain tumors outperformed the expert technicians who created the training data

Abstract: Purpose: Deep learning (DL) algorithms have shown promising results for brain tumor segmentation in MRI. However, validation is required prior to routine clinical use. We report the first randomized and blinded comparison of DL and trained technician segmentations. Approach: We compiled a multi-institutional database of 741 pretreatment MRI exams. Each contained a postcontrast T1-weighted exam, a T2-weighted fluid-attenuated inversion recovery exam, and at least one technician-derived tumor segmentation. The database included 729 unique patients (470 males and 259 females). Of these exams, 641 were used for training the DL system, and 100 were reserved for testing. We developed a platform to enable qualitative, blinded, controlled assessment of lesion segmentations made by technicians and the DL method. On this platform, 20 neuroradiologists performed 400 side-by-side comparisons of segmentations on 100 test cases. They scored each segmentation between 0 (poor) and 10 (perfect). Agreement between segmentations from technicians and the DL method was also evaluated quantitatively using the Dice coefficient, which produces values between 0 (no overlap) and 1 (perfect overlap). Results: The neuroradiologists gave technician and DL segmentations mean scores of 6.97 and 7.31, respectively (p < 0.00007). The DL method achieved a mean Dice coefficient of 0.87 on the test cases. Conclusions: This was the first objective comparison of automated and human segmentation using a blinded controlled assessment study. Our DL system learned to outperform its “human teachers” and produced output that was better, on average, than its training data.

Assessment of Prognostic Value of Cystic Features in Glioblastoma Relative to Sex and Treatment With Standard-of-Care.

Abstract: Glioblastoma (GBM) is the most aggressive primary brain tumor and can have cystic components, identifiable through magnetic resonance imaging (MRI). Previous studies suggest that cysts occur in 7-23% of GBMs and report mixed results regarding their prognostic impact. Using our retrospective cohort of 493 patients with first-diagnosis GBM, we carried out an exploratory analysis on this potential link between cystic GBM and survival. Using pretreatment MRIs, we manually identified 88 patients with GBM that had a significant cystic component at presentation and 405 patients that did not. Patients with cystic GBM had significantly longer overall survival and were significantly younger at presentation. Within patients who received the current standard of care (SOC) (N = 184, 40 cystic), we did not observe a survival benefit of cystic GBM. Unexpectedly, we did not observe a significant survival benefit between this SOC cystic cohort and patients with cystic GBM diagnosed before the standard was established (N = 40 with SOC, N = 19 without SOC); this significant SOC benefit was clearly observed in patients with noncystic GBM (N = 144 with SOC, N = 111 without SOC). When stratified by sex, the survival benefit of cystic GBM was only preserved in male patients (N = 303, 47 cystic). We report differences in the absolute and relative sizes of imaging abnormalities on MRI and the prognostic implication of cysts based on sex. We discuss hypotheses for these differences, including the possibility that the presence of a cyst could indicate a less aggressive tumor.

Quantifying Glioblastoma Drug Response Dynamics Incorporating Treatment Sensitivity and Blood Brain Barrier Penetrance From Experimental Data.

Abstract: Many drugs investigated for the treatment of glioblastoma (GBM) have had disappointing clinical trial results. Efficacy of these agents is dependent on adequate delivery to sensitive tumor cell populations, which is limited by the blood-brain barrier (BBB). Additionally, tumor heterogeneity can lead to subpopulations of cells with different sensitivities to anti-cancer drugs, further impacting therapeutic efficacy. Thus, it may be important to evaluate the extent to which BBB limitations and heterogeneous sensitivity each contribute to a drug's failure. To address this challenge, we developed a minimal mathematical model to characterize these elements of overall drug response, informed by time-series bioluminescence imaging data from a treated patient-derived xenograft (PDX) experimental model. By fitting this mathematical model to a preliminary dataset in a series of nonlinear regression steps, we estimated parameter values for individual PDX subjects that correspond to the dynamics seen in experimental data. Using these estimates as a guide for parameter ranges, we ran model simulations and performed a parameter sensitivity analysis using Latin hypercube sampling and partial rank correlation coefficients. Results from this analysis combined with simulations suggest that BBB permeability may play a slightly greater role in therapeutic efficacy than relative drug sensitivity. Additionally, we discuss recommendations for future experiments based on insights gained from this model. Further research in this area will be vital for improving the development of effective new therapies for glioblastoma patients.

Robust Automatic Whole Brain Extraction on Magnetic Resonance Imaging of Brain Tumor Patients using Dense-Vnet.

Abstract: Whole brain extraction, also known as skull stripping, is a process in neuroimaging in which non-brain tissue such as skull, eyeballs, skin, etc. are removed from neuroimages. Skull striping is a preliminary step in presurgical planning, cortical reconstruction, and automatic tumor segmentation. Despite a plethora of skull stripping approaches in the literature, few are sufficiently accurate for processing pathology-presenting MRIs, especially MRIs with brain tumors. In this work we propose a deep learning approach for skull striping common MRI sequences in oncology such as T1-weighted with gadolinium contrast (T1Gd) and T2-weighted fluid attenuated inversion recovery (FLAIR) in patients with brain tumors. We automatically created gray matter, white matter, and CSF probability masks using SPM12 software and merged the masks into one for a final whole-brain mask for model training. Dice agreement, sensitivity, and specificity of the model (referred herein as DeepBrain) was tested against manual brain masks. To assess data efficiency, we retrained our models using progressively fewer training data examples and calculated average dice scores on the test set for the models trained in each round. Further, we tested our model against MRI of healthy brains from the LBP40A dataset. Overall, DeepBrain yielded an average dice score of 94.5%, sensitivity of 96.4%, and specificity of 98.5% on brain tumor data. For healthy brains, model performance improved to a dice score of 96.2%, sensitivity of 96.6% and specificity of 99.2%. The data efficiency experiment showed that, for this specific task, comparable levels of accuracy could have been achieved with as few as 50 training samples. In conclusion, this study demonstrated that a deep learning model trained on minimally processed automatically-generated labels can generate more accurate brain masks on MRI of brain tumor patients within seconds.

Identifying the spatial and temporal dynamics of molecularly-distinct glioblastoma sub-populations.

Abstract: Glioblastomas (GBMs) are the most aggressive primary brain tumours and have no known cure. Each individual tumour comprises multiple sub-populations of genetically-distinct cells that may respond differently to targeted therapies and may contribute to disappointing clinical trial results. Image-localized biopsy techniques allow multiple biopsies to be taken during surgery and provide information that identifies regions where particular sub-populations occur within an individual GBM, thus providing insight into their regional genetic variability. These sub-populations may also interact with one another in a competitive or cooperative manner; it is important to ascertain the nature of these interactions, as they may have implications for responses to targeted therapies. We combine genetic information from biopsies with a mechanistic model of interacting GBM sub-populations to characterise the nature of interactions between two commonly occurring GBM sub-populations, those with EGFR and PDGFRA genes amplified. We study population levels found across image-localized biopsy data from a cohort of 25 patients and compare this to model outputs under competitive, cooperative and neutral interaction assumptions. We explore other factors affecting the observed simulated sub-populations, such as selection advantages and phylogenetic ordering of mutations, which may also contribute to the levels of EGFR and PDGFRA amplified populations observed in biopsy data.

Does location matter? Characterisation of the anatomic locations, molecular profiles, and clinical features of gliomas.

Abstract: Background. Neuroanatomic locations of gliomas may influence clinical presentations, molecular profiles, and patients’ prognoses. Methods. We investigated our institutional cancer registry to include patients with glioma over a 10-year period. Statistical tests were used to compare demographic, genetic, and clinical characteristics among patients with gliomas in different locations. Survival analysis methods were then used to assess associations between location and overall survival in the full cohort, as well as in relevant subgroups. Results. 182 gliomas were identified. Of the tumours confined to a single lobe, there were 51 frontal (28.0%), 50 temporal (27.5%), 22 parietal (12.1%), and seven occipital tumours (3.8%) identified. Tumours affecting the temporal lobe were associated with reduced overall survival when compared to all other tumours (11 months vs. 13 months, log-rank p = 0.0068). In subgroup analyses, this result was significant for males [HR (95%CI) 2.05 (1.30, 3.24), p = 0.002], but not for females [HR (95%CI) 1.12 (0.65, 1.93), p = 0.691]. Out of 82 cases tested for IDH-1, 10 were mutated (5.5%). IDH-1 mutation was present in six frontal, two temporal, one thalamic, and one multifocal tumour. Out of 21 cases tested for 1p19q deletions, 12 were co-deleted, nine of which were frontal lobe tumours. MGMT methylation was assessed in 45 cases; 7/14 frontal tumours and 6/13 temporal tumours were methylated. Conclusion. Our results support the hypothesis that the anatomical locations of gliomas influence patients’ clinical courses. Temporal lobe tumours were associated with poorer survival, though this association appeared to be driven by these patients’ more aggressive tumour profiles and higher risk baseline demographics. Independently, female patients who had temporal lobe tumours fared better than males. Molecular analysis was limited by the low prevalence of genetic testing in the study sample, highlighting the importance of capturing this information for all gliomas. Importance of this study. The specific neuroanatomic location of tumours in the brain is thought to be predictive of treatment options and overall prognosis. Despite evidence for the clinical significance of this information, there is relatively little information available regarding the incidence and prevalence of tumours in the different anatomical regions of the brain. This study has more fully characterised tumour prevalence in different regions of the brain. Additionally, we have analysed how this information may affect tumours’ molecular characteristics, treatment options offered to patients, and patients’ overall survival. This information will be informative both in the clinical setting and in directing future research.

Assessment of Prognostic Value of Cystic Features in Glioblastoma Relative to Sex and Treatment with Standard-of-Care

Abstract: Glioblastoma (GBM) is the most aggressive primary brain tumor and can have cystic components, identifiable through magnetic resonance imaging (MRI) Previous studies suggest that cysts occur in 7-23% of GBMs and report mixed results regarding their prognostic impact Using our retrospective cohort of 493 patients with first-diagnosis GBM, we carried out an exploratory analysis on this potential link between cystic GBM and survival Using pretreatment MRIs, we manually identified 88 patients with GBM that had a significant cystic component at presentation and 405 patients that did not Patients with cystic GBM had significantly longer overall survival and were significantly younger at presentation Within patients who received the current standard of care (SOC) (N=184, 40 cystic), we did not observe a survival benefit of cystic GBM Unexpectedly, we did not observe a significant survival benefit between this SOC cystic cohort and patients with cystic GBM diagnosed before the standard was established (N=40 with SOC, N=19 without SOC); this significant SOC benefit was clearly observed in patients with noncystic GBM (N=144 with SOC, N=111 without SOC) When stratified by sex, this significant survival benefit was only preserved in male patients (N=303, 47 cystic) We report differences in the absolute and relative sizes of imaging abnormalities on MRI and the prognostic implication of cysts based on sex We discuss hypotheses for these differences, including the possibility that the presence of a cyst could indicate a less aggressive tumor

Identifying the spatial and temporal dynamics of molecularly-distinct glioblastoma sub-populations

Abstract: Glioblastomas (GBMs) are the most aggressive primary brain tumours and have no known cure. Each individual tumour comprises multiple sub-populations of genetically-distinct cells that may respond differently to targeted therapies and may contribute to disappointing clinical trial results. Image-localized biopsy techniques allow multiple biopsies to be taken during surgery and provide information that identifies regions where particular sub-populations occur within an individual GBM, thus providing insight into their regional genetic variability. These sub-populations may also interact with one another through a competitive or cooperative nature; it is important to ascertain the nature of these interactions, as they may have implications for responses to targeted therapies. We combine genetic information from biopsies with a mechanistic model of interacting GBM sub-populations to characterise the nature of interactions between two commonly occurring GBM sub-populations, those with EGFR and PDGFRA genes amplified. We study population levels found across image-localized biopsy data from a cohort of 25 patients and compare this to model outputs under competitive, cooperative and neutral interaction assumptions. We explore other factors affecting the observed simulated sub-populations, such as selection advantages and phylogenetic ordering of mutations, which may also contribute to the levels of EGFR and PDGFRA amplified populations observed in biopsy data.

Learning Equations from Biological Data with Limited Time Samples

Abstract: Equation learning methods present a promising tool to aid scientists in the modeling process for biological data. Previous equation learning studies have demonstrated that these methods can infer models from rich datasets, however, the performance of these methods in the presence of common challenges from biological data has not been thoroughly explored. We present an equation learning methodology comprised of data denoising, equation learning, model selection and post-processing steps that infers a dynamical systems model from noisy spatiotemporal data. The performance of this methodology is thoroughly investigated in the face of several common challenges presented by biological data, namely, sparse data sampling, large noise levels, and heterogeneity between datasets. We find that this methodology can accurately infer the correct underlying equation and predict unobserved system dynamics from a small number of time samples when the data is sampled over a time interval exhibiting both linear and nonlinear dynamics. Our findings suggest that equation learning methods can be used for model discovery and selection in many areas of biology when an informative dataset is used. We focus on glioblastoma multiforme modeling as a case study in this work to highlight how these results are informative for data-driven modeling-based tumor invasion predictions.

Simulated diffusion weighted images based on model-predicted tumor growth

Abstract: Non-invasive magnetic resonance imaging (MRI) is the primary imaging modality for visualizing brain tumor growth and treatment response. While standard MRIs are central to clinical decision making, advanced quantitative imaging sequences like diffusion weighted imaging (DWI) are increasingly relied on. Deciding the best way to interpret DWIs, particularly in the context of treatment, is still an area of intense research. With DWI being indicative of tissue structure, it is important to establish the link between DWI and brain tumor mathematical growth models, which could help researchers and clinicians better understand the tumor’s microenvironmental landscape. Our goal was to demonstrate the potential for creating a DWI patient-specific untreated virtual imaging control (UVICs), which represents an individual tumor’s untreated growth and could be compared with actual patient DWIs. We generated a DWI UVIC by combining a patient-specific mathematical model of tumor growth with a multi-compartmental MRI signal equation. GBM growth was mathematically modeled using the Proliferation-Invasion-Hypoxia-Necrosis-Angiogenesis-Edema (PIHNA-E) model, which simulated tumor as being comprised of multiple cellular phenotypes interacting with vasculature, angiogenic factors, and extracellular fluid. The model’s output consisted of spatial volume fraction maps for each microenvironmental species. The volume fraction maps and corresponding T2 and apparent diffusion coefficient (ADC) values from literature were incorporated into a multi-compartmental signal equation to simulate DWI images. Simulated DWIs were created at multiple b-values and then used to calculate ADC maps. We found that the regional ADC values of simulated tumors were comparable to literature values.

Days gained response discriminates treatment response in patients with recurrent glioblastoma receiving bevacizumab-based therapies.

Abstract: Background Accurate assessments of patient response to therapy are a critical component of personalized medicine. In glioblastoma (GBM), the most aggressive form of brain cancer, tumor growth dynamics are heterogenous across patients, complicating assessment of treatment response. This study aimed to analyze days gained (DG), a burgeoning model-based dynamic metric, for response assessment in patients with recurrent GBM who received bevacizumab-based therapies. Methods DG response scores were calculated using volumetric tumor segmentations for patients receiving bevacizumab with and without concurrent cytotoxic therapy (N = 62). Kaplan-Meier and Cox proportional hazards analyses were implemented to examine DG prognostic relationship to overall (OS) and progression-free survival (PFS) from the onset of treatment for recurrent GBM. Results In patients receiving concurrent bevacizumab and cytotoxic therapy, Kaplan-Meier analysis showed significant differences in OS and PFS at DG cutoffs consistent with previously identified values from newly diagnosed GBM using T1-weighted gadolinium-enhanced magnetic resonance imaging (T1Gd). DG scores for bevacizumab monotherapy patients only approached significance for PFS. Cox regression showed that increases of 25 DG on T1Gd imaging were significantly associated with a 12.5% reduction in OS hazard for concurrent therapy patients and a 4.4% reduction in PFS hazard for bevacizumab monotherapy patients. Conclusion DG has significant meaning in recurrent therapy as a metric of treatment response, even in the context of anti-angiogenic therapies. This provides further evidence supporting the use of DG as an adjunct response metric that quantitatively connects treatment response and clinical outcomes.

Uncertainty Quantification in Radiogenomics: EGFR Amplification in Glioblastoma

Abstract: BACKGROUND Radiogenomics uses machine-learning (ML) to directly connect the morphologic and physiological appearance of tumors on clinical imaging with underlying genomic features. Despite extensive growth in the area of radiogenomics across many cancers, and its potential role in advancing clinical decision making, no published studies have directly addressed uncertainty in these model predictions. METHODS We developed a radiogenomics ML model to quantify uncertainty using transductive Gaussian Processes (GP) and a unique dataset of 95 image-localized biopsies with spatially matched MRI from 25 untreated Glioblastoma (GBM) patients. The model generated predictions for regional EGFR amplification status (a common and important target in GBM) to resolve the intratumoral genetic heterogeneity across each individual tumor - a key factor for future personalized therapeutic paradigms. The model used probability distributions for each sample prediction to quantify uncertainty, and used transductive learning to reduce the overall uncertainty. We compared predictive accuracy and uncertainty of the transductive learning GP model against a standard GP model using leave-one-patient-out cross validation. RESULTS Predictive uncertainty informed the likelihood of achieving an accurate sample prediction. When stratifying predictions based on uncertainty, we observed substantially higher performance in the group cohort (75% accuracy, n=95) and amongst sample predictions with the lowest uncertainty (83% accuracy, n=72) compared to predictions with higher uncertainty (48% accuracy, n=23), due largely to data interpolation (rather than extrapolation). CONCLUSION We present a novel approach to quantify radiogenomics uncertainty to enhance model performance and clinical interpretability. This should help integrate more reliable radiogenomics models for improved medical decision-making.

Methods for Using Machine Learning and Mechanistic Models for Biological Feature Mapping with Multiparametric MRI

Abstract: Described here are systems and methods for generating and implementing a hybrid machine learning and mechanistic model to produce biological feature maps, or other measurements of biological features, based on an input of multiparametric magnetic resonance or other images. The hybrid model can include a combination of a machine learning model and a mechanistic model that takes as an input multiparametric MRI, or other imaging, data to generate biological feature maps (e.g., tumor cell density maps), or other measures or predictions of biological features (e.g., tumor cell density). The hybrid models have capabilities of learning individual-specific relationships between imaging features and biological features.

Technical Note: A digital reference object representing Hoffman's 3D brain phantom for PET scanner simulations.

Abstract: Purpose Physical and digital phantoms play a key role in the development and testing of nuclear medicine instrumentation and processing algorithms for clinical and research applications, including neuroimaging using positron emission tomography (PET). We have developed and tested a digital reference object (DRO) version of the original segmented magnetic resonance imaging (MRI) data used for the three-dimensional (3D) PET brain phantom developed by Hoffman et al., which is used as the basis of a commercially available physical test phantom. Methods The DRO was constructed by subdividing the MRI image planes the original phantom was based on to create equal-thickness slices and re-labeling voxels. The digital data was then embedded in a PET Digital Imaging and Communications in Medicine format and tested for compliance. Results We then tested the DRO by comparing it to computed tomography (CT) images of the physical phantom summed to form composite slices with axial extent similar to the DRO, but with a factor of two better in-slice resolution. For composite slices, 91% of voxels were labeled in full agreement, 5% of the voxels were 50-75% accurate, and the remaining 4% of voxels had 25% or less agreement. Conclusions This DRO can be used as an input for PET scanner simulation studies or for comparing simulations to measured Hoffman phantom images.

A Mechanistic Investigation into Ischemia-Driven Distal Recurrence of Glioblastoma

Abstract: Glioblastoma (GBM) is the most aggressive primary brain tumor with a short median survival. Tumor recurrence is a clinical expectation of this disease and usually occurs along the resection cavity wall. However, previous clinical observations have suggested that in cases of perioperative ischemia, tumors are more likely to recur distally. Through the use of a mechanistic model, the Proliferation Invasion Hypoxia Necrosis Angiogenesis (PIHNA) model, we explore the phenotypic drivers of this observed behavior. We have extended the PIHNA model to include a new nutrient-based vascular efficiency term. The model suggests sensitivity to a hypoxic microenvironment and the inherent migration and proliferation rates of the tumor cells are key factors that drive distant recurrences.

Sex differences in MRI-based metrics of glioma invasion and brain mechanics

Abstract: Gliomas are brain tumors characterized by highly variable growth patterns. Magnetic resonance imaging (MRI) is the cornerstone of glioma diagnosis and management planning. However, glioma features on MRI do not directly correlate with tumor cell distribution. Additionally, there is evidence that glioma tumor characteristics and prognosis are sex-dependent. Magnetic resonance elastography (MRE) is an imaging technique that allows interrogation of tissue stiffness in-vivo and has found utility in the imaging of several cancers. We investigate the relationship between MRI features, MRE features, and growth parameters derived from an established mathematical model of glioma proliferation and invasion. Results suggest that both the relationship between tumor volume and tumor stiffness as well as the relationship between the parameters derived from the mathematical model and tumor stiffness are sex-dependent. These findings lend evidence to a growing body of knowledge about the clinical importance of sex in the context of cancer diagnosis, prognosis and treatment.