Li, Jing

Abstract Intra-tumor genetic heterogeneity is an important cause of treatment failure of GBM. Using MRI and image-localized biopsies, it is possible to train machine learning (ML) models to predict regional genetic status. However, biopsy samples are limited, making it difficult to train a robust ML model. We proposed a data-inclusive model called Weakly Supervised Ordinal Support Vector Machines (WSO-SVM) which leverages the vast amount of MRI data outside the sparsely sampled biopsy regions to augment the biopsy samples to improve ML accuracy. Our study included a unique dataset of 104 image-localized biopsies with spatially matched multiparametric MRI from 30 untreated Glioblastoma (GBM) patients. Each biopsy sample went through genetic sequencing analysis and our study focused on two GBM hallmark genes, EGFR and PDGFRA. For each gene, a biopsy sample was labeled as “altered” if the copy number of this gene was amplified or a mutation was found, and “non-altered” otherwise. From the localized region of six MRI contrasts from T1gd, T2w, diffusion and perfusion imaging, over 300 texture features were extracted. To account for biopsy sample location uncertainty, six neighboring regions of the biopsy sample including four neighbors two pixels away from the biopsy location and two neighbors on adjacent slices were also included in model training. WSO-SVM achieved 0.83 accuracy, 0.77 sensitivity, and 0.86 specificity for classifying EGFR; 0.77 accuracy, 0.74 sensitivity, and 0.79 specificity for classifying PDGFRA, based on 10-fold cross validation. Furthermore, using the trained models, we generated regional EGFR and PDGFRA alteration maps for each patient within the enhancing and non-enhancing tumoral areas. On average we found a greater proportion of enhancing tumor with co-alteration than non-enhancing tumor, while this trend was reversed when considering only one altered gene. The ratio of EGFR vs PDGFRA alterations was higher in non-enhancing tumor than enhancing tumor.

Abstract BACKGROUND Conventional magnetic resonance imaging (MR) guides patient care in GBM. However, there is mounting awareness that MR enhancement is non-specific reflecting either tumor progression or non-tumoral inflammatory changes. Histological evaluation of GBM is held as the gold standard for disease assessment. However, the invasiveness of this methodology and the sample sparsity limit its usefulness. Methods to infer histological underpinnings of MRI are needed to improve clinical care. METHODS A transfer learning mixed effects model based on T1Gd and FLAIR MR voxel based image features trained and cross-validated to predict FPKM values of CD68, CASP3, CD8A and IL13RA2. Training data included RNAseq from 38 image-localized biopsies from 15 newly-diagnosed GBM patients. These models were then applied to two independent patients, chosen based on therapy and the quality of image registration, at three different time points, just prior to receiving IL13RA2 targeted CAR-T therapy for rGBM, after 2 cycles and after 4 cycles, resulting in a voxel-based prediction of the relative expression levels of these genes. RESULTS Cross-validation of the proposed machine learning models demonstrated a Pearson Correlation coefficient between predicted and observed FPKM values of 0.89 (CD68), 0.92 (CASP3), 0.93 (CD8A), and 0.88 (IL13RA2). When the models were applied to the two CAR-T patients, CD68-modeled expression levels were seen to increase throughout therapy for one patient, while remaining stable for the other. Survival from first CAR-T infusion was, respectively, 412 and 83 days suggesting that the increased CD68 was indicative of therapeutic effectivity. Further, the spatial activity predictions were consistent with expected therapeutic action as the correlation coefficient between CASP3 and the product of IL13R2 and CD8A expression was 0.81, suggesting the T-cells targeting IL13RA2 were inducing cell death. CONCLUSIONS Preliminary results with our model highlights the potential of spatially resolved radiomic maps to provide insight into regional therapeutic effectivity.

Abstract Recurrent glioblastoma is challenging to distinguish from so called “treatment effect” on routine clinical imaging. Further, within tumor heterogeneity reveals that some regions can be histologically dominated by tumor progression whilst others can be dominated by secondary effects of treatment response. Apparent tumor progression on MRI can be very difficult to manage clinically as it is unclear the degree to which the imaging changes are actually tumor progression vs response to treatment (including inflammatory response and necrosis). In this analysis, we study a unique cohort of patients for whom image localized-biopsies reveal heterogeneity in response vs progression. Our dataset included 70 biopsy samples from 32 patients with GBM each histolopatholgically characterized for tumor abundance vs immune infiltrate. Six multiparametric MRI contrasts were available, including T1, T1gd, T2, FLAIR, SWI, and ADC. Images were co-registered. Radiomic (statistical + texture) features were extracted from the region of six image contrasts locally matched with each biopsy sample. Machine learning models were built to predict each biomarker using radiomic features. Leave-one-out cross validation was used to evaluate the prediction accuracy. Radiomic features were found to be informative to the prediction of biomarkers. ANOVA tests show significant improvement of using radiomic features compared with the null model. The prediction accuracy was higher when considering the biomarkers on a binary scale using the median as the cutoff than on a numerical scale. Spatially-informed radiomics models for tumor progression vs treatment effect are possible and can play an instrumental role in navigating confounding imaging changed common during treatment progression.

Abstract High-grade gliomas (HGGs) nearly always recur after standard initial treatment, and the resulting mixture of recurrent tumor and treatment-induced reactive changes presents major diagnostic challenges. Anatomical imaging, such as MRI, cannot adequately distinguish progressive disease from treatment effect (pseudo-progression). Furthermore, there is marked intra-tumoral heterogeneity, such that some areas of a tumor may demonstrate necrotic treatment effect and others frank recurrence. Due to this difficulty reliably differentiating between these two clinical findings, analytic methods using multiple modalities are necessary to further our understanding of this disease process. To this end, we sought to correlate radiographic, histopathologic and molecular features of surgically sampled post-treatment suspected recurrence to identify markers distinguishing tumor growth from treatment effect. We performed Stimulated Raman Histology (SRH) imaging and highly multiplexed RNA-sequencing (PLATE-seq) on 84 MRI-localized biopsies from 39 patients with clinically suspected recurrent HGG. The SRH images were classified as recurrent tumor or gliotic/reactive tissue using a convolutional neural network trained on an independent cohort including a large set of recurrent HGG, and an automated cell-counting algorithm was used to quantify cellularity from the SRH image of each sample. Differential gene expression analysis of the PLATE-seq data was used to identify gene sets that distinguish recurrent tumor from treatment effect, and single sample gene set variation analysis (GSVA) was used to further assess the molecular and cellular composition of each MRI-localized sample. The histopathologic and molecular features of each sample were also correlated with the MRI features of the corresponding biopsy sites, and this data is currently being used to train machine learning models that predict the distribution of recurrent tumor and treatment-induced reactive changes within a patient’s radiographic lesion. These predictive radiomic models will help to guide neurosurgical sampling, and improve our ability to monitor glioma progression and response to therapy.

e15626 Background: FGFR2 fusions are found in 10-15% of intrahepatic cholangiocarcinomas. Individuals with FGFR2 fusions have a better prognosis and more indolent natural history. More recently FGFR2 fusions have been described as a predictive marker for tyrosine kinase inhibitors targeting the FGFR2 pathway. Texture analysis from CT imaging has been used in the past to estimate degree of fibrosis and angiogenesis in various tumors types; however, texture analysis has not been used in the past to detect FGFR2 rearrangements. Methods: This is a retrospective study of 33 patients with intrahepatic cholangiocarcinoma who were previously tested for FGFR2 fusions with either a FISH break apart assay or with clinically available next generation sequencing assays. All patients had a contrast enhanced CT performed. To address physiological and pathological variations, matched-size regions of interest (ROIs) over areas of non-necrotic tumor and unaffected liver during the portal venous phase were drawn. The paired ROIs for each patient were then processed via an imaging analytic pipeline for (1) ROI normalization, (2) texture panel creation, and (3) machine learning predictive model development. Results: Fifteen patients with FGFR2 fusions and 18 patients without FGFR2 fusions were included in the study. Using the developed predictive model, accurate FGFR2 fusion classification in 90% of cases was achieved (sensitivity = 87%, specificity = 94%). Conclusions: Utilizing advanced analytics with machine learning techniques, multi-textural data obtained from conventional CT images has the capability to detect genetic aberrations in intrahepatic cholangiocarcinoma, including FGFR2 gene fusions. Radiogenomic evaluation has several attractive benefits including the cost effective and expeditious detection of actionable mutations such as FGFR2 fusions as well as avoidance of invasive procedures such as percutaneous core biopsies. [Table: see text]

ObjectiveTo determine whether machine learning can accurately classify human papillomavirus (HPV) status of oropharyngeal squamous cell carcinoma (OPSCC) using computed tomography (CT)-based texture analysis.MethodsTexture analyses were retrospectively applied to regions of interest from OPSCC primary tumors on contrast-enhanced neck CT, and machine learning was used to create a model that classified HPV status with the highest accuracy. Results were compared against the blinded review of 2 neuroradiologists.ResultsThe HPV-positive (n = 92) and -negative (n = 15) cohorts were well matched clinically. Neuroradiologist classification accuracies for HPV status (44.9%, 55.1%) were not significantly different (P= 0.13), and there was a lack of agreement between the 2 neuroradiologists (κ = −0.145). The best machine learning model had an accuracy of 75.7%, which was greater than either neuroradiologist (P< 0.001,P= 0.002).ConclusionsUseful diagnostic information regarding HPV infection can be extracted from the CT appearance of OPSCC beyond what is apparent to the trained human eye.

Abstract Purpose: Investigate the utility of patient-specific spatial predictions of tumor cell density from a bio-mathematical model. Introduction: Glioblastomas (GBMs) are the most malignant of all primary brain tumors. While it is known there is always a non-detectable portion of the tumor, current techniques of monitoring GBM progression, imaging and initial histological assessment, are not able to reliably estimate the tumor invasion past the enhancing region on T2-Weighted (T2W) imaging. Over the last two decades, a large effort has been made to create a simple patient-specific mathematical model of gliomas. The resulting model, referred to as the Proliferation-Invasion (PI) model, is based on two key parameters, the net growth rate, ρ, and the dispersal coefficient, D. In this model, the ratio of D/ρ is related to degree of invasion and the product D*ρ, is related to the speed of growth. The intuitive understanding provided by this model has been able to provide patient-specific understanding of disease kinetics enabling prediction of outcomes following surgical resection, radiation and the development of a prognostic response metric. Previous literature utilizing this model has been based on the assumption that what is seen on the pretreatment T1-Weighted contrast-enhanced (T1Gd) and T2W, images correspond to an 80% and 16% tumor cell density threshold respectively. This assumption allows for an estimate of D/ρ from a single time point of imaging. While these values were based on extensive experience, for ethical and technical reasons, they have never been rigorously investigated histologically. Recent technological advances have made it possible for surgeons to use an MRI to guide the acquisition of tissue making it possible to know with a good degree of accuracy where on the MR image the histological specimen comes from. Methods: Model Calibration : To estimate D/ρ for each patient, we assume abnormalities on the T1Gd and T2W images correspond to an 80% and 16% tumor cell density threshold respectively. We then utilize a Bayesian calibration approach based on adaptive grid refinement while holding the velocity constant to find the most likely value of D/ρ to match the observed radial measurements. Three-Dimensional Density Maps : Given a gray/white segmentation and an estimate for D/ρ, we can build a tumor cell density prediction in the patient's anatomy using the Eikonal equations and the modified Fast Marching Method (FMM) algorithm presented by Konukoglu et al. Patient Cohort : Eighteen patients were recruited with clinically suspected GBM undergoing preoperative stereotactic MRI for surgical resection with IRB approval Barrow Neurological Institute and Mayo Clinic in Arizona. Surgical Biopsy : Pre-operative conventional MRI, including T1Gd and T2W, was utilized to guide stereotactic biopsies. An average of 5–6 tissue specimens were acquired from each tumor by using stereotactic surgical localization, following the smallest possible diameter craniotomies to minimize brain shift. Histological Analysis : 4 μm tissue sections were stained with hematoxylin and eosin (H&E) for neuropathology review. H&E slides were reviewed by a neuropathologist. The percent tumor nuclei in the field was estimated. Results and Conclusion: Our analysis showed that the intuitive ordering of diffuse to nodular tumor profiles from the PI model is consistent with the histologic data. Further, utilizing the histologic data, limitations to a universal threshold cutoff of the T2/FLAIR region are specified and a better threshold cutoff value is suggested. We hope that this paper will lead to more studies of this kind resulting in more accurate ways to predict the spatial distribution of GBM tumor cells from medical imaging. Such advances could revolutionize surgical procedures and radiation therapy and may enable additional insights into tumor kinetic differences meaningful for treatment. Citation Format: Andrea Hawkins-Daarud, Lauren DeGirolamo, Joshua Jacobs, Kamala Clark-Swanson, Jennifer M. Eschbacher, Kris A. Smith, Peter Nakaji, Leslie C. Baxter, John P. Karis, Teresa Wu, J. Ross Mitchell, Jing Li, Leland Hu, Kristin R. Swanson. Histologic evidence for a bio-mathematical model of glioblastoma invasion. [abstract]. In: Proceedings of the AACR Special Conference on Engineering and Physical Sciences in Oncology; 2016 Jun 25-28; Boston, MA. Philadelphia (PA): AACR; Cancer Res 2017;77(2 Suppl):Abstract nr A08.