GlioPredictor: a deep learning model for identification of high-risk adult IDH-mutant glioma towards adjuvant treatment planning

Identification of isocitrate dehydrogenase (IDH)-mutant glioma patients at high risk of early progression is critical for radiotherapy treatment planning. Currently tools to stratify risk of early progression are lacking. We sought to identify a combination of molecular markers that could be used to identify patients who may have a greater need for adjuvant radiation therapy machine learning technology. 507 WHO Grade 2 and 3 glioma cases from The Cancer Genome Atlas, and 1309 cases from AACR GENIE v13.0 datasets were studied for genetic disparities between IDH1-wildtype and IDH1-mutant cohorts, and between different age groups. Genetic features such as mutations and copy number variations (CNVs) correlated with IDH1 mutation status were selected as potential inputs to train artificial neural networks (ANNs) to predict IDH1 mutation status. Grade 2 and 3 glioma cases from the Memorial Sloan Kettering dataset (n = 404) and Grade 3 glioma cases with subtotal resection (STR) from Northwestern University (NU) (n = 21) were used to further evaluate the best performing ANN model as independent datasets. IDH1 mutation is associated with decreased CNVs of EGFR (21% vs. 3%), CDKN2A (20% vs. 6%), PTEN (14% vs. 1.7%), and increased percentage of mutations for TP53 (15% vs. 63%), and ATRX (10% vs. 54%), which were all statistically significant (p < 0.001). Age > 40 was unable to identify high-risk IDH1-mutant with early progression. A glioma early progression risk prediction (GlioPredictor) score generated from the best performing ANN model (6/6/6/6/2/1) with 6 inputs, including CNVs of EGFR, PTEN and CDKN2A, mutation status of TP53 and ATRX, patient's age can predict IDH1 mutation status with over 90% accuracy. The GlioPredictor score identified a subgroup of high-risk IDH1-mutant in TCGA and NU datasets with early disease progression (p = 0.0019, 0.0238, respectively). The GlioPredictor that integrates age at diagnosis, CNVs of EGFR, CDKN2A, PTEN and mutation status of TP53, and ATRX can identify a small cohort of IDH-mutant with high risk of early progression. The current version of GlioPredictor mainly incorporated clinically often tested genetic biomarkers. Considering complexity of clinical and genetic features that correlate with glioma progression, future derivatives of GlioPredictor incorporating more inputs can be a potential supplement for adjuvant radiotherapy patient selection of IDH-mutant glioma patients.

GlioPredictor: A Deep Learning Model for Identification of High-Risk Low-Grade Glioma toward Adjuvant Treatment Planning

PURPOSE/OBJECTIVE(S)

High-risk low-grade glioma (LGG) patients are recommended to undergo adjuvant radiotherapy whereas watchful waiting is recommended for low-risk LGG patients per the latest NCCN guidelines. Based on Radiation Therapy Oncology Group (RTOG) 9802, high-risk features include age >40 or subtotal resection (STR). However, in the era of molecular-based classification for tumors of central neural system, current risk classification criteria based on gross disease and patient demographics may be outdated. Here, we aim to develop a molecular-based glioma risk classification system (GlioPredictor) that could potentially facilitate identification of high-risk LGG patients.

MATERIALS/METHODS

A total of 507 LGG cases from The Cancer Genome Atlas-low grade glioma (TCGA-LGG), and 1,309 cases from AACR GENIE v13.0 datasets were studied for genetic disparities between IDH1-wildtype and mutated cohorts, and varying age groups. Through a feature selection technique using genomic profiling and correlation analyses, features such as mutation status, copy number variations (CNVs), among other clinicopathologic features prognostic of IDH1 mutation status were selected as potential inputs to train an artificial neural networks (ANNs) that could predict IDH1 mutation status. Model performance was assessed using the area under the receiver operating characteristic curve (AUC). Memorial Sloan Kettering (MSK) dataset (n = 404) for LGG was used to cross-validate the trained ANN. The optimized ANN model has 6 layers with 6 input nodes, 20 hidden nodes, and a binary output layer. The weights and biases of the hidden layers of the best-performing model were retrieved and reconstructed to yield the GlioPredictor score-the predicted risk of progression for IDH1-wildtype LGG.

RESULTS

Over 81% of glioma patients age less than 40 have IDH1 mutation, as compared with 31% in those age above 60. Using age > 40 as a cutoff failed to identify high-risk IDH1-mutant LGG with early progression. IDH1 mutation is associated with decreased CNVs of EGFR (21 % vs. 3%), CDKN2A (20% vs. 6%) and PTEN (14% vs. 1.7%), and increased percentage of mutations for TP53 (15% vs. 63%), and ATRX (10% vs. 54%) (p<0.001). Using these molecular features, along with the patient's age, an ANN model with 6 layers and 20 hidden nodes can predict IDH1 mutation status with over 90% accuracy and AUC score over 0.91.

CONCLUSION

We have developed an ANN model that is capable of learning the prognostic features of LGG associated with an IDH1-mutated LGG cohort and using the features to predict high-risk patients from the IDH1-wildtype cohort. This ANN model facilitates the selection of LGG patients who could benefit from immediate adjuvant radiotherapy. Future work includes the integration of image features to improve the prediction performance of the GlioPredictor system.

Whole-brain radiotherapy associated with structural changes resembling aging as determined by anatomic surface-based deep learning

BACKGROUND

Brain metastases are the most common intracranial tumors in adults and are associated with significant morbidity and mortality. Whole-brain radiotherapy (WBRT) is used frequently in patients for palliation, but can result in neurocognitive deficits. While dose-dependent injury to individual areas such as the hippocampus has been demonstrated, global structural shape changes after WBRT remain to be studied.

METHODS

We studied healthy controls and patients with brain metastases and examined MRI brain anatomic surface data before and after WBRT. We implemented a validated graph convolutional neural network model to estimate patient's "brain age". We further developed a mixed-effects linear model to compare the estimated age of the whole brain and substructures before and after WBRT.

RESULTS

4220 subjects were analyzed (4148 healthy controls and 72 patients). The median radiation dose was 30 Gy (range 25-37.5 Gy). The whole brain and substructures underwent structural change resembling rapid aging in radiated patients compared to healthy controls; the whole brain "aged" 9.32 times faster, the cortex 8.05 times faster, the subcortical structures 12.57 times faster, and the hippocampus 10.14 times faster. In a subset analysis, the hippocampus "aged" 8.88 times faster in patients after conventional WBRT versus after hippocampal avoidance (HA)-WBRT.

CONCLUSIONS

Our findings suggest that WBRT causes the brain and its substructures to undergo structural changes at a pace up to 13x of the normal aging pace, where hippocampal avoidance offers focal structural protection. Correlating these structural imaging changes with neurocognitive outcomes following WBRT or HA-WBRT would benefit from future analysis.

History of Technological Advancements towards MR-Linac: The Future of Image-Guided Radiotherapy

Image-guided radiotherapy (IGRT) enables optimal tumor targeting and sparing of organs-at-risk, which ultimately results in improved outcomes for patients. Magnetic resonance imaging (MRI) revolutionized diagnostic imaging with its superior soft tissue contrast, high spatiotemporal resolution, and freedom from ionizing radiation exposure. Over the past few years there has been burgeoning interest in MR-guided radiotherapy (MRgRT) to overcome current challenges in X-ray-based IGRT, including but not limited to, suboptimal soft tissue contrast, lack of efficient daily adaptation, and incremental exposure to ionizing radiation. In this review, we present an overview of the technologic advancements in IGRT that led to MRI-linear accelerator (MRL) integration. Our report is organized in three parts: (1) a historical timeline tracing the origins of radiotherapy and evolution of IGRT, (2) currently available MRL technology, and (3) future directions and aspirations for MRL applications.

Whole brain radiotherapy and association with rapid brain aging as determined by anatomic surface morphology

e14007

Background: Brain metastases are the most common intracranial tumors in adults and are associated with significant morbidity and mortality. Whole brain radiotherapy (WBRT) is used frequently in patients for palliation, but can result in neurocognitive deficits. While dose-dependent injury to individual areas such as the hippocampus have been demonstrated, global structural changes after WBRT remain to be studied. Our group previously published a magnetic resonance imaging (MRI) deep learning model based on anatomic brain surface morphology to accurately predict brain age in healthy subjects. We now report the effect of WBRT on aging pace of the irradiated brain. Methods: We studied patients with brain metastases and examined MRI brain anatomic surface data before and after WBRT. We implemented a graph convolutional neural network model to estimate patient’s brain age. We further developed a mixed-effects linear model to compare age of whole brain and substructures before and after WBRT, written as follows: ΔAge = c + β(ΔScan) + 1|patient_ID; where for each patient, ΔAge = [(model_predicted_age_at_follow up – actual_age_at_follow up) – (model_predicted_age_pre_treatment – actual_age_pre_treatment)], ΔScan = time interval between pre-and post-treatment MRI scans, β = aging coefficient (β =0 corresponds to normal aging), and c = intercept (model_predicted_age_pre_treatment – actual_age_pre_treatment). Results: 56 patients were analyzed. The median age was 62 (range 32 – 85). Two-thirds of patients were female. Primary organ site was breast or lung in 87% of cases and 77% of patients had five or more metastases. Median radiation dose was 30Gy (range 25 – 37.5Gy). Results of aging analysis are presented in Table. Small c values demonstrate that model accurately predicted age pre-treatment. The whole brain and substructures underwent rapid aging compared to normal aging pace (β>>0). Based on median follow up of 6.3 months, the whole brain aged approximately 4.94 years, the cortex aged approximately 4.53 years, the subcortical structures aged approximately 5.94 years, and the hippocampus aged approximately 5.17 years. Conclusions: Our findings suggest that WBRT causes the brain and its substructures to age at a pace of 9-11x of the normal aging pace, mirroring deficits in long-term neurocognition seen post-treatment. Given post-treatment aging pace and increasing survival for many patients with brain metastases, WBRT needs to be used judiciously. [Table: see text]

Tumor-associated alterations in white matter connectivity have prognostic significance in MGMT-unmethylated glioblastoma

PURPOSE

We investigated the prognostic significance of tumor-associated white matter (TA-WM) tracts in glioblastoma (GBM) using magnetic resonance-diffusion tensor imaging (MR-DTI). We hypothesized that (1) TA-WM tracts harbor microscopic disease not targeted through surgery or radiotherapy (RT), and (2) the greater the extent of TA-WM involvement, the worse the survival outcomes.

METHODS

We studied a retrospective cohort of 76 GBM patients. TA-WM tracts were identified by MR-DTI fractional anisotropy (FA) maps. For each patient, 22 TA-WM tracts were analyzed and each tract was graded 1-3 based on FA. A TA-WM score (TA-WMS) was computed based on number of involved tracts and corresponding FA grade of involvement. Kaplan-Meier statistics were utilized to determine survival outcomes, log-rank test was used to compare survival between groups, and Cox regression was utilized to determine prognostic variables.

RESULTS

For the MGMT-unmethylated cohort, there was a decrease in OS for increasing TA-WMS (median OS 16.5 months for TA-WMS 0-4; 13.6 months for TA-WMS 5-8; 7.3 months for TA-WMS > 9; p = 0.0002). This trend was not observed in the MGMT-methylated cohort. For MGMT-unmethylated patients with TA-WMS > 6 and involvement of tracts passing through brainstem or contralateral hemisphere, median OS was 8.3 months versus median OS 14.1 months with TA-WMS > 6 but not involving aforementioned critical tracts (p = 0.003 log-rank test). For MGMT-unmethylated patients, TA-WMS was predictive of overall survival in multivariate analysis (HR = 1.14, 95% CI 1.03-1.27, p = 0.012) while age, gender, and largest tumor dimension were non-significant.

CONCLUSION

Increased TA-WMS and involvement of critical tracts are associated with decreased overall survival in MGMT-unmethylated GBM.

Water-Soluble Nanoconjugate for Enhanced Cellular Delivery of Receptor-Targeted Magnetic Resonance Contrast Agents

ProGlo is an efficient steroid receptor-targeted magnetic resonance (MR) imaging contrast agent (CA). It has been shown to bind to the progesterone receptor (PR) and produce enhanced image contrast in PR-positive cells and tissues in vitro and in vivo. However, the hydrophobicity of the steroid targeting domain of ProGlo (logP = 1.4) limits its formulation and delivery at clinically relevant doses. In this work, a hydrophobic moiety was utilized to drive efficient adsorption onto nanodiamond (ND) clusters to form a water-soluble nanoconstruct (logP = -2.4) with 80% release in 8 h under biological conditions. In cell culture, the ND-ProGlo construct delivered increased concentrations of ProGlo to target cells compared to ProGlo alone. Importantly, these results were accomplished without the use of solvents such as DMSO, providing a significant advance toward formulating ProGlo for translational applications. Biodistribution studies confirm the delivery of ProGlo to PR(+) tissues with enhanced efficacy over untargeted controls. These results demonstrate the potential for a noncovalent ND-CA construct as a general strategy for solubilizing and delivering hydrophobic targeted MR CAs.

Gd(III)-Gold Nanoconjugates Provide Remarkable Cell Labeling for High Field Magnetic Resonance Imaging

In vivo cell tracking is vital for understanding migrating cell populations, particularly cancer and immune cells. Magnetic resonance (MR) imaging for long-term tracking of transplanted cells in live organisms requires cells to effectively internalize Gd(III) contrast agents (CAs). Clinical Gd(III)-based CAs require high dosing concentrations and extended incubation times for cellular internalization. To combat this, we have devised a series of Gd(III)-gold nanoconjugates (Gd@AuNPs) with varied chelate structure and nanoparticle-chelate linker length, with the goal of labeling and imaging breast cancer cells. These new Gd@AuNPs demonstrate significantly enhanced labeling compared to previous Gd(III)-gold-DNA nanoconstructs. Variations in Gd(III) loading, surface packing, and cell uptake were observed among four different Gd@AuNP formulations suggesting that linker length and surface charge play an important role in cell labeling. The best performing Gd@AuNPs afforded 23.6 ± 3.6 fmol of Gd(III) per cell at an incubation concentration of 27.5 μM-this efficiency of Gd(III) payload delivery (Gd(III)/cell normalized to dose) exceeds that of previous Gd(III)-Au conjugates and most other Gd(III)-nanoparticle formulations. Further, Gd@AuNPs were well-tolerated in vivo in terms of biodistribution and clearance, and supports future cell tracking applications in whole-animal models.

Nanodiamond-Gadolinium(III) Aggregates for Tracking Cancer Growth In Vivo at High Field

The ability to track labeled cancer cells in vivo would allow researchers to study their distribution, growth, and metastatic potential within the intact organism. Magnetic resonance (MR) imaging is invaluable for tracking cancer cells in vivo as it benefits from high spatial resolution and the absence of ionizing radiation. However, many MR contrast agents (CAs) required to label cells either do not significantly accumulate in cells or are not biologically compatible for translational studies. We have developed carbon-based nanodiamond-gadolinium(III) aggregates (NDG) for MR imaging that demonstrated remarkable properties for cell tracking in vivo. First, NDG had high relaxivity independent of field strength, a finding unprecedented for gadolinium(III) [Gd(III)]-nanoparticle conjugates. Second, NDG demonstrated a 300-fold increase in the cellular delivery of Gd(III) compared to that of clinical Gd(III) chelates without sacrificing biocompatibility. Further, we were able to monitor the tumor growth of NDG-labeled flank tumors by T1- and T2-weighted MR imaging for 26 days in vivo, longer than was reported for other MR CAs or nuclear agents. Finally, by utilizing quantitative maps of relaxation times, we were able to describe tumor morphology and heterogeneity (corroborated by histological analysis), which would not be possible with competing molecular imaging modalities.

Gd(III)-Dithiolane Gold Nanoparticles for T1-Weighted Magnetic Resonance Imaging of the Pancreas

Pancreatic adenocarcinoma has a 5 year survival of approximately 3% and median survival of 6 months and is among the most dismal of prognoses in all of medicine. This poor prognosis is largely due to delayed diagnosis where patients remain asymptomatic until advanced disease is present. Therefore, techniques to allow early detection of pancreatic adenocarcinoma are desperately needed. Imaging of pancreatic tissue is notoriously difficult, and the development of new imaging techniques would impact our understanding of organ physiology and pathology with applications in disease diagnosis, staging, and longitudinal response to therapy in vivo. Magnetic resonance imaging (MRI) provides numerous advantages for these types of investigations; however, it is unable to delineate the pancreas due to low inherent contrast within this tissue type. To overcome this limitation, we have prepared a new Gd(III) contrast agent that accumulates in the pancreas and provides significant contrast enhancement by MR imaging. We describe the synthesis and characterization of a new dithiolane-Gd(III) complex and a straightforward and scalable approach for conjugation to a gold nanoparticle. We present data that show the nanoconjugates exhibit very high per particle values of r1 relaxivity at both low and high magnetic field strengths due to the high Gd(III) payload. We provide evidence of pancreatic tissue labeling that includes MR images, post-mortem biodistribution analysis, and pancreatic tissue evaluation of particle localization. Significant contrast enhancement was observed allowing clear identification of the pancreas with contrast-to-noise ratios exceeding 35:1.