Preventing bad behavior in academia.

We gave young scientists this prompt: Describe one change to scientific policy or culture that would substantially decrease incidents of scientific misconduct or other unethical behavior.

Quantifying intra-tumoral genetic heterogeneity of glioblastoma toward precision medicine using MRI and a data-inclusive machine learning algorithm.

BACKGROUND AND OBJECTIVE: Glioblastoma (GBM) is one of the most aggressive and lethal human cancers. Intra-tumoral genetic heterogeneity poses a significant challenge for treatment. Biopsy is invasive, which motivates the development of non-invasive, MRI-based machine learning (ML) models to quantify intra-tumoral genetic heterogeneity for each patient. This capability holds great promise for enabling better therapeutic selection to improve patient outcome. METHODS: We proposed a novel Weakly Supervised Ordinal Support Vector Machine (WSO-SVM) to predict regional genetic alteration status within each GBM tumor using MRI. WSO-SVM was applied to a unique dataset of 318 image-localized biopsies with spatially matched multiparametric MRI from 74 GBM patients. The model was trained to predict the regional genetic alteration of three GBM driver genes (EGFR, PDGFRA and PTEN) based on features extracted from the corresponding region of five MRI contrast images. For comparison, a variety of existing ML algorithms were also applied. Classification accuracy of each gene were compared between the different algorithms. The SHapley Additive exPlanations (SHAP) method was further applied to compute contribution scores of different contrast images. Finally, the trained WSO-SVM was used to generate prediction maps within the tumoral area of each patient to help visualize the intra-tumoral genetic heterogeneity. RESULTS: WSO-SVM achieved 0.80 accuracy, 0.79 sensitivity, and 0.81 specificity for classifying EGFR; 0.71 accuracy, 0.70 sensitivity, and 0.72 specificity for classifying PDGFRA; 0.80 accuracy, 0.78 sensitivity, and 0.83 specificity for classifying PTEN; these results significantly outperformed the existing ML algorithms. Using SHAP, we found that the relative contributions of the five contrast images differ between genes, which are consistent with findings in the literature. The prediction maps revealed extensive intra-tumoral region-to-region heterogeneity within each individual tumor in terms of the alteration status of the three genes. CONCLUSIONS: This study demonstrated the feasibility of using MRI and WSO-SVM to enable non-invasive prediction of intra-tumoral regional genetic alteration for each GBM patient, which can inform future adaptive therapies for individualized oncology.

Biologically-informed deep neural networks provide quantitative assessment of intratumoral heterogeneity in post-treatment glioblastoma.

Intratumoral heterogeneity poses a significant challenge to the diagnosis and treatment of glioblastoma (GBM). This heterogeneity is further exacerbated during GBM recurrence, as treatment-induced reactive changes produce additional intratumoral heterogeneity that is ambiguous to differentiate on clinical imaging. There is an urgent need to develop non-invasive approaches to map the heterogeneous landscape of histopathological alterations throughout the entire lesion for each patient. We propose to predictively fuse Magnetic Resonance Imaging (MRI) with the underlying intratumoral heterogeneity in recurrent GBM using machine learning (ML) by leveraging image-localized biopsies with their associated locoregional MRI features. To this end, we develop BioNet, a biologically-informed neural network model, to predict regional distributions of three tissue-specific gene modules: proliferating tumor, reactive/inflammatory cells, and infiltrated brain tissue. BioNet offers valuable insights into the integration of multiple implicit and qualitative biological domain knowledge, which are challenging to describe in mathematical formulations. BioNet performs significantly better than a range of existing methods on cross-validation and blind test datasets. Voxel-level prediction maps of the gene modules by BioNet help reveal intratumoral heterogeneity, which can improve surgical targeting of confirmatory biopsies and evaluation of neuro-oncological treatment effectiveness. The non-invasive nature of the approach can potentially facilitate regular monitoring of the gene modules over time, and making timely therapeutic adjustment. These results also highlight the emerging role of ML in precision medicine.

Digital twins for health: a scoping review.

The use of digital twins (DTs) has proliferated across various fields and industries, with a recent surge in the healthcare sector. The concept of digital twin for health (DT4H) holds great promise to revolutionize the entire healthcare system, including management and delivery, disease treatment and prevention, and health well-being maintenance, ultimately improving human life. The rapid growth of big data and continuous advancement in data science (DS) and artificial intelligence (AI) have the potential to significantly expedite DT research and development by providing scientific expertise, essential data, and robust cybertechnology infrastructure. Although various DT initiatives have been underway in the industry, government, and military, DT4H is still in its early stages. This paper presents an overview of the current applications of DTs in healthcare, examines consortium research centers and their limitations, and surveys the current landscape of emerging research and development opportunities in healthcare. We envision the emergence of a collaborative global effort among stakeholders to enhance healthcare and improve the quality of life for millions of individuals worldwide through pioneering research and development in the realm of DT technology.

Image-localized biopsy mapping of brain tumor heterogeneity: A single-center study protocol.

Brain cancers pose a novel set of difficulties due to the limited accessibility of human brain tumor tissue. For this reason, clinical decision-making relies heavily on MR imaging interpretation, yet the mapping between MRI features and underlying biology remains ambiguous. Standard (clinical) tissue sampling fails to capture the full heterogeneity of the disease. Biopsies are required to obtain a pathological diagnosis and are predominantly taken from the tumor core, which often has different traits to the surrounding invasive tumor that typically leads to recurrent disease. One approach to solving this issue is to characterize the spatial heterogeneity of molecular, genetic, and cellular features of glioma through the intraoperative collection of multiple image-localized biopsy samples paired with multi-parametric MRIs. We have adopted this approach and are currently actively enrolling patients for our 'Image-Based Mapping of Brain Tumors' study. Patients are eligible for this research study (IRB #16-002424) if they are 18 years or older and undergoing surgical intervention for a brain lesion. Once identified, candidate patients receive dynamic susceptibility contrast (DSC) perfusion MRI and diffusion tensor imaging (DTI), in addition to standard sequences (T1, T1Gd, T2, T2-FLAIR) at their presurgical scan. During surgery, sample anatomical locations are tracked using neuronavigation. The collected specimens from this research study are used to capture the intra-tumoral heterogeneity across brain tumors including quantification of genetic aberrations through whole-exome and RNA sequencing as well as other tissue analysis techniques. To date, these data (made available through a public portal) have been used to generate, test, and validate predictive regional maps of the spatial distribution of tumor cell density and/or treatment-related key genetic marker status to identify biopsy and/or treatment targets based on insight from the entire tumor makeup. This type of methodology, when delivered within clinically feasible time frames, has the potential to further inform medical decision-making by improving surgical intervention, radiation, and targeted drug therapy for patients with glioma.

Neighborhood Environment and Epigenetic Age: A Scoping Review.

BACKGROUND: Interest in how the neighborhood environment impacts age-related health conditions has been increasing for decades. Epigenetic changes are environmentally derived modifications to the genome that alter the way genes function-thus altering health status. Epigenetic age, a biomarker for biological age, has been shown to be a useful predictor of several age-related health conditions. Consequently, its relation to the neighborhood environment has been the focus of a growing body of literature. OBJECTIVE: We aimed to describe the scope of the evidence on the relationship between neighborhood environmental characteristics and epigenetic age. METHODS: Using scoping review following methods established by Arksey and O'Malley, we first defined our research questions and searched the literature in PubMed, PsycINFO, and EMBASE. Next, we selected the literature to be included, and finally, we analyzed and summarized the information. RESULTS: Nine articles met the inclusion criteria. Most studies examined deprivation as the neighborhood characteristic of interest. While all studies were observational in design, the articles included diverse participants, including men and women, adults and children, and multiple ethnicities. Results demonstrated a relationship between the neighborhood environment and epigenetic age, whether the characteristic of interest is socioeconomic or physical. CONCLUSIONS: Overall, studies concluded there was a relationship between neighborhood characteristics and epigenetic age, whether the characteristic of interest was socioeconomic or physical. However, findings varied based on how the neighborhood characteristic and/or epigenetic age was measured. Furthermore, a paucity of investigations on physical characteristics was noticeable and warrants increased attention.

Integrated molecular and multiparametric MRI mapping of high-grade glioma identifies regional biologic signatures.

Sampling restrictions have hindered the comprehensive study of invasive non-enhancing (NE) high-grade glioma (HGG) cell populations driving tumor progression. Here, we present an integrated multi-omic analysis of spatially matched molecular and multi-parametric magnetic resonance imaging (MRI) profiling across 313 multi-regional tumor biopsies, including 111 from the NE, across 68 HGG patients. Whole exome and RNA sequencing uncover unique genomic alterations to unresectable invasive NE tumor, including subclonal events, which inform genomic models predictive of geographic evolution. Infiltrative NE tumor is alternatively enriched with tumor cells exhibiting neuronal or glycolytic/plurimetabolic cellular states, two principal transcriptomic pathway-based glioma subtypes, which respectively demonstrate abundant private mutations or enrichment in immune cell signatures. These NE phenotypes are non-invasively identified through normalized K2 imaging signatures, which discern cell size heterogeneity on dynamic susceptibility contrast (DSC)-MRI. NE tumor populations predicted to display increased cellular proliferation by mean diffusivity (MD) MRI metrics are uniquely associated with EGFR amplification and CDKN2A homozygous deletion. The biophysical mapping of infiltrative HGG potentially enables the clinical recognition of tumor subpopulations with aggressive molecular signatures driving tumor progression, thereby informing precision medicine targeting.

Epigenetic age acceleration mediates the relationship between neighborhood deprivation and pain severity in adults with or at risk for knee osteoarthritis pain.

An estimated 250 million people worldwide suffer from knee osteoarthritis (KOA), with older adults having greater risk. Like other age-related diseases, residents of high-deprivation neighborhoods experience worse KOA pain outcomes compared to their more affluent neighbors. The purpose of this study was to examine the relationship between neighborhood deprivation and pain severity in KOA and the influence of epigenetic age acceleration (EpAA) on that relationship. The sample of 128 participants was mostly female (60.9%), approximately half non-Hispanic Black (49.2%), and had a mean age of 58 years. Spearman bivariate correlations revealed that pain severity positively correlated with EpAA (ρ = 0.47, p ≤ 0.001) and neighborhood deprivation (ρ = 0.25, p = 0.004). We found a positive significant relationship between neighborhood deprivation and EpAA (ρ = 0.47, p ≤ 0.001). Results indicate a mediating relationship between neighborhood deprivation (predictor), EpAA (mediator), and pain severity (outcome variable). There was a significant indirect effect of neighborhood deprivation on pain severity through EpAA, as the mediator accounted for a moderate portion of the total effect, PM = 0.44. Epigenetic age acceleration may act as a mechanism through which neighborhood deprivation leads to worse KOA pain outcomes and may play a role in the well-documented relationship between the neighborhood of residence and age-related diseases.

Towards Longitudinal Glioma Segmentation: Evaluating combined pre- and post-treatment MRI training data for automated tumor segmentation using nnU-Net.

Identification of key phenotypic regions such as necrosis, contrast enhancement, and edema on magnetic resonance imaging (MRI) is important for understanding disease evolution and treatment response in patients with glioma. Manual delineation is time intensive and not feasible for a clinical workflow. Automating phenotypic region segmentation overcomes many issues with manual segmentation, however, current glioma segmentation datasets focus on pre-treatment, diagnostic scans, where treatment effects and surgical cavities are not present. Thus, existing automatic segmentation models are not applicable to post-treatment imaging that is used for longitudinal evaluation of care. Here, we present a comparison of three-dimensional convolutional neural networks (nnU-Net architecture) trained on large temporally defined pre-treatment, post-treatment, and mixed cohorts. We used a total of 1563 imaging timepoints from 854 patients curated from 13 different institutions as well as diverse public data sets to understand the capabilities and limitations of automatic segmentation on glioma images with different phenotypic and treatment appearance. We assessed the performance of models using Dice coefficients on test cases from each group comparing predictions with manual segmentations generated by trained technicians. We demonstrate that training a combined model can be as effective as models trained on just one temporal group. The results highlight the importance of a diverse training set, that includes images from the course of disease and with effects from treatment, in the creation of a model that can accurately segment glioma MRIs at multiple treatment time points.

An 8-week exercise study to improve cancer treatment related fatigue and QOL among African American breast cancer patients undergoing radiation treatment: A pilot randomized clinical trial.

BACKGROUND: Cancer treatment related fatigue (CTRF) is one of the most debilitating side effects of adjuvant radiation therapy (RT). Several studies have found that physical activity (PA) may be an effective intervention to decrease fatigue and enhance QOL in cancer survivors. The primary objective of the PEDLAR study is to test the feasibility of an easily administered 8-week structured moderate-intensity PA intervention, delivered concurrently with RT, in reducing CTRF and improving health-related QOL among African-American breast cancer patients. This study is also designed to provide pilot data on the acceptability and adherence of PA interventions in African-American women with breast cancer. METHODS: It is a prospective, 2-arm, 8-week feasibility trial. Participants are randomized to either a structured, moderate-intensity aerobic training exercise regimen concurrent with radiotherapy or a control group. RESULTS: Participants in intervention group reported high satisfaction with exercise and adherence was >75% for exercise sessions. CONCLUSIONS: African-American breast cancer patients in a moderate-intensity 75 min/wk aerobic exercise intervention had marginally lower fatigue at 8-wk follow-up compared to baseline. The control group participants had marginally higher fatigue at 8-wk follow-up compared to baseline. Participants in the intervention group reported slightly better quality of life at 8-wk follow-up compared to baseline (P = 0.06).

Genome-wide DNA methylation study identifies significant epigenomic changes associated with internalized stigma in adults with non-specific chronic low back pain.

Non-specific chronic low back pain (cLBP) represents a common musculoskeletal condition with no identifiable cause. It cannot be diagnosed with conventional neuroimaging techniques such as computerized tomography (CT). The diagnostic uncertainty that characterizes non-specific cLBP can lead to stigmatizing responses from others that can become internalized Among individuals with non-specific cLBP, internalized stigma is associated with greater pain intensity and disability. Yet, no study has examined the biological mechanism linking high internalized stigma to worse outcomes in individuals with non-specific cLBP. We aimed to identify differentially methylated loci (DML), enrichment pathways, and associated network interactions among individuals with non-specific cLBP experiencing low vs. high internalized stigma. We examined DNA methylation in whole blood samples from 48 adults, ages 19-85, using reduced representation bisulfite sequencing (RRBS). After controlling for age, sex, race, and multiple testing, differentially methylated loci (DML) differed in adults with low vs. high internalized stigma by at least 10% and q < 0.01 in 3,665 CpG sites: 2,280 hypomethylated and 1,385 hypermethylated. Gene ontology (GO) analyses of the annotated genes from these sites revealed significant enrichment of 274 biological processes, 29 cellular components, and 24 molecular functions (adjusted p < 0.05). The top enriched molecular functions regulate protein binding and DNA binding of transcription factor activity. Pathway analyses indicated that many functional genomic pathways, including Hippo Signaling, Melanogenesis, and Pathways in Cancer, were enriched with differentially methylated genes. Also, there was a significant interaction between relevance pathways such as P53, mTOR, PI3K-Akt, and Wnt signaling pathways. These pathways have previously been associated with neuroinflammation, neurodegeneration, and stress-related conditions. Thus, findings point to possible stress-induced DNAm changes as the link between high levels of internalized stigma and worse outcomes in adults with non-specific cLBP.

Exploring approaches for predictive cancer patient digital twins: Opportunities for collaboration and innovation.

We are rapidly approaching a future in which cancer patient digital twins will reach their potential to predict cancer prevention, diagnosis, and treatment in individual patients. This will be realized based on advances in high performance computing, computational modeling, and an expanding repertoire of observational data across multiple scales and modalities. In 2020, the US National Cancer Institute, and the US Department of Energy, through a trans-disciplinary research community at the intersection of advanced computing and cancer research, initiated team science collaborative projects to explore the development and implementation of predictive Cancer Patient Digital Twins. Several diverse pilot projects were launched to provide key insights into important features of this emerging landscape and to determine the requirements for the development and adoption of cancer patient digital twins. Projects included exploring approaches to using a large cohort of digital twins to perform deep phenotyping and plan treatments at the individual level, prototyping self-learning digital twin platforms, using adaptive digital twin approaches to monitor treatment response and resistance, developing methods to integrate and fuse data and observations across multiple scales, and personalizing treatment based on cancer type. Collectively these efforts have yielded increased insights into the opportunities and challenges facing cancer patient digital twin approaches and helped define a path forward. Given the rapidly growing interest in patient digital twins, this manuscript provides a valuable early progress report of several CPDT pilot projects commenced in common, their overall aims, early progress, lessons learned and future directions that will increasingly involve the broader research community.

Differential DNA methylation in Black and White individuals with chronic low back pain enrich different genomic pathways.

Compared to Non-Hispanic Whites (NHWs), individuals who self-identify as Non-Hispanic Blacks (NHBs) in the United States experience more severe and disabling chronic low back pain (cLBP). We hypothesized that differences in DNA methylation (DNAm) play a role in racial disparities in cLBP. PURPOSE: To determine the relationship between DNAm levels and racial group differences in adults with cLBP. Our study's secondary purpose was to perform a race-stratified comparison of adults with cLBP and pain-free controls and identify functional genomic pathways enriched by annotated differentially methylated genes. PATIENTS AND METHODS: We recruited 49 NHBs and 49 NHWs (49 cLBP and 49 pain-free controls, PFCs), analyzed DNAm from whole blood using reduced representation bisulfite sequencing, and identified enriched genomic pathways. RESULTS: Among participants with cLBP, we identified 2873 differentially methylated loci (DML; methylation differences of at least 10% and p < 0.0001), many of which were annotated to genes of importance to pain pathology. These DMLs significantly enriched pathways to involved in nociception/pain processing (Dopamine-DARPP32 Feedback in cAMP signaling, GABA Receptor Signaling, Opioid Signaling) and neuronal differentiation (e.g., Calcium Signaling, Axon Guidance Signaling, and Endocannabinoid Neuronal Synapse). Our race stratified analyses of individuals with cLBP versus PFCs revealed 2356 DMLs in NHBs and 772 DMLs in NHWs with p < 0.0001 and > 10% methylation difference. Ingenuity Pathway Analysis revealed that many pathways of significance to pain such as Corticotropin Releasing Hormone Signaling, White Adipose Tissue Browning, and GABA Receptor Signaling pathways, were more significant in NHBs than NHWs. CONCLUSION: Even though an individual's self-identified race is a social construct, not a biological variable, racism associated with that classification affects virtually every aspect of life, including disease risk. DNAm induced alterations in stress signaling pathways may explain worse pain outcomes in NHBs.

Epigenome-wide DNA methylation profiling of conditioned pain modulation in individuals with non-specific chronic low back pain.

BACKGROUND: The pathoanatomic cause of chronic low back pain (cLBP) cannot be identified for up to 90% of individuals. However, dysfunctional processing of endogenous nociceptive input, measured as conditioned pain modulation (CPM), has been associated with cLBP and may involve changes in neuronal gene expression. Epigenetic-induced changes such as DNA methylation (DNAm) have been associated with cLBP. METHODS: In the present study, the relationship between CPM and DNAm changes in a sample of community-dwelling adults with nonspecific cLBP (n = 48) and pain-free controls (PFC; n = 50) was examined using reduced representation bisulfite sequencing. Gene ontology (GO) term enrichment and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis were applied to identify key pathways involved in efficient versus deficient CPM. RESULTS: Based on CPM efficiency, we identified 6006 and 18,305 differentially methylated CpG sites (DMCs) with q values < 0.01 among individuals with cLBP and PFCs, respectively. Most of the DMCs were hypomethylated and annotated to genes of relevance to pain, including OPRM1, ADRB2, CACNA2D3, GNA12, LPL, NAXD, and ASPHD1. In both cLBP and PFC groups, the DMCs annotated genes enriched many GO terms relevant to pain processing, including transcription regulation by RNA polymerase II, nervous system development, generation of neurons, neuron differentiation, and neurogenesis. Both groups also enriched the pathways involved in Rap1-signaling, cancer, and dopaminergic neurogenesis. However, MAPK-Ras signaling pathways were enriched in the cLBP, not the PFC group. CONCLUSIONS: This is the first study to investigate the genome-scale DNA methylation profiles of CPM phenotype in adults with cLBP and PFCs. Based on CPM efficiency, fewer DMC enrichment pathways were unique to the cLBP than the PFCs group. Our results suggest that epigenetically induced modification of neuronal development/differentiation pathways may affect CPM efficiency, suggesting novel potential therapeutic targets for central sensitization. However, CPM efficiency and the experience of nonspecific cLBP may be independent. Further mechanistic studies are required to confirm the relationship between CPM, central sensitization, and nonspecific cLBP.

The Area Deprivation Index Corresponds Effectively With Other Measures of Objective Socioeconomic Status in Adults With Chronic Low Back Pain.

Background and Purpose: How the Area Deprivation Index (ADI) performs compared to other measures of socioeconomic status (SES) is unknown. The study purpose is to compare the ADI and other measures of SES in their ability to predict pain severity/interference. Methods: Four measures of SES were compared-ADI, income, education, and subjective social status (SSS). Results: Pain severity/interference correlated positively with ADI (r = .396/r = .33), and negatively with income (r = -.507/r = -.428) and education (r = -.271/r = -.102). Criterion scores of the pain severity model suggest income performs best (AIC = 428.29/BIC = 436.22), followed by ADI (AIC = 437.24/BIC = 445.17), with education performing least well (AIC = 446.35/BIC = 454.29). Similar results were seen for the pain interference model. Conclusions: Neighborhood-level factors warrant consideration along with individual-level factors when attempting to understand the impact of SES on chronic low back pain.

Heat Islands and Chronic Disease: Could African Americans Be More Vulnerable to Heat-Related Health Impacts?

Global warming and environmental heat stress are public health concerns. Urban heat islands, metropolitan areas with higher temperatures compared to their surrounding rural areas, compound the effects of increased environmental heat. In addition to acute heat-related illness, increased environmental heat is linked to exacerbation of chronic diseases. The purpose of this narrative review is to provide an overview of heat islands and how the effects of heat stress intersect with chronic diseases in the African American (AA) community. Across the United States, AAs are more likely to reside in heat islands, resulting in greater exposure to environmental heat. Unfortunately, chronic diseases exacerbated by increased environmental heat disproportionately impact the AA community. Due to the intersection of these disparities, heat-related health risks are likely higher for the AAs. The increased health risks posed by urban heat island exposure on AAs have significant implications for nursing practice, research, and policy.

A Mathematical Model of Breast Tumor Progression Based on Immune Infiltration.

Breast cancer is the most prominent type of cancer among women. Understanding the microenvironment of breast cancer and the interactions between cells and cytokines will lead to better treatment approaches for patients. In this study, we developed a data-driven mathematical model to investigate the dynamics of key cells and cytokines involved in breast cancer development. We used gene expression profiles of tumors to estimate the relative abundance of each immune cell and group patients based on their immune patterns. Dynamical results show the complex interplay between cells and molecules, and sensitivity analysis emphasizes the direct effects of macrophages and adipocytes on cancer cell growth. In addition, we observed the dual effect of IFN-γ on cancer proliferation, either through direct inhibition of cancer cells or by increasing the cytotoxicity of CD8+ T-cells.

Sleep and neighborhood socioeconomic status: a micro longitudinal study of chronic low-back pain and pain-free individuals.

Individuals with chronic low back pain (cLBP) frequently report sleep disturbances. Living in a neighborhood characterized by low-socioeconomic status (SES) is associated with a variety of negative health outcomes, including poor sleep. Whether low-neighborhood SES exacerbates sleep disturbances of people with cLBP, relative to pain-free individuals, has not previously been observed. This study compared associations between neighborhood-level SES, pain-status (cLBP vs. pain-free), and daily sleep metrics in 117 adults (cLBP = 82, pain-free = 35). Neighborhood-level SES was gathered from Neighborhood Atlas, which provides a composite measurement of overall neighborhood deprivation (e.g. area deprivation index). Individuals completed home sleep monitoring for 7-consecutive days/nights. Neighborhood SES and pain-status were tested as predictors of actigraphic sleep variables (e.g., sleep efficiency). Analyses revealed neighborhood-level SES and neighborhood-level SES*pain-status interaction significantly impacted objective sleep quality. These findings provide initial support for the negative impact of low neighborhood-level SES and chronic pain on sleep quality.

Radiation Modalities Used in Lung Cancer: An Overview for Thoracic Surgeons.

Radiation is a constantly evolving technology which plays a role in the management of lung cancer in a variety of settings: as an adjunct to surgery, definitively, and palliatively. Key aspects of radiation oncology-including acute and chronic toxicities of thoracic radiation and rationale for choosing one modality of radiation over another-may be obscure to those outside the field. We aim to provide a useful overview relevant for the thoracic surgeon of radiation technology and delivery. A review was performed of salient articles identifying radiation technologies used in lung cancer which were summarized and expounded upon with focus on integrating their history, evolution, and landmark trials establishing basis of their use. This article reviews the four fundamental means of external beam radiation employed in managing lung cancer and provides visual examples of comparison plans. We also touch on potential practice-changing developments in regards to proton therapy and radiation in the era of immunotherapy. Radiation oncology has evolved considerably over time to become a critical part of lung cancer management, particularly in early-stage inoperable disease and locally advanced disease. Maximizing tumor control while minimizing toxicity drives treatment strategies. Knowledge of these fundamentals will help the thoracic surgeon answer many questions patients pose regarding radiation.

Uncertainty quantification in the radiogenomics modeling of EGFR amplification in glioblastoma.

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. 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. Additionally, we used a separate dataset containing 24 image-localized biopsies from 7 high-grade glioma patients to validate the model. 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). On the separate validation set, our model achieved 78% accuracy amongst the sample predictions with lowest uncertainty. 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.