Assessing the Severity of COVID-19 Lung Injury in Rheumatic Diseases Versus the General Population Using Deep Learning-Derived Chest Radiograph Scores.

OBJECTIVE: COVID-19 patients with rheumatic disease have a higher risk of mechanical ventilation than the general population. The present study was undertaken to assess lung involvement using a validated deep learning algorithm that extracts a quantitative measure of radiographic lung disease severity. METHODS: We performed a comparative cohort study of rheumatic disease patients with COVID-19 and ≥1 chest radiograph within ±2 weeks of COVID-19 diagnosis and matched comparators. We used unadjusted and adjusted (for age, Charlson comorbidity index, and interstitial lung disease) quantile regression to compare the maximum pulmonary x-ray severity (PXS) score at the 10th to 90th percentiles between groups. We evaluated the association of severe PXS score (>9) with mechanical ventilation and death using Cox regression. RESULTS: We identified 70 patients with rheumatic disease and 463 general population comparators. Maximum PXS scores were similar in the rheumatic disease patients and comparators at the 10th to 60th percentiles but significantly higher among rheumatic disease patients at the 70th to 90th percentiles (90th percentile score of 10.2 versus 9.2; adjusted P = 0.03). Rheumatic disease patients were more likely to have a PXS score of >9 (20% versus 11%; P = 0.02), indicating severe pulmonary disease. Rheumatic disease patients with PXS scores >9 versus ≤9 had higher risk of mechanical ventilation (hazard ratio [HR] 24.1 [95% confidence interval (95% CI) 6.7, 86.9]) and death (HR 8.2 [95% CI 0.7, 90.4]). CONCLUSION: Rheumatic disease patients with COVID-19 had more severe radiographic lung involvement than comparators. Higher PXS scores were associated with mechanical ventilation and will be important for future studies leveraging big data to assess COVID-19 outcomes in rheumatic disease patients.

The Radiology: Artificial Intelligence Trainee Editorial Board: Initial Experience and Future Directions.

In 2019, the journal Radiology: Artificial Intelligence introduced its Trainee Editorial Board (TEB) to offer formal training in medical journalism to medical students, radiology residents and fellows, and research-career trainees. The TEB aims to build a community of radiologists, radiation oncologists, medical physicists, and researchers in fields related to artificial intelligence (AI) in radiology. The program presented opportunities to learn about the editorial process, improve skills in writing and reviewing, advance the field of AI in radiology, and help translate and disseminate AI research. To meet these goals, TEB members contribute actively to the editorial process from peer review to publication, participate in educational webinars, and create and curate content in a variety of forms. Almost all of the contact has been mediated through the web. In this article, we share initial experiences and identify future directions and opportunities.

Artificial intelligence applied to musculoskeletal oncology: a systematic review.

Developments in artificial intelligence have the potential to improve the care of patients with musculoskeletal tumors. We performed a systematic review of the published scientific literature to identify the current state of the art of artificial intelligence applied to musculoskeletal oncology, including both primary and metastatic tumors, and across the radiology, nuclear medicine, pathology, clinical research, and molecular biology literature. Through this search, we identified 252 primary research articles, of which 58 used deep learning and 194 used other machine learning techniques. Articles involving deep learning have mostly involved bone scintigraphy, histopathology, and radiologic imaging. Articles involving other machine learning techniques have mostly involved transcriptomic analyses, radiomics, and clinical outcome prediction models using medical records. These articles predominantly present proof-of-concept work, other than the automated bone scan index for bone metastasis quantification, which has translated to clinical workflows in some regions. We systematically review and discuss this literature, highlight opportunities for multidisciplinary collaboration, and identify potentially clinically useful topics with a relative paucity of research attention. Musculoskeletal oncology is an inherently multidisciplinary field, and future research will need to integrate and synthesize noisy siloed data from across clinical, imaging, and molecular datasets. Building the data infrastructure for collaboration will help to accelerate progress towards making artificial intelligence truly useful in musculoskeletal oncology.

Automated Radiology-Arthroscopy Correlation of Knee Meniscal Tears Using Natural Language Processing Algorithms.

RATIONALE AND OBJECTIVES: Train and apply natural language processing (NLP) algorithms for automated radiology-arthroscopy correlation of meniscal tears. MATERIALS AND METHODS: In this retrospective single-institution study, we trained supervised machine learning models (logistic regression, support vector machine, and random forest) to detect medial or lateral meniscus tears on free-text MRI reports. We trained and evaluated model performances with cross-validation using 3593 manually annotated knee MRI reports. To assess radiology-arthroscopy correlation, we then randomly partitioned this dataset 80:20 for training and testing, where 108 test set MRIs were followed by knee arthroscopy within 1 year. These free-text arthroscopy reports were also manually annotated. The NLP algorithms trained on the knee MRI training dataset were then evaluated on the MRI and arthroscopy report test datasets. We assessed radiology-arthroscopy agreement using the ensembled NLP-extracted findings versus manually annotated findings. RESULTS: The NLP models showed high cross-validation performance for meniscal tear detection on knee MRI reports (medial meniscus F1 scores 0.93-0.94, lateral meniscus F1 scores 0.86-0.88). When these algorithms were evaluated on arthroscopy reports, despite never training on arthroscopy reports, performance was similar, though higher with model ensembling (medial meniscus F1 score 0.97, lateral meniscus F1 score 0.99). However, ensembling did not improve performance on knee MRI reports. In the radiology-arthroscopy test set, the ensembled NLP models were able to detect mismatches between MRI and arthroscopy reports with sensitivity 79% and specificity 87%. CONCLUSION: Radiology-arthroscopy correlation can be automated for knee meniscal tears using NLP algorithms, which shows promise for education and quality improvement.

Yttrium-90 Hepatic Radioembolization for Advanced Chemorefractory Metastatic Colorectal Cancer: Survival Outcomes Based on Right- Versus Left-Sided Primary Tumor Location.

BACKGROUND. Primary colon cancer location affects survival of patients with metastatic colorectal cancer (mCRC). Outcomes based on primary tumor location after salvage hepatic radioembolization with 90Y resin microspheres are not well studied. OBJECTIVE. The objectives of this study are to assess the survival outcomes of patients with advanced chemorefractory mCRC treated with 90Y radioembolization, as stratified by primary tumor location, and to explore potential factors that are predictive of survival. METHODS. A total of 99 patients who had progressive mCRC liver metastases while receiving systemic therapy and who were treated with 90Y radioembolization at a single center were retrospectively analyzed. For 89 patients, tumor response on the first imaging follow-up examination (CT or MRI performed at a mean [± SD] of 1.9 ± 0.9 months after 90Y radioembolization) was evaluated using RECIST. Overall survival (OS), OS after 90Y radioembolization, and hepatic progression-free survival (PFS) were calculated using the Kaplan-Meier method. Outcomes and associations of outcomes with tumor response were compared between patients with left- and right-sided tumors. RESULTS. A total of 74 patients had left-sided colon cancer, and 25 patients had right-sided colon cancer. Median OS from the time of mCRC diagnosis was 37.2 months, median OS after 90Y radioembolization was 5.8 months, and median hepatic PFS was 3.3 months. Based on RECIST, progressive disease on first imaging follow-up was observed in 38 patients (43%) after 90Y radioembolization and was associated with shorter OS after 90Y radioembolization compared with observation of disease control on first imaging follow-up (4.0 vs 10.5 months; p < .001). Patients with right-sided primary tumors showed decreased median OS after 90Y radioembolization compared with patients with left-sided primary tumors (5.4 vs 6.2 months; p = .03). Right- and left-sided primary tumors showed no significant difference in RECIST tumor response, hepatic PFS, or extrahepatic disease progression (p > .05). Median survival after 90Y radioembolization was significantly lower among patients with progressive disease than among those with disease control in the group with left-sided primary tumors (4.2 vs 13.9 months; p < .001); however, this finding was not observed in the group with right-sided primary tumors (3.3 vs 7.2 months; p = .05). CONCLUSION. Right-sided primary tumors were independently associated with decreased survival among patients with chemorefractory mCRC after 90Y radioembolization, despite these patients having a similar RECIST tumor response, hepatic PFS, and extrahepatic disease progression compared with patients with left-sided primary tumors. CLINICAL IMPACT. Primary colon cancer location impacts outcomes after salvage 90Y radioembolization and may help guide patient selection.

Same-Day Yttrium-90 Radioembolization: Feasibility with Resin Microspheres.

PURPOSE: To evaluate the feasibility of a same-day yttrium-90 (90Y) radioembolization protocol with resin microspheres (including pretreatment angiography, lung shunt fraction [LSF] determination, and radioembolization) for the treatment of hepatocellular carcinoma (HCC) and liver metastases. MATERIALS AND METHODS: All same-day radioembolization procedures performed over 1 y (February 2017 to January 2018) were included in this single-institutional retrospective analysis, in which 34 procedures were performed in 26 patients (median age, 63 y; 13 women), 19 with liver metastases and 7 with HCC. Yttrium-90 treatment activities were calculated by body surface area method. Tumor imaging response was assessed by Response Evaluation Criteria In Solid Tumors (RECIST) 1.1 for liver metastases and modified RECIST for HCC. Clinical side effects and adverse events were graded per Common Terminology Criteria for Adverse Events version 4.0. RESULTS: All planned cases were technically successful, and no cases were canceled for elevated LSF or vascular anatomic reasons. Pretreatment angiography modified the planned 90Y treatment activity in 1 case in which vascular anatomy required a lobar-dose split into 2 for segmental infusions. In 18% of cases, patients were briefly admitted after the procedure for observation or symptom management. Imaging evaluation of initial efficacy at 1 month demonstrated partial response in 25% and stable disease in 67% of patients with liver metastases and partial/complete response in 43% and stable disease in 14% of patients with HCC. Grade ≥ 3 adverse events occurred in 6% of cases, with no systemic therapy-limiting toxicities. The mean total procedure time was 4.2 hours. CONCLUSIONS: A same-day 90Y radioembolization protocol with resin microspheres is feasible in select patients, which can expedite cancer therapy.

Chemoradiation impairs normal developmental cortical thinning in medulloblastoma.

Medulloblastoma patients are treated with surgery, radiation and chemotherapy. Radiation dose to the temporal lobe may be associated with neurocognitive sequelae. Longitudinal changes of temporal lobe cortical thickness may result from neurodevelopmental processes such as synaptic pruning. This study applies longitudinal image analysis to compare developmental change in cortical thickness in medulloblastoma (MB) patients who were treated by combined modality therapy to that of cerebellar juvenile pilocytic astrocytoma (JPA) patients who were treated by surgery alone. We hypothesized that the rates of developmental change in cortical thickness would differ between these two groups. This retrospective cohort study assessed changes in cortical thickness over time between MB and JPA patients. High-resolution magnetic resonance (MR) images of 14 MB and 7 JPA subjects were processed to measure cortical thickness of bilateral temporal lobe substructures. A linear mixed effects model was used to identify differences in substructure longitudinal changes in cortical thickness. The left temporal lobe exhibited overall increased cortical thickness in MB patients relative to JPA patients who showed overall cortical thinning (mean annual cortical thickness change: MB 0.14 mm/year versus JPA -0.018 mm/year across all substructures), particularly in the inferior temporal lobe substructures (p < 0.0001). The cortical thickness change of the right temporal lobe substructures exhibited similar, though attenuated trends (p = 0.002). MB patients exhibit overall increased cortical thickness rather than cortical thinning as seen in JPA patients and as expected in normal cortical development. These observations are possibly due to chemoradiation induced-disruption of normal neuronal mechanisms. Longitudinal image analysis may identify early biomarkers for neurocognitive function with routine imaging.

Brain Perfusion and Diffusion Abnormalities in Children Treated for Posterior Fossa Brain Tumors.

OBJECTIVE: To compare cerebral perfusion and diffusion in survivors of childhood posterior fossa brain tumor with neurologically normal controls and correlate differences with cognitive dysfunction. STUDY DESIGN: We analyzed retrospectively arterial spin-labeled cerebral blood flow (CBF) and apparent diffusion coefficient (ADC) in 21 patients with medulloblastoma (MB), 18 patients with pilocytic astrocytoma (PA), and 64 neurologically normal children. We generated ANCOVA models to evaluate treatment effects on the cerebral cortex, thalamus, caudate, putamen, globus pallidus, hippocampus, amygdala, nucleus accumbens, and cerebral white matter at time points an average of 5.7 years after original diagnosis. A retrospective review of patient charts identified 12 patients with neurocognitive data and in whom the relationship between IQ and magnetic resonance imaging variables was assessed for each brain structure. RESULTS: Patients with MB (all treated with surgery, chemotherapy, and radiation) had significantly lower global CBF relative to controls (10%-23% lower, varying by anatomic region, all adjusted P?

Radiation-induced brain injury: low-hanging fruit for neuroregeneration.

Brain radiation is a fundamental tool in neurooncology to improve local tumor control, but it leads to profound and progressive impairments in cognitive function. Increased attention to quality of life in neurooncology has accelerated efforts to understand and ameliorate radiation-induced cognitive sequelae. Such progress has coincided with a new understanding of the role of CNS progenitor cell populations in normal cognition and in their potential utility for the treatment of neurological diseases. The irradiated brain exhibits a host of biochemical and cellular derangements, including loss of endogenous neurogenesis, demyelination, and ablation of endogenous oligodendrocyte progenitor cells. These changes, in combination with a state of chronic neuroinflammation, underlie impairments in memory, attention, executive function, and acquisition of motor and language skills. Animal models of radiation-induced brain injury have demonstrated a robust capacity of both neural stem cells and oligodendrocyte progenitor cells to restore cognitive function after brain irradiation, likely through a combination of cell replacement and trophic effects. Oligodendrocyte progenitor cells exhibit a remarkable capacity to migrate, integrate, and functionally remyelinate damaged white matter tracts in a variety of preclinical models. The authors here critically address the opportunities and challenges in translating regenerative cell therapies from rodents to humans. Although valiant attempts to translate neuroprotective therapies in recent decades have almost uniformly failed, the authors make the case that harnessing human radiation-induced brain injury as a scientific tool represents a unique opportunity to both successfully translate a neuroregenerative therapy and to acquire tools to facilitate future restorative therapies for human traumatic and degenerative diseases of the central nervous system.

Decreased tumor apparent diffusion coefficient correlates with objective response of pediatric low-grade glioma to bevacizumab.

Recent small, retrospective series suggest bevacizumab may be a therapeutic option for recurrent pediatric low-grade glioma (LGG). Assessment of therapeutic responses is complicated by the unpredictable natural history of these tumors. Because diffusion-weighted imaging quantifies microscopic water motion affected by cellular density and histologic features, we hypothesized that it may be helpful in monitoring therapeutic response of LGG to bevacizumab. We retrospectively reviewed eight consecutive patients, median age 4.8 (range 2.3-12.3) years at initiation of bevacizumab therapy for recurrent or refractory LGG. Patients received 10 mg/kg/dose every 2 weeks (median 16 doses/therapy course). Mean apparent diffusion coefficient (ADC) was measured and analyzed in respect to tumor volume. Following the first treatment course, seven of eight patients had reduced tumor volume (≥25 %) and ADC. The median decrease in tumor volume was 47% (range -6 to 78 %) and the median decrease in ADC was 14 % (range -5 to 30 %). The ADC was significantly decreased during therapy, whereas the decrease in volume was seen only after therapy completion. There was a positive correlation between percent change in tumor volume and ADC (p < 0.05). We report a decrease in tumor ADC during initial bevacizumab therapy that is accompanied by a decrease in volume following therapy. Imaging changes in microscopic water motion associated with histology may be useful in monitoring the therapeutic response of LGG to bevacizumab.

Aging-like changes in the transcriptome of irradiated microglia.

Whole brain irradiation remains important in the management of brain tumors. Although necessary for improving survival outcomes, cranial irradiation also results in cognitive decline in long-term survivors. A chronic inflammatory state characterized by microglial activation has been implicated in radiation-induced brain injury. We here provide the first comprehensive transcriptional profile of irradiated microglia. Fluorescence-activated cell sorting was used to isolate CD11b+ microglia from the hippocampi of C57BL/6 and Balb/c mice 1 month after 10 Gy cranial irradiation. Affymetrix gene expression profiles were evaluated using linear modeling and rank product analyses. One month after irradiation, a conserved irradiation signature across strains was identified, comprising 448 and 85 differentially up- and downregulated genes, respectively. Gene set enrichment analysis demonstrated enrichment for inflammation, including M1 macrophage-associated genes, but also an unexpected enrichment for extracellular matrix and blood coagulation-related gene sets, in contrast previously described microglial states. Weighted gene coexpression network analysis confirmed these findings and further revealed alterations in mitochondrial function. The RNA-seq transcriptome of microglia 24-h postradiation proved similar to the 1-month transcriptome, but additionally featured alterations in apoptotic and lysosomal gene expression. Reanalysis of published aging mouse microglia transcriptome data demonstrated striking similarity to the 1-month irradiated microglia transcriptome, suggesting that shared mechanisms may underlie aging and chronic irradiation-induced cognitive decline. GLIA 2015;63:754-767.

The global landscape of stem cell clinical trials.

AIM: To provide a comprehensive analysis of clinical trials (CTs) listed in worldwide registries involving new applications for stem cell-based treatments and account for the role of industry. MATERIALS & METHODS: We developed a data set of 4749 stem cell CTs up to 2013 in worldwide registries. We defined 1058 novel CTs (i.e., trials that were not observational in nature; did not involve an established stem cell therapy for an established indication, such as hematopoietic stem cells for leukemia; and did not investigate supportive measures). Based on trial descriptions, we manually coded these for eight additional elements. RESULTS: Our analysis details the characteristics of novel stem cell CTs (e.g., stem cell types being tested, disease being targeted, and whether interventions were autologous or allogeneic), geotemporal trends, and private sector involvement as sponsor or collaborator. CONCLUSION: The field is progressing at a steady pace with emerging business models for stem cell therapeutics. However, therapeutic rhetoric must be tempered to reflect current clinical and research realities.

Multiplex meta-analysis of medulloblastoma expression studies with external controls.

We propose and discuss a method for doing gene expression meta-analysis (multiple datasets) across multiplex measurement modalities measuring the expression of many genes simultaneously (e.g. microarrays and RNAseq) using external control samples and a method of heterogeneity detection to identify and filter on comparable gene expression measurements. We demonstrate this approach on publicly available gene expression datasets from samples of medulloblastoma and normal cerebellar tissue and identify some potential new targets in the treatment of medulloblastoma.

Is belief larger than fact: expectations, optimism and reality for translational stem cell research.

BACKGROUND: Stem cell (SC) therapies hold remarkable promise for many diseases, but there is a significant gulf between public expectations and the reality of progress toward clinical application. Public expectations are fueled by stakeholder arguments for research and public funding, coupled with intense media coverage in an ethically charged arena. We examine media representations in light of the expanding global landscape of SC clinical trials, asking what patients may realistically expect by way of timelines for the therapeutic and curative potential of regenerative medicine? METHODS: We built 2 international datasets: (1) 3,404 clinical trials (CT) containing 'stem cell*' from ClinicalTrials.gov and the World Health Organization's International Clinical Trials Registry Search Portal; and (2) 13,249 newspaper articles on SC therapies using Factiva.com. We compared word frequencies between the CT descriptions and full-text newspaper articles for the number containing terms for SC type and diseases/conditions. We also developed inclusion and exclusion criteria to identify novel SC CTs, mainly regenerative medicine applications. RESULTS: Newspaper articles focused on human embryonic SCs and neurological conditions with significant coverage as well of cardiovascular disease and diabetes. In contrast, CTs used primarily hematopoietic SCs, with an increase in CTs using mesenchymal SCs since 2007. The latter dominated our novel classification for CTs, most of which are in phases I and II. From the perspective of the public, expecting therapies for neurological conditions, there is limited activity in what may be considered novel applications of SC therapies. CONCLUSIONS: Given the research, regulatory, and commercialization hurdles to the clinical translation of SC research, it seems likely that patients and political supporters will become disappointed and disillusioned. In this environment, proponents need to make a concerted effort to temper claims. Even though the field is highly promising, it lacks significant private investment and is largely reliant on public support, requiring a more honest acknowledgement of the expected therapeutic benefits and the timelines to achieving them.