Anonymization and validation of three-dimensional volumetric renderings of computed tomography data using commercially available T1-weighted magnetic resonance imaging-based algorithms.

Purpose: Previous studies have demonstrated that three-dimensional (3D) volumetric renderings of magnetic resonance imaging (MRI) brain data can be used to identify patients using facial recognition. We have shown that facial features can be identified on simulation-computed tomography (CT) images for radiation oncology and mapped to face images from a database. We aim to determine whether CT images can be anonymized using anonymization software that was designed for T1-weighted MRI data. Approach: Our study examines (1) the ability of off-the-shelf anonymization algorithms to anonymize CT data and (2) the ability of facial recognition algorithms to identify whether faces could be detected from a database of facial images. Our study generated 3D renderings from 57 head CT scans from The Cancer Imaging Archive database. Data were anonymized using AFNI (deface, reface, and 3Dskullstrip) and FSL's BET. Anonymized data were compared to the original renderings and passed through facial recognition algorithms (VGG-Face, FaceNet, DLib, and SFace) using a facial database (labeled faces in the wild) to determine what matches could be found. Results: Our study found that all modules were able to process CT data and that AFNI's 3Dskullstrip and FSL's BET data consistently showed lower reidentification rates compared to the original. Conclusions: The results from this study highlight the potential usage of anonymization algorithms as a clinical standard for deidentifying brain CT data. Our study demonstrates the importance of continued vigilance for patient privacy in publicly shared datasets and the importance of continued evaluation of anonymization methods for CT data.

Interplay of Immunosuppression and Immunotherapy Among Patients With Cancer and COVID-19.

Importance: Cytokine storm due to COVID-19 can cause high morbidity and mortality and may be more common in patients with cancer treated with immunotherapy (IO) due to immune system activation. Objective: To determine the association of baseline immunosuppression and/or IO-based therapies with COVID-19 severity and cytokine storm in patients with cancer. Design, Setting, and Participants: This registry-based retrospective cohort study included 12 046 patients reported to the COVID-19 and Cancer Consortium (CCC19) registry from March 2020 to May 2022. The CCC19 registry is a centralized international multi-institutional registry of patients with COVID-19 with a current or past diagnosis of cancer. Records analyzed included patients with active or previous cancer who had a laboratory-confirmed infection with SARS-CoV-2 by polymerase chain reaction and/or serologic findings. Exposures: Immunosuppression due to therapy; systemic anticancer therapy (IO or non-IO). Main Outcomes and Measures: The primary outcome was a 5-level ordinal scale of COVID-19 severity: no complications; hospitalized without requiring oxygen; hospitalized and required oxygen; intensive care unit admission and/or mechanical ventilation; death. The secondary outcome was the occurrence of cytokine storm. Results: The median age of the entire cohort was 65 years (interquartile range [IQR], 54-74) years and 6359 patients were female (52.8%) and 6598 (54.8%) were non-Hispanic White. A total of 599 (5.0%) patients received IO, whereas 4327 (35.9%) received non-IO systemic anticancer therapies, and 7120 (59.1%) did not receive any antineoplastic regimen within 3 months prior to COVID-19 diagnosis. Although no difference in COVID-19 severity and cytokine storm was found in the IO group compared with the untreated group in the total cohort (adjusted odds ratio [aOR], 0.80; 95% CI, 0.56-1.13, and aOR, 0.89; 95% CI, 0.41-1.93, respectively), patients with baseline immunosuppression treated with IO (vs untreated) had worse COVID-19 severity and cytokine storm (aOR, 3.33; 95% CI, 1.38-8.01, and aOR, 4.41; 95% CI, 1.71-11.38, respectively). Patients with immunosuppression receiving non-IO therapies (vs untreated) also had worse COVID-19 severity (aOR, 1.79; 95% CI, 1.36-2.35) and cytokine storm (aOR, 2.32; 95% CI, 1.42-3.79). Conclusions and Relevance: This cohort study found that in patients with cancer and COVID-19, administration of systemic anticancer therapies, especially IO, in the context of baseline immunosuppression was associated with severe clinical outcomes and the development of cytokine storm. Trial Registration: ClinicalTrials.gov Identifier: NCT04354701.

Trends in guideline-adherent chemoradiation therapy for locally advanced cervical cancer before and after the affordable care act.

OBJECTIVE: To assess trends in guideline-adherent chemoradiation therapy (GA-CRT) for locally advanced cervical cancer relative to Patient Protection and Affordable Care Act (ACA) implementation. METHODS: National Cancer Database patients treated with chemoradiation for locally advanced cervical cancer (FIGO 2018 Stage IB3-IVA) from 2004 to 2016 were included. GA-CRT was defined according to NCCN guidelines and included: 1) delivery of external beam radiation, 2) brachytherapy, and 3) chemotherapy, 4) no radical hysterectomy. Logistic regression was used to determine trends in GA-CRT relative to the ACA. Survival was also estimated using Kaplan-Meier analysis. RESULTS: 37,772 patients met inclusion criteria (Pre-ACA:16,169; Post-ACA:21,673). A total of 33,116 patients had squamous cell carcinoma and 4626 patients had other histologies. Forty-five percent of patients had lymph node-positive disease. A total of 14.6% of patients had Stage I disease, 41.8% had Stage II disease, 36.4% had Stage III disease, and 7.9% had Stage IVA disease. On multivariable analysis, medicare insurance (OR 0.91; 95%CI: 0.84-0.99 compared to commercial insurance), non-squamous histology (OR 0.83; 95%CI: 0.77-0.89 for adenocarcinoma) and increasing Charlson-Deyo score were associated with decreased odds of receiving GA care. Increasing T-stage was associated with greater receipt of GA-CRT. The percentage of the population that received guideline adherent care increased post-ACA (Pre-ACA 28%; Post-ACA 34%; p < 0.001). Adherence to treatment guidelines increased 2-year survival by 15% (GA 76%; Not GA 61%; p < 0.001). Increased 2-year survival was seen in the post-ACA cohort (Pre-ACA 62%; Post-ACA 69%; p < 0.001). CONCLUSIONS: Implementation of the ACA was associated with improved GA-CRT and survival in patients with locally advanced cervical cancer.

Unmasking a Privacy Concern: Potential Identification of Patients in an Immobilization Mask from 3-Dimensional Reconstructions of Simulation Computed Tomography.

Previous studies have demonstrated that patients can be identified from 3-dimensional (3D) reconstructions of computed tomography (CT) or magnetic resonance imaging data of the brain or head and neck. This presents a privacy and security concern for scan data released to public data sets. It is unknown whether thermoplastic immobilization masks used for treatment planning in radiation therapy are sufficient to prevent facial recognition. Our study sought to evaluate whether patients with an immobilization mask could be identified on 3D reconstructions of scan data. Our study reconstructed 3D images from simulation CT (SIM-CT) scans of 35 patients and compared these to original patient photographs to test if the thermoplastic mask obfuscated facial features. Blind review from 4 facial recognition algorithms and a human (radiation oncologist) was evaluated for the ability to match 3D reconstructions of patients scans to patient images. The matching procedure was repeated against an expanded testing data set of the 35 patient photographs plus 13,233 facial photographs from the "Labeled Faces in the Wild" data set (13,268 photographs in total). Facial recognition algorithms were able to match a maximum of 83% (range, 60%-83%) of patients to the corresponding images. Radiation Oncologist blinded review correctly matched 80% of patients to the corresponding images. Ethnicity and facial hair were the most common reasons for patient mismatch. In the expanded testing data set, algorithms were also able to match a maximum of 83% (range, 57%-83%) of patients. The majority of patients were able to be identified through computer algorithm or human review even under a SIM-CT mask. These results suggest there is a potential privacy and security concern when SIM-CT data are released to publicly available data sets.

Categorization of Adverse Events Reported to the FDA Pertaining to Tibia Intramedullary Nailing.

OpenFDA is an open access database maintained by the United States Food and Drug Administration (FDA) that we queried for adverse events (AEs) related to product devices used during tibia intramedullary nailing (IMN) procedures. There was a total of 1,799 reports pertaining to tibial intramedullary nailing from 1996 to 2020. Causes included infection (451), nonunion (380), intraoperative issue (343), painful hardware (234), implant fracture (195), other (68), loosening (35), surgeon error (24), packing problem (24), patient injury (12), expiration (12), contamination (11) and allergic reaction (10). The total number of events increased in 2016 and 2018, which was attributed to 510k approval for Stryker. Of the Aes, 1,400 resulted in an injury to the patient. In total, 78% occurred in the post-operative period, and 68% required additional surgery. Most incidents related to tibia IMNs result in injury and require additional surgery. When new products are released, AEs occur quickly and in bulk. (Journal of Surgical Orthopaedic Advances 31(4):237-241, 2022).

Adverse events of after-loading high dose rate brachytherapy reported to the United States Food and Drug Administration (FDA).

PURPOSE: To provide an assessment of safety regarding high-dose-rate after-loading brachytherapy (HDR-BT) based on adverse events reported to the OpenFDA, an open access database maintained by the United States Food and Drug Administration (FDA). METHODS: OpenFDA was queried for HDR-BT events between 1993 and 2019. A brachytherapist categorized adverse events (AEs) based on disease site, applicator, manufacturer, event type, dosimetry impact, and outcomes. Important findings are summarized. RESULTS: 372 AEs were reported between 1993 and 2019, with a downwards trend after 2014. Nearly half of AEs (48.9%) were caused by a device malfunction, and 27.4% resulted in patient injury. Breast (49.2%) and Gyn (23.7%) were the most common disease sites of AEs. Applicator breaks cause the majority of AEs (64.2%) and breast balloon implants were the most common applicator to malfunction (38.7%). User error contributed to only 16.7% of events. 11.0% of events required repair of the afterloader. There were no reported staff injuries or patient deaths from an AE, however 24.7% of patients received resultant incorrect radiation dose, 16.4% required additional procedures to rectify the AE, and 3.0% resulted in unintended radiation to staff. CONCLUSION: The OpenFDA database has shown a decreasing trend in AEs since 2014 for HDR-BT. Most AEs are not caused by user error and do not cause patient injury or incorrect radiation dose. Investigation into methods to prevent failures and improve applicators such as the breast balloon could improve safety. These results support the continued use of HDR-BT as a safe treatment modality for cancer.

Exercise alters brain activation in Gulf War Illness and Myalgic Encephalomyelitis/Chronic Fatigue Syndrome.

Gulf War Illness affects 25-30% of American veterans deployed to the 1990-91 Persian Gulf War and is characterized by cognitive post-exertional malaise following physical effort. Gulf War Illness remains controversial since cognitive post-exertional malaise is also present in the more common Myalgic Encephalomyelitis/Chronic Fatigue Syndrome. An objective dissociation between neural substrates for cognitive post-exertional malaise in Gulf War Illness and Myalgic Encephalomyelitis/Chronic Fatigue Syndrome would represent a biological basis for diagnostically distinguishing these two illnesses. Here, we used functional magnetic resonance imaging to measure neural activity in healthy controls and patients with Gulf War Illness and Myalgic Encephalomyelitis/Chronic Fatigue Syndrome during an N-back working memory task both before and after exercise. Whole brain activation during working memory (2-Back > 0-Back) was equal between groups prior to exercise. Exercise had no effect on neural activity in healthy controls yet caused deactivation within dorsal midbrain and cerebellar vermis in Gulf War Illness relative to Myalgic Encephalomyelitis/Chronic Fatigue Syndrome patients. Further, exercise caused increased activation among Myalgic Encephalomyelitis/Chronic Fatigue Syndrome patients within the dorsal midbrain, left operculo-insular cortex (Rolandic operculum) and right middle insula. These regions-of-interest underlie threat assessment, pain, interoception, negative emotion and vigilant attention. As they only emerge post-exercise, these regional differences likely represent neural substrates of cognitive post-exertional malaise useful for developing distinct diagnostic criteria for Gulf War Illness and Myalgic Encephalomyelitis/Chronic Fatigue Syndrome.

Machine Learning Detects Pattern of Differences in Functional Magnetic Resonance Imaging (fMRI) Data between Chronic Fatigue Syndrome (CFS) and Gulf War Illness (GWI).

BACKGROUND: Gulf War Illness (GWI) and Chronic Fatigue Syndrome (CFS) are two debilitating disorders that share similar symptoms of chronic pain, fatigue, and exertional exhaustion after exercise. Many physicians continue to believe that both are psychosomatic disorders and to date no underlying etiology has been discovered. As such, uncovering objective biomarkers is important to lend credibility to criteria for diagnosis and to help differentiate the two disorders. METHODS: We assessed cognitive differences in 80 subjects with GWI and 38 with CFS by comparing corresponding fMRI scans during 2-back working memory tasks before and after exercise to model brain activation during normal activity and after exertional exhaustion, respectively. Voxels were grouped by the count of total activity into the Automated Anatomical Labeling (AAL) atlas and used in an "ensemble" series of machine learning algorithms to assess if a multi-regional pattern of differences in the fMRI scans could be detected. RESULTS: A K-Nearest Neighbor (70%/81%), Linear Support Vector Machine (SVM) (70%/77%), Decision Tree (82%/82%), Random Forest (77%/78%), AdaBoost (69%/81%), Naïve Bayes (74%/78%), Quadratic Discriminant Analysis (QDA) (73%/75%), Logistic Regression model (82%/82%), and Neural Net (76%/77%) were able to differentiate CFS from GWI before and after exercise with an average of 75% accuracy in predictions across all models before exercise and 79% after exercise. An iterative feature selection and removal process based on Recursive Feature Elimination (RFE) and Random Forest importance selected 30 regions before exercise and 33 regions after exercise that differentiated CFS from GWI across all models, and produced the ultimate best accuracies of 82% before exercise and 82% after exercise by Logistic Regression or Decision Tree by a single model, and 100% before and after exercise when selected by any six or more models. Differential activation on both days included the right anterior insula, left putamen, and bilateral orbital frontal, ventrolateral prefrontal cortex, superior, inferior, and precuneus (medial) parietal, and lateral temporal regions. Day 2 had the cerebellum, left supplementary motor area and bilateral pre- and post-central gyri. Changes between days included the right Rolandic operculum switching to the left on Day 2, and the bilateral midcingulum switching to the left anterior cingulum. CONCLUSION: We concluded that CFS and GWI are significantly differentiable using a pattern of fMRI activity based on an ensemble machine learning model.

Logistic Regression Algorithm Differentiates Gulf War Illness (GWI) Functional Magnetic Resonance Imaging (fMRI) Data from a Sedentary Control.

Gulf War Illness (GWI) is a debilitating condition characterized by dysfunction of cognition, pain, fatigue, sleep, and diverse somatic symptoms with no known underlying pathology. As such, uncovering objective biomarkers such as differential regions of activity within a Functional Magnetic Resonance Imaging (fMRI) scan is important to enhance validity of the criteria for diagnosis. Symptoms are exacerbated by mild activity, and exertional exhaustion is a key complaint amongst sufferers. We modeled this exertional exhaustion by having GWI (n = 80) and sedentary control (n = 31) subjects perform submaximal exercise stress tests on two consecutive days. Cognitive differences were assessed by comparing fMRI scans performed during 2-Back working memory tasks before and after the exercise. Machine learning algorithms were used to identify differences in brain activation patterns between the two groups on Day 1 (before exercise) and Day 2 (after exercise). The numbers of voxels with t > 3.17 (corresponding to p < 0.001 uncorrected) were determined for brain regions defined by the Automated Anatomical Labeling (AAL) atlas. Data were divided 70:30 into training and test sets. Recursive feature selection identified twenty-nine regions of interest (ROIs) that significantly distinguished GWI from control on Day 1 and 28 ROIs on Day 2. Ten regions were present in both models between the two days, including right anterior insula, orbital frontal cortex, thalamus, bilateral temporal poles, and left supramarginal gyrus and cerebellar Crus 1. The models had 70% accuracy before exercise on Day 1 and 85% accuracy after exercise on Day 2, indicating the logistic regression model significantly differentiated subjects with GWI from the sedentary control group. Exercise caused changes in these patterns that may indicate the cognitive differences caused by exertional exhaustion. A second set of predictive models was able to classify previously identified GWI exercise subgroups START, STOPP, and POTS for both Days 1 and Days 2 with 67% and 69% accuracy respectively. This study was the first of its kind to differentiate GWI and the three sub-phenotypes START, STOPP, and POTS from a sedentary control using a logistic regression estimation method.

A Machine Learning Approach to the Differentiation of Functional Magnetic Resonance Imaging Data of Chronic Fatigue Syndrome (CFS) From a Sedentary Control.

Chronic Fatigue Syndrome (CFS) is a debilitating condition estimated to impact at least 1 million individuals in the United States, however there persists controversy about its existence. Machine learning algorithms have become a powerful methodology for evaluating multi-regional areas of fMRI activation that can classify disease phenotype from sedentary control. Uncovering objective biomarkers such as an fMRI pattern is important for lending credibility to diagnosis of CFS. fMRI scans were evaluated for 69 patients (38 CFS and 31 Control) taken before (Day 1) and after (Day 2) a submaximal exercise test while undergoing the n-back memory paradigm. A predictive model was created by grouping fMRI voxels into the Automated Anatomical Labeling (AAL) atlas, splitting the data into a training and testing dataset, and feeding these inputs into a logistic regression to evaluate differences between CFS and control. Model results were cross-validated 10 times to ensure accuracy. Model results were able to differentiate CFS from sedentary controls at a 80% accuracy on Day 1 and 76% accuracy on Day 2 (Table 3). Recursive features selection identified 29 ROI's that significantly distinguished CFS from control on Day 1 and 28 ROI's on Day 2 with 10 regions of overlap shared with Day 1 (Figure 3). These 10 shared regions included the putamen, inferior frontal gyrus, orbital (F3O), supramarginal gyrus (SMG), temporal pole; superior temporal gyrus (T1P) and caudate ROIs. This study was able to uncover a pattern of activated neurological regions that differentiated CFS from Control. This pattern provides a first step toward developing fMRI as a diagnostic biomarker and suggests this methodology could be emulated for other disorders. We concluded that a logistic regression model performed on fMRI data significantly differentiated CFS from Control.

Exercise alters cerebellar and cortical activity related to working memory in phenotypes of Gulf War Illness.

Gulf War Illness affects 25-32% of veterans from the 1990-91 Persian Gulf War. Post-exertional malaise with cognitive dysfunction, pain and fatigue following physical and/or mental effort is a defining feature of Gulf War Illness. We modelled post-exertional malaise by assessing changes in functional magnetic resonance imaging at 3T during an N-Back working memory task performed prior to a submaximal bicycle stress test and after an identical stress test 24 h later. Serial trends in postural changes in heart rate between supine and standing defined three subgroups of veterans with Gulf War Illness: Postural Orthostatic Tachycardia Syndrome (GWI-POTS, 15%, n = 11), Stress Test Associated Reversible Tachycardia (GWI-START, 31%, n = 23) and Stress Test Originated Phantom Perception (GWI-STOPP, no postural tachycardia, 54%, n = 46). Before exercise, there were no differences in blood oxygenation level-dependent activity during the N-Back task between control (n = 31), GWI-START, GWI-STOPP and GWI-POTS subgroups. Exercise had no effects on blood oxygenation level-dependent activation in controls. GWI-START had post-exertional deactivation of cerebellar dentate nucleus and vermis regions associated with working memory. GWI-STOPP had significant activation of the anterior supplementary motor area that may be a component of the anterior salience network. There was a trend for deactivation of the vermis in GWI-POTS after exercise. These patterns of cognitive dysfunction were apparent in Gulf War Illness only after the exercise stressor. Mechanisms linking the autonomic dysfunction of Stress Test Associated Reversible Tachycardia and Postural Orthostatic Tachycardia Syndrome to cerebellar activation, and Stress Test Originated Phantom Perception to cortical sensorimotor alterations, remain unclear but may open new opportunities for understanding, diagnosing and treating Gulf War Illness.

Learning curves: historical trends of FDA-reported adverse events for dermal fillers.

Dermal fillers are medical devices regulated by the US Food and Drug Administration (FDA); therefore, reported adverse events (AEs) are publicly available via OpenFDA. Evaluation of historical AE data trends may help distinguish between AEs related to expected learning curves associated with a new type of filler from AEs related to inherent characteristics of a product. In this study, the full history of AE data was evaluated to establish reproducible learning curves for FDA-approved dermal fillers. Reactions to AEs for new fillers that garner FDA approval or are awarded new indications should be in response to analysis of AE rate data and determination of whether they fit on a historically normal learning curve.