Deep Learning-Based ASPECTS Algorithm Enhances Reader Performance and Reduces Interpretation Time.

BACKGROUND AND PURPOSE: ASPECTS is a long-standing and well documented selection criteria for acute ischemic stroke treatment, however, the interpretation of ASPECTS is a challenging and time-consuming task for physicians with significant interobserver variabilities. We conducted a multi-reader, multi-case study in which readers assessed ASPECTS without and with the support of a deep learning (DL)-based algorithm in order to analyze the impact of the software on clinicians' performance and interpretation time. MATERIALS AND METHODS: A total of 200 NCCT scans from 5 clinical sites (27 scanner models, 4 different vendors) were retrospectively collected. Reference standard was established through the consensus of three expert neuroradiologists who had access to baseline CTA and CTP data. Subsequently, eight additional clinicians (four typical ASPECTS reader and four senior neuroradiologists) analyzed the NCCT scans without and with the assistance of CINA-ASPECTS (Avicenna.AI, La Ciotat, France), a DLbased FDA-cleared and CE-marked algorithm designed to automatically compute ASPECTS. Differences were evaluated in both performance and interpretation time between the assisted and unassisted assessments. RESULTS: With software aid, readers demonstrated increased region-based accuracy from 72.4% to 76.5% (p<0.05), and increased ROC AUC from 0.749 to 0.788 (p<0.05). Notably, all readers exhibited an improved ROC AUC when utilizing the software. Moreover, use of the algorithm improved the score-based inter-observer reliability and correlation coefficient of ASPECTS evaluation by 0.222 and 0.087 (p<0.0001), respectively. Additionally, the readers' mean time spent analyzing a case was significantly reduced by 6% (p<0.05) when aided by the algorithm. CONCLUSIONS: With the assistance of the algorithm, readers' analyses were not only more accurate but also faster. Additionally, the overall ASPECTS evaluation exhibited greater consistency, less variabilities and higher precision compared to the reference standard. This novel tool has the potential to enhance patient selection for appropriate treatment by enabling physicians to deliver accurate and timely diagnosis of acute ischemic stroke. ABBREVIATIONS: ASPECTS = Alberta Stroke Program Early Computed Tomography Score; DL = Deep Learning; EIC = Early Ischemic Changes; ICC = Intraclass Correlation Coefficient; IS = Ischemic Stroke; ROC AUC = Receiver Operating Characteristics Area Under the Curve.

Diagnostic Performance of a Deep Learning-Powered Application for Aortic Dissection Triage Prioritization and Classification.

This multicenter retrospective study evaluated the diagnostic performance of a deep learning (DL)-based application for detecting, classifying, and highlighting suspected aortic dissections (ADs) on chest and thoraco-abdominal CT angiography (CTA) scans. CTA scans from over 200 U.S. and European cities acquired on 52 scanner models from six manufacturers were retrospectively collected and processed by CINA-CHEST (AD) (Avicenna.AI, La Ciotat, France) device. The diagnostic performance of the device was compared with the ground truth established by the majority agreement of three U.S. board-certified radiologists. Furthermore, the DL algorithm's time to notification was evaluated to demonstrate clinical effectiveness. The study included 1303 CTAs (mean age 58.8 ± 16.4 years old, 46.7% male, 10.5% positive). The device demonstrated a sensitivity of 94.2% [95% CI: 88.8-97.5%] and a specificity of 97.3% [95% CI: 96.2-98.1%]. The application classified positive cases by the AD type with an accuracy of 99.5% [95% CI: 98.9-99.8%] for type A and 97.5 [95% CI: 96.4-98.3%] for type B. The application did not miss any type A cases. The device flagged 32 cases incorrectly, primarily due to acquisition artefacts and aortic pathologies mimicking AD. The mean time to process and notify of potential AD cases was 27.9 ± 8.7 s. This deep learning-based application demonstrated a strong performance in detecting and classifying aortic dissection cases, potentially enabling faster triage of these urgent cases in clinical settings.

Generating colloquial radiology reports with large language models.

OBJECTIVES: Patients are increasingly being given direct access to their medical records. However, radiology reports are written for clinicians and typically contain medical jargon, which can be confusing. One solution is for radiologists to provide a "colloquial" version that is accessible to the layperson. Because manually generating these colloquial translations would represent a significant burden for radiologists, a way to automatically produce accurate, accessible patient-facing reports is desired. We propose a novel method to produce colloquial translations of radiology reports by providing specialized prompts to a large language model (LLM). MATERIALS AND METHODS: Our method automatically extracts and defines medical terms and includes their definitions in the LLM prompt. Using our method and a naive strategy, translations were generated at 4 different reading levels for 100 de-identified neuroradiology reports from an academic medical center. Translations were evaluated by a panel of radiologists for accuracy, likability, harm potential, and readability. RESULTS: Our approach translated the Findings and Impression sections at the 8th-grade level with accuracies of 88% and 93%, respectively. Across all grade levels, our approach was 20% more accurate than the baseline method. Overall, translations were more readable than the original reports, as evaluated using standard readability indices. CONCLUSION: We find that our translations at the eighth-grade level strike an optimal balance between accuracy and readability. Notably, this corresponds to nationally recognized recommendations for patient-facing health communication. We believe that using this approach to draft patient-accessible reports will benefit patients without significantly increasing the burden on radiologists.

Performance and clinical utility of an artificial intelligence-enabled tool for pulmonary embolism detection.

PURPOSE: Diagnosing pulmonary embolism (PE) is still challenging due to other conditions that can mimic its appearance, leading to incomplete or delayed management and several inter-observer variabilities. This study evaluated the performance and clinical utility of an artificial intelligence (AI)-based application designed to assist clinicians in the detection of PE on CT pulmonary angiography (CTPA). PATIENTS AND METHODS: CTPAs from 230 US cities acquired on 57 scanner models from 6 different vendors were retrospectively collected. Three US board certified expert radiologists defined the ground truth by majority agreement. The same cases were analyzed by CINA-PE, an AI-driven algorithm capable of detecting and highlighting suspected PE locations. The algorithm's performance at a per-case and per-finding level was evaluated. Furthermore, cases with PE not mentioned in the clinical report but correctly detected by the algorithm were analyzed. RESULTS: A total of 1204 CTPAs (mean age 62.1 years ± 16.6[SD], 44.4 % female, 14.9 % positive) were included in the study. Per-case sensitivity and specificity were 93.9 % (95%CI: 89.3 %-96.9 %) and 94.8 % (95%CI: 93.3 %-96.1 %), respectively. Per-finding positive predictive value was 89.5 % (95%CI: 86.7 %-91.9 %). Among the 196 positive cases, 29 (15.6 %) were not mentioned in the clinical report. The algorithm detected 22/29 (76 %) of these cases, leading to a reduction in the miss rate from 15.6 % to 3.8 % (7/186). CONCLUSIONS: The AI-based application may improve diagnostic accuracy in detecting PE and enhance patient outcomes through timely intervention. Integrating AI tools in clinical workflows can reduce missed or delayed diagnoses, and positively impact healthcare delivery and patient care.

Artificial Intelligence Efficacy as a Function of Trainee Interpreter Proficiency: Lessons from a Randomized Controlled Trial.

BACKGROUND AND PURPOSE: Recently, artificial intelligence tools have been deployed with increasing speed in educational and clinical settings. However, the use of artificial intelligence by trainees across different levels of experience has not been well-studied. This study investigates the impact of artificial intelligence assistance on the diagnostic accuracy for intracranial hemorrhage and large-vessel occlusion by medical students and resident trainees. MATERIALS AND METHODS: This prospective study was conducted between March 2023 and October 2023. Medical students and resident trainees were asked to identify intracranial hemorrhage and large-vessel occlusion in 100 noncontrast head CTs and 100 head CTAs, respectively. One group received diagnostic aid simulating artificial intelligence for intracranial hemorrhage only (n = 26); the other, for large-vessel occlusion only (n = 28). Primary outcomes included accuracy, sensitivity, and specificity for intracranial hemorrhage/large-vessel occlusion detection without and with aid. Study interpretation time was a secondary outcome. Individual responses were pooled and analyzed with the t test; differences in continuous variables were assessed with ANOVA. RESULTS: Forty-eight participants completed the study, generating 10,779 intracranial hemorrhage or large-vessel occlusion interpretations. With diagnostic aid, medical student accuracy improved 11.0 points (P < .001) and resident trainee accuracy showed no significant change. Intracranial hemorrhage interpretation time increased with diagnostic aid for both groups (P < .001), while large-vessel occlusion interpretation time decreased for medical students (P < .001). Despite worse performance in the detection of the smallest-versus-largest hemorrhages at baseline, medical students were not more likely to accept a true-positive artificial intelligence result for these more difficult tasks. Both groups were considerably less accurate when disagreeing with the artificial intelligence or when supplied with an incorrect artificial intelligence result. CONCLUSIONS: This study demonstrated greater improvement in diagnostic accuracy with artificial intelligence for medical students compared with resident trainees. However, medical students were less likely than resident trainees to overrule incorrect artificial intelligence interpretations and were less accurate, even with diagnostic aid, than the artificial intelligence was by itself.

Posttreatment Surveillance Imaging After Radiation for Head and Neck Cancer.

Importance: The role of surveillance imaging after treatment for head and neck cancer is controversial and evidence to support decision-making is limited. Objective: To determine the use of surveillance imaging in asymptomatic patients with head and neck cancer in remission after completion of chemoradiation. Design, Setting, and Participants: This was a retrospective, comparative effectiveness research review of adult patients who had achieved a complete metabolic response to initial treatment for head and neck cancer as defined by having an unequivocally negative positron emission tomography (PET) scan using the PET response criteria in solid tumors (PERCIST) scale within the first 6 months of completing therapy. The medical records of 501 consecutive patients who completed definitive radiation therapy (with or without chemotherapy) for newly diagnosed squamous cell carcinoma of the head and neck between January 2014 and June 2022 were reviewed. Exposure: Surveillance imaging was defined as the acquisition of a PET with computed tomography (CT), magnetic resonance imaging (MRI), or CT of the head and neck region in the absence of any clinically suspicious symptoms and/or examination findings. For remaining patients, subsequent surveillance after the achievement of a complete metabolic response to initial therapy was performed on an observational basis in the setting of routine follow-up using history-taking and physical examination, including endoscopy. This expectant approach led to imaging only in the presence of clinically suspicious symptoms and/or physical examination findings. Main Outcome and Measures: Local-regional control, overall survival, and progression-free survival based on assignment to either the surveillance imaging or expectant management cohort. Results: This study included 340 patients (mean [SD] age, 59 [10] years; 201 males [59%]; 88 Latino patients [26%]; 145 White patients [43%]) who achieved a complete metabolic response during this period. There was no difference in 3-year local-regional control, overall survival, progression-free survival, or freedom from distant metastasis between patients treated with surveillance imaging vs those treated expectantly. Conclusions and Relevance: In this comparative effectiveness research, imaging-based surveillance failed to improve outcomes compared with expectant management for patients who were seemingly in remission after completion of primary radiation therapy for head and neck cancer.

Impact of an automated large vessel occlusion detection tool on clinical workflow and patient outcomes.

Purpose: Automated large vessel occlusion (LVO) tools allow for prompt identification of positive LVO cases, but little is known about their role in acute stroke triage when implemented in a real-world setting. The purpose of this study was to evaluate the automated LVO detection tool's impact on acute stroke workflow and clinical outcomes. Materials and methods: Consecutive patients with a computed tomography angiography (CTA) presenting with suspected acute ischemic stroke were compared before and after the implementation of an AI tool, RAPID LVO (RAPID 4.9, iSchemaView, Menlo Park, CA). Radiology CTA report turnaround times (TAT), door-to-treatment times, and the NIH stroke scale (NIHSS) after treatment were evaluated. Results: A total of 439 cases in the pre-AI group and 321 cases in the post-AI group were included, with 62 (14.12%) and 43 (13.40%) cases, respectively, receiving acute therapies. The AI tool demonstrated a sensitivity of 0.96, a specificity of 0.85, a negative predictive value of 0.99, and a positive predictive value of 0.53. Radiology CTA report TAT significantly improved post-AI (mean 30.58 min for pre-AI vs. 22 min for post-AI, p < 0.0005), notably at the resident level (p < 0.0003) but not at higher levels of expertise. There were no differences in door-to-treatment times, but the NIHSS at discharge was improved for the pre-AI group adjusted for confounders (parameter estimate = 3.97, p < 0.01). Conclusion: Implementation of an automated LVO detection tool improved radiology TAT but did not translate to improved stroke metrics and outcomes in a real-world setting.

Deep Learning-Based Algorithm for Automatic Detection of Pulmonary Embolism in Chest CT Angiograms.

PURPOSE: Since the prompt recognition of acute pulmonary embolism (PE) and the immediate initiation of treatment can significantly reduce the risk of death, we developed a deep learning (DL)-based application aimed to automatically detect PEs on chest computed tomography angiograms (CTAs) and alert radiologists for an urgent interpretation. Convolutional neural networks (CNNs) were used to design the application. The associated algorithm used a hybrid 3D/2D UNet topology. The training phase was performed on datasets adequately distributed in terms of vendors, patient age, slice thickness, and kVp. The objective of this study was to validate the performance of the algorithm in detecting suspected PEs on CTAs. METHODS: The validation dataset included 387 anonymized real-world chest CTAs from multiple clinical sites (228 U.S. cities). The data were acquired on 41 different scanner models from five different scanner makers. The ground truth (presence or absence of PE on CTA images) was established by three independent U.S. board-certified radiologists. RESULTS: The algorithm correctly identified 170 of 186 exams positive for PE (sensitivity 91.4% [95% CI: 86.4-95.0%]) and 184 of 201 exams negative for PE (specificity 91.5% [95% CI: 86.8-95.0%]), leading to an accuracy of 91.5%. False negative cases were either chronic PEs or PEs at the limit of subsegmental arteries and close to partial volume effect artifacts. Most of the false positive findings were due to contrast agent-related fluid artifacts, pulmonary veins, and lymph nodes. CONCLUSIONS: The DL-based algorithm has a high degree of diagnostic accuracy with balanced sensitivity and specificity for the detection of PE on CTAs.

Impact of easing COVID-19 safety measures on trauma computed tomography imaging volumes.

PURPOSE: The coronavirus disease 2019 (COVID-19) pandemic has led to substantial disruptions in healthcare staffing and operations. Stay-at-home (SAH) orders and limitations in social gathering implemented in spring 2020 were followed by initial decreases in healthcare and imaging utilization. This study aims to evaluate the impact of subsequent easing of SAH on trauma volumes, demand for, and turnaround times for trauma computed tomography (CT) exams, hypothesizing that after initial decreases, trauma volumes have increased as COVID safety measures have been reduced. METHODS: Patient characteristics, CT imaging volumes, and turnaround time were analyzed for all adult activated emergency department trauma patients requiring CT imaging at a single Level-I trauma center (1/2018-2/2022) located in the sixth most populous county in the USA. Based on COVID safety measures in place in the state of California, three time periods were compared: baseline (PRE, 1/1/2018-3/19/2020), COVID safety measures (COVID, 3/20/2020-1/25/2021), and POST (1/26/2021-2/28/2022). RESULTS: There were 16,984 trauma patients across the study (PRE = 8289, COVID = 3139, POST = 5556). The average daily trauma patient volumes increased significantly in the POST period compared to the PRE and COVID periods (13.9 vs. 10.3 vs. 10.1, p < 0.001), with increases in both blunt (p < 0.001) and penetrating (p = 0.002) trauma. The average daily number of trauma CT examinations performed increased significantly in the POST period compared to the PRE and COVID periods (56.7 vs. 48.3 vs. 47.6, p < 0.001), with significant increases in average turnaround time (47 min vs. 31 and 37, p < 0.001). CONCLUSION: After initial decreases in trauma radiology volumes following stay-at-home orders, subsequent easing of safety measures has coincided with increases in trauma imaging volumes above pre-pandemic levels and longer exam turnaround times.

Point-of-Care Brain MRI: Preliminary Results from a Single-Center Retrospective Study.

Background Point-of-care (POC) MRI is a bedside imaging technology with fewer than five units in clinical use in the United States and a paucity of scientific studies on clinical applications. Purpose To evaluate the clinical and operational impacts of deploying POC MRI in emergency department (ED) and intensive care unit (ICU) patient settings for bedside neuroimaging, including the turnaround time. Materials and Methods In this preliminary retrospective study, all patients in the ED and ICU at a single academic medical center who underwent noncontrast brain MRI from January 2021 to June 2021 were investigated to determine the number of patients who underwent bedside POC MRI. Turnaround time, examination limitations, relevant findings, and potential CT and fixed MRI findings were recorded for patients who underwent POC MRI. Descriptive statistics were used to describe clinical variables. The Mann-Whitney U test was used to compare the turnaround time between POC MRI and fixed MRI examinations. Results Of 638 noncontrast brain MRI examinations, 36 POC MRI examinations were performed in 35 patients (median age, 66 years [IQR, 57-77 years]; 21 women), with one patient undergoing two POC MRI examinations. Of the 36 POC MRI examinations, 13 (36%) occurred in the ED and 23 (64%) in the ICU. There were 12 of 36 (33%) POC MRI examinations interpreted as negative, 14 of 36 (39%) with clinically significant imaging findings, and 10 of 36 (28%) deemed nondiagnostic for reasons such as patient motion. Of 23 diagnostic POC MRI examinations with comparison CT available, three (13%) demonstrated acute infarctions not apparent on CT scans. Of seven diagnostic POC MRI examinations with subsequent fixed MRI examinations, two (29%) demonstrated missed versus interval subcentimeter infarctions, while the remaining demonstrated no change. The median turnaround time of POC MRI was 3.4 hours in the ED and 5.3 hours in the ICU. Conclusion Point-of-care (POC) MRI was performed rapidly in the emergency department and intensive care unit. A few POC MRI examinations demonstrated acute infarctions not apparent at standard-of-care CT examinations. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Anzai and Moy in this issue.

Neuroanatomical Correlates Underlying the Association Between Maternal Interleukin 6 Concentration During Pregnancy and Offspring Fluid Reasoning Performance in Early Childhood.

BACKGROUND: Maternal inflammation during pregnancy can alter offspring brain development and influence risk for disorders commonly accompanied by deficits in cognitive functioning. We therefore examined associations between maternal interleukin 6 (IL-6) concentrations during pregnancy and offspring cognitive ability and concurrent magnetic resonance imaging-based measures of brain anatomy in early childhood. We further examined newborn brain anatomy in secondary analyses to consider whether effects are evident soon after birth and to increase capacity to differentiate effects of pre- versus postnatal exposures. METHODS: IL-6 concentrations were quantified in early (12.6 ± 2.8 weeks), mid (20.4 ± 1.5 weeks), and late (30.3 ± 1.3 weeks) pregnancy. Offspring nonverbal fluid intelligence (Gf) was assessed at 5.2 ± 0.6 years using a spatial reasoning task (Wechsler Preschool and Primary Scale of Intelligence-Matrix) (n = 49). T1-weighted magnetic resonance imaging scans were acquired at birth (n = 89, postmenstrual age = 42.9 ± 2.0 weeks) and in early childhood (n = 42, scan age = 5.1 ± 1.0 years). Regional cortical volumes were examined for a joint association between maternal IL-6 and offspring Gf performance. RESULTS: Average maternal IL-6 concentration during pregnancy was inversely associated with offspring Gf performance after adjusting for socioeconomic status and the quality of the caregiving and learning environment (R2 = 13%; p = .02). Early-childhood pars triangularis volume was jointly associated with maternal IL-6 and childhood Gf (pcorrected < .001). An association also was observed between maternal IL-6 and newborn pars triangularis volume (R2 = 6%; p = .02). CONCLUSIONS: These findings suggest that the origins of variation in child cognitive ability can, in part, trace back to maternal conditions during the intrauterine period of life and support the role of inflammation as an important component of this putative biological pathway.

Validation of a Deep Learning Tool in the Detection of Intracranial Hemorrhage and Large Vessel Occlusion.

Purpose: Recently developed machine-learning algorithms have demonstrated strong performance in the detection of intracranial hemorrhage (ICH) and large vessel occlusion (LVO). However, their generalizability is often limited by geographic bias of studies. The aim of this study was to validate a commercially available deep learning-based tool in the detection of both ICH and LVO across multiple hospital sites and vendors throughout the U.S. Materials and Methods: This was a retrospective and multicenter study using anonymized data from two institutions. Eight hundred fourteen non-contrast CT cases and 378 CT angiography cases were analyzed to evaluate ICH and LVO, respectively. The tool's ability to detect and quantify ICH, LVO, and their various subtypes was assessed among multiple CT vendors and hospitals across the United States. Ground truth was based off imaging interpretations from two board-certified neuroradiologists. Results: There were 255 positive and 559 negative ICH cases. Accuracy was 95.6%, sensitivity was 91.4%, and specificity was 97.5% for the ICH tool. ICH was further stratified into the following subtypes: intraparenchymal, intraventricular, epidural/subdural, and subarachnoid with true positive rates of 92.9, 100, 94.3, and 89.9%, respectively. ICH true positive rates by volume [small (<5 mL), medium (5-25 mL), and large (>25 mL)] were 71.8, 100, and 100%, respectively. There were 156 positive and 222 negative LVO cases. The LVO tool demonstrated an accuracy of 98.1%, sensitivity of 98.1%, and specificity of 98.2%. A subset of 55 randomly selected cases were also assessed for LVO detection at various sites, including the distal internal carotid artery, middle cerebral artery M1 segment, proximal middle cerebral artery M2 segment, and distal middle cerebral artery M2 segment with an accuracy of 97.0%, sensitivity of 94.3%, and specificity of 97.4%. Conclusion: Deep learning tools can be effective in the detection of both ICH and LVO across a wide variety of hospital systems. While some limitations were identified, specifically in the detection of small ICH and distal M2 occlusion, this study highlights a deep learning tool that can assist radiologists in the detection of emergent findings in a variety of practice settings.

Outcomes of Artificial Intelligence Volumetric Assessment of Kidneys and Renal Tumors for Preoperative Assessment of Nephron-Sparing Interventions.

Background: Renal-cell carcinoma is the most common kidney cancer and the 13th most common cause of cancer death worldwide. Partial nephrectomy and percutaneous ablation, increasingly utilized to treat small renal masses and preserve renal parenchyma, require precise preoperative imaging interpretation. We sought to develop and evaluate a convolutional neural network (CNN), a type of deep learning (DL) artificial intelligence (AI), to act as a surgical planning aid by determining renal tumor and kidney volumes through segmentation on single-phase CT. Materials and Methods: After Institutional Review Board approval, the CT images of 319 patients were retrospectively analyzed. Two distinct CNNs were developed for (1) bounding cube localization of the right and left hemiabdomen and (2) segmentation of the renal parenchyma and tumor within each bounding cube. Training was performed on a randomly selected cohort of 269 patients. CNN performance was evaluated on a separate cohort of 50 patients using Sorensen-Dice coefficients (which measures the spatial overlap between the manually segmented and neural network-derived segmentations) and Pearson correlation coefficients. Experiments were run on a graphics processing unit-optimized workstation with a single NVIDIA GeForce GTX Titan X (12GB, Maxwell Architecture). Results: Median Dice coefficients for kidney and tumor segmentation were 0.970 and 0.816, respectively; Pearson correlation coefficients between CNN-generated and human-annotated estimates for kidney and tumor volume were 0.998 and 0.993 (p < 0.001), respectively. End-to-end trained CNNs were able to perform renal parenchyma and tumor segmentation on a new test case in an average of 5.6 seconds. Conclusions: Initial experience with automated DL AI demonstrates that it is capable of rapidly and accurately segmenting kidneys and renal tumors on single-phase contrast-enhanced CT scans and calculating tumor and renal volumes.

Development and external validation of a prognostic tool for COVID-19 critical disease.

BACKGROUND: The rapid spread of coronavirus disease 2019 (COVID-19) revealed significant constraints in critical care capacity. In anticipation of subsequent waves, reliable prediction of disease severity is essential for critical care capacity management and may enable earlier targeted interventions to improve patient outcomes. The purpose of this study is to develop and externally validate a prognostic model/clinical tool for predicting COVID-19 critical disease at presentation to medical care. METHODS: This is a retrospective study of a prognostic model for the prediction of COVID-19 critical disease where critical disease was defined as ICU admission, ventilation, and/or death. The derivation cohort was used to develop a multivariable logistic regression model. Covariates included patient comorbidities, presenting vital signs, and laboratory values. Model performance was assessed on the validation cohort by concordance statistics. The model was developed with consecutive patients with COVID-19 who presented to University of California Irvine Medical Center in Orange County, California. External validation was performed with a random sample of patients with COVID-19 at Emory Healthcare in Atlanta, Georgia. RESULTS: Of a total 3208 patients tested in the derivation cohort, 9% (299/3028) were positive for COVID-19. Clinical data including past medical history and presenting laboratory values were available for 29% (87/299) of patients (median age, 48 years [range, 21-88 years]; 64% [36/55] male). The most common comorbidities included obesity (37%, 31/87), hypertension (37%, 32/87), and diabetes (24%, 24/87). Critical disease was present in 24% (21/87). After backward stepwise selection, the following factors were associated with greatest increased risk of critical disease: number of comorbidities, body mass index, respiratory rate, white blood cell count, % lymphocytes, serum creatinine, lactate dehydrogenase, high sensitivity troponin I, ferritin, procalcitonin, and C-reactive protein. Of a total of 40 patients in the validation cohort (median age, 60 years [range, 27-88 years]; 55% [22/40] male), critical disease was present in 65% (26/40). Model discrimination in the validation cohort was high (concordance statistic: 0.94, 95% confidence interval 0.87-1.01). A web-based tool was developed to enable clinicians to input patient data and view likelihood of critical disease. CONCLUSIONS AND RELEVANCE: We present a model which accurately predicted COVID-19 critical disease risk using comorbidities and presenting vital signs and laboratory values, on derivation and validation cohorts from two different institutions. If further validated on additional cohorts of patients, this model/clinical tool may provide useful prognostication of critical care needs.

Predictive Values of Location and Volumetric MRI Injury Patterns for Neurodevelopmental Outcomes in Hypoxic-Ischemic Encephalopathy Neonates.

Hypoxic-ischemic encephalopathy (HIE) is a severe neonatal complication with up to 40-60% long-term morbidity. This study evaluates the distribution and burden of MRI changes as a prognostic indicator of neurodevelopmental (ND) outcomes at 18-24 months in HIE infants who were treated with therapeutic hypothermia (TH). Term or late preterm infants who were treated with TH for HIE were analyzed between June 2012 and March 2016. Brain MRI scans were obtained from 107 TH treated infants. For each infant, diffusion weighted brain image (DWI) sequences from a 3T Siemens scanner were obtained for analysis. Of the 107 infants, 36 of the 107 infants (33.6%) had normal brain MR images, and 71 of the 107 infants (66.4%) had abnormal MRI findings. The number of clinical seizures was significantly higher in the abnormal MRI group (p < 0.001) than in the normal MRI group. At 18-24 months, 76 of the 107 infants (70.0%) showed normal ND stages, and 31 of the 107 infants (29.0%) exhibited abnormal ND stages. A lesion size count >500 was significantly associated with abnormal ND. Similarly, the total lesion count was larger in the abnormal ND group (14.16 vs. 5.29). More lesions in the basal ganglia (BG) and thalamus areas and a trend towards more abnormal MRI scans were significantly associated with abnormal ND at 18-24 months. In addition to clinical seizure, a larger total lesion count and lesion size as well as lesion involvement of the basal ganglia and thalamus were significantly associated with abnormal neurodevelopment at 18-24 months.

Updates on Deep Learning and Glioma: Use of Convolutional Neural Networks to Image Glioma Heterogeneity.

Deep learning represents end-to-end machine learning in which feature selection from images and classification happen concurrently. This articles provides updates on how deep learning is being applied to the study of glioma and its genetic heterogeneity. Deep learning algorithms can detect patterns in routine and advanced MR imaging that elude the eyes of neuroradiologists and make predictions about glioma genetics, which impact diagnosis, treatment response, patient management, and long-term survival. The success of these deep learning initiatives may enhance the performance of neuroradiologists and add greater value to patient care by expediting treatment.

Impact of COVID-19 on Acute Stroke Presentation at a Comprehensive Stroke Center.

Background: COVID-19 has impacted healthcare in many ways, including presentation of acute stroke. Since time-sensitive thrombolysis is essential for reducing morbidity and mortality in acute stroke, any delays due to the pandemic can have serious consequences. Methods: We retrospectively reviewed the electronic medical records for patients presenting with acute ischemic stroke at a comprehensive stroke center in March-April 2020 (the early months of COVID-19) and compared to the same time period in 2019. Stroke metrics such as incidence, time to arrival, and immediate outcomes were assessed. Results: There were 48 acute ischemic strokes (of which 7 were transfers) in March-April 2020 compared to 64 (of which 12 were transfers) in 2019. The average last known well to arrival time (±SD) for stroke codes was 1,041 (±1682.1) min in 2020 and 554 (±604.9) min in 2019. Of the patients presenting directly to the ED with a known last known well time, 27.8% (10/36) presented in the first 4.5 h in 2020, in contrast to 40.5% (15/37) in 2019. Patients who died comprised 10.4% of the stroke cohort in 2020 (5/48) compared to 6.3% in 2019 (4/64). Conclusions: During the first 2 months of COVID-19, there were fewer overall stroke cases who presented to our hospital, and of these cases, there was delayed presentation in comparison to the same time period in 2019. Recognizing how stroke presentation may be affected by COVID-19 would allow for optimization of established stroke triage algorithms in order to ensure safe and timely delivery of stroke care during a pandemic.

Applications of Artificial Intelligence to Prostate Multiparametric MRI (mpMRI): Current and Emerging Trends.

Prostate carcinoma is one of the most prevalent cancers worldwide. Multiparametric magnetic resonance imaging (mpMRI) is a non-invasive tool that can improve prostate lesion detection, classification, and volume quantification. Machine learning (ML), a branch of artificial intelligence, can rapidly and accurately analyze mpMRI images. ML could provide better standardization and consistency in identifying prostate lesions and enhance prostate carcinoma management. This review summarizes ML applications to prostate mpMRI and focuses on prostate organ segmentation, lesion detection and segmentation, and lesion characterization. A literature search was conducted to find studies that have applied ML methods to prostate mpMRI. To date, prostate organ segmentation and volume approximation have been well executed using various ML techniques. Prostate lesion detection and segmentation are much more challenging tasks for ML and were attempted in several studies. They largely remain unsolved problems due to data scarcity and the limitations of current ML algorithms. By contrast, prostate lesion characterization has been successfully completed in several studies because of better data availability. Overall, ML is well situated to become a tool that enhances radiologists' accuracy and speed.

Deep Learning AI Applications in the Imaging of Glioma.

This manuscript will review emerging applications of artificial intelligence, specifically deep learning, and its application to glioblastoma multiforme (GBM), the most common primary malignant brain tumor. Current deep learning approaches, commonly convolutional neural networks (CNNs), that take input data from MR images to grade gliomas (high grade from low grade) and predict overall survival will be shown. There will be more in-depth review of recent articles that have applied different CNNs to predict the genetics of glioma on pre-operative MR images, specifically 1p19q codeletion, MGMT promoter, and IDH mutations, which are important criteria for the diagnosis, treatment management, and prognostication of patients with GBM. Finally, there will be a brief mention of current challenges with DL techniques and their application to image analysis in GBM.