Byung Chul Yoon
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Byung Chul Yoon has a total of 86 co-authors. Here are the top co-authors by number of shared publications:
- Karen Buch
Department of Radiology, Massachusetts General Hospital, Boston, MA
6 shared publications - Min Lang
Harvard Medical School, Boston, USA
6 shared publications - Sandra Rincon
Harvard Med Sch, Massachusetts Gen Hosp, Dept Radiol, Massachusetts Gen Brigham, Boston, MA USA
6 shared publications - William A. Mehan
From the Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts
6 shared publications - Brooks P. Applewhite
Department of Radiology
4 shared publications - Thabele M. Leslie-Mazwi
Department of Neurology, University of Washington, Seattle
4 shared publications
Latest Publications
- Open Access
Multimodal neuroimaging approach for cognitive impairment in Alzheimer’s disease
PURPOSE: Alzheimer’s disease (AD) is associated with cognitive impairment, brain atrophy, and elevated amyloid-beta (Aß) and tau. The study aimed to characterize regional atrophy associated with elevated Aß and tau, as measured by [¹ F]florbetapir (FBP) and [¹ F]flortaucipir (FTP) positron emission tomography (PET), respectively, and determine whether combining PET and atrophy data improves the prediction of cognitive impairment. METHODS: Alzheimer’s Disease Neuroimaging Initiative data (n = 381) were retrospectively analyzed. PET results were correlated with cortical thickness, gray matter (GM) volumes, Mini-Mental State Examination, and Montreal Cognitive Assessment. Linear/logistic regression and area under the curve (AUC) were used to evaluate for significant correlations and compare performances in distinguishing cognitive impairment, respectively. RESULTS: Incremental loss of cortical thickness and GM volume was observed from FBP-/FTP-(n = 205) to single PET-positive (FBP+/FTP-, n = 133; FBP-/FTP+, n = 5) and FBP+/FTP+ (n = 38) groups, particularly in the temporal and parietal lobes. FBP+/FTP+ showed the most severe cortical thickness loss in the entorhinal cortex, temporal lobe GM atrophy, and cognitive impairment. Adding brain atrophy as the third variable resulted in higher odds ratios and improved AUCs for cognitive impairment, with FBP+/FTP+/temporal GM or entorhinal cortical atrophy+ demonstrating the strongest associations with cognitive impairment. CONCLUSION: A multimodal approach combining PET and MRI may help improve the assessment of cognitive impairment in AD.
Open AccessMultimodal neuroimaging approach for cognitive impairment in Alzheimer’s disease
PURPOSE: Alzheimer’s disease (AD) is associated with cognitive impairment, brain atrophy, and elevated amyloid-beta (Aß) and tau. The study aimed to characterize regional atrophy associated with elevated Aß and tau, as measured by [¹ F]florbetapir (FBP) and [¹ F]flortaucipir (FTP) positron emission tomography (PET), respectively, and determine whether combining PET and atrophy data improves the prediction of cognitive impairment. METHODS: Alzheimer’s Disease Neuroimaging Initiative data (n = 381) were retrospectively analyzed. PET results were correlated with cortical thickness, gray matter (GM) volumes, Mini-Mental State Examination, and Montreal Cognitive Assessment. Linear/logistic regression and area under the curve (AUC) were used to evaluate for significant correlations and compare performances in distinguishing cognitive impairment, respectively. RESULTS: Incremental loss of cortical thickness and GM volume was observed from FBP-/FTP-(n = 205) to single PET-positive (FBP+/FTP-, n = 133; FBP-/FTP+, n = 5) and FBP+/FTP+ (n = 38) groups, particularly in the temporal and parietal lobes. FBP+/FTP+ showed the most severe cortical thickness loss in the entorhinal cortex, temporal lobe GM atrophy, and cognitive impairment. Adding brain atrophy as the third variable resulted in higher odds ratios and improved AUCs for cognitive impairment, with FBP+/FTP+/temporal GM or entorhinal cortical atrophy+ demonstrating the strongest associations with cognitive impairment. CONCLUSION: A multimodal approach combining PET and MRI may help improve the assessment of cognitive impairment in AD.
- Open Access
- 8 April 2026
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 21 (4) , e0346661
White matter microstructure disruption associated with PET and cognitive impairment in Alzheimer’s disease
Alzheimer’s disease (AD) is associated with regional brain atrophy as well as elevated positron emission tomography (PET) markers of amyloid-beta (e.g., [¹⁸F]florbetapir (FBP)) and tau protein (e.g., [¹⁸F]flortaucipir (FTP). White matter microstructures have also been shown to be disrupted in AD, but there is limited understanding of their specific associations with FBP, FTP, and cognitive impairment. Herein, we used both voxel-based and fixel-based analyses of diffusion tensor imaging (DTI) to characterize microstructural white matter changes associated with PET and cognitive changes in AD. A retrospective study was performed using the data from 381 ADNI-3 participants (F:M = 200:181). FBP and FTP results were correlated with DTI metrics, including the apparent fiber density (AFD), complexity (CX), functional anisotropy (FA), fixel number (FN), and mean diffusivity (MD). Linear regression analysis was performed, adjusted for age, sex, education, and cognitive impairment. Greatest negative correlations were observed between FN and FBP standardized uptake value ratio (SUVR) in 15 out of 18 white matter tracts examined (beta coefficients of −0.3991 to −0.2877). No significant correlation was observed between DTI measures and FTP SUVR, independently. However, combined PET positivity (FBP + /FTP+) generally showed the greatest reductions in CX, FN, and FA of various tracts, compared to single PET-positive or PET-negative groups. Widespread changes in FA were positively associated with cognitive impairment, with stronger associations seen with the Montreal Cognitive Assessment (MoCA) than the Mini-Mental State Examination (MMSE). Only females showed significant correlations between MD and FBP/FTP levels and showed more widespread correlations between FA and MD changes and cognitive impairment. Taken together, these findings suggest specific patterns of white matter microstructure disruption in AD with underlying sex differences and support their potential role as early biomarkers.
- 8 April 2026
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 21 (4) , e0346661
Open AccessWhite matter microstructure disruption associated with PET and cognitive impairment in Alzheimer’s disease
Alzheimer’s disease (AD) is associated with regional brain atrophy as well as elevated positron emission tomography (PET) markers of amyloid-beta (e.g., [¹⁸F]florbetapir (FBP)) and tau protein (e.g., [¹⁸F]flortaucipir (FTP). White matter microstructures have also been shown to be disrupted in AD, but there is limited understanding of their specific associations with FBP, FTP, and cognitive impairment. Herein, we used both voxel-based and fixel-based analyses of diffusion tensor imaging (DTI) to characterize microstructural white matter changes associated with PET and cognitive changes in AD. A retrospective study was performed using the data from 381 ADNI-3 participants (F:M = 200:181). FBP and FTP results were correlated with DTI metrics, including the apparent fiber density (AFD), complexity (CX), functional anisotropy (FA), fixel number (FN), and mean diffusivity (MD). Linear regression analysis was performed, adjusted for age, sex, education, and cognitive impairment. Greatest negative correlations were observed between FN and FBP standardized uptake value ratio (SUVR) in 15 out of 18 white matter tracts examined (beta coefficients of −0.3991 to −0.2877). No significant correlation was observed between DTI measures and FTP SUVR, independently. However, combined PET positivity (FBP + /FTP+) generally showed the greatest reductions in CX, FN, and FA of various tracts, compared to single PET-positive or PET-negative groups. Widespread changes in FA were positively associated with cognitive impairment, with stronger associations seen with the Montreal Cognitive Assessment (MoCA) than the Mini-Mental State Examination (MMSE). Only females showed significant correlations between MD and FBP/FTP levels and showed more widespread correlations between FA and MD changes and cognitive impairment. Taken together, these findings suggest specific patterns of white matter microstructure disruption in AD with underlying sex differences and support their potential role as early biomarkers.
- Open Access
- 9 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 55 (12) , 5619-5632
Toward Foundational Model for Sleep Analysis Using a Multimodal Hybrid-Self-Supervised Learning Framework
Sleep is essential for maintaining human health and quality of life. Analyzing physiological signals during sleep is critical in assessing sleep quality and diagnosing sleep disorders. However, manual diagnoses by clinicians are time-intensive and subjective. Despite advances in deep learning that have enhanced automation, these approaches remain heavily dependent on large-scale labeled datasets. This study introduces SynthSleepNet, a multimodal hybrid-self-supervised learning (SSL) framework designed for analyzing polysomnography (PSG) data. SynthSleepNet effectively integrates masked prediction and contrastive learning to leverage complementary features across multiple modalities, including electroencephalogram (EEG), electrooculography (EOG), electromyography (EMG), and electrocardiogram (ECG). This approach enables the model to learn highly expressive representations of PSG data. Furthermore, a TCM based on Mamba was developed to efficiently capture contextual information across signals. SynthSleepNet achieved superior performance compared to state-of-the-art methods across three downstream tasks: sleep-stage classification, apnea detection, and hypopnea detection, with accuracies of 89.89%, 99.75%, and 89.60%, respectively. The model demonstrated robust performance in a semi-SSL environment with limited labels, achieving accuracies of 87.98%, 99.37%, and 77.52% in the same tasks. These results underscore the potential of the model as a foundational tool for the comprehensive analysis of PSG data. SynthSleepNet demonstrates comprehensively superior performance across multiple downstream tasks compared to other methodologies, making it expected to set a new standard for sleep disorder monitoring and diagnostic systems. The source code is available at https://github.com/dlcjfgmlnasa/SynthSleepNet.
- 9 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 55 (12) , 5619-5632
Open AccessToward Foundational Model for Sleep Analysis Using a Multimodal Hybrid-Self-Supervised Learning Framework
Sleep is essential for maintaining human health and quality of life. Analyzing physiological signals during sleep is critical in assessing sleep quality and diagnosing sleep disorders. However, manual diagnoses by clinicians are time-intensive and subjective. Despite advances in deep learning that have enhanced automation, these approaches remain heavily dependent on large-scale labeled datasets. This study introduces SynthSleepNet, a multimodal hybrid-self-supervised learning (SSL) framework designed for analyzing polysomnography (PSG) data. SynthSleepNet effectively integrates masked prediction and contrastive learning to leverage complementary features across multiple modalities, including electroencephalogram (EEG), electrooculography (EOG), electromyography (EMG), and electrocardiogram (ECG). This approach enables the model to learn highly expressive representations of PSG data. Furthermore, a TCM based on Mamba was developed to efficiently capture contextual information across signals. SynthSleepNet achieved superior performance compared to state-of-the-art methods across three downstream tasks: sleep-stage classification, apnea detection, and hypopnea detection, with accuracies of 89.89%, 99.75%, and 89.60%, respectively. The model demonstrated robust performance in a semi-SSL environment with limited labels, achieving accuracies of 87.98%, 99.37%, and 77.52% in the same tasks. These results underscore the potential of the model as a foundational tool for the comprehensive analysis of PSG data. SynthSleepNet demonstrates comprehensively superior performance across multiple downstream tasks compared to other methodologies, making it expected to set a new standard for sleep disorder monitoring and diagnostic systems. The source code is available at https://github.com/dlcjfgmlnasa/SynthSleepNet.
- Open Access
- 1 September 2025
- Published by AME Publishing Company in Journal of Spine Surgery
- Vol. 11 (3) , 757-763
Giant calcified lumbar disc herniation in post-operative adjacent segment degeneration: a case report
Case Report Giant calcified lumbar disc herniation in post-operative adjacent segment degeneration: a case report Harold Keyserling, Yi Zhang, Stephen Skirboll, Raymond A. Sobel, Byung C. Yoon
- 1 September 2025
- Published by AME Publishing Company in Journal of Spine Surgery
- Vol. 11 (3) , 757-763
Open AccessGiant calcified lumbar disc herniation in post-operative adjacent segment degeneration: a case report
Case Report Giant calcified lumbar disc herniation in post-operative adjacent segment degeneration: a case report Harold Keyserling, Yi Zhang, Stephen Skirboll, Raymond A. Sobel, Byung C. Yoon
- Open Access
- 25 July 2025
- Published by American Association for the Advancement of Science (AAAS) in Science Advances
- Vol. 11 (30) , eadw2601
Improving real-time ultrasound spine imaging with a large-aperture array
Ultrasound offers a safe, low-cost alternative to computed tomography (CT) and magnetic resonance imaging for spinal diagnostics and intervention by enabling real-time imaging. However, the complex structure of the spine and acoustic shadowing from bones present challenges for ultrasonography. This study addresses these limitations using an 8.8-centimeter 384-element large-aperture array and full aperture-based imaging protocols. Volumetric scanning across multiple vertebrae was accomplished in 5 seconds using ultrafast, diverging wave acquisition. In seven healthy volunteers, the large-aperture array and diverging wave transmission improved resolution, contrast, and visualization of the spinal canal, venous plexuses, and facet joints compared with conventional probes. A comparison between the coregistered CT and ultrasound scan confirmed the imaging accuracy. A simulated lumbar puncture demonstrated needle tip visualization throughout the trajectory into the spinal canal. The results suggest that large-aperture arrays, coupled with diverging wave imaging sequences, are a valuable tool for spine imaging and image-guided intervention.
- 25 July 2025
- Published by American Association for the Advancement of Science (AAAS) in Science Advances
- Vol. 11 (30) , eadw2601
Open AccessImproving real-time ultrasound spine imaging with a large-aperture array
Ultrasound offers a safe, low-cost alternative to computed tomography (CT) and magnetic resonance imaging for spinal diagnostics and intervention by enabling real-time imaging. However, the complex structure of the spine and acoustic shadowing from bones present challenges for ultrasonography. This study addresses these limitations using an 8.8-centimeter 384-element large-aperture array and full aperture-based imaging protocols. Volumetric scanning across multiple vertebrae was accomplished in 5 seconds using ultrafast, diverging wave acquisition. In seven healthy volunteers, the large-aperture array and diverging wave transmission improved resolution, contrast, and visualization of the spinal canal, venous plexuses, and facet joints compared with conventional probes. A comparison between the coregistered CT and ultrasound scan confirmed the imaging accuracy. A simulated lumbar puncture demonstrated needle tip visualization throughout the trajectory into the spinal canal. The results suggest that large-aperture arrays, coupled with diverging wave imaging sequences, are a valuable tool for spine imaging and image-guided intervention.
- Open Access
- 18 November 2024
- Published by Elsevier in Brain Stimulation
- Vol. 17 (6) , 1290-1292
Low-intensity focused ultrasound (LIFU) for the treatment of post-traumatic headache (PTH) in veterans: A feasibility study
- 18 November 2024
- Published by Elsevier in Brain Stimulation
- Vol. 17 (6) , 1290-1292
Open AccessLow-intensity focused ultrasound (LIFU) for the treatment of post-traumatic headache (PTH) in veterans: A feasibility study
- Open Access
- 1 September 2024
- Published by Korean Neurosurgical Society in Journal of Korean Neurosurgical Society
- Vol. 67 (5) , 493-509
Artificial Intelligence-Enhanced Neurocritical Care for Traumatic Brain Injury : Past, Present and Future
In neurointensive care units (NICUs), particularly in cases involving traumatic brain injury (TBI), swift and accurate decision-making is critical because of rapidly changing patient conditions and the risk of secondary brain injury. The use of artificial intelligence (AI) in NICU can enhance clinical decision support and provide valuable assistance in these complex scenarios. This article aims to provide a comprehensive review of the current status and future prospects of AI utilization in the NICU, along with the challenges that must be overcome to realize this. Presently, the primary application of AI in NICU is outcome prediction through the analysis of preadmission and high-resolution data during admission. Recent applications include augmented neuromonitoring via signal quality control and real-time event prediction. In addition, AI can integrate data gathered from various measures and support minimally invasive neuromonitoring to increase patient safety. However, despite the recent surge in AI adoption within the NICU, the majority of AI applications have been limited to simple classification tasks, thus leaving the true potential of AI largely untapped. Emerging AI technologies, such as generalist medical AI and digital twins, harbor immense potential for enhancing advanced neurocritical care through broader AI applications. If challenges such as acquiring high-quality data and ethical issues are overcome, these new AI technologies can be clinically utilized in the actual NICU environment. Emphasizing the need for continuous research and development to maximize the potential of AI in the NICU, we anticipate that this will further enhance the efficiency and accuracy of TBI treatment within the NICU.
- 1 September 2024
- Published by Korean Neurosurgical Society in Journal of Korean Neurosurgical Society
- Vol. 67 (5) , 493-509
Open AccessArtificial Intelligence-Enhanced Neurocritical Care for Traumatic Brain Injury : Past, Present and Future
In neurointensive care units (NICUs), particularly in cases involving traumatic brain injury (TBI), swift and accurate decision-making is critical because of rapidly changing patient conditions and the risk of secondary brain injury. The use of artificial intelligence (AI) in NICU can enhance clinical decision support and provide valuable assistance in these complex scenarios. This article aims to provide a comprehensive review of the current status and future prospects of AI utilization in the NICU, along with the challenges that must be overcome to realize this. Presently, the primary application of AI in NICU is outcome prediction through the analysis of preadmission and high-resolution data during admission. Recent applications include augmented neuromonitoring via signal quality control and real-time event prediction. In addition, AI can integrate data gathered from various measures and support minimally invasive neuromonitoring to increase patient safety. However, despite the recent surge in AI adoption within the NICU, the majority of AI applications have been limited to simple classification tasks, thus leaving the true potential of AI largely untapped. Emerging AI technologies, such as generalist medical AI and digital twins, harbor immense potential for enhancing advanced neurocritical care through broader AI applications. If challenges such as acquiring high-quality data and ethical issues are overcome, these new AI technologies can be clinically utilized in the actual NICU environment. Emphasizing the need for continuous research and development to maximize the potential of AI in the NICU, we anticipate that this will further enhance the efficiency and accuracy of TBI treatment within the NICU.
- 17 January 2024
- Published by Elsevier in Current Problems in Diagnostic Radiology
- Vol. 53 (3) , 372-376
Implicit screening of abdominal aortic aneurysms among veterans using lumbar spine MRI
- 17 January 2024
- Published by Elsevier in Current Problems in Diagnostic Radiology
- Vol. 53 (3) , 372-376
Implicit screening of abdominal aortic aneurysms among veterans using lumbar spine MRI
- Open Access
- 13 March 2023
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 18 (3) , e0281900
Incorporating algorithmic uncertainty into a clinical machine deep learning algorithm for urgent head CTs
Machine learning (ML) algorithms to detect critical findings on head CTs may expedite patient management. Most ML algorithms for diagnostic imaging analysis utilize dichotomous classifications to determine whether a specific abnormality is present. However, imaging findings may be indeterminate, and algorithmic inferences may have substantial uncertainty. We incorporated awareness of uncertainty into an ML algorithm that detects intracranial hemorrhage or other urgent intracranial abnormalities and evaluated prospectively identified, 1000 consecutive noncontrast head CTs assigned to Emergency Department Neuroradiology for interpretation. The algorithm classified the scans into high (IC+) and low (IC-) probabilities for intracranial hemorrhage or other urgent abnormalities. All other cases were designated as No Prediction (NP) by the algorithm. The positive predictive value for IC+ cases (N = 103) was 0.91 (CI: 0.84–0.96), and the negative predictive value for IC- cases (N = 729) was 0.94 (0.91–0.96). Admission, neurosurgical intervention, and 30-day mortality rates for IC+ was 75% (63–84), 35% (24–47), and 10% (4–20), compared to 43% (40–47), 4% (3–6), and 3% (2–5) for IC-. There were 168 NP cases, of which 32% had intracranial hemorrhage or other urgent abnormalities, 31% had artifacts and postoperative changes, and 29% had no abnormalities. An ML algorithm incorporating uncertainty classified most head CTs into clinically relevant groups with high predictive values and may help accelerate the management of patients with intracranial hemorrhage or other urgent intracranial abnormalities.
- 13 March 2023
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 18 (3) , e0281900
Open AccessIncorporating algorithmic uncertainty into a clinical machine deep learning algorithm for urgent head CTs
Machine learning (ML) algorithms to detect critical findings on head CTs may expedite patient management. Most ML algorithms for diagnostic imaging analysis utilize dichotomous classifications to determine whether a specific abnormality is present. However, imaging findings may be indeterminate, and algorithmic inferences may have substantial uncertainty. We incorporated awareness of uncertainty into an ML algorithm that detects intracranial hemorrhage or other urgent intracranial abnormalities and evaluated prospectively identified, 1000 consecutive noncontrast head CTs assigned to Emergency Department Neuroradiology for interpretation. The algorithm classified the scans into high (IC+) and low (IC-) probabilities for intracranial hemorrhage or other urgent abnormalities. All other cases were designated as No Prediction (NP) by the algorithm. The positive predictive value for IC+ cases (N = 103) was 0.91 (CI: 0.84–0.96), and the negative predictive value for IC- cases (N = 729) was 0.94 (0.91–0.96). Admission, neurosurgical intervention, and 30-day mortality rates for IC+ was 75% (63–84), 35% (24–47), and 10% (4–20), compared to 43% (40–47), 4% (3–6), and 3% (2–5) for IC-. There were 168 NP cases, of which 32% had intracranial hemorrhage or other urgent abnormalities, 31% had artifacts and postoperative changes, and 29% had no abnormalities. An ML algorithm incorporating uncertainty classified most head CTs into clinically relevant groups with high predictive values and may help accelerate the management of patients with intracranial hemorrhage or other urgent intracranial abnormalities.
- 4 February 2021
- Published by American Society of Neuroradiology (ASNR) in American Journal of Neuroradiology
- Vol. 42 (5) , 831-837
Severity of Chest Imaging is Correlated with Risk of Acute Neuroimaging Findings among Patients with COVID-19
BACKGROUND AND PURPOSE: Severe respiratory distress in patients with COVID-19 has been associated with higher rate of neurologic manifestations. Our aim was to investigate whether the severity of chest imaging findings among patients with coronavirus disease 2019 (COVID-19) correlates with the risk of acute neuroimaging findings. MATERIALS AND METHODS: This retrospective study included all patients with COVID-19 who received care at our hospital between March 3, 2020, and May 6, 2020, and underwent chest imaging within 10 days of neuroimaging. Chest radiographs were assessed using a previously validated automated neural network algorithm for COVID-19 (Pulmonary X-ray Severity score). Chest CTs were graded using a Chest CT Severity scoring system based on involvement of each lobe. Associations between chest imaging severity scores and acute neuroimaging findings were assessed using multivariable logistic regression. RESULTS: Twenty-four of 93 patients (26%) included in the study had positive acute neuroimaging findings, including intracranial hemorrhage (n = 7), infarction (n = 7), leukoencephalopathy (n = 6), or a combination of findings (n = 4). The average length of hospitalization, prevalence of intensive care unit admission, and proportion of patients requiring intubation were significantly greater in patients with acute neuroimaging findings than in patients without them (P < .05 for all). Compared with patients without acute neuroimaging findings, patients with acute neuroimaging findings had significantly higher mean Pulmonary X-ray Severity scores (5.0 [SD, 2.9] versus 9.2 [SD, 3.4], P < .001) and mean Chest CT Severity scores (9.0 [SD, 5.1] versus 12.1 [SD, 5.0], P = .041). The pulmonary x-ray severity score was a significant predictor of acute neuroimaging findings in patients with COVID-19. CONCLUSIONS: Patients with COVID-19 and acute neuroimaging findings had more severe findings on chest imaging on both radiographs and CT compared with patients with COVID-19 without acute neuroimaging findings. The severity of findings on chest radiography was a strong predictor of acute neuroimaging findings in patients with COVID-19.
- 4 February 2021
- Published by American Society of Neuroradiology (ASNR) in American Journal of Neuroradiology
- Vol. 42 (5) , 831-837
Severity of Chest Imaging is Correlated with Risk of Acute Neuroimaging Findings among Patients with COVID-19
BACKGROUND AND PURPOSE: Severe respiratory distress in patients with COVID-19 has been associated with higher rate of neurologic manifestations. Our aim was to investigate whether the severity of chest imaging findings among patients with coronavirus disease 2019 (COVID-19) correlates with the risk of acute neuroimaging findings. MATERIALS AND METHODS: This retrospective study included all patients with COVID-19 who received care at our hospital between March 3, 2020, and May 6, 2020, and underwent chest imaging within 10 days of neuroimaging. Chest radiographs were assessed using a previously validated automated neural network algorithm for COVID-19 (Pulmonary X-ray Severity score). Chest CTs were graded using a Chest CT Severity scoring system based on involvement of each lobe. Associations between chest imaging severity scores and acute neuroimaging findings were assessed using multivariable logistic regression. RESULTS: Twenty-four of 93 patients (26%) included in the study had positive acute neuroimaging findings, including intracranial hemorrhage (n = 7), infarction (n = 7), leukoencephalopathy (n = 6), or a combination of findings (n = 4). The average length of hospitalization, prevalence of intensive care unit admission, and proportion of patients requiring intubation were significantly greater in patients with acute neuroimaging findings than in patients without them (P < .05 for all). Compared with patients without acute neuroimaging findings, patients with acute neuroimaging findings had significantly higher mean Pulmonary X-ray Severity scores (5.0 [SD, 2.9] versus 9.2 [SD, 3.4], P < .001) and mean Chest CT Severity scores (9.0 [SD, 5.1] versus 12.1 [SD, 5.0], P = .041). The pulmonary x-ray severity score was a significant predictor of acute neuroimaging findings in patients with COVID-19. CONCLUSIONS: Patients with COVID-19 and acute neuroimaging findings had more severe findings on chest imaging on both radiographs and CT compared with patients with COVID-19 without acute neuroimaging findings. The severity of findings on chest radiography was a strong predictor of acute neuroimaging findings in patients with COVID-19.