About

Chuan Huang, Ph.D., is an Assistant Professor in Research Radiology and Psychiatry at Stony Brook University. He received his B.S. in Mathematics (Computational and Information Sciences) from the University of Science and Technology of China in 2006 and his Ph.D. in Mathematics with a minor in Optical Sciences from The University of Arizona in 2012. His doctoral research focused on Magnetic Resonance Imaging within the Department of Radiology at The University of Arizona Medical Center. Following his Ph.D., he joined the Center for Advanced Medical Imaging Sciences at Massachusetts General Hospital and Harvard Medical School as a Research Fellow, later being promoted to Assistant in Physics at MGH and Instructor at HMS in June 2014. He joined Stony Brook University’s faculty in October 2014. His research interests include Medical Image Reconstruction and Analysis, Quantitative MRI, Simultaneous PET-MRI, Rapid MRI, Objective Assessment of Image Quality, and Mathematical Modeling. His Ph.D. work involved image analysis, reconstruction, and parametric MRI, notably developing a radial FSE technique to obtain T2 maps of the entire brain within two minutes. In 2012, he extended his research into simultaneous PET/MRI and authored the first paper on MR microcoil-based PET motion correction for the head, which was featured in a press release at the 2013 SNMMI annual meeting. Dr. Huang has led the MRI efforts in simultaneous PET/MRI projects at Massachusetts General Hospital and has been recognized with awards such as the Young Investigator Award Honorable Mentions at SNMMI and the Magna Cum Laude Awards at ISMRM.

Research topics

• Medicine
• Computer science
• Nuclear medicine
• Artificial intelligence
• Psychology

Selected publications

• Theta burst stimulation for suicidal ideation in depression: A systematic review and meta-analysis of efficacy and protocol moderators

  Psychiatry Research · 2026-05-16

  article
  PublisherDOI

• Orientation-Aware Diffusion Super-Resolution for 3T-Like Fetal MRI from Routine 1.5T Scans.

  PubMed · 2026-07-01

  articleOpen access

  inhomogeneity limits wide adoption for routine fetal imaging. Consequently, most clinical examinations are performed at 1.5T, where greater motion tolerance comes at the cost of lower SNR, reduced gray-white matter contrast, and partial-volume blurring - factors that undermine downstream morphometric analysis. Bridging this quality gap without sacrificing motion robustness of 1.5T would enable 3T-like morphometric reliability in routine clinical acquisitions. We propose an orientation-aware diffusion super-resolution framework that synthesizes 3T-like fetal brain contrast from routine 1.5T scans. The model combines a Swin-UNet backbone with gated FiLM-based orientation embeddings and a residual error-shifting diffusion mechanism. Training leverages the FaBiAN phantom to generate controllable high-/low-resolution pairs with monotonic intensity remapping, geometric perturbations, and simulated signal voids, thereby ensuring generalization to clinical data. Our model produces markedly sharper gyri and mitigates partial-volume effects in both synthesized and clinical data. When evaluated using Fetal-SynthSeg following NeSVoR reconstruction, the framework consistently improves tissue segmentation accuracy over state-of-the-art restoration baselines, yielding more reliable morphometric estimates for fetal brain analysis.

  PublisherOA PDF

• The anatomical relationship between tonsillo-biventral fissure and dentate nucleus in surgical approaches for hypertensive cerebellar hemorrhage

  World Neurosurgery · 2026-05-01

  articleOpen accessCorresponding

  OBJECTIVE: To investigate the anatomical relationship between the tonsillo-biventral fissure and the dentate nucleus in detail. Additionally, to apply this knowledge to guide the surgical management of hypertensive cerebellar hemorrhage. MATERIALS AND METHODS: A total of nine cases of hypertensive cerebellar hemorrhage treated between January 2025 and October 2025 were reviewed, in which the anatomical relationship between the tonsillo-biventral fissure and the dentate nucleus was fully utilized to guide surgery. The specific operative steps and underlying rationale of this innovative surgical concept were analyzed and described in detail. RESULTS: There is a close anatomical relationship between the tonsillo-biventral fissure and the dentate nucleus. Since hypertensive cerebellar hemorrhage mainly originates from the dentate nucleus, these anatomical characteristics should be integrated with patient-specific imaging findings to guide surgical planning. The hematoma can be directly exposed through the natural corridor of the tonsillo-biventral fissure, or this fissure can serve as a constant anatomical landmark to guide cortical fenestration, thereby providing the surgeon with a more straightforward operative strategy. CONCLUSION: Fully utilizing the anatomical relationship between the tonsillo-biventral fissure and the dentate nucleus to guide the surgical treatment of hypertensive cerebellar hemorrhage is a safe, efficient, simple, and minimally invasive technique worth promoting and disseminating.

  PublisherDOI

• A Cross‐Sectional Network Analysis of Psychological Resilience and Multidimensional Sleep Quality in Nurses

  International Nursing Review · 2026-05-04

  article

  AIM: This study examined the associations between nurses' resilience and specific components of sleep quality and explored whether prior experiences of patient attacks influenced these relationships. BACKGROUND: Nurses work under demanding conditions that may compromise resilience and sleep health. Understanding these relationships may help inform targeted strategies to support well-being and practice. METHODS: A cross-sectional correlational study was conducted among registered nurses from tertiary hospitals in Southwest China (N = 697). Resilience was assessed using the 10-item Connor-Davidson Resilience Scale (CD-RISC-10) and sleep quality using the seven Pittsburgh Sleep Quality Index (PSQI) components. A psychometric network model was estimated using EBICglasso regularization. Strength centrality, bridge centrality and network accuracy and stability were assessed using bootstrap procedures. Group differences by patient attack experience were examined using the Network Comparison Test with false-discovery-rate correction. RESULTS: The sleep components were closely interconnected. The strongest positive associations were observed between sleep duration and sleep efficiency and between sleep disturbances and daytime dysfunction. The strongest negative association was between sleep latency and subjective sleep quality. Sleep disturbances and subjective sleep quality were the most central nodes. Bootstrap analyses supported acceptable stability (CS = 0.52). Network structure did not differ significantly by patient attack experience. CONCLUSIONS: Sleep disturbances and subjective sleep quality emerged as the most central components linking resilience and multidimensional sleep quality. Interventions targeting these core domains may offer a pathway to strengthen nurses' well-being. IMPLICATIONS FOR NURSING AND HEALTH POLICY: Greater attention to resilience and sleep-focused support within hospital systems may help strengthen nurses' well-being and occupational health.

  PublisherDOI

• Body mass index is associated with functional brain network efficiency in midlife world trade center responders with cognitive impairment

  Discover Neuroscience · 2025-11-17

  articleOpen access

  Higher body mass index (BMI) is associated with lowered risk of dementia in aging populations, possibly because it improves cognitive reserve in old age. Little is known about mechanisms implicated in reductions in vulnerability and less is known about implications of BMI in cognitively impaired (CI) individuals at midlife. Here, we examined whether BMI relates to functional brain network efficiency and cognition in a physically active cohort of midlife World Trade Center (WTC) responders with documented 9/11-related exposures, testing how systemic inflammatory burden and body composition jointly shape brain networks. Resting-state fMRI data from 99 WTC responders and 10 matched controls were analyzed. Functional cerebral network efficiency metrics included characteristic path length (CPL), clustering coefficients (CC), global efficiency (GE), and small-worldness (SWN), and were derived across proportional sparsity thresholds to enhance robustness. Multivariate models tested the effects of BMI, CI, and their interaction on network efficiency. Higher BMI and CI were independently associated with cerebral network efficiency. A significant BMI × CI interaction was identified (CPL: p=0.024; SWN: p=0.010; GE: p=0.034), indicating that the positive association between BMI and network efficiency was strongest among cognitively impaired responders. Specifically, elevated BMI correlated with more integrated and efficient networks (e.g., shorter CPL and greater CC, GE, and SWN). Functional network efficiency metrics were modestly associated with attention and processing speed, but not with memory or visuospatial performance, suggesting selective relevance to cognitive domains vulnerable to early disruption. Consistent with hypotheses of cognitive reserve, this study provides novel evidence that functional brain network topology is influenced by BMI among cognitively impaired WTC responders. Findings highlight a complex interplay among systemic health, brain organization, and cognitive function at midlife.

  PublisherOA PDFDOI

• RobustSplat: Decoupling Densification and Dynamics for Transient-Free 3DGS

  2025-10-19 · 1 citations

  article
  PublisherDOI

• The effects of non-invasive brain stimulation on cognitive impairment in depression: A systematic review and meta-analysis

  Asian Journal of Psychiatry · 2025-06-05 · 3 citations

  review
  PublisherDOI

• Fast and Slow Recovery of Consciousness Following Traumatic Brain Injury

  Neurocritical Care · 2025-06-27 · 1 citations

  article
  PublisherDOI

• Alzheimer's Disease Risk Prediction in the Elderly: A Machine Learning Approach Combining Clinical Characteristics and Polygenic Risk Scores

  2025-08-20

  article

  Motivation: Alzheimer's disease (AD) is the most common type of dementia. Given the lack of a cure, early identification of high-risk populations is crucial for timely prevention. While several studies have focused on AD risk prediction, single feature (e.g., age) may dominate model performance, limiting the discovery of other potential risk factors. This study incorporates key features identified in previous research and applies propensity score matching for age and sex, aiming to improve the predictive performance of AD risk models for older adults.Methods: This study utilized data from the UK Biobank to integrate genetic and clinical data and developed 5-year and 10- year AD risk prediction models for older adults, respectively. The workflow included genome-wide association studies (GWAS) on 433,589 participants were conducted to identify significant Single nucleotide polymorphisms (SNPs) under three p-value thresholds, followed by polygenic risk score (PRS) calculation for 13,282 participants using PRSice-2 and Lassosum, and the integration of multiple features to construct prediction models. Clinical features, PRS, and significant SNPs were then incorporated into four machine learning models: Logistic Regression, LightGBM, XGBoost, and Multi-Layer Perceptron (MLP) for prediction and performance comparison.Results: For the 5-year risk prediction, the MLP model demonstrated the best performance, achieving an AUC of 0.88 based on 37 clinical features and 206 significant SNPs. For the 10-year risk prediction, the MLP model also demonstrated the best performance, achieving an AUC of 0.89 based on 37 clinical features, 206 significant SNPs, and PRS based on these SNPs. SHAP analysis revealed that key contributors across both models included ApoE genotype, urinary tract infection (N390), disorientation, depressive symptoms, and pairs matching time. The 5-year model emphasized immediate clinical and cognitive indicators such as reaction time and number of medications taken, whereas the 10-year model highlighted long-term risk factors including BMI, diabetes, and peak expiratory flow.Conclusion: This study demonstrates that integrating clinical features with PRS can effectively enhance the accuracy of AD risk prediction models for older adults. However, to further validate the utility of PRS, future research should involve collaborations across diverse populations and databases. Additionally, further exploration of other potential risk factors is needed to enhance the clinical applicability of these models.

  PublisherDOI

• Mesentery morphological features on computed tomography for preoperative prediction of tumor invasion and lymph node metastasis in colon cancer

  World Journal of Clinical Oncology · 2025-07-22

  articleOpen access

  BACKGROUND: Accurate identification of tumor invasion depth and lymph node (LN) involvement in patients with colon cancer (CC) is critical for guiding treatment strategies. However, the preoperative prediction of tumor invasion depth and LN metastasis in CC remains challenging. As the intestinal tumor develops, the fat density in the mesentery increases. AIM: To investigate the efficacy of computed tomography (CT) value change in the mesentery contributed by the tumor (CT-T value) for predicting tumor invasion depth and LN metastasis. METHODS: Patients, who were diagnosed with CC and underwent surgery, were included and divided into the training and validation cohorts. CT-T values of the mesentery were extracted from the CT images. Cutoff points were determined using the receiver operating characteristic (ROC) curve, and the area under the ROC curve was employed to assess the performance of the CT-T value for tumor invasion depth and LN status prediction. RESULTS: N1/2, respectively. With a cutoff CT-T value of 11.83, the total diagnostic accuracy for T stage was 83.1% (81.5% for the training cohort and 86.2% for the validation cohort). With a cutoff CT-T value of 17.17, the total diagnostic accuracy for N stage was 77.3% (75.8% for the training cohort and 80.1% for the validation cohort), which was higher than that of CT-reported LN metastasis. CONCLUSION: In this study, we explored an efficient method for predicting preoperative T and N stages using the tumor-contributed CT value of the mesentery in CC, which displayed superior predictive accuracy.

  PublisherDOI

Recent grants

• Early Treatment Response Detection Using Highly Accurate and Reliable Breast Density Measure Derived From MRI

  NIH · $157k · 2018–2021

Frequent coauthors

• Georges El Fakhri

  Yale University

  151 shared

• Yoann Petibon

  Takeda (United States)

  86 shared

• Jinsong Ouyang

  Yale University

  86 shared

• Timothy G. Reese

  Harvard University

  74 shared

• Christine DeLorenzo

  Stony Brook University

  61 shared

• Quanzheng Li

  Harvard University

  46 shared

• Mark Slifstein

  Stony Brook School

  44 shared

• Benjamin J. Luft

  Stony Brook School

  40 shared

Education

• PhD

  University of Arizona

  2013

Awards & honors

• Distinguished Reviewer for Magnetic Resonance in Medicine (2…
• ISMRM Young Investigator Award Honorable Mention (2014)
• SNMMI Annual Meeting Young Investigator Award Honorable Ment…
• Magna Cum Laude Award for abstract #106 (2012)
• Magna Cum Laude Award for abstract #362 (2012)