Yun Wang

Yun Wang

Auto-generated profile, based on publicly available information

Yun Wang

Department of Psychiatry, Columbia University Medical Center, New York, NY, USA

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 September 2022 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Open access
XZXuzhe Zhang
Xuzhe Zhang
XHXinzi He
Xinzi He
JGJia Guo
Jia Guo
NENabil Ettehadi
Nabil Ettehadi
NANatalie Aw
Natalie Aw
YWYun Wang
Yun Wang
An increased interest in longitudinal neurodevelopment during the first few years after birth has emerged in recent years. Noninvasive magnetic resonance imaging (MRI) can provide crucial information about the development of brain structures in the early months of life. Despite the success of MRI collections and analysis for adults, it remains a challenge for researchers to collect high-quality multimodal MRIs from developing infant brains because of their irregular sleep pattern, limited attention, inability to follow instructions to stay still during scanning. In addition, there are limited analytic approaches available. These challenges often lead to a significant reduction of usable MRI scans and pose a problem for modeling neurodevelopmental trajectories. Researchers have explored solving this problem by synthesizing realistic MRIs to replace corrupted ones. Among synthesis methods, the convolutional neural network-based (CNN-based) generative adversarial networks (GANs) have demonstrated promising performance. In this study, we introduced a novel 3D MRI synthesis framework– pyramid transformer network (PTNet3D)– which relies on attention mechanisms through transformer and performer layers. We conducted extensive experiments on high-resolution Developing Human Connectome Project (dHCP) and longitudinal Baby Connectome Project (BCP) datasets. Compared with CNN-based GANs, PTNet3D consistently shows superior synthesis accuracy and superior generalization on two independent, large-scale infant brain MRI datasets. Notably, we demonstrate that PTNet3D synthesized more realistic scans than CNN-based models when the input is from multi-age subjects. Potential applications of PTNet3D include synthesizing corrupted or missing images. By replacing corrupted scans with synthesized ones, we observed significant improvement in infant whole brain segmentation.

1 January 2019 in NeuroImage: Clinical
Verified
Journal Article
Open access
YWYun Wang
Yun Wang
CXChenxiao Xu
Chenxiao Xu
JPJi-Hwan Park
Ji-Hwan Park
SLSeonjoo Lee
Seonjoo Lee
YSYaakov Stern
Yaakov Stern
JCJiook Cha
Jiook Cha
Accurate, reliable prediction of risk for Alzheimer's disease (AD) is essential for early, disease-modifying therapeutics. Multimodal MRI, such as structural and diffusion MRI, is likely to contain complementary information of neurodegenerative processes in AD. Here we tested the utility of the multimodal MRI (T1-weighted structure and diffusion MRI), combined with high-throughput brain phenotyping-morphometry and structural connectomics-and machine learning, as a diagnostic tool for AD. We used, firstly, a clinical cohort at a dementia clinic (National Health Insurance Service-Ilsan Hospital [NHIS-IH]; N = 211; 110 AD, 64 mild cognitive impairment [MCI], and 37 cognitively normal with subjective memory complaints [SMC]) to test the diagnostic models; and, secondly, Alzheimer's Disease Neuroimaging Initiative (ADNI)-2 to test the generalizability. Our machine learning models trained on the morphometric and connectome estimates (number of features = 34,646) showed optimal classification accuracy (AD/SMC: 97% accuracy, MCI/SMC: 83% accuracy; AD/MCI: 97% accuracy) in NHIS-IH cohort, outperforming a benchmark model (FLAIR-based white matter hyperintensity volumes). In ADNI-2 data, the combined connectome and morphometry model showed similar or superior accuracies (AD/HC: 96%; MCI/HC: 70%; AD/MCI: 75% accuracy) compared with the CSF biomarker model (t-tau, p-tau, and Amyloid β, and ratios). In predicting MCI to AD progression in a smaller cohort of ADNI-2 (n = 60), the morphometry model showed similar performance with 69% accuracy compared with CSF biomarker model with 70% accuracy. Our comparisons of the classifiers trained on structural MRI, diffusion MRI, FLAIR, and CSF biomarkers showed the promising utility of the white matter structural connectomes in classifying AD and MCI in addition to the widely used structural MRI-based morphometry, when combined with machine learning.

7 October 2022 in Brain Sciences
Verified
Journal Article
Open access
PDF file
GDGopikrishna Deshpande
Gopikrishna Deshpande
YWYun Wang
Yun Wang
Layer-specific cortical microcircuits have been explored through invasive animal studies, yet it is not possible to reliably characterize them functionally and noninvasively in the human brain. However, recent advances in ultra-high-field functional magnetic resonance imaging (fMRI) have made it feasible to reasonably resolve layer-specific fMRI signals with sub-millimeter resolution. Here, we propose an experimental and analytical framework that enables the noninvasive functional characterization of layer-specific cortical microcircuits. Specifically, we illustrate this framework by characterizing layer-specific functional pathways in the corticogeniculate network of the human visual system by obtaining sub-millimeter fMRI at 7T using a task which engages the magnocellular pathway between the lateral geniculate nucleus (LGN) and the primary visual cortex. Our results demonstrate that: (i) center-surround inhibition in magnocellular neurons within LGN is detectable using localized fMRI responses; (ii) feedforward (LGN → layers VI/IV, layer IV → layer VI) and feedback (layer VI → LGN) functional pathways, known to exist from invasive animal studies, can be inferred using dynamic directional connectivity models of fMRI and could potentially explain the mechanism underlying center-surround inhibition as well as gain control by layer VI in the human visual system. Our framework is domain-neutral and could potentially be employed to investigate the layer-specific cortical microcircuits in other systems related to cognition, memory and language.

25 May 2020 in bioRxiv
Verified
Preprint
Open access
PDF file
YWYun Wang
Yun Wang
FHFateme Sadat Haghpanah
Fateme Sadat Haghpanah
NANatalie Aw
Natalie Aw
ALAndrew Laine
Andrew Laine
JPJonathan Posner
Jonathan Posner
The months between birth and age 2 are increasingly recognized as a period critical for neuro-development, with potentially life-long implications for cognitive functioning. However, little is known about the growth trajectories of brain structure and function across this time period. This is in large part because of insufficient approaches to analyze infant MRI scans at different months, especially brain segmentation. Addressing technical gaps in infant brain segmentation would significantly improve our capacity to efficiently measure and identify relevant infant brain structures and connectivity, and their role in long-term development. In this paper, we propose a transfer-learning approach based on convolutional neural network (CNN)-based image segmentation architecture, QuickNAT, to segment brain structures for newborns and 6-month infants separately. We pre-trained QuickNAT on auxiliary labels from a large-scale dataset, fine-tuned on manual labels, and then cross-validated the model’s performance on two separate datasets. Compared to other commonly used methods, our transfer-learning approach showed superior segmentation performance on both newborns and 6-month infants. Moreover, we demonstrated improved hippocampus segmentation performance via our approach in preterm infants.

30 March 2021 in bioRxiv
Verified
Preprint
Open access
PDF file
YWYun Wang
Yun Wang
FHFateme Sadat Haghpanah
Fateme Sadat Haghpanah
XZXuzhe Zhang
Xuzhe Zhang
KSKatie Santamaria
Katie Santamaria
GAGabriela Koch da Costa Aguiar Alves
Gabriela Koch da Costa Aguiar Alves
JPJonathan Posner
Jonathan Posner
Early postnatal period brain magnetic resonance imaging (MRI) is becoming an important approach to measure the impact of prenatal exposures on neurodevelopment and to investigate early biomarkers for risk. Among brain structures, Limbic structures are particular of interest in psychiatric disorder-related research. However, despite the promise of infant neuroimaging and the success of initial infant MRI studies, assessing limbic regions’ structure and function remains a significant challenge due to low inter-regional intensity contrast and high curvature (e.g., hippocampus). In addition, the agreement between existing automatic techniques and manual segmentation remains either untested or insufficient, particularly for the amygdala and hippocampus. In this work, we developed an accurate (based on three segmentation evaluation metrics), reliable and efficient infant deep learning segmentation framework (ID-Seg) to address the aforementioned challenges. Specifically, we leveraged a large dataset of 473 infant MRI scans to train ID-Seg and rigorously evaluated ID-Seg’s performance on internal and external datasets with manual segmentations. Compared with a state-of-the-art segmentation pipeline, we demonstrated that ID-Seg significantly improved the segmentation accuracy of limbic structures (hippocampus and amygdala) in newborn infants. Moreover, in a medium-size dataset, we found that ID-Seg-derived morphometric measures yield strong brain-behavior associations. As such, our ID-Seg may improve our capacity and efficiency to measure MRI-based brain features relevant to neuropsychological development and ultimately advance the success of quantitative analyses on large-scale datasets.

25 June 2020 in bioRxiv
Verified
Preprint
Open access
PDF file
YWYun Wang
Yun Wang
WHWalter Hinds
Walter Hinds
CDCristiane S Duarte
Cristiane S Duarte
SLSeonjoo Lee
Seonjoo Lee
CMCatherine Monk
Catherine Monk
JPJonathan Posner
Jonathan Posner
Resting functional MRI studies of the infant brain are increasingly becoming an important tool in developmental neuroscience. Whereas the test-retest reliability of functional connectivity (FC) measures derived from resting fMRI data have been characterized in the adult and child brain, similar assessments have not been conducted in infants. In this study, we examined the intra-session test-retest reliability of FC measures from 119 infant brain MRI scans from four neurodevelopmental studies. We investigated edge-level and subject-level reliability within one MRI session (between and within runs) measured by the Intraclass correlation coefficient (ICC). First, using an atlas-based approach, we examined whole-brain connectivity as well as connectivity within two common resting fMRI networks – the default mode network (DMN) and the sensorimotor network (SMN). Second, we examined the influence of run duration, study site, and scanning manufacturer (e.g., Philips and General Electric) on ICCs. Lastly, we tested spatial similarity using the Jaccard Index from networks derived from independent component analysis (ICA). Consistent with resting fMRI studies from adults, our findings indicated poor edge-level reliability (ICC = 0.14 - 0.18), but moderate-to-good subject-level intra-session reliability for whole-brain, DMN, and SMN connectivity (ICC = 0.40 - 0.78). We also found significant effects of run duration, site, and scanning manufacturer on reliability estimates. Some ICA-derived networks showed strong spatial reproducibility (e.g., DMN, SMN, and Visual Network), and were labelled based on their spatial similarity to analogous networks measured in adults. These networks were reproducibly found across different study studies. However, other ICA-networks (e.g. Executive Control Network) did not show strong spatial reproducibility, suggesting that the reliability and/or maturational course of functional connectivity may vary by network. In sum, our findings suggest that developmental scientist may be on safe ground examining the functional organization of some major neural networks (e.g. DMN and SMN), but judicious interpretation of functional connectivity is essential to its ongoing success. Highlights: Infant functional connectivity (FC) shows poor edge-level reliability (ICCs) However, subject-level infant FC estimates show good-to-excellent ICCs Spatial reproducibility is better for some resting networks (DMN, SMN) than others (ECN) Reliability estimates differ across study site and MRI scanner Conclusion - Infant FC can be a reliable measurement, but judicious use is needed