Biology subjects

Li, H. B.

Publications and source records attributed to Li, H. B..

5 recordsLinked to original sources

bioRxiv2026

Accessing Mesoscale Functional Organization from Standard Functional MRI Leveraging AI-Based Super-Resolution

Access to the fine-scale functional organization of the human brain is essential for understanding cognition and neurological disorders yet remains beyond the reach of conventional functional MRI (fMRI) because of its limited spatial resolution and contrast-to-noise ratio. To overcome this limitation, we developed f-LENNS (functional Localization Enhancement via Neural-Net-Sharpening), an artificial intelligence (AI)-based framework that enhances the effective spatial resolution of reconstructed fMRI magnitude images. The model was trained exclusively on high-resolution synthetic MRI data using extensive domain randomization and no adversarial or generative components. This approach enables robust out-of-the-box generalization (without retraining) to experimental datasets obtained with diverse acquisitions, while effectively curbing hallucination. Our experiments show that our publicly available model substantially improves the spatial fidelity of functional activation maps across multiple imaging paradigms and generalizes to a cohort of individuals with atypical brain function caused by amblyopia (lazy eye). F-LENNS consistently outperforms conventional resolution enhancement approaches, including interpolation-based upsampling and sharpening methods. These findings demonstrate that AI-driven super-resolution combined with domain randomization can overcome domain shifts arising from differences in MRI acquisition, enabling scalable, fine-scale functional brain mapping with widely available MRI hardware.

neuroscience↗

bioRxiv2025

Claustrum volume in human lifespan trajectory and effect of age, hemisphere, and sex

The human claustrum is a bilateral, thin, irregularly shaped gray matter structure located between the striatum and insula. While previous research demonstrated the effect of distinct medical conditions, such as prematurity, schizophrenia, and Alzheimers disease, on claustrum function and structure, it is poorly understood how non-pathologic biological conditions effect the claustrum. This study aimed to investigate the effect of age, hemisphere, and sex on claustrum volume. We used T1-weighted 3 Tesla MRI scans of 3,474 healthy participants ranging from 1 to 80 years of age, deep learning-based automated claustrum segmentation, and a normative modeling approach to delineate lifespan trajectories of claustrum volumes for both hemispheres and sexes. Additionally, ordinary least squares regression analyses were applied to further characterize age, hemisphere, and sex effect. Lifespan analysis revealed a trajectory of rapid claustrum volume increase from infancy to adolescence ([~] 1-15 years, annual growth 39.300 mm3/year), a plateau phase from early to middle adulthood ([~] 15-40 years, annual change 0.153 mm3/year), and a subsequent decline from middle adulthood to old age ([~] 40-80 years, annual decrease 10.325 mm3/year). The right claustrum was on average larger than the left one across all ages. Finally, overall, females had larger total intracranial volume-adjusted claustrum volumes than males across the lifespan. Results demonstrate a distinct effect of age, hemisphere, and sex on claustrum volume. Data provide a comprehensive framework for sex- and hemisphere-sensitive claustrum structure lifespan trajectories relevant for studying neurodevelopmental and neurodegenerative effects on the claustrum.

neuroscience↗

bioRxiv2024

WMH-DualTasker: A Dual-Task Deep Learning Model with Self-supervised Consistency for Automated Segmentation and Visual Rating of White matter Hyperintensities - a Multicentre study

BackgroundWhite matter hyperintensities (WMH) are neuroimaging markers linked to an elevated risk of cognitive decline. WMH severity is typically assessed via visual rating scales and through volumetric segmentation. While visual rating scales are commonly used in clinical practice, they offer limited descriptive power. In contrast, supervised volumetric segmentation requires manually annotated masks, which is labor-intensive and challenging to scale for large studies. Therefore, our goal was to develop an automated deep learning model that can provide accurate and holistic quantification of WMH severity with minimal supervision. MethodsWe developed WMH-DualTasker, a deep learning model that simultaneously performs voxel-wise segmentation and visual rating score prediction. The model employs self-supervised learning with transformation-invariant consistency constraints, using WMH visual ratings (ARWMC scale, range 0-30) from clinical settings as the sole supervisory signal. Additionally, we assessed its clinical utility by applying it to identify individuals with mild cognitive impairment (MCI) and to predict dementia conversion. FindingsThe volumetric quantification performance of WMH-DualTasker was either superior to or on par with existing supervised methods, as demonstrated on the MICCAI-WMH dataset (N=60, Dice=0.602) and the SINGER dataset (N=64, Dice=0.608). Furthermore, the model exhibited strong agreement with clinical visual rating scales on an external dataset (SINGER, MAE=1.880, K=0.77). Importantly, WMH severity metrics derived from WMH-DualTasker improved predictive performance beyond conventional clinical features for MCI classification (AUC=0.718, p<0.001), MCI conversion prediction (AUC=0.652, p<0.001) using the ADNI dataset. InterpretationsWMH-DualTasker substantially reduces the reliance on labor-intensive manual annotations, facilitating more efficient and scalable quantification of WMH severity in large-scale population studies. This innovative approach has the potential to advance preventive and precision medicine by enhancing the assessment and management of vascular cognitive impairment associated with WMH. Code and model weights are publicly available at https://github.com/hzlab/WMH-DualTasker.

neuroscience↗

bioRxiv2024

Mapping the Cerebrovascular Abnormality in Transgenic Alzheimer's Disease (AD) Mice with deep-learning-based super-resolution cerebral blood volume (CBV)-MRI

To measure the brain-wide vascular density (VD) alteration in degenerated brains with Alzheimers Disease (AD), deep learning-based super-resolution approach was developed to assist the segmentation of micro-vessels from the Monocrystalline Iron Oxide Nanoparticle (MION)-based CBV MRI images of transgenic mouse brains. Iron-induced T2* amplification effect well separated micro-vessels with tens of microns from capillary-enriched parenchyma voxels, enabling vascular compartment-specific VD differential analysis between AD and wildtype control mice. The differential maps based on segmented micro-vessels identified decreased VD in the anterior cingulate cortex (ACC) and medial entorhinal cortex (mEC) and increased VD in several highlighted brain regions, including dentate gyrus (DG) of the hippocampus, central and geniculate thalamus, medial septal area (MS), ventral tegmental area (VTA), and lateral entorhinal cortex (lEC). In contrast, the T2*-weighted capillary density mapping from parenchyma voxels showed increased VD in several cortical regions, including somatosensory and visual cortex, retrosplenial cortex, as well as piriform area and lEC in AD brains. However, dramatic capillary VD decrease was observed in the subcortical areas including hippocampus, thalamus, hypothalamus, and pontine areas. These high-resolution MION-based CBV MRI elucidates altered vascular compartments in degenerated AD brains, reconciling the various region-specific vascular impairment and angiogenesis in functional areas critical for cognitive decline of AD.

neuroscience↗

bioRxiv2024

A new protocol for multispecies bacterial infections in zebrafish and their monitoring through automated image analysis

The zebrafish Danio rerio has become a popular model host to explore disease pathology caused by infectious agents. A main advantage is its transparency at an early age, which enables live imaging of infection dynamics. While multispecies infections are common in patients, the zebrafish model is rarely used to study them, although the model would be ideal for investigating pathogen-pathogen and pathogen-host interactions. This may be due to the absence of an established multispecies infection protocol for a defined organ and the lack of suitable image analysis pipelines for automated image processing. To address these issues, we developed a protocol for establishing and tracking single and multispecies bacterial infections in the inner ear structure (otic vesicle) of the zebrafish by imaging. Subsequently, we generated an image analysis pipeline that involved deep learning for the automated segmentation of the otic vesicle, and scripts for quantifying pathogen frequencies through fluorescence intensity measures. We used Pseudomonas aeruginosa, Acinetobacter baumannii, and Klebsiella pneumoniae, three of the difficult-to-treat ESKAPE pathogens, to show that our infection protocol and image analysis pipeline work both for single pathogens and pairwise pathogen combinations. Thus, our protocols provide a comprehensive toolbox for studying single and multispecies infections in real-time in zebrafish.

microbiology↗