Yuheng Lu

Yuheng Lu

Auto-generated profile, based on publicly available information

Yuheng Lu

Beijing Key Laboratory of Brainnetome and Brain-Computer Interface, Institute of Automation, Chinese Academy of Sciences, Beijing, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
18 October 2022 in Cerebral Cortex
Verified
Journal Article
Open access
PDF file
WLWen Li
Wen Li
LFLingzhong Fan
Lingzhong Fan
WSWeiyang Shi
Weiyang Shi
YLYuheng Lu
Yuheng Lu
JLJin Li
Jin Li
TJTianzi Jiang
Tianzi Jiang
During the preadolescent period, when the cerebral thickness, curvature, and myelin are constantly changing, the brain's regionalization patterns underwent persistent development, contributing to the continuous improvements of various higher cognitive functions. Using a brain atlas to study the development of these functions has attracted much attention. However, the brains of children do not always have the same topological patterns as those of adults. Therefore, age-specific brain mapping is particularly important, serving as a basic and indispensable tool to study the normal development of children. In this study, we took advantage of longitudinal data to create the brain atlas specifically for preadolescent children. The resulting human Child Brainnetome Atlas, with 188 cortical and 36 subcortical subregions, provides a precise period-specific and cross-validated version of the brain atlas that is more appropriate for adoption in the preadolescent period. In addition, we compared and illustrated for regions with different topological patterns in the child and adult atlases, providing a topologically consistent reference for subsequent research studying child and adolescent development.

31 October 2022 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
LMLiang Ma
Liang Ma
YZYu Zhang
Yu Zhang
HZHantian Zhang
Hantian Zhang
LCLuqi Cheng
Luqi Cheng
ZYZhengyi Yang
Zhengyi Yang
TJTianzi Jiang
Tianzi Jiang
Brain atlas is an important tool in the diagnosis and treatment of neurological disorders. However, due to large variations in the organizational principles of individual brains, many challenges remain in clinical applications. Brain atlas individualization network (BAI-Net) is an algorithm that subdivides individual cerebral cortex into segregated areas using brain morphology and connectomes. The presented method integrates group priors derived from a population atlas, adjusts areal probabilities using the context of connectivity fingerprints derived from the fiber-tract embedding of tractography, and provides reliable and explainable individualized brain areas across multiple sessions and scanners. We demonstrate that BAI-Net outperforms the conventional iterative clustering approach by capturing significantly heritable topographic variations in individualized cartographies. The topographic variability of BAI-Net cartographies has shown strong associations with individual variability in brain morphology, connectivity as well as higher relationship on individual cognitive behaviors and genetics. This study provides an explainable framework for individualized brain cartography that may be useful in the precise localization of neuromodulation and treatments on individual brains.

23 May 2022
Verified
Conference Paper
Open access
YHYi Hou
Yi Hou
CLChengyang Li
Chengyang Li
YLYuheng Lu
Yuheng Lu
LZLiping Zhu
Liping Zhu
YLYuan Li
Yuan Li
XXXiaodong Xie
Xiaodong Xie
In this article, we propose a simulated crowd counting dataset CrowdX, which has a large scale, accurate labeling, parameterized realization, and high fidelity. The experimental results of using this dataset as data enhancement show that the performance of the proposed streamlined and efficient benchmark network ESA-Net can be improved by 8.4%. The other two classic heterogeneous architectures MCNN and CSRNet pre-trained on CrowdX also show significant performance improvements. Considering many influencing factors determine performance, such as background, camera angle, human density, and resolution. Although these factors are important, there is still a lack of research on how they affect crowd counting. Thanks to the CrowdX dataset with rich annotation information, we conduct a large number of data-driven comparative experiments to analyze these factors. Our research provides a reference for a deeper understanding of the crowd counting problem and puts forward some useful suggestions in the actual deployment of the algorithm.

24 April 2024 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
YCYue Cui
Yue Cui
CLChengyi Li
Chengyi Li
YLYuheng Lu
Yuheng Lu
LMLiang Ma
Liang Ma
LCLuqi Cheng
Luqi Cheng
TJTianzi Jiang
Tianzi Jiang
Individual brains vary greatly in morphology, connectivity and organization. Individualized brain parcellation is capable of precisely localizing subject-specific functional regions. However, most individualization approaches examined single modality of data and have not generalized to nonhuman primates. The present study proposed a novel multimodal connectivity-based individual parcellation (MCIP) method, which optimizes within-region homogeneity, spatial continuity and similarity to a reference atlas with the fusion of personal functional and anatomical connectivity. Comprehensive evaluation demonstrated that MCIP outperformed state-of-the-art multimodal individualization methods in terms of functional and anatomical homogeneity, predictability of cognitive measures, heritability, reproducibility and generalizability across species. Comparative investigation showed a higher topographic variability in humans than that in macaques. Therefore, MCIP provides improved accurate and reliable mapping of brain functional regions over existing methods at an individual level across species, and could facilitate comparative and translational neuroscience research.

1 October 2021
Verified
Conference Paper
Closed access
FCFangping Chen
Fangping Chen
YLYuheng Lu
Yuheng Lu
BCBinbin Cai
Binbin Cai
XXXiaodong Xie
Xiaodong Xie
Reconstruction and mapping of outdoor urban environment are critical to a large variety of applications, ranging from large-scale city-level 3D content creation for augmented and virtual reality to the digital twin construction of smart cities and automatic driving. The construction of large-scale city-level 3D model will become another important medium after images and videos. We propose an autonomous approach to reconstruct the voxel model of the scene in real-time, and estimate the best set of viewing angles according to the precision requirement. These task views are assigned to the drones based on Optimal Mass Transport (OMT) optimization. In this process, the multi-level pipelining in the chip design method is applied to accelerate the parallelism between exploration and data acquisition. Our method includes: (1) real-time perception and reconstruction of scene voxel model and obstacle avoidance; (2) determining the best observation and viewing angles of scene geometry through global and local optimization; (3) assigning the task views to the drones and planning path based on the OMT optimization, and iterating continuously according to new exploration results; (4) expediting exploration and data acquisition in parallel through multi-stage pipeline to improve efficiency. Our method can schedule routes for drones according to the scene and its optimal acquisition perspective in real-time, which avoids the model void and lack of accuracy caused by traditional aerial 3D scanning using routes of cultivating land regardless of the object, and lays a solid foundation for the 3D real-life model to directly become the available 3D data source for AR and VR. We evaluate the effectiveness of our method by collecting several groups of large-scale city-level data. Facts have proved that the accuracy and efficiency of reconstruction have been greatly improved.

4 November 2025 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
ZDZhenwei Dong
Zhenwei Dong
XLXinyi Liu
Xinyi Liu
WSWeiyang Shi
Weiyang Shi
YLYuheng Lu
Yuheng Lu
YLYanyan Liu
Yanyan Liu
TJTianzi Jiang
Tianzi Jiang
Precise quantification and localization of tracer-labeled neurons are essential for unraveling brain connectivity patterns and constructing a mesoscopic brain connectome atlas in macaques. However, methodological challenges and limitations in dataset development have impeded this scientific progress. This work introduced the Macaque Fluorescently Labeled Neurons (MFN) dataset, derived from retrograde tracing on three rhesus macaques. The dataset, meticulously annotated by six specialists, includes 1,600 images and 33,411 high-quality neuron annotations. Leveraging this dataset, we developed a Dense Convolutional Attention U-Net (DAUNet) cell counting model. By integrating Dense Convolutional blocks and a multi-scale attention module, the model exhibits robust feature extraction and representation capabilities while maintaining low complexity. On the MFN dataset, DAUNet achieved a Mean Absolute Error of 0.97 for cell counting and an F1-score of 96.29% for cell localization, outperforming several benchmark models. Extensive validation across four additional public datasets demonstrated the robust generalization ability of the model. Furthermore, the trained model was applied to quantify labeled neurons of a macaque brain, mapping the input connectivity patterns of two adjacent subregions in the lateral prefrontal cortex. This work provides a training dataset and algorithmic resource that advances mesoscopic brain connectivity research in macaques. The MFN dataset and source code are available at https://github.com/Gendwar/DAUnet.