Yu Liu

Yu Liu

Auto-generated profile, based on publicly available information

Yu Liu

Technical University of Munich

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
25 May 2021 in IEEE Transactions on Cybernetics
Verified
Journal Article
Closed access
YLYang Li
Yang Li
YLYu Liu
Yu Liu
Yuzhu GuoYuzhu Guo
Yuzhu Guo
XLXiaofeng Liao
Xiaofeng Liao
BHBin Hu
Bin Hu
TYTao Yu
Tao Yu
Graph theory analysis using electroencephalogram (EEG) signals is currently an advanced technique for seizure prediction. Recent deep learning approaches, which fail to fully explore both the characterizations in EEGs themselves and correlations among different electrodes simultaneously, generally neglect the spatial or temporal dependencies in an epileptic brain and, thus, produce suboptimal seizure prediction performance consequently. To tackle this issue, in this article, a patient-specific EEG seizure predictor is proposed by using a novel spatio-temporal-spectral hierarchical graph convolutional network with an active preictal interval learning scheme (STS-HGCN-AL). Specifically, since the epileptic activities in different brain regions may be of different frequencies, the proposed STS-HGCN-AL framework first infers a hierarchical graph to concurrently characterize an epileptic cortex under different rhythms, whose temporal dependencies and spatial couplings are extracted by a spectral-temporal convolutional neural network and a variant self-gating mechanism, respectively. Critical intrarhythm spatiotemporal properties are then captured and integrated jointly and further mapped to the final recognition results by using a hierarchical graph convolutional network. Particularly, since the preictal transition may be diverse from seconds to hours prior to a seizure onset among different patients, our STS-HGCN-AL scheme estimates an optimal preictal interval patient dependently via a semisupervised active learning strategy, which further enhances the robustness of the proposed patient-specific EEG seizure predictor. Competitive experimental results validate the efficacy of the proposed method in extracting critical preictal biomarkers, indicating its promising abilities in automatic seizure prediction.

26 July 2021 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Verified
Journal Article
Open access
YLYang Li
Yang Li
LGLianghui Guo
Lianghui Guo
YLYu Liu
Yu Liu
JLJingyu Liu
Jingyu Liu
FMFangang Meng
Fangang Meng
Motor imagery (MI) electroencephalography (EEG) decoding plays an important role in brain-computer interface (BCI), which enables motor-disabled patients to communicate with the outside world via external devices. Recent deep learning methods, which fail to fully explore both deep-temporal characterizations in EEGs itself and multi-spectral information in different rhythms, generally ignore the temporal or spectral dependencies in MI-EEG. Also, the lack of effective feature fusion probably leads to redundant or irrelative information and thus fails to achieve the most discriminative features, resulting in the limited MI-EEG decoding performance. To address these issues, in this paper, a MI-EEG decoding framework is proposed, which uses a novel temporal-spectral-based squeeze-and-excitation feature fusion network (TS-SEFFNet). First, the deep-temporal convolution block (DT-Conv block) implements convolutions in a cascade architecture, which extracts high-dimension temporal representations from raw EEG signals. Second, the multi-spectral convolution block (MS-Conv block) is then conducted in parallel using multi-level wavelet convolutions to capture discriminative spectral features from corresponding clinical subbands. Finally, the proposed squeeze-and-excitation feature fusion block (SE-Feature-Fusion block) maps the deep-temporal and multi-spectral features into comprehensive fused feature maps, which highlights channel-wise feature responses by constructing interdependencies among different domain features. Competitive experimental results on two public datasets demonstrate that our method is able to achieve promising decoding performance compared with the state-of-the-art methods.

7 September 2021 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
YLYang Li
Yang Li
JLJingyu Liu
Jingyu Liu
YJYiqiao Jiang
Yiqiao Jiang
YLYu Liu
Yu Liu
BLBaiying Lei
Baiying Lei
Dynamic functional connectivity (dFC) network inferred from resting-state fMRI reveals macroscopic dynamic neural activity patterns for brain disease identification. However, dFC methods ignore the causal influence between the brain regions. Furthermore, due to the complex non-Euclidean structure of brain networks, advanced deep neural networks are difficult to be applied for learning high-dimensional representations from brain networks. In this paper, a group constrained Kalman filter (gKF) algorithm is proposed to construct dynamic effective connectivity (dEC), where the gKF provides a more comprehensive understanding of the directional interaction within the dynamic brain networks than the dFC methods. Then, a novel virtual adversarial training convolutional neural network (VAT-CNN) is employed to extract the local features of dEC. The VAT strategy improves the robustness of the model to adversarial perturbations, and therefore avoids the overfitting problem effectively. Finally, we propose the high-order connectivity weight-guided graph attention networks (cwGAT) to aggregate features of dEC. By injecting the weight information of high-order connectivity into the attention mechanism, the cwGAT provides more effective high-level feature representations than the conventional GAT. The high-level features generated from the cwGAT are applied for binary classification and multiclass classification tasks of mild cognitive impairment (MCI). Experimental results indicate that the proposed framework achieves the classification accuracy of 90.9%, 89.8%, and 82.7% for normal control (NC) vs. early MCI (EMCI), EMCI vs. late MCI (LMCI), and NC vs. EMCI vs. LMCI classification respectively, outperforming the state-of-the-art methods significantly.

26 October 2024
Verified
Book Chapter
Closed access
PDF file
TCTomáš Chobola
Tomáš Chobola
YLYu Liu
Yu Liu
HZHanyi Zhang
Hanyi Zhang
JSJulia A. Schnabel
Julia A. Schnabel
TPTingying Peng
Tingying Peng

27 October 2025 in bioRxiv
Verified
Preprint
Open access
YLYu Liu
Yu Liu
GMGesine F. Müller
Gesine F. Müller
LKLennart Kowitz
Lennart Kowitz
TCTomáš Chobola
Tomáš Chobola
KWKurt Weiss
Kurt Weiss
TPTingying Peng
Tingying Peng
Selective plane illumination microscopy (SPIM, also known as light sheet fluorescence microscopy) is the method of choice for studying morphogenesis and function in biological specimens over extended periods, as it permits gentle and rapid volumetric imaging. In inhomogeneous samples, however, sample-induced artifacts, including light absorption, scattering, and refraction, can impact the image quality, particularly as the focal plane gets deeper into the sample. Here, we present Leonardo , the first toolbox designed to address the major sample-induced artifacts by using two modules: (1) DeStripe removes stripe artifacts in SPIM caused by light absorption while preserving fine sample structures; (2) Fuse reconstructs a single high-quality image from dualsided illumination and/or dual-sided detection, while eliminating blur and optical distortions caused by light scattering and refraction. The efficacy of Leonardo is validated on a wide range of biological samples, from minimally invasive experiments on sensitive specimens (translucent embryonic and optically opaque larval zebrafish) to cleared mouse samples up to two centimeters in size. We provide model code and a Napari-based graphical user interface, enabling the SPIM community to easily apply Leonardo to advance light sheet imaging of inhomogeneous and complex specimens.