Hulin Zhao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Hulin Zhao has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- An’aN Ping
State Key Laboratory of Cognitive Neuroscience and Learning and IDG/McGovern Institute for Brain Research, Division of Psychology, Beijing Normal University, Beijing, China
1 shared publication Chenyu Wang
State Key Laboratory of Cognitive Neuroscience and Learning and IDG/McGovern Institute for Brain Research, Division of Psychology, Beijing Normal University, Beijing, China
1 shared publicationFan Zhang
School of Information Science and Technology, ShanghaiTech University, Shanghai, China
1 shared publication- Fei Gao
School of Biomedical Engineering, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, China
1 shared publication Jianning Zhang
Department of Neurosurgery, First Medical Center, Chinese Peoples Liberation Army General Hospital, Beijing, China
1 shared publication- Mingsha Zhang
State Key Laboratory of Cognitive Neuroscience and Learning and IDG/McGovern Institute for Brain Research, Division of Psychology, Beijing Normal University, Beijing 100875, China
1 shared publication
Latest Publications
- 11 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Imaging
- Vol. 11 (25730436) , 1142-1149
HDN: Hybrid Deep-Learning and Non-Line-of-Sight Reconstruction Framework for Transcranial Photoacoustic Imaging of Human Brain
Photoacoustic imaging combines the high contrast of optical imaging with the deep penetration depth of ultrasonic imaging, showing great potential in cerebrovascular disease detection. However, the ultrasonic wave suffers strong attenuation and multi-scattering when it passes through the skull tissue, resulting in the distortion of the collected photoacoustic signal. In this paper, inspired by the principles of deep learning and non-line-of-sight imaging, we propose an image reconstruction framework named HDN (Hybrid Deep-learning and Non-line-of-sight), which consists of the signal extraction part and difference utilization part. The signal extraction part is used to correct the distorted signal and reconstruct an initial image. The difference utilization part is used to make further use of the signal difference between the distorted signal and corrected signal, reconstructing the residual image between the initial image and the target image. The test results on a photoacoustic digital brain simulation dataset show that compared with the traditional method (delay-and-sum) and deep-learning-based method (UNet), the HDN achieved superior performance in both signal correction and image reconstruction. Specifically for the structural similarity index, the HDN reached 0.661 in imaging results, compared to 0.157 for the delay-and-sum method and 0.305 for the deep-learning-based method.
- 11 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Imaging
- Vol. 11 (25730436) , 1142-1149
HDN: Hybrid Deep-Learning and Non-Line-of-Sight Reconstruction Framework for Transcranial Photoacoustic Imaging of Human Brain
Photoacoustic imaging combines the high contrast of optical imaging with the deep penetration depth of ultrasonic imaging, showing great potential in cerebrovascular disease detection. However, the ultrasonic wave suffers strong attenuation and multi-scattering when it passes through the skull tissue, resulting in the distortion of the collected photoacoustic signal. In this paper, inspired by the principles of deep learning and non-line-of-sight imaging, we propose an image reconstruction framework named HDN (Hybrid Deep-learning and Non-line-of-sight), which consists of the signal extraction part and difference utilization part. The signal extraction part is used to correct the distorted signal and reconstruct an initial image. The difference utilization part is used to make further use of the signal difference between the distorted signal and corrected signal, reconstructing the residual image between the initial image and the target image. The test results on a photoacoustic digital brain simulation dataset show that compared with the traditional method (delay-and-sum) and deep-learning-based method (UNet), the HDN achieved superior performance in both signal correction and image reconstruction. Specifically for the structural similarity index, the HDN reached 0.661 in imaging results, compared to 0.157 for the delay-and-sum method and 0.305 for the deep-learning-based method.
- Top Cited Papers
- 4 April 2025
- Published by American Association for the Advancement of Science (AAAS) in Science
- Vol. 388 (6742) , eadr3675
Human high-order thalamic nuclei gate conscious perception through the thalamofrontal loop
Human high-order thalamic nuclei activity is known to closely correlate with conscious states. However, it is not clear how those thalamic nuclei and thalamocortical interactions directly contribute to the transient process of human conscious perception. We simultaneously recorded stereoelectroencephalography data from the thalamic nuclei and prefrontal cortex (PFC), while patients with implanted electrodes performed a visual consciousness task. Compared with the ventral nuclei and PFC, the intralaminar and medial nuclei presented earlier and stronger consciousness-related activity. Transient thalamofrontal neural synchrony and cross-frequency coupling were both driven by the θ phase of the intralaminar and medial nuclei during conscious perception. The intralaminar and medial thalamic nuclei thus play a gate role to drive the activity of the PFC during the emergence of conscious perception.
- 4 April 2025
- Published by American Association for the Advancement of Science (AAAS) in Science
- Vol. 388 (6742) , eadr3675
Top Cited PapersHuman high-order thalamic nuclei gate conscious perception through the thalamofrontal loop
Human high-order thalamic nuclei activity is known to closely correlate with conscious states. However, it is not clear how those thalamic nuclei and thalamocortical interactions directly contribute to the transient process of human conscious perception. We simultaneously recorded stereoelectroencephalography data from the thalamic nuclei and prefrontal cortex (PFC), while patients with implanted electrodes performed a visual consciousness task. Compared with the ventral nuclei and PFC, the intralaminar and medial nuclei presented earlier and stronger consciousness-related activity. Transient thalamofrontal neural synchrony and cross-frequency coupling were both driven by the θ phase of the intralaminar and medial nuclei during conscious perception. The intralaminar and medial thalamic nuclei thus play a gate role to drive the activity of the PFC during the emergence of conscious perception.
- Open Access
- 16 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 106567-106578
Double Discrete Variational Autoencoder for Epileptic EEG Signals Classification
Electroencephalography (EEG) plays a key role in the clinical evaluation of epilepsy and provides strong support for treatment decisions. However, analyzing and decoding EEG recordings is a burdensome task for neurologists and clinical experts. Existing automated detection techniques make considerable efforts in feature engineering, but often fall short when it comes to representing complex patterns in EEG signals. Deep learning methods allow for higher-order representations and intricate pattern learning, experiencing explosive success in the performance of automated EEG diagnostics. In this paper, we propose a novel Double Discrete Variational AutoEncoder (D 2 -VAE) network to learn the latent representations in EEG signals and perform deep discretization. Specifically, the method builds a learnable codebook based on the Vector Quantized Variational AutoEncoder (VQ-VAE) to obtain a generic representation of the EEG signal. The discretization of the local patterns of the signal is obtained by codebook queries, whereas the discretization of the global information of the signal is characterized by building a histogram of the quantization patterns. Such local-global signal portrayal is more attuned to the single-mode repetition and multi-mode mixing that characterizes epileptic signals. Multiple epilepsy diagnostic tasks and multiple evaluation metrics are used to validate the effectiveness of the proposed method for the classification of complex EEG signals. The experimental results show that D 2 -VAE possesses a low-dimensional yet powerful quantitative representation, with a significant improvement in performance over existing methods.
- 16 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 106567-106578
Open AccessDouble Discrete Variational Autoencoder for Epileptic EEG Signals Classification
Electroencephalography (EEG) plays a key role in the clinical evaluation of epilepsy and provides strong support for treatment decisions. However, analyzing and decoding EEG recordings is a burdensome task for neurologists and clinical experts. Existing automated detection techniques make considerable efforts in feature engineering, but often fall short when it comes to representing complex patterns in EEG signals. Deep learning methods allow for higher-order representations and intricate pattern learning, experiencing explosive success in the performance of automated EEG diagnostics. In this paper, we propose a novel Double Discrete Variational AutoEncoder (D 2 -VAE) network to learn the latent representations in EEG signals and perform deep discretization. Specifically, the method builds a learnable codebook based on the Vector Quantized Variational AutoEncoder (VQ-VAE) to obtain a generic representation of the EEG signal. The discretization of the local patterns of the signal is obtained by codebook queries, whereas the discretization of the global information of the signal is characterized by building a histogram of the quantization patterns. Such local-global signal portrayal is more attuned to the single-mode repetition and multi-mode mixing that characterizes epileptic signals. Multiple epilepsy diagnostic tasks and multiple evaluation metrics are used to validate the effectiveness of the proposed method for the classification of complex EEG signals. The experimental results show that D 2 -VAE possesses a low-dimensional yet powerful quantitative representation, with a significant improvement in performance over existing methods.