Chu Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Chu Chen has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
Raymond H. Chan
3 shared publicationsElena Loli Piccolomini
University of Bologna
2 shared publicationsKangning Cui
City University of Hong Kong
2 shared publicationsKannie W. Y. Chan
2 shared publicationsPasquale Cascarano
University of Bologna
2 shared publicationsSe Weon Park
2 shared publications
Latest Publications
- Top Cited PapersOpen Access
- 12 February 2026
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 14 (4) , 351
SEAF-Net: A Sustainable and Lightweight Attention-Enhanced Detection Network for Underwater Fish Species Recognition
This study presents SEAF-Net, a lightweight and efficient detection network designed for low-contrast and highly dynamic underwater environments. Built upon YOLOv11n, SEAF-Net introduces three complementary structural enhancements: (1) Omni-Dimensional Dynamic Convolution (ODConv) to improve adaptive modeling of multi-scale and directional texture variations; (2) SimA-SPPF, which embeds the SimAM attention mechanism into the SPPF module to enable neuron-level saliency reweighting and effective suppression of complex background interference; and (3) GhostC3k2 to reduce redundant computation while preserving sufficient representational capacity. Evaluated on a standardized 13-class underwater fish dataset under a unified training and evaluation protocol, SEAF-Net achieves 6.1 GFLOPs, 92.683% Precision, 88.459% Recall, 93.333% mAP50, 73.445% mAP, and a 90.522% F1-score. Compared with the YOLOv11n baseline, SEAF-Net improves F1-score and Recall by 0.510% and 0.575%, respectively, while reducing computational cost by approximately 6%, demonstrating a favorable accuracy–efficiency trade-off under lightweight constraints. Ablation results further confirm that SimA-SPPF plays a dominant role in background suppression, ODConv consistently enhances deformation and directional texture modeling, and GhostC3k2 effectively controls computational overhead without degrading detection accuracy. To assess deployment feasibility, additional test set evaluations were conducted under deployment-oriented conditions using resource-limited hardware, yielding an F1-score of 88.54%. This result confirms that the proposed model maintains stable detection performance and robustness beyond training and validation stages. Overall, SEAF-Net provides an effective balance of accuracy, efficiency, and robustness, offering practical support for low-carbon, scalable, and sustainable intelligent aquaculture monitoring and underwater ecological assessment in real-world environments.
- 12 February 2026
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 14 (4) , 351
Top Cited PapersOpen AccessSEAF-Net: A Sustainable and Lightweight Attention-Enhanced Detection Network for Underwater Fish Species Recognition
This study presents SEAF-Net, a lightweight and efficient detection network designed for low-contrast and highly dynamic underwater environments. Built upon YOLOv11n, SEAF-Net introduces three complementary structural enhancements: (1) Omni-Dimensional Dynamic Convolution (ODConv) to improve adaptive modeling of multi-scale and directional texture variations; (2) SimA-SPPF, which embeds the SimAM attention mechanism into the SPPF module to enable neuron-level saliency reweighting and effective suppression of complex background interference; and (3) GhostC3k2 to reduce redundant computation while preserving sufficient representational capacity. Evaluated on a standardized 13-class underwater fish dataset under a unified training and evaluation protocol, SEAF-Net achieves 6.1 GFLOPs, 92.683% Precision, 88.459% Recall, 93.333% mAP50, 73.445% mAP, and a 90.522% F1-score. Compared with the YOLOv11n baseline, SEAF-Net improves F1-score and Recall by 0.510% and 0.575%, respectively, while reducing computational cost by approximately 6%, demonstrating a favorable accuracy–efficiency trade-off under lightweight constraints. Ablation results further confirm that SimA-SPPF plays a dominant role in background suppression, ODConv consistently enhances deformation and directional texture modeling, and GhostC3k2 effectively controls computational overhead without degrading detection accuracy. To assess deployment feasibility, additional test set evaluations were conducted under deployment-oriented conditions using resource-limited hardware, yielding an F1-score of 88.54%. This result confirms that the proposed model maintains stable detection performance and robustness beyond training and validation stages. Overall, SEAF-Net provides an effective balance of accuracy, efficiency, and robustness, offering practical support for low-carbon, scalable, and sustainable intelligent aquaculture monitoring and underwater ecological assessment in real-world environments.
- Open Access
Blind Adaptive Local Denoising for CEST Imaging
Chemical Exchange Saturation Transfer (CEST) MRI enables molecular-level visualization of low-concentration metabolites by leveraging proton exchange dynamics. However, its clinical translation is hindered by inherent challenges: spatially varying noise arising from hardware limitations, and complex imaging protocols introduce heteroscedasticity in CEST data, perturbing the accuracy of quantitative contrast mapping such as amide proton transfer (APT) imaging. Traditional denoising methods are not designed for this complex noise and often alter the underlying information that is critical for biomedical analysis. To overcome these limitations, we propose a new Blind Adaptive Local Denoising (BALD) method. BALD exploits the self-similar nature of CEST data to derive an adaptive variance-stabilizing transform that equalizes the noise distributions across CEST pixels without prior knowledge of noise characteristics. Then, BALD performs two-stage denoising on a linear transformation of data to disentangle molecular signals from noise. A local SVD decomposition is used as a linear transform to prevent spatial and spectral denoising artifacts. We conducted extensive validation experiments on multiple phantoms and \textit{in vivo} CEST scans. In these experiments, BALD consistently outperformed state-of-the-art CEST denoisers in both denoising metrics and downstream tasks such as molecular concentration maps estimation and cancer detection.
Open AccessBlind Adaptive Local Denoising for CEST Imaging
Chemical Exchange Saturation Transfer (CEST) MRI enables molecular-level visualization of low-concentration metabolites by leveraging proton exchange dynamics. However, its clinical translation is hindered by inherent challenges: spatially varying noise arising from hardware limitations, and complex imaging protocols introduce heteroscedasticity in CEST data, perturbing the accuracy of quantitative contrast mapping such as amide proton transfer (APT) imaging. Traditional denoising methods are not designed for this complex noise and often alter the underlying information that is critical for biomedical analysis. To overcome these limitations, we propose a new Blind Adaptive Local Denoising (BALD) method. BALD exploits the self-similar nature of CEST data to derive an adaptive variance-stabilizing transform that equalizes the noise distributions across CEST pixels without prior knowledge of noise characteristics. Then, BALD performs two-stage denoising on a linear transformation of data to disentangle molecular signals from noise. A local SVD decomposition is used as a linear transform to prevent spatial and spectral denoising artifacts. We conducted extensive validation experiments on multiple phantoms and \textit{in vivo} CEST scans. In these experiments, BALD consistently outperformed state-of-the-art CEST denoisers in both denoising metrics and downstream tasks such as molecular concentration maps estimation and cancer detection.
- 21 September 2025
- Published by Springer Nature
- p. 77-87
Blind Restoration of High-Resolution Ultrasound Video
- 21 September 2025
- Published by Springer Nature
- p. 77-87
Blind Restoration of High-Resolution Ultrasound Video
- 28 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- Vol. 72 (12) , 3663-3673
High-Quality CEST Mapping With Lorentzian-Model Informed Neural Representation
Chemical Exchange Saturation Transfer (CEST) MRI has demonstrated its remarkable ability to enhance the detection of macromolecules and metabolites with low concentrations. While CEST mapping is essential for quantifying molecular information, conventional methods face critical limitations: model-based approaches are constrained by limited sensitivity and robustness depending heavily on parameter setups, while data-driven deep learning methods lack generalizability across heterogeneous datasets and acquisition protocols. To overcome these challenges, we propose a Lorentzian-model Informed Neural Representation (LINR) framework for high-quality CEST mapping. LINR employs a self-supervised neural architecture embedding the Lorentzian equation – the fundamental biophysical model of CEST signal evolution – to directly reconstruct high-sensitivity parameter maps from raw z-spectra, eliminating dependency on labeled training data. Convergence of the self-supervised training strategy is guaranteed theoretically, ensuring LINR's mathematical validity. The superior performance of LINR in capturing CEST contrasts is revealed through comprehensive evaluations based on synthetic phantoms and in-vivo experiments (including tumor and Alzheimer's disease models). The intuitive parameter-free design enables adaptive integration into diverse CEST imaging workflows, positioning LINR as a versatile tool for non-invasive molecular diagnostics and pathophysiological discovery.
- 28 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- Vol. 72 (12) , 3663-3673
High-Quality CEST Mapping With Lorentzian-Model Informed Neural Representation
Chemical Exchange Saturation Transfer (CEST) MRI has demonstrated its remarkable ability to enhance the detection of macromolecules and metabolites with low concentrations. While CEST mapping is essential for quantifying molecular information, conventional methods face critical limitations: model-based approaches are constrained by limited sensitivity and robustness depending heavily on parameter setups, while data-driven deep learning methods lack generalizability across heterogeneous datasets and acquisition protocols. To overcome these challenges, we propose a Lorentzian-model Informed Neural Representation (LINR) framework for high-quality CEST mapping. LINR employs a self-supervised neural architecture embedding the Lorentzian equation – the fundamental biophysical model of CEST signal evolution – to directly reconstruct high-sensitivity parameter maps from raw z-spectra, eliminating dependency on labeled training data. Convergence of the self-supervised training strategy is guaranteed theoretically, ensuring LINR's mathematical validity. The superior performance of LINR in capturing CEST contrasts is revealed through comprehensive evaluations based on synthetic phantoms and in-vivo experiments (including tumor and Alzheimer's disease models). The intuitive parameter-free design enables adaptive integration into diverse CEST imaging workflows, positioning LINR as a versatile tool for non-invasive molecular diagnostics and pathophysiological discovery.
- Open Access
Blind Restoration of High-Resolution Ultrasound Video
Ultrasound imaging is widely applied in clinical practice, yet ultrasound videos often suffer from low signal-to-noise ratios (SNR) and limited resolutions, posing challenges for diagnosis and analysis. Variations in equipment and acquisition settings can further exacerbate differences in data distribution and noise levels, reducing the generalizability of pre-trained models. This work presents a self-supervised ultrasound video super-resolution algorithm called Deep Ultrasound Prior (DUP). DUP employs a video-adaptive optimization process of a neural network that enhances the resolution of given ultrasound videos without requiring paired training data while simultaneously removing noise. Quantitative and visual evaluations demonstrate that DUP outperforms existing super-resolution algorithms, leading to substantial improvements for downstream applications.
Open AccessBlind Restoration of High-Resolution Ultrasound Video
Ultrasound imaging is widely applied in clinical practice, yet ultrasound videos often suffer from low signal-to-noise ratios (SNR) and limited resolutions, posing challenges for diagnosis and analysis. Variations in equipment and acquisition settings can further exacerbate differences in data distribution and noise levels, reducing the generalizability of pre-trained models. This work presents a self-supervised ultrasound video super-resolution algorithm called Deep Ultrasound Prior (DUP). DUP employs a video-adaptive optimization process of a neural network that enhances the resolution of given ultrasound videos without requiring paired training data while simultaneously removing noise. Quantitative and visual evaluations demonstrate that DUP outperforms existing super-resolution algorithms, leading to substantial improvements for downstream applications.
- Open Access
Circular Image Deturbulence using Quasi-conformal Geometry
The presence of inhomogeneous media between optical sensors and objects leads to distorted imaging outputs, significantly complicating downstream image-processing tasks. A key challenge in image restoration is the lack of high-quality, paired-label images required for training supervised models. In this paper, we introduce the Circular Quasi-Conformal Deturbulence (CQCD) framework, an unsupervised approach for removing image distortions through a circular architecture. This design ensures that the restored image remains both geometrically accurate and visually faithful while preventing the accumulation of incorrect estimations. The circular restoration process involves both forward and inverse mapping. To ensure the bijectivity of the estimated non-rigid deformations, computational quasi-conformal geometry theories are leveraged to regularize the mapping, enforcing its homeomorphic properties. This guarantees a well-defined transformation that preserves structural integrity and prevents unwanted artifacts. Furthermore, tight-frame blocks are integrated to encode distortion-sensitive features for precise recovery. To validate the performance of our approach, we conduct evaluations on various synthetic and real-world captured images. Experimental results demonstrate that CQCD not only outperforms existing state-of-the-art deturbulence methods in terms of image restoration quality but also provides highly accurate deformation field estimations.
Open AccessCircular Image Deturbulence using Quasi-conformal Geometry
The presence of inhomogeneous media between optical sensors and objects leads to distorted imaging outputs, significantly complicating downstream image-processing tasks. A key challenge in image restoration is the lack of high-quality, paired-label images required for training supervised models. In this paper, we introduce the Circular Quasi-Conformal Deturbulence (CQCD) framework, an unsupervised approach for removing image distortions through a circular architecture. This design ensures that the restored image remains both geometrically accurate and visually faithful while preventing the accumulation of incorrect estimations. The circular restoration process involves both forward and inverse mapping. To ensure the bijectivity of the estimated non-rigid deformations, computational quasi-conformal geometry theories are leveraged to regularize the mapping, enforcing its homeomorphic properties. This guarantees a well-defined transformation that preserves structural integrity and prevents unwanted artifacts. Furthermore, tight-frame blocks are integrated to encode distortion-sensitive features for precise recovery. To validate the performance of our approach, we conduct evaluations on various synthetic and real-world captured images. Experimental results demonstrate that CQCD not only outperforms existing state-of-the-art deturbulence methods in terms of image restoration quality but also provides highly accurate deformation field estimations.
- 27 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Implicit Regression in Subspace for High-Sensitivity CEST Imaging
Chemical Exchange Saturation Transfer (CEST) MRI demonstrates its capability in significantly enhancing the detection of proteins and metabolites with low concentrations through exchangeable protons. The clinical application of CEST, however, is constrained by its low contrast and low signal-to-noise ratio (SNR) in the acquired data. Denoising, as one of the post-processing stages for CEST data, can effectively improve the accuracy of CEST quantification. In this work, by modeling spatial variant z-spectrums into low-dimensional subspace, we introduce Implicit Regression in Subspace (IRIS), which is an unsupervised denoising algorithm utilizing the excellent property of implicit neural representation for continuous mapping. Experiments conducted on both synthetic and in-vivo data demonstrate that our proposed method surpasses other CEST denoising methods regarding both qualitative and quantitative performance.
- 27 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Implicit Regression in Subspace for High-Sensitivity CEST Imaging
Chemical Exchange Saturation Transfer (CEST) MRI demonstrates its capability in significantly enhancing the detection of proteins and metabolites with low concentrations through exchangeable protons. The clinical application of CEST, however, is constrained by its low contrast and low signal-to-noise ratio (SNR) in the acquired data. Denoising, as one of the post-processing stages for CEST data, can effectively improve the accuracy of CEST quantification. In this work, by modeling spatial variant z-spectrums into low-dimensional subspace, we introduce Implicit Regression in Subspace (IRIS), which is an unsupervised denoising algorithm utilizing the excellent property of implicit neural representation for continuous mapping. Experiments conducted on both synthetic and in-vivo data demonstrate that our proposed method surpasses other CEST denoising methods regarding both qualitative and quantitative performance.
- Open Access
DMNR: Unsupervised De-noising of Point Clouds Corrupted by Airborne Particles
LiDAR sensors are critical for autonomous driving and robotics applications due to their ability to provide accurate range measurements and their robustness to lighting conditions. However, airborne particles, such as fog, rain, snow, and dust, will degrade its performance and it is inevitable to encounter these inclement environmental conditions outdoors. It would be a straightforward approach to remove them by supervised semantic segmentation. But annotating these particles point wisely is too laborious. To address this problem and enhance the perception under inclement conditions, we develop two dynamic filtering methods called Dynamic Multi-threshold Noise Removal (DMNR) and DMNR-H by accurate analysis of the position distribution and intensity characteristics of noisy points and clean points on publicly available WADS and DENSE datasets. Both DMNR and DMNR-H outperform state-of-the-art unsupervised methods by a significant margin on the two datasets and are slightly better than supervised deep learning-based methods. Furthermore, our methods are more robust to different LiDAR sensors and airborne particles, such as snow and fog.
Open AccessDMNR: Unsupervised De-noising of Point Clouds Corrupted by Airborne Particles
LiDAR sensors are critical for autonomous driving and robotics applications due to their ability to provide accurate range measurements and their robustness to lighting conditions. However, airborne particles, such as fog, rain, snow, and dust, will degrade its performance and it is inevitable to encounter these inclement environmental conditions outdoors. It would be a straightforward approach to remove them by supervised semantic segmentation. But annotating these particles point wisely is too laborious. To address this problem and enhance the perception under inclement conditions, we develop two dynamic filtering methods called Dynamic Multi-threshold Noise Removal (DMNR) and DMNR-H by accurate analysis of the position distribution and intensity characteristics of noisy points and clean points on publicly available WADS and DENSE datasets. Both DMNR and DMNR-H outperform state-of-the-art unsupervised methods by a significant margin on the two datasets and are slightly better than supervised deep learning-based methods. Furthermore, our methods are more robust to different LiDAR sensors and airborne particles, such as snow and fog.