Jia Li

Jia Li

Auto-generated profile, based on publicly available information

Jia Li

Key Laboratory of Optoelectronic Devices and Systems College of Physics and Optoelectronic Engineering State Key Laboratory of Radio Frequency Heterogeneous Integration (Shenzhen University) Shenzhen University Shenzhen China

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
5 January 2023 in PhotoniX
Verified
Journal Article
Open access
PDF file
BHBoyi Huang
Boyi Huang
JLJia Li
Jia Li
BYBowen Yao
Bowen Yao
ZYZhigang Yang
Zhigang Yang
ELEdmund Y. Lam
Edmund Y. Lam
Junle QuJunle Qu
Junle Qu
Super-resolution optical imaging is crucial to the study of cellular processes. Current super-resolution fluorescence microscopy is restricted by the need of special fluorophores or sophisticated optical systems, or long acquisition and computational times. In this work, we present a deep-learning-based super-resolution technique of confocal microscopy. We devise a two-channel attention network (TCAN), which takes advantage of both spatial representations and frequency contents to learn a more precise mapping from low-resolution images to high-resolution ones. This scheme is robust against changes in the pixel size and the imaging setup, enabling the optimal model to generalize to different fluorescence microscopy modalities unseen in the training set. Our algorithm is validated on diverse biological structures and dual-color confocal images of actin-microtubules, improving the resolution from ~ 230 nm to ~ 110 nm. Last but not least, we demonstrate live-cell super-resolution imaging by revealing the detailed structures and dynamic instability of microtubules.

7 December 2022 in Journal of Innovative Optical Health Sciences
Verified
Journal Article
Open access
PDF file
JLJianhui Liao
Jianhui Liao
Junle QuJunle Qu
Junle Qu
YHYongqi Hao
Yongqi Hao
JLJia Li
Jia Li
The algorithm used for reconstruction or resolution enhancement is one of the factors affecting the quality of super-resolution images obtained by fluorescence microscopy. Deep-learning-based algorithms have achieved state-of-the-art performance in super-resolution fluorescence microscopy and are becoming increasingly attractive. We firstly introduce commonly-used deep learning models, and then review the latest applications in terms of the network architectures, the training data and the loss functions. Additionally, we discuss the challenges and limits when using deep learning to analyze the fluorescence microscopic data, and suggest ways to improve the reliability and robustness of deep learning applications.

9 July 2023 in Advanced Science
Verified
Journal Article
Open access
JLJianhui Liao
Jianhui Liao
CZChenshuang Zhang
Chenshuang Zhang
XXXiangcong Xu
Xiangcong Xu
LZLiangliang Zhou
Liangliang Zhou
BYBin Yu
Bin Yu
Junle QuJunle Qu
Junle Qu
Fast and precise reconstruction algorithm is desired for for multifocal structured illumination microscopy (MSIM) to obtain the super‐resolution image. This work proposes a deep convolutional neural network (CNN) to learn a direct mapping from raw MSIM images to super‐resolution image, which takes advantage of the computational advances of deep learning to accelerate the reconstruction. The method is validated on diverse biological structures and in vivo imaging of zebrafish at a depth of 100 µm. The results show that high‐quality, super‐resolution images can be reconstructed in one‐third of the runtime consumed by conventional MSIM method, without compromising spatial resolution. Last but not least, a fourfold reduction in the number of raw images required for reconstruction is achieved by using the same network architecture, yet with different training data.

24 June 2024 in Applied Physics Letters
Verified
Journal Article
Open access
PDF file
ZLZiyi Luo
Ziyi Luo
XXXiangcong Xu
Xiangcong Xu
DLDanying Lin
Danying Lin
Junle QuJunle Qu
Junle Qu
FLFangrui Lin
Fangrui Lin
JLJia Li
Jia Li
Coherent anti-Stokes Raman scattering (CARS) microscopy requires the removal of non-resonant background (NRB) to ensure spectral accuracy and quality. This study introduces a deep-learning-based algorithm that leverages its enhanced capability for NRB removal and spectra retrieval. A generative adversarial network is trained using simulated noisy CARS data, enabling straightforward analysis of real CARS spectra obtained from pork belly and living mice brains. The results highlight the algorithm's ability to accurately extract vibrational information in the CH region. Importantly, this method eliminates the need for additional experimental measurements or extensive data preprocessing or postprocessing.

2 January 2026 in Applied Physics Reviews
Verified
Journal Article
Closed access
FLFangrui Lin
Fangrui Lin
CZChenshuang Zhang
Chenshuang Zhang
ZHZhenlong Huang
Zhenlong Huang
YWYiqiang Wang
Yiqiang Wang
MYMin Yi
Min Yi
Junle QuJunle Qu
Junle Qu
Fluorescence lifetime imaging microscopy (FLIM) has emerged as a powerful biomedical imaging technique for the quantitative visualization of intricate molecular and cellular processes. Significant advancements in photonics, sensor technology, data acquisition systems, and computational algorithms have substantially improved the spatiotemporal resolution, imaging depth, and analytical throughput of FLIM. These developments have diversified FLIM methodologies, including time-domain techniques such as time-correlated single-photon counting (TCSPC), time-gated detection, streak cameras, and direct pulse-recording systems, as well as frequency-domain approaches. Concurrently, FLIM has been successfully integrated with advanced imaging modalities, such as multiphoton microscopy, light-sheet imaging, and endoscopy. This review provides a comprehensive synthesis of advanced FLIM technologies. We present in-depth discussions on the principles of lifetime quantification, recent innovations in hardware and algorithms for lifetime recovery, and state-of-the-art strategies to accelerate imaging speed while maintaining resolution and sensitivity. Moreover, we explore FLIM's unique capability to investigate dynamic metabolic states through endogenous autofluorescent cofactors, quantify physicochemical parameters of the cellular microenvironment (e.g., pH, polarity, viscosity, and ion concentrations), and facilitate the diagnosis of diseases such as cancer and neurodegeneration. Finally, we discuss future directions for FLIM development, including integration with deep learning, miniaturized hardware for point-of-care applications, and real-time clinical translation. Collectively, this review aims to provide researchers, clinicians, and engineers with both fundamental knowledge and forward-looking perspectives to further unlock the potential of FLIM in advancing biomedical science.

29 September 2023 in Optics Express
Verified
Journal Article
Closed access
ZLZiyi Luo
Ziyi Luo
GZGuorui Zhu
Guorui Zhu
HXHao Xu
Hao Xu
DLDanying Lin
Danying Lin
JLJia Li
Jia Li
Junle QuJunle Qu
Junle Qu
In vivo imaging and accurate identification of amyloid-β (Aβ) plaque are crucial in Alzheimer’s disease (AD) research. In this work, we propose to combine the coherent anti-Stokes Raman scattering (CARS) microscopy, a powerful detection technology for providing Raman spectra and label-free imaging, with deep learning to distinguish Aβ from non-Aβ regions in AD mice brains in vivo. The 1D CARS spectra is firstly converted to 2D CARS figures by using two different methods: spectral recurrence plot (SRP) and spectral Gramian angular field (SGAF). This can provide more learnable information to the network, improving the classification precision. We then devise a cross-stage attention network (CSAN) that automatically learns the features of Aβ plaques and non-Aβ regions by taking advantage of the computational advances in deep learning. Our algorithm yields higher accuracy, precision, sensitivity and specificity than the results of conventional multivariate statistical analysis method and 1D CARS spectra combined with deep learning, demonstrating its competence in identifying Aβ plaques. Last but not least, the CSAN framework requires no prior information on the imaging modality and may be applicable to other spectroscopy analytical fields.