YWYueyun Weng

Yueyun Weng

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yueyun Weng has a total of 107 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • CellDiffuser: Multimodal Optical Time-Stretch Imaging Flow Cytometry and Diffusion Models for Lung Cancer Immunotherapy Diagnosis

    by Zhaoyi Ye, Congkuan Song, Yueyun Weng, Sheng Liu, Du Wang, Liye Mei, Cheng Lei

    Immune checkpoint inhibitors have emerged as frontline therapies for lung cancer, yet the lack of reliable biomarkers for predicting the treatment response remains a critical challenge. While single-cell analysis offers a potent approach to probing physiological states, conventional techniques suffer from limited throughput and insufficient multimodal profiling capability. To address the aforementioned issues, we propose a novel framework for lung cancer immunotherapy diagnosis. Specifically, we develop multimodal optical time-stretch imaging flow cytometry (OTS-IFC) that simultaneously acquires label-free bright-field (BF) and quantitative phase (QP) images at a throughput of 10,000 cells/s. In response to the influence of phase unwrapping artifacts, we propose CellDiffuser, an intermediate domain transformation diffusion model that aligns BF and QP images in a shared latent space at a preselected time step, thus generating high-fidelity synthesized QP images. CellDiffuser achieves an SSIM of 0.747 in the leukocyte immunotherapy response prediction data set and an SSIM of 0.708 in the A549 cell death state identification data set. Finally, our framework demonstrates its practical utility in lung cancer immunotherapy diagnosis in the above two clinically relevant data sets. This work establishes a cost-effective, high-throughput framework for single-cell phenotyping, offering a new paradigm to guide lung cancer personalized immunotherapy diagnosis. The code is available at: https://github.com/yzygit1230/CellDiffuser.

  • Mechanical behavior of Cu–Ni functionally graded material-faced sandwich structures: A molecular dynamics study

    by Yuxuan Fu, Feixiang Tang, Xinyu Wu, Jiaxin Liu, Qianyun Shu, Siyu He, Zhaoxu Zhou, Qiying Liu, Yueyun Weng

    To investigate the atomistic mechanical behavior of Cu–Ni functionally graded sandwich structures, molecular dynamics simulations were performed on models with Cu–Ni graded face sheets and a homogeneous Ni core. Tensile and compressive responses were examined at 220, 300, and 420 K for three thickness ratios (1:1:1, 1:2:1, and 1:4:1) and gradient indices from 0.1 to ∞. Mechanical behavior and deformation mechanisms were characterized using stress–strain curves, elastic modulus, common neighbor analysis, and a dislocation extraction algorithm. Results show that the mechanical properties are strongly governed by Ni content. Lower gradient indices and larger Ni-core fractions significantly increase yield strength and elastic modulus, but reduce yield strain and ductility. Increasing temperature decreases elastic modulus and promotes dislocation rearrangement and defect recovery. These results demonstrate that the strength, stiffness, and thermal adaptability of Cu–Ni functionally graded sandwich structures can be effectively tuned by controlling temperature, thickness ratio, and gradient index.

  • All-optical classification of real biomedical cell images using a diffractive neural network: a simulation study

    by Norihide Sagami, Yueyun Weng, Cheng Lei, Ryosuke Oketani, Kotaro Hiramatsu

    We report an in-silico demonstration of an all-optical cell classification system using a single-layer diffractive neural network (DNN) optimized for real-world biomedical images. Implemented virtually with a spatial light modulator (SLM), the DNN was numerically trained via backpropagation to differentiate breast cells, lung cancer cells, and white blood cells. The training utilized experimentally acquired phase and amplitude images from optofluidic time-stretch quantitative phase imaging. Classification was simulated by computing the optical intensities at the detection plane. The optimized DNN achieved 96.1% accuracy, approaching that of conventional convolutional neural networks. This study highlights the potential of SLM-based DNNs for ultrafast, energy-efficient biomedical image processing in practical optical computing scenarios.


  • Ultrafast Multipoint Flow Sensing via Optical Time-Stretch Interferometry

    by Mingjie Yu, Qiyun Yao, Rongwei Zha, Yueyun Weng, Shubin Wei, Quanxing Zhai, Xiaoya Ma, Shuang Chen, Du Wang, Cheng Lei

  • Open Access

    Rapid-manufacturing and cost-effective single-layer microfluidic device for high-throughput three-dimensional hydrodynamic focusing

    by Ruopeng Yan, Shubin Wei, Yueyun Weng, Rubing Li, Yan Jin, Xun Liu, Jinxuan Hou, Yu Xu, Sheng Li, Du Wang, et al.

    Microfluidic devices play a crucial role in the widespread application of single-cell analysis, where hydrodynamic focusing stands out due to its simplicity in structure and excellent adaptability to a wide range of flow rates. Owing to the extensive application of soft lithography, polydimethylsiloxane (PDMS) is widely used in the fabrication of microfluidic devices. However, challenges arise under high-throughput conditions, where the elastic deformation of PDMS can cause microchannel expansion, diminishing focusing effect. To address this challenge, this work introduces a three-dimensional (3D) hydrodynamic focusing device with simplified single-layer structure, which is fabricated by the double transfer process, specifically designed for fabricating polyurethane acrylate (PUA) microfluidic devices. Notably, this approach eliminates the time-consuming heating procedures, which significantly enhances manufacturing speed by an order of magnitude compared to the soft lithography process. To evaluate the practical focusing performance of the microfluidic device, optical time-stretch (OTS) microscopy is employed for high-throughput imaging of clinical urine samples. Experimental results demonstrate that as the flow rate increases, the focusing efficiency gradually improves in both vertical and lateral directions. At an averaged velocity of 16.7 m/s, the focusing efficiency reaches 98.4% in the vertical direction and 95.0% in the lateral direction. Thus, the amalgamation of simplicity, efficiency, and adaptability positions this technology as a promising tool in the realm of microfluidics, particularly for applications requiring precise cell focusing in high-throughput scenarios.


  • Open Access

    Heart failure assessment using red blood cell image feature via label-free imaging flow cytometry

    by Yueyun Weng, Shubin Wei, Na Yu, Zhaoyi Ye, Xiaoyang Chen, Yan Jin, Xiaolan Ruan, Du Wang, Sheng Liu, Difei Shen, et al.

    Heart failure, as a clinical syndrome and the end-stage manifestation of cardiac disease, has a five-year survival rate of less than 50%. The diagnosis of heart failure requires a multifaceted integration of clinical manifestations and indicators, which often renders the diagnostic process inefficient and misses the optimal treatment window. In this study, we utilize the features of label-free images of peripheral red blood cells acquired through an optical time-stretch imaging flow cytometer to assess the stages of heart failure. In particular, our approach involves the high-throughput acquisition of red cell images, from which we extract features, including size, statistical, and frequency characteristics. By establishing correlations between peripheral red cell image features and multimodal clinical indicators (cardiac ultrasound, B-type natriuretic peptide, and inflammatory factors), we have successfully achieved heart failure assessment through red blood cell image features, and these results were validated by clinical diagnostic outcomes, with a correlation exceeding 0.9. Our system holds promise as a comprehensive method for evaluating heart failure status.

  • High-throughput label-free assessment of sperm DNA fragmentation index via intelligent morphological imaging

    by Yan Jin, Yujie Zou, Yueyun Weng, Zhaoyi Ye, Xiaoyang Chen, Zhengwu Liu, Tailang Yin, Sheng Liu, Yan Zhang, Cheng Lei

    Intelligent morphological imaging flow cytometry is developed for high-throughput label-free sperm DNA fragmentation index assessment.


  • Label‐Free and Intelligent Cell Death Recognition Toward Lung Cancer Chemotherapy

    by Shubin Wei, Guoqing Luo, Zhaoyi Ye, Yueyun Weng, Liye Mei, Yan Jin, Yi Liu, Du Wang, Sheng Liu, Qing Geng, et al.

    The lack of high‐throughput, label‐free, and intelligent recognition models for assessing cell death hinders the broad application of cell death analysis in chemotherapy for lung cancer. We propose an intelligent quantitative detection technique for cell deaths. Using high‐throughput quantitative phase imaging flow cytometry to capture numerous label‐free images and employing convolutional neural networks (CNN) to characterize the heterogeneity and quantitative detection of cell death. We revealed the heterogeneity of cell death through morphology features and achieved interpretability analysis of the CNN using clustering. Finally, the classification reliability of the CNN was validated by extracting features from classified cells. This method, compared with biochemical methods, showed a correlation of 0.92 and 0.91 with autophagy detection (Pearson and Cosine Similarity), and an average error of 12.52% with apoptosis detection. Our approach has the potential to become a valuable tool for studying cell death mechanisms and offers a new perspective for cancer treatment.

  • High‐Throughput and Stain‐Free Morphological Analysis of Sperm Using Optofluidic Time‐Stretch Imaging Flow Cytometry

    by Yueyun Weng, Yujie Zou, Yan Jin, Shubin Wei, Feng Zhang, Rubing Li, Liye Mei, Dongyong Yang, Zhimin Deng, Rui Qu, et al.

    The incidence of male infertility has kept increasing year by year, severely affecting the sustainability of society. Sperm morphological analysis plays an important role in assessing sperm fertility. However, current sperm morphological analysis is usually performed using microscopic images of stained sperm, which requires complex staining operations, making it difficult to achieve a comprehensive and efficient diagnosis. In this work, we propose and experimentally demonstrate sperm morphological analysis with optofluidic time‐stretch (OTS) imaging flow cytometry. Specifically, we capture the stain‐free sperm images with high‐throughput OTS imaging flow cytometry and analyze the morphological features using a U‐Net network. The analysis of 40,000 images from 20 clinical semen samples indicates that our method achieves higher accuracy than the smear test and shows high concordance with the results using comprehensive methods of routine semen examination. This work provides a high‐throughput, stain‐free sperm morphological analysis method, which holds promise for a comprehensive evaluation of semen.


  • Label-Free Prediction of Immunotherapy Response in Lung Cancer

    by Shubin Wei, Congkuan Song, Zhaoyi Ye, Yueyun Weng, Liye Mei, Rubing Li, Ruopeng Yan, Yu Deng, Xiaohong Liu, Ximing Xu, et al.