YZYinglin Zhang

Yinglin Zhang

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yinglin Zhang has a total of 31 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Long-term stabilized iris tracking with unsupervised constraints on dynamic AS-OCT

    by Lingxi Hu, Xiao Wu, Risa Higashita, Xiaoli Xing, Menglan Zhou, Song Lin, Xiaorong Li, Yi Yue, Zunjie Xiao, Yinglin Zhang, et al.

  • Online Bayesian Approximation Based Uncertainty Aware Model for Ophthalmic Image Segmentation

    by Yinglin Zhang, Risa Higashita, Lingxi Zeng, Jialin Li, Ruiling Xi, Tianhang Liu, Huazhu Fu, Dave Towey, Ruibin Bai, Jiang Liu

    The robust segmentation of different targets in multiple modality images is challenging due to factors such as low contrast, variations in target size and shape, and interference from diseases, which may lead to segmentation ambiguity. In addition, the assessment of the reliability of artificial intelligence is crucial for its clinical application. This paper proposes the Online Bayesian approximation based Uncertainty-aware Network (OBU-Net) for robust ophthalmic image segmentation. Our approach introduces an efficient online Bayesian method to update a spatial uncertainty map during training continuously. Then, the Spatial Uncertainty Aware Block (SUA-B) leverages the uncertainty map to localize and prioritize attention to ambiguous regions. Additionally, we extract pixel-wise confidence from multi-scale predictions to integrate hierarchical predictions. We compare OBU-Net with state-of-the-art (SOTA) methods on six datasets. The experimental results demonstrate that our method achieves the best overall performance across different modalities and segmentation tasks, highlighting the robustness of our approach. Additionally, metamorphic testing experiments were conducted, exploring the algorithm's stability against random perturbations. Lastly, we propose an image-level uncertainty score and demonstrate its effectiveness for evaluating the model's segmentation reliability.


  • Prior Anatomical Knowledge-guided GAN for ICL surgery postoperative prediction based on AS-OCT image

    by Yinglin Zhang, Ruiling Xi, Risa Higashita, Keiichiro Okamoto, Kazutaka Kamiya, Kazunori Miyata, Akihito Igarashi, Seiichiro Hata, Tomoaki Nakamura, Jiang Liu


  • Low-Contrast Medical Image Segmentation via Transformer and Boundary Perception

    by Yinglin Zhang, Ruiling Xi, Wei Wang, Heng Li, Lingxi Hu, Huiyan Lin, Dave Towey, Ruibin Bai, Huazhu Fu, Risa Higashita, et al.

    Low-contrast medical image segmentation is a challenging task that requires full use of local details and global context. However, existing convolutional neural networks (CNNs) cannot fully exploit global information due to limited receptive fields and local weight sharing. On the other hand, the transformer effectively establishes long-range dependencies but lacks desirable properties for modeling local details. This paper proposes a Transformer-embedded Boundary perception Network (TBNet) that combines the advantages of transformer and convolution for low-contrast medical image segmentation. Firstly, the transformer-embedded module uses convolution at the low-level layer to model local details and uses the Enhanced TRansformer (ETR) to capture long-range dependencies at the high-level layer. This module can extract robust features with semantic contexts to infer the possible target location and basic structure in low-contrast conditions. Secondly, we utilize the decoupled body-edge branch to promote general feature learning and precept precise boundary locations. The ETR establishes long-range dependencies across the whole feature map range and is enhanced by introducing local information. We implement it in a parallel mode, i.e., the group of self-attention with multi-head captures the global relationship, and the group of convolution retains local details. We compare TBNet with other state-of-the-art (SOTA) methods on the cornea endothelial cell, ciliary body, and kidney segmentation tasks. The TBNet improves segmentation performance, proving its effectiveness and robustness.


  • Open Access

    Corneal Endothelial Cell Segmentation with Multiple Long-range Dependencies

    by Lingxi Zeng, Yinglin Zhang, Risa Higashita, Jiang Liu

    Corneal endothelial cell segmentation is an important task in ophthalmology, but it is challenging due to variations in image characteristics across different datasets. Existing deep learning methods have limitations in capturing long-range dependencies that are critical for accurate segmentation. To address this issue, we propose a novel multiple long-range dependencies network (MLD-Net) that effectively incorporates different types of long-range dependency information to achieve robust segmentation across datasets. The network employs dilated convolutions and attention gates to capture spatial and layer-level dependencies, respectively. The entire network is densely connected, facilitating the sharing of long-range dependency information across multiple scales. We demonstrate the effectiveness of MLD-Net on four different corneal endothelium microscope image datasets: SREP, BiolmLab, Rodrep, and TM-EM3000. Our experimental results show that MLD-Net outperforms existing state-of-the-art methods, achieving robustness and high accuracy in corneal endothelial cell segmentation.

  • Structural Priors Guided Network for the Corneal Endothelial Cell Segmentation

    by Yinglin Zhang, Ruiling Xi, Lingxi Zeng, Dave Towey, Ruibin Bai, Risa Higashita, Jiang Liu

    The segmentation of blurred cell boundaries in cornea endothelium microscope images is challenging, which affects the clinical parameter estimation accuracy. Existing deep learning methods only consider pixel-wise classification accuracy and lack of utilization of cell structure knowledge. Therefore, the segmentation of the blurred cell boundary is discontinuous. This paper proposes a structural prior guided network (SPG-Net) for corneal endothelium cell segmentation. We first employ a hybrid transformer convolution backbone to capture more global context. Then, we use Feature Enhancement (FE) module to improve the representation ability of features and Local Affinity-based Feature Fusion (LAFF) module to propagate structural information among hierarchical features. Finally, we introduce the joint loss based on cross entropy and structure similarity index measure (SSIM) to supervise the training process under pixel and structure levels. We compare the SPG-Net with various state-of-the-art methods on four corneal endothelial datasets. The experiment results suggest that the SPG-Net can alleviate the problem of discontinuous cell boundary segmentation and balance the pixel-wise accuracy and structure preservation. We also evaluate the agreement of parameter estimation between ground truth and the prediction of SPG-Net. The statistical analysis results show a good agreement and correlation.