Qi Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Qi Zhang has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
Bob Zhang
PAMI Research Group, Dept. of Computer and Information Science, University of Macau, Macau SAR, P. R. China
1 shared publication- Derek Fai Wong
University of Macau
1 shared publication - Henghua Shen
Department of Mechanical, Industrial and Aerospace Engineering, Concordia University, Montreal, QC, Canada
1 shared publication - Jia Gu
Faculty of Data Science, City University of Macau, Macau, China
1 shared publication Jian Shen
Kiang Wu Hospital, Macau SAR, P. R. China
1 shared publication- Jianhang Zhou
School of Computer Engineering and Science, Shanghai University, Shanghai, China
1 shared publication
Latest Publications
- 28 April 2026
- Published by World Scientific Pub Co Pte Ltd in International Journal of Image and Graphics
DCAU-KAN: Dual Cross Attention Network for Segmenting Medical Images
Currently, in the field of medical image segmentation, deep learning methods have shown significant advantages and have been widely applied. However, mainstream U-shaped segmentation models still face two critical and unresolved challenges in practical applications: on the one hand, traditional U-Net and its improved variants rely on multi-layer perceptron (MLP) for feature transformation, leading to severe parameter redundancy and heavy computational overhead; on the other hand, these models lack targeted guidance from image inherent features in the contextual information acquisition stage, which results in insufficient mining of position and channel correlation features. To address these, we introduce DCAU-KAN, a improved U-shaped architecture that fuses Kolmogorov–Arnold Networks (KANs) with a novel dual cross attention block (DCA-Block). The DCA block guides the acquisition of contextual information by introducing the inherent features of the image (position and channel features), thereby enhancing the feature extraction capability. Furthermore, we use the residual skip multi-path (RSMP block) to integrate the features of the encoder and decoder, increasing the representation of the features and reducing feature confusion. To evaluate our method, we conducted experiments using five widely recognized medical datasets. The experimental results demonstrate that the improved model achieves an average IoU of 84.02% and a DSC of 90.59% across five datasets, representing an improvement of 3.65% and 2.97%, respectively, compared to the original model.
- 28 April 2026
- Published by World Scientific Pub Co Pte Ltd in International Journal of Image and Graphics
DCAU-KAN: Dual Cross Attention Network for Segmenting Medical Images
Currently, in the field of medical image segmentation, deep learning methods have shown significant advantages and have been widely applied. However, mainstream U-shaped segmentation models still face two critical and unresolved challenges in practical applications: on the one hand, traditional U-Net and its improved variants rely on multi-layer perceptron (MLP) for feature transformation, leading to severe parameter redundancy and heavy computational overhead; on the other hand, these models lack targeted guidance from image inherent features in the contextual information acquisition stage, which results in insufficient mining of position and channel correlation features. To address these, we introduce DCAU-KAN, a improved U-shaped architecture that fuses Kolmogorov–Arnold Networks (KANs) with a novel dual cross attention block (DCA-Block). The DCA block guides the acquisition of contextual information by introducing the inherent features of the image (position and channel features), thereby enhancing the feature extraction capability. Furthermore, we use the residual skip multi-path (RSMP block) to integrate the features of the encoder and decoder, increasing the representation of the features and reducing feature confusion. To evaluate our method, we conducted experiments using five widely recognized medical datasets. The experimental results demonstrate that the improved model achieves an average IoU of 84.02% and a DSC of 90.59% across five datasets, representing an improvement of 3.65% and 2.97%, respectively, compared to the original model.
- 16 March 2024
- Published by World Scientific Pub Co Pte Ltd in International Journal of Image and Graphics
- Vol. 25 (06)
Unsupervised Color-Based Nuclei Segmentation in Histopathology Images with Various Color Spaces and K Values Selection
The development of digital pathology offers a significant opportunity to evaluate and analyze the whole slides of disease tissue effectively. In particular, the segmentation of nuclei from histopathology images plays an important role in quantitatively measuring and evaluating the acquired diseased tissue. There are many automatic methods to segment cell nuclei in histopathology images. One widely used unsupervised segmentation approach is based on standard k-means or fuzzy c-means (FCM) to process the color histopathology images to segment cell nuclei. Compared with the supervised learning method, this approach can obtain segmented nuclei without annotated nuclei labels for training, which saves a lot of labeling and training time. The color space and [ ] value among this method plays a crucial role in determining the nuclei segmentation performance. However, few works have investigated various color spaces and [ ] value selection simultaneously in unsupervised color-based nuclei segmentation with [ ]-means or FCM algorithms. In this study, we will present color-based nuclei segmentation methods with standard [ ]-means and FCM algorithms for histopathology images. Several color spaces of Haematoxylin and Eosin (H&E) stained histopathology data and various [ ] values among [ ]-means and FCM are investigated correspondingly to explore the suitable selection for nuclei segmentation. A comprehensive nuclei dataset with 7 different organs is used to validate our proposed method. Related experimental results indicate that [ ] and the YCbCr color spaces with a [ ] of 4 are more reasonable for nuclei segmentation via [ ]-means, while the [ ] color space with [ ] of 4 is useful via FCM.
- 16 March 2024
- Published by World Scientific Pub Co Pte Ltd in International Journal of Image and Graphics
- Vol. 25 (06)
Unsupervised Color-Based Nuclei Segmentation in Histopathology Images with Various Color Spaces and K Values Selection
The development of digital pathology offers a significant opportunity to evaluate and analyze the whole slides of disease tissue effectively. In particular, the segmentation of nuclei from histopathology images plays an important role in quantitatively measuring and evaluating the acquired diseased tissue. There are many automatic methods to segment cell nuclei in histopathology images. One widely used unsupervised segmentation approach is based on standard k-means or fuzzy c-means (FCM) to process the color histopathology images to segment cell nuclei. Compared with the supervised learning method, this approach can obtain segmented nuclei without annotated nuclei labels for training, which saves a lot of labeling and training time. The color space and [ ] value among this method plays a crucial role in determining the nuclei segmentation performance. However, few works have investigated various color spaces and [ ] value selection simultaneously in unsupervised color-based nuclei segmentation with [ ]-means or FCM algorithms. In this study, we will present color-based nuclei segmentation methods with standard [ ]-means and FCM algorithms for histopathology images. Several color spaces of Haematoxylin and Eosin (H&E) stained histopathology data and various [ ] values among [ ]-means and FCM are investigated correspondingly to explore the suitable selection for nuclei segmentation. A comprehensive nuclei dataset with 7 different organs is used to validate our proposed method. Related experimental results indicate that [ ] and the YCbCr color spaces with a [ ] of 4 are more reasonable for nuclei segmentation via [ ]-means, while the [ ] color space with [ ] of 4 is useful via FCM.