Ge Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ge Zhang has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Jiansheng Peng
College of Automation, Guangxi University of Science and Technology, Liuzhou, China
2 shared publications - Yinghua Fu
School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China
2 shared publications - Lei Zhang
Jiangsu University of Technology
1 shared publication Mangmang Liu
University of Shanghai for Science and Technology
1 shared publication- Mangmang Liu
School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China
1 shared publication - Songlin Yin
School of automation and Information Engineering, Sichuan University of Science & Engineering, Zigong, China
1 shared publication
Latest Publications
- 10 April 2025
- Published by Springer Nature in Multimedia Systems
- Vol. 31 (3) , 1-17
MSCFF-Net: multi-scale context feature fusion network for polyp segmentation
- 10 April 2025
- Published by Springer Nature in Multimedia Systems
- Vol. 31 (3) , 1-17
MSCFF-Net: multi-scale context feature fusion network for polyp segmentation
- Open Access
- 8 August 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (16) , 6941
Lightweight Frequency Recalibration Network for Diabetic Retinopathy Multi-Lesion Segmentation
Automated segmentation of diabetic retinopathy (DR) lesions is crucial for assessing DR severity and diagnosis. Most previous segmentation methods overlook the detrimental impact of texture information bias, resulting in suboptimal segmentation results. Additionally, the role of lesion shape is not thoroughly considered. In this paper, we propose a lightweight frequency recalibration network (LFRC-Net) for simultaneous multi-lesion DR segmentation, which integrates a frequency recalibration module into the bottleneck layers of the encoder to analyze texture information and shape features together. The module utilizes a Gaussian pyramid to generate features at different scales, constructs a Laplacian pyramid using a difference of Gaussian filter, and then analyzes object features in different frequency domains with the Laplacian pyramid. The high-frequency component handles texture information, while the low-frequency area focuses on learning the shape features of DR lesions. By adaptively recalibrating these frequency representations, our method can differentiate the objects of interest. In the decoder, we introduce a residual attention module (RAM) to enhance lesion feature extraction and efficiently suppress irrelevant information. We evaluate the proposed model’s segmentation performance on two public datasets, IDRiD and DDR, and a private dataset, an ultra-wide-field fundus images dataset. Extensive comparative experiments and ablation studies are conducted across multiple datasets. With minimal model parameters, our approach achieves an mAP_PR of 60.51%, 34.83%, and 14.35% for the segmentation of EX, HE, and MA on the DDR dataset and also obtains excellent results for EX and SE on the IDRiD dataset, which validates the effectiveness of our network.
- 8 August 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (16) , 6941
Open AccessLightweight Frequency Recalibration Network for Diabetic Retinopathy Multi-Lesion Segmentation
Automated segmentation of diabetic retinopathy (DR) lesions is crucial for assessing DR severity and diagnosis. Most previous segmentation methods overlook the detrimental impact of texture information bias, resulting in suboptimal segmentation results. Additionally, the role of lesion shape is not thoroughly considered. In this paper, we propose a lightweight frequency recalibration network (LFRC-Net) for simultaneous multi-lesion DR segmentation, which integrates a frequency recalibration module into the bottleneck layers of the encoder to analyze texture information and shape features together. The module utilizes a Gaussian pyramid to generate features at different scales, constructs a Laplacian pyramid using a difference of Gaussian filter, and then analyzes object features in different frequency domains with the Laplacian pyramid. The high-frequency component handles texture information, while the low-frequency area focuses on learning the shape features of DR lesions. By adaptively recalibrating these frequency representations, our method can differentiate the objects of interest. In the decoder, we introduce a residual attention module (RAM) to enhance lesion feature extraction and efficiently suppress irrelevant information. We evaluate the proposed model’s segmentation performance on two public datasets, IDRiD and DDR, and a private dataset, an ultra-wide-field fundus images dataset. Extensive comparative experiments and ablation studies are conducted across multiple datasets. With minimal model parameters, our approach achieves an mAP_PR of 60.51%, 34.83%, and 14.35% for the segmentation of EX, HE, and MA on the DDR dataset and also obtains excellent results for EX and SE on the IDRiD dataset, which validates the effectiveness of our network.
- Open Access
- 1 April 2024
- Published by Springer Nature in Research Square
Light-weight Frequency Re-calibration Network for Diabetic Retinopathy Multi-lesion Segmentation
Automated segmentation of Diabetic Retinopathy (DR) lesions is crucial for assessing DR severity and diagnosis. Most previous segmentation methods overlook the detrimental impact of texture information bias, resulting in suboptimal segmentation results. Additionally, the role of lesion shape is also not thoroughly considered. In this paper, we propose a light-weight frequency re-calibration network (LFRC-Net) for simultaneous multi-lesion DR segmentation, which integrates a Laplacian pyramid into the bottleneck layer of the encoder to analyze object features in different frequency domains. The high-frequency component handles texture information, while the low-frequency area focuses on learning the shape characteristics of DR lesions. By adaptively re-calibrating these frequency representations, our method can effectively differentiate the objects of interest. In the decoder, we introduce a residual attention module (RAM) to enhance lesion feature extraction and efficiently suppress irrelevant information. We evaluate the proposed model's segmentation performance on two public datasets, IDRiD and DDR, and a private dataset, Ultra-wide-field fundus images dataset. Extensive comparative experiments and ablation studies are conducted across multiple datasets. With minimal model parameters, our approach achieves mAP_PR of 60.51%, 34.83%, and 14.35% for the segmentation of EX, HE, and MA on the DDR dataset, and surpass those of the current state-of-the-art methods for EX and HE on the IDRiD dataset, which validates the effectiveness of our network.
- 1 April 2024
- Published by Springer Nature in Research Square
Open AccessLight-weight Frequency Re-calibration Network for Diabetic Retinopathy Multi-lesion Segmentation
Automated segmentation of Diabetic Retinopathy (DR) lesions is crucial for assessing DR severity and diagnosis. Most previous segmentation methods overlook the detrimental impact of texture information bias, resulting in suboptimal segmentation results. Additionally, the role of lesion shape is also not thoroughly considered. In this paper, we propose a light-weight frequency re-calibration network (LFRC-Net) for simultaneous multi-lesion DR segmentation, which integrates a Laplacian pyramid into the bottleneck layer of the encoder to analyze object features in different frequency domains. The high-frequency component handles texture information, while the low-frequency area focuses on learning the shape characteristics of DR lesions. By adaptively re-calibrating these frequency representations, our method can effectively differentiate the objects of interest. In the decoder, we introduce a residual attention module (RAM) to enhance lesion feature extraction and efficiently suppress irrelevant information. We evaluate the proposed model's segmentation performance on two public datasets, IDRiD and DDR, and a private dataset, Ultra-wide-field fundus images dataset. Extensive comparative experiments and ablation studies are conducted across multiple datasets. With minimal model parameters, our approach achieves mAP_PR of 60.51%, 34.83%, and 14.35% for the segmentation of EX, HE, and MA on the DDR dataset, and surpass those of the current state-of-the-art methods for EX and HE on the IDRiD dataset, which validates the effectiveness of our network.