Qiushi Ren
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Qiushi Ren has a total of 64 co-authors. Here are the top co-authors by number of shared publications:
Haihan Zhang
Beijing Tongren Eye Center, Beijing key Laboratory of Intraocular Tumor Diagnosis and Treatment, Beijing Ophthalmology&Visual Sciences Key Lab, Medical Artificial Intelligence Research and Verification Key Laboratory of the Ministry of Industry and Information Technology, Beijing Tongren Hospital, Capital Medical University, Beijing, China
3 shared publicationsHaowen Li
Beijing Tongren Eye Center, Beijing key Laboratory of Intraocular Tumor Diagnosis and Treatment, Beijing Ophthalmology&Visual Sciences Key Lab, Medical Artificial Intelligence Research and Verification Key Laboratory of the Ministry of Industry and Information Technology, Beijing Tongren Hospital, Capital Medical University, Beijing, China
3 shared publicationsJingyuan Zhu
Beijing Tongren Eye Center, Beijing key Laboratory of Intraocular Tumor Diagnosis and Treatment, Beijing Ophthalmology&Visual Sciences Key Lab, Medical Artificial Intelligence Research and Verification Key Laboratory of the Ministry of Industry and Information Technology, Beijing Tongren Hospital, Capital Medical University, Beijing, China
3 shared publicationsJinyuan Wang
School of Clinical Medicine, Tsinghua University, Beijing, CHINA
3 shared publicationsShiyi Yin
Beijing Tongren Eye Center, Beijing key Laboratory of Intraocular Tumor Diagnosis and Treatment, Beijing Ophthalmology&Visual Sciences Key Lab, Medical Artificial Intelligence Research and Verification Key Laboratory of the Ministry of Industry and Information Technology, Beijing Tongren Hospital, Capital Medical University, Beijing, China
3 shared publications- Wen Bin Wei
Beijing Tongren Eye Center, Beijing key Laboratory of Intraocular Tumor Diagnosis and Treatment, Beijing Ophthalmology&Visual Sciences Key Lab, Medical Artificial Intelligence Research and Verification Key Laboratory of the Ministry of Industry and Information Technology, Beijing Tongren Hospital, Capital Medical University, Beijing, China
3 shared publications
Latest Publications
- Open Access
- 19 October 2025
- Published by MDPI AG in Bioengineering
- Vol. 12 (10) , 1119
Design and Performance Assessment of a High-Resolution Small-Animal PET System
This work reports the performance evaluation of a newly developed small-animal positron emission tomography (PET) system based on lutetium-yttrium oxyorthosilicate (LYSO) crystals and multi-pixel photon counter (MPPC). Performance was evaluated, including spatial resolution, system sensitivity, energy resolution, scatter fraction (SF), noise–equivalent count rate (NECR), micro-Derenzo phantom imaging, and in vivo imaging of mice and rats. The system achieved a tangential spatial resolution of 0.9 mm in the axial direction at a quarter axial offset using the three-dimensional ordered-subsets expectation maximization (3D OSEM) reconstruction algorithm. The peak sensitivity was 8.74% within a 200–750 keV energy window, with an average energy resolution of 12.5%. Scatter fractions were 12.9% and 30.0% for mouse- and rat-like phantoms, respectively. The NECR reached 878.7 kcps at 57.6 MBq for the mouse phantom and 421.4 kcps at 63.2 MBq for the rat phantom. High-resolution phantom and in vivo images confirmed the system’s capability for quantitative, high-sensitivity small-animal imaging, demonstrating its potential for preclinical molecular imaging studies.
- 19 October 2025
- Published by MDPI AG in Bioengineering
- Vol. 12 (10) , 1119
Open AccessDesign and Performance Assessment of a High-Resolution Small-Animal PET System
This work reports the performance evaluation of a newly developed small-animal positron emission tomography (PET) system based on lutetium-yttrium oxyorthosilicate (LYSO) crystals and multi-pixel photon counter (MPPC). Performance was evaluated, including spatial resolution, system sensitivity, energy resolution, scatter fraction (SF), noise–equivalent count rate (NECR), micro-Derenzo phantom imaging, and in vivo imaging of mice and rats. The system achieved a tangential spatial resolution of 0.9 mm in the axial direction at a quarter axial offset using the three-dimensional ordered-subsets expectation maximization (3D OSEM) reconstruction algorithm. The peak sensitivity was 8.74% within a 200–750 keV energy window, with an average energy resolution of 12.5%. Scatter fractions were 12.9% and 30.0% for mouse- and rat-like phantoms, respectively. The NECR reached 878.7 kcps at 57.6 MBq for the mouse phantom and 421.4 kcps at 63.2 MBq for the rat phantom. High-resolution phantom and in vivo images confirmed the system’s capability for quantitative, high-sensitivity small-animal imaging, demonstrating its potential for preclinical molecular imaging studies.
- Open Access
Novel Extraction of Discriminative Fine-Grained Feature to Improve Retinal Vessel Segmentation
Retinal vessel segmentation is a vital early detection method for several severe ocular diseases. Despite significant progress in retinal vessel segmentation with the advancement of Neural Networks, there are still challenges to overcome. Specifically, retinal vessel segmentation aims to predict the class label for every pixel within a fundus image, with a primary focus on intra-image discrimination, making it vital for models to extract more discriminative features. Nevertheless, existing methods primarily focus on minimizing the difference between the output from the decoder and the label, but ignore fully using feature-level fine-grained representations from the encoder. To address these issues, we propose a novel Attention U-shaped Kolmogorov-Arnold Network named AttUKAN along with a novel Label-guided Pixel-wise Contrastive Loss for retinal vessel segmentation. Specifically, we implement Attention Gates into Kolmogorov-Arnold Networks to enhance model sensitivity by suppressing irrelevant feature activations and model interpretability by non-linear modeling of KAN blocks. Additionally, we also design a novel Label-guided Pixel-wise Contrastive Loss to supervise our proposed AttUKAN to extract more discriminative features by distinguishing between foreground vessel-pixel pairs and background pairs. Experiments are conducted across four public datasets including DRIVE, STARE, CHASE_DB1, HRF and our private dataset. AttUKAN achieves F1 scores of 82.50%, 81.14%, 81.34%, 80.21% and 80.09%, along with MIoU scores of 70.24%, 68.64%, 68.59%, 67.21% and 66.94% in the above datasets, which are the highest compared to 11 networks for retinal vessel segmentation. Quantitative and qualitative results show that our AttUKAN achieves state-of-the-art performance and outperforms existing retinal vessel segmentation methods. Our code will be available at https://github.com/stevezs315/AttUKAN.
Open AccessNovel Extraction of Discriminative Fine-Grained Feature to Improve Retinal Vessel Segmentation
Retinal vessel segmentation is a vital early detection method for several severe ocular diseases. Despite significant progress in retinal vessel segmentation with the advancement of Neural Networks, there are still challenges to overcome. Specifically, retinal vessel segmentation aims to predict the class label for every pixel within a fundus image, with a primary focus on intra-image discrimination, making it vital for models to extract more discriminative features. Nevertheless, existing methods primarily focus on minimizing the difference between the output from the decoder and the label, but ignore fully using feature-level fine-grained representations from the encoder. To address these issues, we propose a novel Attention U-shaped Kolmogorov-Arnold Network named AttUKAN along with a novel Label-guided Pixel-wise Contrastive Loss for retinal vessel segmentation. Specifically, we implement Attention Gates into Kolmogorov-Arnold Networks to enhance model sensitivity by suppressing irrelevant feature activations and model interpretability by non-linear modeling of KAN blocks. Additionally, we also design a novel Label-guided Pixel-wise Contrastive Loss to supervise our proposed AttUKAN to extract more discriminative features by distinguishing between foreground vessel-pixel pairs and background pairs. Experiments are conducted across four public datasets including DRIVE, STARE, CHASE_DB1, HRF and our private dataset. AttUKAN achieves F1 scores of 82.50%, 81.14%, 81.34%, 80.21% and 80.09%, along with MIoU scores of 70.24%, 68.64%, 68.59%, 67.21% and 66.94% in the above datasets, which are the highest compared to 11 networks for retinal vessel segmentation. Quantitative and qualitative results show that our AttUKAN achieves state-of-the-art performance and outperforms existing retinal vessel segmentation methods. Our code will be available at https://github.com/stevezs315/AttUKAN.
- Open Access
- 22 April 2025
- Published by Wiley in Cancer Medicine
- Vol. 14 (8) , e70854
Retinal Oxygen Kinetics and Hemodynamics in Choroidal Melanoma After Iodine‐125 Plaque Radiotherapy Using a Novel Structural‐Functional Imaging Analysis System
Background: To investigate the changes in retinal oxygen kinetics and hemodynamics in patients with choroidal melanoma (CM) within 2 years before and after iodine‐125 plaque radiotherapy (PRT) using a novel noninvasive structure‐functional imaging analysis system.Methods: A novel noninvasive cost‐effective imaging analysis system that integrates multimodal structural and functional retinal imaging techniques has been used, which allows rapid acquisition of vascular structural, hemodynamic, and oxygenation metrics using multispectral imaging (MSI) and laser speckle contrast imaging (LSCI) techniques. Follow‐ups have been arranged at the time before plaque implantation surgery, and 1 month, 3 months, 6 months, 12 months, 18 months, and 24 months after iodine‐125 plaque removal.Results: CM patients after PRT demonstrated a significant decrease in retinal arterial oxygen concentration (CO2a), arterial oxygen saturation (SO2a), oxygen utilization (SO2av, CO2av), and metabolism (oxygen extraction fraction, OEF) over time. However, there was no significant difference in SO2 and CO2 compared with healthy controls. Systolic time (Time_sr), acceleration time index (ATI), and resistivity index (RI) gradually increase over time; ATI and RI were significantly higher than those of the healthy controls. At baseline, mean arterial blood flow velocity (BFVa) and mean arterial retinal blood flow (RBFa) in CM eyes were significantly higher than those in the healthy control group. BFVa and RBFa showed a decreasing trend over time after PRT. In addition, some retinal oxygen kinetics and hemodynamic indicators were also correlated with tumor size, patient gender, and age.Conclusion: CM patients after iodine‐125 plaque radiotherapy had significant retinal and vascular changes. Future research should focus on rapidly screening radiation microvascular complications and exploring more timely and effective interventions to protect visual function in CM patients.
- 22 April 2025
- Published by Wiley in Cancer Medicine
- Vol. 14 (8) , e70854
Open AccessRetinal Oxygen Kinetics and Hemodynamics in Choroidal Melanoma After Iodine‐125 Plaque Radiotherapy Using a Novel Structural‐Functional Imaging Analysis System
Background: To investigate the changes in retinal oxygen kinetics and hemodynamics in patients with choroidal melanoma (CM) within 2 years before and after iodine‐125 plaque radiotherapy (PRT) using a novel noninvasive structure‐functional imaging analysis system.Methods: A novel noninvasive cost‐effective imaging analysis system that integrates multimodal structural and functional retinal imaging techniques has been used, which allows rapid acquisition of vascular structural, hemodynamic, and oxygenation metrics using multispectral imaging (MSI) and laser speckle contrast imaging (LSCI) techniques. Follow‐ups have been arranged at the time before plaque implantation surgery, and 1 month, 3 months, 6 months, 12 months, 18 months, and 24 months after iodine‐125 plaque removal.Results: CM patients after PRT demonstrated a significant decrease in retinal arterial oxygen concentration (CO2a), arterial oxygen saturation (SO2a), oxygen utilization (SO2av, CO2av), and metabolism (oxygen extraction fraction, OEF) over time. However, there was no significant difference in SO2 and CO2 compared with healthy controls. Systolic time (Time_sr), acceleration time index (ATI), and resistivity index (RI) gradually increase over time; ATI and RI were significantly higher than those of the healthy controls. At baseline, mean arterial blood flow velocity (BFVa) and mean arterial retinal blood flow (RBFa) in CM eyes were significantly higher than those in the healthy control group. BFVa and RBFa showed a decreasing trend over time after PRT. In addition, some retinal oxygen kinetics and hemodynamic indicators were also correlated with tumor size, patient gender, and age.Conclusion: CM patients after iodine‐125 plaque radiotherapy had significant retinal and vascular changes. Future research should focus on rapidly screening radiation microvascular complications and exploring more timely and effective interventions to protect visual function in CM patients.
- Open Access
- 2 January 2025
- Published by Association for Research in Vision and Ophthalmology (ARVO) in Translational Vision Science & Technology
- Vol. 14 (1) , 18
Relationship Between Axial Length and Retinal Oxygen Dynamics in Adults With Myopia
The purpose of this study was to evaluate the correlation between axial length (AL) and retinal oxygen dynamic parameters in adult patients. This was an observational cross-sectional study with 79 Chinese adults with myopia aged 18 to 37 years. All participants underwent AL measurements, cycloplegic refraction, and other ophthalmic examinations. Additionally, the retinal oxygen kinetics imaging and analysis (ROKIA) system was utilized to obtain the retinal oxygen dynamic parameters of all patients. Simple and multiple linear regression tests were used to assess the correlation between various oxygen dynamic parameters and AL. The mean age, AL, and spherical equivalent (SE) of subjects were 26.32 ± 5.4 years, 25.78 ± 1.06 mm, and -5.13 ± 2.1 diopters (D), respectively. The Pearson correlation coefficients among AL and retinal oxygen delivery (DO2) and retinal oxygen metabolism (MO2) were -0.44 (95% confidence interval = -0.24 to -0.60, P < 0.001), -0.26 (95% confidence interval = -0.04 to -0.46, P = 0.02), respectively. The group with high myopia exhibited lower DO2 and higher oxygen extraction fraction (OEF) compared with the group with moderate myopia, and no significant difference was observed in MO2 between the two groups. In multivariate analyses adjusting for age, sex, intraocular pressure (IOP), and anterior chamber depth (ACD), a longer AL was significantly associated with decreased DO2 (standardized regression coefficient B = -0.47, P < 0.001). Retinal oxygen dynamic parameters, including DO2 and MO2, were decreased with longer AL in myopic eyes. Patients with high myopia demonstrated an elevated OEF than those with moderate myopia. This study demonstrated that the retinal oxygen metabolism changes in myopia, as confirmed using a novel device that quantifies retinal oxygen dynamic parameters and provides a new monitoring approach for other hypoxic retinal diseases.
- 2 January 2025
- Published by Association for Research in Vision and Ophthalmology (ARVO) in Translational Vision Science & Technology
- Vol. 14 (1) , 18
Open AccessRelationship Between Axial Length and Retinal Oxygen Dynamics in Adults With Myopia
The purpose of this study was to evaluate the correlation between axial length (AL) and retinal oxygen dynamic parameters in adult patients. This was an observational cross-sectional study with 79 Chinese adults with myopia aged 18 to 37 years. All participants underwent AL measurements, cycloplegic refraction, and other ophthalmic examinations. Additionally, the retinal oxygen kinetics imaging and analysis (ROKIA) system was utilized to obtain the retinal oxygen dynamic parameters of all patients. Simple and multiple linear regression tests were used to assess the correlation between various oxygen dynamic parameters and AL. The mean age, AL, and spherical equivalent (SE) of subjects were 26.32 ± 5.4 years, 25.78 ± 1.06 mm, and -5.13 ± 2.1 diopters (D), respectively. The Pearson correlation coefficients among AL and retinal oxygen delivery (DO2) and retinal oxygen metabolism (MO2) were -0.44 (95% confidence interval = -0.24 to -0.60, P < 0.001), -0.26 (95% confidence interval = -0.04 to -0.46, P = 0.02), respectively. The group with high myopia exhibited lower DO2 and higher oxygen extraction fraction (OEF) compared with the group with moderate myopia, and no significant difference was observed in MO2 between the two groups. In multivariate analyses adjusting for age, sex, intraocular pressure (IOP), and anterior chamber depth (ACD), a longer AL was significantly associated with decreased DO2 (standardized regression coefficient B = -0.47, P < 0.001). Retinal oxygen dynamic parameters, including DO2 and MO2, were decreased with longer AL in myopic eyes. Patients with high myopia demonstrated an elevated OEF than those with moderate myopia. This study demonstrated that the retinal oxygen metabolism changes in myopia, as confirmed using a novel device that quantifies retinal oxygen dynamic parameters and provides a new monitoring approach for other hypoxic retinal diseases.
- Open Access
- 1 December 2024
- Published by SPIE-Intl Soc Optical Eng in Journal of Biomedical Optics
- Vol. 29 (12) , 126003-10
Investigating ocular biomarkers and differential diagnosis of Alzheimer’s disease and vascular cognitive impairment based on multimodal imaging
Given the rapid global aging trend, the prevalence of cognitive impairment is escalating rapidly, posing an urgent public health concern.1 The primary causes of cognitive impairment are Alzheimer’s disease (AD) and vascular cognitive impairment (VCI), respectively.2,3 According to the diagnostic criteria, AD is a cognitive disorder due to the deposition of core pathological proteins such as amyloid beta () and phosphorylated tau proteins, whereas VCI is a cognitive disorder due to cerebrovascular disease.4,5 The clinical symptoms of AD and VCI are similar, including cognition disorders and mental symptoms, which are easily confused in clinics.2,3 Neuropsychological examination reveals that AD cognitive deficits are more frequently characterized by impairments in amnestic and parietal functions, whereas VCI is more often associated with attentional and executive dysfunction.6 Pathologically, AD is pathologically characterized by the presence of plaques, phosphorylated tau, neurofibrillary tangles, and cerebrovascular amyloidosis, whereas VCI is pathologically characterized as ischemic, hypoperfusion, and hemorrhagic damage.4,7 Therefore, it is crucial to distinguish between AD and VCI to guide treatment and evaluate the prognosis of cognitive impairment for more appropriate treatment. Currently, neuroimaging tests are used to identify AD and VCI, but the method is time-consuming and expensive.8 The eye is considered as the window of the brain, and ocular examination is an objective, quick, and low-cost alternative. As a result, ocular examination has recently become a research focus for detecting cognitive impairment.1,9 – 13- 1 December 2024
- Published by SPIE-Intl Soc Optical Eng in Journal of Biomedical Optics
- Vol. 29 (12) , 126003-10
Open AccessInvestigating ocular biomarkers and differential diagnosis of Alzheimer’s disease and vascular cognitive impairment based on multimodal imaging
Given the rapid global aging trend, the prevalence of cognitive impairment is escalating rapidly, posing an urgent public health concern.1 The primary causes of cognitive impairment are Alzheimer’s disease (AD) and vascular cognitive impairment (VCI), respectively.2,3 According to the diagnostic criteria, AD is a cognitive disorder due to the deposition of core pathological proteins such as amyloid beta () and phosphorylated tau proteins, whereas VCI is a cognitive disorder due to cerebrovascular disease.4,5 The clinical symptoms of AD and VCI are similar, including cognition disorders and mental symptoms, which are easily confused in clinics.2,3 Neuropsychological examination reveals that AD cognitive deficits are more frequently characterized by impairments in amnestic and parietal functions, whereas VCI is more often associated with attentional and executive dysfunction.6 Pathologically, AD is pathologically characterized by the presence of plaques, phosphorylated tau, neurofibrillary tangles, and cerebrovascular amyloidosis, whereas VCI is pathologically characterized as ischemic, hypoperfusion, and hemorrhagic damage.4,7 Therefore, it is crucial to distinguish between AD and VCI to guide treatment and evaluate the prognosis of cognitive impairment for more appropriate treatment. Currently, neuroimaging tests are used to identify AD and VCI, but the method is time-consuming and expensive.8 The eye is considered as the window of the brain, and ocular examination is an objective, quick, and low-cost alternative. As a result, ocular examination has recently become a research focus for detecting cognitive impairment.1,9 – 13 - 16 November 2024
- Published by Elsevier in Journal of Magnetic Resonance
- Vol. 369, 107796
16-channel sleeve antenna array based on passive decoupling method at 14 T
- 16 November 2024
- Published by Elsevier in Journal of Magnetic Resonance
- Vol. 369, 107796
16-channel sleeve antenna array based on passive decoupling method at 14 T
- Open Access
- 8 November 2024
- Published by Elsevier in Microvascular Research
- Vol. 157, 104762
A multimodal imaging approach to investigate retinal oxygen and vascular dynamics, and neural dysfunction in bietti crystalline dystrophy
- 8 November 2024
- Published by Elsevier in Microvascular Research
- Vol. 157, 104762
Open AccessA multimodal imaging approach to investigate retinal oxygen and vascular dynamics, and neural dysfunction in bietti crystalline dystrophy
- 9 September 2023
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 132 (2) , 515-536
One-Pot Multi-frame Denoising
- 9 September 2023
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 132 (2) , 515-536
One-Pot Multi-frame Denoising