Hongmei Zheng

Dr. Hongmei Zheng


Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 December 2022 in Ophthalmology and Therapy
Verified
Journal Article
Open access
PDF file
GSGongpeng Sun
Gongpeng Sun
XWXiaoling Wang
Xiaoling Wang
LXLizhang Xu
Lizhang Xu
CLChang Li
Chang Li
WWWenyu Wang
Wenyu Wang
CCChangzheng Chen
Changzheng Chen
Introduction To design and evaluate a deep learning model based on ultra-widefield images (UWFIs) that can detect several common fundus diseases. Methods Based on 4574 UWFIs, a deep learning model was trained and validated that can identify normal fundus and eight common fundus diseases, namely referable diabetic retinopathy, retinal vein occlusion, pathologic myopia, retinal detachment, retinitis pigmentosa, age-related macular degeneration, vitreous opacity, and optic neuropathy. The model was tested on three test sets with data volumes of 465, 979, and 525. The performance of the three deep learning networks, EfficientNet-B7, DenseNet, and ResNet-101, was evaluated on the internal test set. Additionally, we compared the performance of the deep learning model with that of doctors in a tertiary referral hospital. Results Compared to the other two deep learning models, EfficientNet-B7 achieved the best performance. The area under the receiver operating characteristic curves of the EfficientNet-B7 model on the internal test set, external test set A and external test set B were 0.9708 (0.8772, 0.9849) to 1.0000 (1.0000, 1.0000), 0.9683 (0.8829, 0.9770) to 1.0000 (0.9975, 1.0000), and 0.8919 (0.7150, 0.9055) to 0.9977 (0.9165, 1.0000), respectively. On a data set of 100 images, the total accuracy of the deep learning model was 93.00%, the average accuracy of three ophthalmologists who had been working for 2 years and three ophthalmologists who had been working in fundus imaging for more than 5 years was 88.00% and 94.00%, respectively. Conclusion High performance was achieved on all three test sets using our UWFI multidisease classification model with a small sample size and fast model inference. The performance of the artificial intelligence model was comparable to that of a physician with 2–5 years of experience in fundus diseases at a tertiary referral hospital. The model is expected to be used as an effective aid for fundus disease screening.

8 September 2021 in Journal of Diabetes Research
Verified
Journal Article
Open access
PDF file
XWXiaoling Wang
Xiaoling Wang
ZJZexuan Ji
Zexuan Ji
XMXiao Ma
Xiao Ma
ZZZiyue Zhang
Ziyue Zhang
ZYZuohuizi Yi
Zuohuizi Yi
CCChangzheng Chen
Changzheng Chen
Purpose. The objective of this study was to establish diagnostic technology to automatically grade the severity of diabetic retinopathy (DR) according to the ischemic index and leakage index with ultra-widefield fluorescein angiography (UWFA) and the Early Treatment Diabetic Retinopathy Study (ETDRS) 7-standard field (7-SF). Methods. This is a cross-sectional study. UWFA samples from 280 diabetic patients and 119 normal patients were used to train and test an artificial intelligence model to differentiate PDR and NPDR based on the ischemic index and leakage index with UWFA. A panel of retinal specialists determined the ground truth for our data set before experimentation. A confusion matrix as a metric was used to measure the precision of our algorithm, and a simple linear regression function was implemented to explore the discrimination of indexes on the DR grades. In addition, the model was tested with simulated 7-SF. Results. The model classification of DR in the original UWFA images achieved 88.50 accuracy and 73.68 accuracy in the simulated 7-SF images. A simple linear regression function demonstrated that there is a significant relationship between the ischemic index and leakage index and the severity of DR. These two thresholds were set to classify the grade of DR, which achieved 76.8 accuracy. Conclusions. The optimization of the cycle generative adversarial network (CycleGAN) and convolutional neural network (CNN) model classifier achieved DR grading based on the ischemic index and leakage index with UWFA and simulated 7-SF and provided accurate inference results. The classification accuracy with UWFA is slightly higher than that of simulated 7-SF.

14 September 2020 in Journal of Medical Virology
Verified
Journal Article
Open access
PDF file
TCTing Chen
Ting Chen
GLGuoju Li
Guoju Li
HLHongli Liu
Hongli Liu
WWWei Wan
Wei Wan
HZHongmei Zheng
Hongmei Zheng
CCChangzheng Chen
Changzheng Chen
Many healthcare workers (HCWs) have been confirmed to be infected with SARS‐CoV‐2 in China. A retrospective, single‐center study was conducted. The median age of the 132 HCWs with COVID‐19 was 32 years, with 92 (69.7%) being females. There were 47 (35.6%) doctors, 72 (54.6%) nurses, and 13 (9.9%) other HCWs. Ten of the 132 patients (7.6%) had underlying diseases. The most common symptoms of illness onset were fever (70, 53.0%), cough (66, 50.0%), and fatigue (58, 43.9%). All patients were categorized into mild or moderate COVID‐19 type on admission to hospital, and five (3.8%) progressed to the severe COVID‐19 type. Sixty‐six HCWs patients were included in both the early and later discharged group. In the logistic analysis, the later discharged patients had a longer time for illness onset to hospital admission (per 1 day; OR, 1.10; 95% CI, 1.03–1.18; p = .006), a higher proportion of >3 onset symptoms clustering (OR, 3.11; 95% CI, 1.27–7.62; p = .01), and a higher percentage of other HCWs (OR, 6.20; 95% CI, 1.49–25.80; p = .01). HCW patients were young female nurses with fewer comorbidities, and most were mild or moderate COVID‐19 type. The later discharged patients exhibited characteristics of longer time for illness onset to hospitalization and clustering of onset symptoms.


1 January 2008 in Molecular Diagnosis & Therapy
Verified
Journal Article
Closed access
PDF file
DZDianliang Zhang
Dianliang Zhang
HZHongmei Zheng
Hongmei Zheng
YZYanbing Zhou
Yanbing Zhou
BYBaoJun Yu
BaoJun Yu
JLJieShou Li
JieShou Li

29 September 2023 in Annals of Medicine
Verified
Journal Article
Open access
DXDi Xiao
Di Xiao
TCTianyue Cao
Tianyue Cao
YMYang Meng
Yang Meng
YXYishuang Xu
Yishuang Xu
YXYonghong Xu
Yonghong Xu
DHDihao Hua
Dihao Hua
To evaluate the retinal and choroidal microvasculature after one or two horizontal rectus muscle surgeries in strabismus patients using swept-source optical coherence tomography angiography (SS-OCTA). 30 eyes of 26 patients who underwent horizontal rectus muscle surgery were included in this study. Group A, A’ and Group B , B’ respectively consisted preoperative and postoperative measurements of patients who underwent one or two horizontal rectus muscle surgeries. We analyzed the vessel density (VD) of the superficial vascular complex (SVC), the deep vascular complex (DVC), the choriocapillary layer (CC), choroidal vascular index (CVI), choroidal thickness (T-Ch) and retinal nerve fiber layer thickness (T-RNFL) preoperatively, and one week postoperatively. Only in the nasal sector of the perifoveal zone, the VD in SVC demonstrated a significant increase in Group A’ (p = 0.027). There was a statistically significant difference in the VD changes of SVC between Group A and Group B (p = 0.043). The VD in DVC did not change significantly in the whole macular compared with the preoperative. Moreover, in both Group A’ and Group B’, the VD in CC showed a reduction in a single sector of the parafoveal area (p < 0.05). Group A’ have increased CVI in the nasal sector of the perifoveal region (p = 0.008). In addition, the T-Ch increase in the perifoveal region was more significant in Group B’ than in Group A’ (p < 0.05). Group A’ showed statistically significant decreases in T-RNFL in the foveal and parafoveal regions (p < 0.05). This study revealed that the increase in choroidal thickness was more significant after two rectus muscle surgery. In addition, there were microvascular changes in sectional macular regions after strabismus surgery. OCTA is an excellent way to study the impact of strabismus surgery on the macular structure and blood flow.