Yang Li

Dr. Yang Li

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
5 September 2023 in Osteoporosis International
Verified
Journal Article
Open access
PDF file
TPTao Peng
Tao Peng
XZXiaohui Zeng
Xiaohui Zeng
YLYang Li
Yang Li
MLMan Li
Man Li
BPBingjie Pu
Bingjie Pu
HQHaibo Qu
Haibo Qu
Summary This study utilized deep learning to classify osteoporosis and predict bone density using opportunistic CT scans and independently tested the models on data from different hospitals and equipment. Results showed high accuracy and strong correlation with QCT results, showing promise for expanding osteoporosis screening and reducing unnecessary radiation and costs. Purpose To explore the feasibility of using deep learning to establish a model for osteoporosis classification and bone density value prediction based on opportunistic CT scans and to verify its generalization and diagnostic ability using an independent test set. Methods A total of 1219 cases of opportunistic CT scans were included in this study, with QCT results as the reference standard. The training set: test set: independent test set ratio was 703: 176: 340, and the independent test set data of 340 cases were from 3 different hospitals and 4 different CT scanners. The VB-Net structure automatic segmentation model was used to segment the trabecular bone, and DenseNet was used to establish a three-classification model and bone density value prediction regression model. The performance parameters of the models were calculated and evaluated. Results The ROC curves showed that the mean AUCs of the three-category classification model for categorizing cases into “normal,” “osteopenia,” and “osteoporosis” for the training set, test set, and independent test set were 0.999, 0.970, and 0.933, respectively. The F1 score, accuracy, precision, recall, precision, and specificity of the test set were 0.903, 0.909, 0.899, 0.908, and 0.956, respectively, and those of the independent test set were 0.798, 0.815, 0.792, 0.81, and 0.899, respectively. The MAEs of the bone density prediction regression model in the training set, test set, and independent test set were 3.15, 6.303, and 10.257, respectively, and the RMSEs were 4.127, 8.561, and 13.507, respectively. The R-squared values were 0.991, 0.962, and 0.878, respectively. The Pearson correlation coefficients were 0.996, 0.981, and 0.94, respectively, and the p values were all < 0.001. The predicted values and bone density values were highly positively correlated, and there was a significant linear relationship. Conclusion Using deep learning neural networks to process opportunistic CT scan images of the body can accurately predict bone density values and perform bone density three-classification diagnosis, which can reduce the radiation risk, economic consumption, and time consumption brought by specialized bone density measurement, expand the scope of osteoporosis screening, and have broad application prospects.

6 March 2026 in Medicine
Verified
Journal Article
Open access
WZWei Zhou
Wei Zhou
JZJing Zhu
Jing Zhu
YMYinshuo Mei
Yinshuo Mei
YLYang Li
Yang Li
RSRuonan Sun
Ruonan Sun
CZChangjun Zheng
Changjun Zheng
This study aims to explore the predictive value of radiomics based on high-resolution computed tomography for assessing the invasiveness of pulmonary adenocarcinoma manifested as ground-glass nodules (GGNs). We collected data from 360 GGNs cases confirmed as pulmonary adenocarcinoma by surgical pathology at the First Affiliated Hospital of Chengdu Medical College between January 2019 and December 2023. Clinical information and imaging features were also gathered. The cases were divided into a noninvasive group with 127 cases (35.3%) and an invasive lesion group with 233 cases (64.7%). A total of 279 GGN patients were randomly divided into a training group (195 cases) and a test group (84 cases), with a 7:3 ratio, and 81 cases were included in the validation group. Based on the selected clinical features and radiomics features of GGN, a radiomics model, a clinical model, and a combined clinical-radiomics model were constructed using LASSO and multivariate Logistic Regression. The predictive performance of the 3 models was evaluated and compared using the area under the curve, decision curve analysis, and DeLong test. In the validation set, the area under the curves for the radiomics model (using 29 radiomics features), the clinical model (mean length and air bronchogram), and the combined clinical-radiomics model were 0.856, 0.901, and 0.911, respectively. Decision curve analysis and DeLong’s test indicated that the combined clinical-radiomics model has higher value in predicting the invasiveness of GGNs than the other 2 models. The combined clinical-radiomics model demonstrates good performance in predicting the invasiveness of pulmonary adenocarcinoma presenting as GGNs. It has the potential to provide effective imaging methods for patients planning precise treatment.

14 November 2025 in Abdominal Radiology
Verified
Journal Article
Closed access
PDF file
YLYing Liu
Ying Liu
XZXiao Zhang
Xiao Zhang
WHWangyang He
Wangyang He
YLYang Li
Yang Li
FHFubi Hu
Fubi Hu