Li Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Li Yang has a total of 34 co-authors. Here are the top co-authors by number of shared publications:
T. Li
Department of Radiology, Chinese PLA General Hospital, 28 Fuxing RD, Haidian District, Beijing 100853, China
2 shared publicationsC. Luo
Department of Radiology, General Hospital of Chinese People's Liberation Army, No. 28, Fuxing Road, Beijing 100853, China
1 shared publicationChang Ruiping
Department of Radiology, The First Medical Center, Chinese PLA General Hospital, Beijing 100853, China
1 shared publication- Chuncai Luo
Department of Radiology, Chinese People's Liberation Army General Hospital, Beijing, China
1 shared publication Fan Zhang
Radiology, Hainan Hospital of Chinese PLA General Hospital, Haitang District, Sanya City, 572013, Hainan Provence, PR China
1 shared publicationFei Yan
Radiology Department, Chinese PLA General Hospital, Beijing, China
1 shared publication
Latest Publications
- 3 February 2023
- Published by Elsevier in Journal of Cardiovascular Computed Tomography
- Vol. 17 (2) , 144-145
Discussion about the “P” classification in CAR-RADS2.0: Plaque burden sub-classification
- 3 February 2023
- Published by Elsevier in Journal of Cardiovascular Computed Tomography
- Vol. 17 (2) , 144-145
Discussion about the “P” classification in CAR-RADS2.0: Plaque burden sub-classification
- 15 March 2022
- Published by Springer Nature in European Radiology
- Vol. 32 (8) , 5276-5286
Automatic coronary plaque detection, classification, and stenosis grading using deep learning and radiomics on computed tomography angiography images: a multi-center multi-vendor study
Objectives An automatic system utilizing both the advantages of the neural network and the radiomics was proposed for coronary plaque detection, classification, and stenosis grading. Methods This study retrospectively included 505 patients with 127,763 computed tomography angiography (CTA) images from 5 medical center. A convolutional neural network (CNN) model was used to segment the coronary artery, detect the plaque candidate, and extract the image patch with high computation efficiency. The manually designed radiomics feature extractor was utilized to collect plaque patterns, followed by the different classifiers to perform the plaque classification and stenosis grading. Results The CNN model achieved 100% of sensitivity and the highest positive predictive value (83.9%) than U-Net and baseline model in plaque candidate detection. Twenty-six representative radiomics features were selected to construct the classifiers. Among different models, the gradient-boosting decision tree (GBDT) achieved the best performance in plaque classification (accuracy: 87.0%, sensitivity: 83.2%, specificity: 91.4%) and stenosis grading (accuracy: 90.9%, sensitivity: 84.1%, specificity: 95.7%). GBDT also achieved the highest AUC of 0.873 in plaque classification and 0.910 in stenosis grading. The computation time of processing one patient was 56.2 ± 5.7 s which was significantly less than radiologist manual analysis (285.6 ± 134.5 s, p = 0.0001). Conclusions In this study, an automatic workflow was proposed to detect and analyze coronary plaques with high accuracy and efficiency, showing the potential in clinical application. Key Points • The proposed automatic system integrated deep learning and radiomics to perform the coronary plaque analysis. • The proposed automatic system achieved high accuracy in both plaque classification and stenosis grading. • The proposed automatic system was five times more efficient than radiologist manual analysis.
- 15 March 2022
- Published by Springer Nature in European Radiology
- Vol. 32 (8) , 5276-5286
Automatic coronary plaque detection, classification, and stenosis grading using deep learning and radiomics on computed tomography angiography images: a multi-center multi-vendor study
Objectives An automatic system utilizing both the advantages of the neural network and the radiomics was proposed for coronary plaque detection, classification, and stenosis grading. Methods This study retrospectively included 505 patients with 127,763 computed tomography angiography (CTA) images from 5 medical center. A convolutional neural network (CNN) model was used to segment the coronary artery, detect the plaque candidate, and extract the image patch with high computation efficiency. The manually designed radiomics feature extractor was utilized to collect plaque patterns, followed by the different classifiers to perform the plaque classification and stenosis grading. Results The CNN model achieved 100% of sensitivity and the highest positive predictive value (83.9%) than U-Net and baseline model in plaque candidate detection. Twenty-six representative radiomics features were selected to construct the classifiers. Among different models, the gradient-boosting decision tree (GBDT) achieved the best performance in plaque classification (accuracy: 87.0%, sensitivity: 83.2%, specificity: 91.4%) and stenosis grading (accuracy: 90.9%, sensitivity: 84.1%, specificity: 95.7%). GBDT also achieved the highest AUC of 0.873 in plaque classification and 0.910 in stenosis grading. The computation time of processing one patient was 56.2 ± 5.7 s which was significantly less than radiologist manual analysis (285.6 ± 134.5 s, p = 0.0001). Conclusions In this study, an automatic workflow was proposed to detect and analyze coronary plaques with high accuracy and efficiency, showing the potential in clinical application. Key Points • The proposed automatic system integrated deep learning and radiomics to perform the coronary plaque analysis. • The proposed automatic system achieved high accuracy in both plaque classification and stenosis grading. • The proposed automatic system was five times more efficient than radiologist manual analysis.
- Open Access
- 13 November 2019
- Published by Chinese Medical Sciences Journal in Chinese Medical Sciences Journal
- Vol. 34 (4) , 241-247
Correlation between C-reactive Protein and Morphology of Aortic Intramural Hematoma on CT Angiography
Objectives To investigate the morphologic characteristics of intramural hematoma (IMH) on CT angiography (CTA), and evaluate the possible correlation of serum C-reactive protein (CRP) with morphologic characteristics of IMH. Material and Methods Forty-two patients who were initially diagnosed as IMH by aortic CTA and also had serum CRP examination on the same day of CTA were enrolled in this retrospective study, including 30 males and 12 females, with the mean age of 61 ± 14 years old. The volumetric CT data were retrospectively processed and analyzed on post-processing workstation. Based on the thickness of IMH and the length-area curve, the cross-sectional area of true lumen and total vessel were measured, the hematoma-vessel ratio (HVR) was calculated. Imaging characteristics were compared between patients who had pathological elevated CRP (> 0.8 mg/dl) and those did not. Spearman correlation analyses of CRP level and morphological characteristics of IMH were performed, and the receiver operating characteristic (ROC) curve was used to evaluate the diagnostic validity of CRP. Results Of all 42 IMH patients, the mean serum CRP was 3.94 ± 4.71 mg/dl, and the mean HVR was 46.7%± 14.2%. HVR in patients with elevated CRP was significantly higher than those with normal CRP (49.7% ± 15.0% vs. 40.7% ± 10.5 %, P = 0.030). HVR was mildly correlated with CRP in all patients (r =0.48, P < 0.001). CRP levels differed neither between patients with Stanford type A and B (P = 0.207), nor between patients with and without intimal disruption (P = 0.230). To discriminate HVR > 47% (the mean value), the area under curve (AUC) were 0.700 (95% CI: 0.535-0.865) for CRP at a cutoff point of 3.55 mg/dl, with a sensitivity of 54.5% and a specificity of 90.0%. Conclusion CRP was mildly correlated with the severity of cross-sectional hematoma area of IMH, but not with Stanford types and the presence of intimal disruption.
- 13 November 2019
- Published by Chinese Medical Sciences Journal in Chinese Medical Sciences Journal
- Vol. 34 (4) , 241-247
Open AccessCorrelation between C-reactive Protein and Morphology of Aortic Intramural Hematoma on CT Angiography
Objectives To investigate the morphologic characteristics of intramural hematoma (IMH) on CT angiography (CTA), and evaluate the possible correlation of serum C-reactive protein (CRP) with morphologic characteristics of IMH. Material and Methods Forty-two patients who were initially diagnosed as IMH by aortic CTA and also had serum CRP examination on the same day of CTA were enrolled in this retrospective study, including 30 males and 12 females, with the mean age of 61 ± 14 years old. The volumetric CT data were retrospectively processed and analyzed on post-processing workstation. Based on the thickness of IMH and the length-area curve, the cross-sectional area of true lumen and total vessel were measured, the hematoma-vessel ratio (HVR) was calculated. Imaging characteristics were compared between patients who had pathological elevated CRP (> 0.8 mg/dl) and those did not. Spearman correlation analyses of CRP level and morphological characteristics of IMH were performed, and the receiver operating characteristic (ROC) curve was used to evaluate the diagnostic validity of CRP. Results Of all 42 IMH patients, the mean serum CRP was 3.94 ± 4.71 mg/dl, and the mean HVR was 46.7%± 14.2%. HVR in patients with elevated CRP was significantly higher than those with normal CRP (49.7% ± 15.0% vs. 40.7% ± 10.5 %, P = 0.030). HVR was mildly correlated with CRP in all patients (r =0.48, P < 0.001). CRP levels differed neither between patients with Stanford type A and B (P = 0.207), nor between patients with and without intimal disruption (P = 0.230). To discriminate HVR > 47% (the mean value), the area under curve (AUC) were 0.700 (95% CI: 0.535-0.865) for CRP at a cutoff point of 3.55 mg/dl, with a sensitivity of 54.5% and a specificity of 90.0%. Conclusion CRP was mildly correlated with the severity of cross-sectional hematoma area of IMH, but not with Stanford types and the presence of intimal disruption.
- Open Access
- 1 January 2019
- Published by XMLink in Korean Journal of Radiology
- Vol. 20 (5) , 729-738
Coronary CT Angiography with Knowledge-Based Iterative Model Reconstruction for Assessing Coronary Arteries and Non-Calcified Predominant Plaques
Li T, et al. Korean J Radiol. 2019 May;20(5):729-738. https://doi.org/10.3348/kjr.2018.0435
- 1 January 2019
- Published by XMLink in Korean Journal of Radiology
- Vol. 20 (5) , 729-738
Open AccessCoronary CT Angiography with Knowledge-Based Iterative Model Reconstruction for Assessing Coronary Arteries and Non-Calcified Predominant Plaques
Li T, et al. Korean J Radiol. 2019 May;20(5):729-738. https://doi.org/10.3348/kjr.2018.0435
- 25 July 2018
- Published by Elsevier in Clinical Radiology
- Vol. 73 (11) , 982.e1-982.e7
Delayed enhancement of the peritumoural cortex in clear cell renal cell carcinoma: correlation with Fuhrman grade
- 25 July 2018
- Published by Elsevier in Clinical Radiology
- Vol. 73 (11) , 982.e1-982.e7
Delayed enhancement of the peritumoural cortex in clear cell renal cell carcinoma: correlation with Fuhrman grade
- 1 October 2017
- Published by Elsevier in Clinical Radiology
- Vol. 72 (10) , 864-870
Feasibility of high-pitch spiral dual-source CT angiography in children with complex congenital heart disease compared to retrospective-gated spiral acquisition
- 1 October 2017
- Published by Elsevier in Clinical Radiology
- Vol. 72 (10) , 864-870
Feasibility of high-pitch spiral dual-source CT angiography in children with complex congenital heart disease compared to retrospective-gated spiral acquisition