JZJiayin Zhang

Jiayin Zhang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Jiayin Zhang has a total of 314 co-authors. Here are the top co-authors by number of shared publications:

  • Zhigang Lu

    Department of Cardiology, Shanghai Jiao Tong University Affiliated Sixth People’s Hospital, Shanghai, China

    29 shared publications
  • Lihua Yu

    Department of Radiology, Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine , Shanghai 200080

    26 shared publications
  • Xu Dai

    Department of Radiology, Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine , Shanghai 200080

    26 shared publications
  • Yarong Yu

    Department of Radiology, Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine , Shanghai 200080

    22 shared publications
  • Mengmeng Yu

    Institute of Diagnostic and Interventional Radiology Shanghai Jiao Tong University Affiliated Sixth People's Hospital Shanghai China

    17 shared publications
  • Yuehua Li

    Institute of Diagnostic and Interventional Radiology, Shanghai Jiao Tong University Affiliated Sixth People’s Hospital , #600, Yishan Rd, Shanghai

    14 shared publications

Latest Publications

  • Coronary atherosclerosis, myocardial perfusion, and interstitial fibrosis between diabetic and nondiabetic patients with stable chest pain: a propensity score matching study

    by Jiajun Yuan, Yidan Xu, Xiaoying Ding, Yarong Yu, Lihua Yu, Xu Dai, Runjianya Ling, Yufan Wang, Qian Luo, Jiayin Zhang

    Objectives: To evaluate the effect of diabetes mellitus on coronary atherosclerosis, myocardial perfusion, and interstitial fibrosis using cardiac CT. Methods: This study included 409 diabetic patients with stable chest pain who prospectively underwent coronary CT angiography, stress CT myocardial perfusion imaging, and late iodine enhancement. Additionally, 413 symptomatic non-diabetic patients were retrospectively enrolled as controls. Propensity score matching (1:1) was performed based on cardiovascular risk factors. Cardiac CT parameters including coronary artery calcium score, stenosis extent, high-risk plaque features, stress myocardial blood flow (MPF), and myocardial fibrosis were compared. Results: Diabetic patients exhibited lower global stress MPF (143.1 vs 147.2 mL/100 mL/min; P = .001) and a higher incidence of myocardial ischemia (43.8% vs 31.3%; P = .003). Diabetes remained an independent predictor of ischemia (odds ratio: 2.070; 95% CI, 1.413-3.033; P < .001). In CAD-RADS 0 patients, diabetes was associated with higher ischemia rates (33.7% vs 14.5%; P = .004), and in CAD-RADS 1-2 patients, with more frequent napkin-ring signs (NRS) (10.3% vs 3.5%; P = .042). Coronary calcification and myocardial fibrosis showed no significant difference between groups. Conclusions: Diabetes is associated with impaired myocardial perfusion. Even in the absence of coronary atherosclerosis, diabetic patients have a higher prevalence of myocardial ischemia. In patients with nonobstructive CAD, diabetes was associated with a higher frequency of NRS. Advances in knowledge: Diabetes is associated with myocardial perfusion deficits and high-risk plaque independent of other cardiovascular risk determinants.

  • Open Access

    Deep Learning Optimizes the Diagnostic Performance of Coronary Computed Tomography Angiography in Heavily Calcified Coronary Plaques: A Chinese Multicenter Study

    by Chunyan Shi, Chengjin Yu, Bin Zhang, Benjamin Ellison, Zhifan Gao, Zhe Fang, Bin Hu, Jiayin Zhang, Ximing Wang, Longjiang Zhang, et al.

    Background: Accurate evaluation of coronary luminal stenosis using coronary computed tomography angiography (CCTA) remains significantly impaired in the presence of severe coronary artery calcification. Calcification-related blooming artifacts frequently lead to overestimation of stenosis severity and reduced diagnostic specificity, representing a persistent and unresolved challenge in clinical practice. Thus, this study aimed to develop and validate a self-supervised deep learning (DL) algorithm to improve the diagnostic performance of CCTA for assessing luminal stenosis in patients with heavily calcified coronary plaques (Agatston score >300), using quantitative coronary angiography (QCA) as the reference standard. Methods: This multicenter retrospective study enrolled 786 patients with agatston score (AS) >300 who underwent both CCTA and QCA from four Chinese hospitals. The dataset was randomly divided into a training group (80%, n = 628) for algorithm development and a validation group (20%, n = 158). The diagnostic performance of the DL model and radiologists was compared using sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) for detecting ≥50% diameter stenosis at the lesion, vessel, and patient levels. Reporting time was also evaluated. Results: In the validation cohort, 476 calcified lesions in 213 vessels from 93 patients were confirmed by QCA to have ≥50% diameter stenosis. The DL model demonstrated significantly higher specificity than radiologists at both the vessel level (52% vs. 30%) and patient level (74% vs. 57%) (all p < 0.05). In lesions with severe calcification (cross-sectional calcium arc 270°–360°), DL further improved lesion-level specificity and NPV by 27% and 36%, respectively (all p < 0.05). In addition, DL markedly reduced reporting time compared with radiologists (61.9 ± 2.56 s vs. 376.6 ± 127.2 s; p < 0.001). Conclusion: The proposed self-supervised DL model enables rapid and more accurate assessment of luminal stenosis in the presence of heavily calcified plaques, with improved diagnostic specificity and greater workflow efficiency.


  • Open Access

    Automated quantification of pericoronary fat attenuation index using deep learning: a validation study against expert manual measurement

    by Yige Lu, Rilei Gao, Wei He, Shan Yang, Mengsu Zeng, Jianfeng Huang, Jiayin Zhang, Weifeng Guo

    Background: Pericoronary fat attenuation index (FAI) is a novel biomarker for coronary inflammation and cardiovascular risk. However, manual FAI measurement is time-consuming and prone to observer variability. We aimed to develop and validate a deep learning (DL)-based software for automated FAI quantification. Methods: A DL framework comprising cardiac chamber segmentation, coronary artery segmentation, and vessel trajectory labeling networks was developed using 8,025 coronary computed tomography angiography (CCTA) scans. An external validation cohort of 209 patients (627 vessels) with stable coronary artery disease (CAD) was retrospectively enrolled to evaluate the agreement between the automated DL-FAI and expert manual measurements. Performance was assessed using processing time, Pearson correlation, Bland-Altman analysis, and linear regression. Results: The mean processing time for DL-FAI was significantly shorter than manual measurement (30 seconds vs. 15 minutes, PConclusions: The proposed DL-based method enables rapid automated quantification of coronary FAI. It shows good agreement with manual reference measurement while substantially improving processing efficiency, and it demonstrated preliminary stability in vessels with evident calcification. These findings support its potential use as a standardized method for large-scale FAI analysis.

  • Two-stage robust 3D CTA–2D DSA alignment via vascular-aware rigid and pyramid-based hierarchical non-rigid registration

    by Xiaosong Xiong, Caiwen Jiang, Han Wu, Xiao Zhang, Peng Wu, Jia Mi, Yanli Song, Xinyi Zhang, Jiayin Zhang, Dijia Wu, et al.

  • A deep learning system for non-invasive breast cancer diagnosis with multimodal data

    by Yonghao Li, Jiadong Zhang, Haoyuan Chen, Long Yang, Yu Xie, Qi Xu, Pinxiong Li, Jun Li, Zheren Li, Ling Dai, et al.

    Early and accurate diagnosis of breast cancer is critical for minimizing needle biopsies and enhancing patient outcomes and requires effective integration of multimodal information. In this article, we introduce a breast cancer intelligent non-invasive diagnosis system (BINDS) to integrate multimodal medical imaging data for breast cancer risk assessment and subtype classification. BINDS uses a two-stage diagnostic approach to match the clinical workflow, where an initial assessment with ultrasound and/or mammography is performed, followed by a more comprehensive multimodal diagnosis incorporating magnetic resonance imaging. In addition, a new radiology-pathology alignment mechanism is proposed to facilitate extraction of pathology-relevant features from radiological images. BINDS is developed and validated with a diverse dataset of 27,048 participants from 8 centres and 7 public datasets. Importantly, BINDS supports flexible combinations of input modalities during training and validation. Notably, BINDS attains an area under the receiver operating characteristic curve of 0.973, and can assist radiologists in reducing biopsies of benign lesions by up to 32.4%. These findings highlight the potential of BINDS to advance breast cancer diagnosis by enabling precise and adaptable decision-making across diverse clinical scenarios and resource settings.


  • Open Access

    Coronary stenosis assessment: AI-based CT quantification, visual analysis of invasive angiography, and quantitative coronary angiography

    by Lihua Yu, Mingyuan Yuan, Xu Dai, Yarong Yu, Jiajun Yuan, Chao Zheng, Lei Xu, Ting Liu, Jiayin Zhang

    Objective: To evaluate the diagnostic performance for coronary stenosis of artificial intelligence (AI)-based CT quantification, manual CT quantification, and visual invasive coronary angiography (ICA) assessment against quantitative coronary angiography (QCA). Materials and methods: This retrospective study included patients who underwent both coronary CT angiography (CCTA) and ICA within 1 month. Diameter stenosis (DS) was quantified on CCTA images both automatically by a deep-learning model and manually by radiologists, and was assessed visually on ICA. Diagnostic performance for detecting obstructive stenosis (DS ≥ 50% and ≥ 70%) was assessed against QCA using receiver operating characteristic (ROC) curve analysis on per-patient, per-vessel, and per-segment levels. Agreement with QCA was evaluated using Bland-Altman analysis. Results: A total of 368 patients were included. AI-based CT quantification demonstrated high diagnostic accuracy. For DS ≥ 50%, area under the curves (AUCs) were 0.93 (per-patient), 0.94 (per-vessel), and 0.96 (per-segment). For DS ≥ 70%, AUCs were 0.85, 0.89, and 0.90, respectively. AI-based CT quantification significantly outperformed manual CT and visual ICA assessments at most levels in terms of AUC (all p < 0.05), except vs manual quantification by a senior radiologist at the segment level for ≥ 70% stenosis ( p = 0.060). Bland-Altman analysis showed superior agreement between AI-based CT quantification of DS and QCA (mean differences: 1.5% per-patient, −0.7% per-vessel, −1.2% per-segment) compared with manual CT quantification and visual assessment of ICA. Conclusions: AI-based CT quantification demonstrated high diagnostic performance for obstructive stenosis with good agreement against QCA, outperforming manual CT quantification and visual assessment of ICA in most scenarios, with the exception of segment-level assessment of ≥ 70% DS compared with manual quantification by senior radiologists. Critical relevance statement: AI-aided CT quantification outperforms both manual CT quantification and visual ICA analysis in diagnosing obstructive stenosis using QCA as the reference standard, providing an objective tool to reduce diagnostic uncertainty and guide subsequent patient management. Key Points: Manual coronary stenosis quantification is subject to significant inter-observer variability. AI-based CT quantification outperforms both manual CT quantification and visual ICA analysis. Discordance between AI results and the angiographer’s visual estimation should prompt a physiological evaluation. Graphical


  • Open Access

    Association between deep learning-based coronary artery calcium score on non-gated chest CT and progression of chronic kidney disease: a retrospective observational cohort study

    by Kai Yang, Meiling Li, Jiayu Wang, Yarong Yu, Lihua Yu, Xu Dai, Dijia Wu, Jiayin Zhang

    Coronary artery calcification (CAC) is a pathological manifestation of coronary atherosclerosis in chronic kidney disease (CKD) patients. CAC on non-gated


  • Development and validation of a computed tomography myocardial perfusion imaging radiomic model for major adverse cardiovascular events prediction: a multicenter study

    by Zhiqi Zhong, Dong Li, Shengliang Liu, Runjianya Ling, Ping Chen, Weifang Kong, Mengmeng Zhu, Yilin Tian, Fan Yang, Guokun Wang, et al.

    Aims: Accurate prediction of major adverse cardiovascular events (MACE) is crucial for risk stratification in patients with suspected coronary artery disease. CT myocardial perfusion imaging (CT-MPI) provides various parameters, which may help comprehensively characterize perfusion features. This study aimed to develop a combined model, including clinical risk factors, coronary atherosclerotic characteristics, and radiomic features derived from CT-MPI, to predict MACE. Methods and results: 784 patients who underwent coronary CT angiography (CCTA) and CT-MPI from eight hospitals were retrospectively enrolled. Radiomic analysis was performed on eight perfusion parameter maps. Three prediction models were established accordingly: Model 1 (clinical risk factors and coronary atherosclerotic characteristics), Model 2 (incorporating myocardial blood flow values upon Model 1), and Model 3 (integrating radiomic scores upon Model 2). The C-indices for Model 3 in the training, internal validation, and external validation sets were 0.898 (95% confidence interval [CI]: 0.856–0.947), 0.844 (95% CI: 0.780–0.908), and 0.840 (95% CI: 0.791–0.889), respectively, demonstrating significant improvements over Model 1 and Model 2 (all P < 0.05). In the external validation set, Model 3 had the largest time-dependent areas under the curve (AUC) values for 1-, 3-, and 5-year MACE prediction (0.890 [95% CI: 0.831–0.948], 0.880 [95% CI: 0.823–0.938], and 0.837 [95% CI: 0.726–0.949]), compared with Model 1 and Model 2. Conclusion: The radiomic features from multiparametric CT-MPI maps simultaneously captured perfusion features associated with MACE at both macrovascular and microvascular levels. The combined model exhibited improved MACE prognostic performance compared with conventional models while maintaining high interpretability.

  • Open Access

    Clinical Applications of Artificial Intelligence in Cardiac CT: From Coronary CT Angiography to CT-Derived Fractional Flow Reserve and Myocardial Perfusion Imaging

    by Yarong Yu, Jiayin Zhang

    Yu Y, et al. Korean J Radiol. 2026 Sep;27(9):840-855. https://doi.org/10.3348/kjr.2025.1963