YPYun Peng

Yun Peng

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yun Peng has a total of 476 co-authors. Here are the top co-authors by number of shared publications:

  • Jihang Sun

    Imaging Center, Beijing Children’s Hospital, Capital Medical University, National Center for Children’s Health, Beijing, China

    16 shared publications
  • Di Hu

    Department of Radiology Beijing Children's Hospital Capital Medical University National Center for Children's Health China

    15 shared publications
  • Jihang Sun

    Department of Radiology, Beijing Children’s Hospital, Capital Medical University, National Center for Children’s Health, Beijing, China

    14 shared publications
  • Huiying Kang

    Department of Radiology Beijing Children's Hospital Capital Medical University National Center for Children's Health China

    13 shared publications
  • Tong Yu

    Department of Radiology, Beijing Children's Hospital, Capital Medical University, National Center for Children's Health, No. 56 Nanlishi Road, Xicheng District, Beijing, 100045, China

    10 shared publications
  • Haoyan Li

    Department of Radiology, Beijing Children’s Hospital, Capital Medical University, National Center for Children’s Health, Beijing, China

    8 shared publications

Latest Publications

  • Open Access

    H 2 AL: Hyperbolic Hierarchy-aware Aggregative Learning for Registration-based Few-shot Medical Image Segmentation

    by Jia Wang, Jiaming Cai, Zunying Hu, Zhanjie Wu, Jinyuan Liu, Hua Cheng, Yun Peng, Xin Fan

  • Open Access

    A pretreatment multiphasic CT-based decision-support model for differentiating pediatric hepatoblastoma from focal nodular hyperplasia

    by Lizhu Cai, Yun Peng

    Background: Hepatoblastoma (HB) and focal nodular hyperplasia (FNH) require markedly different management strategies in children, but differentiation can be challenging when multiphasic computed tomography (CT) findings are atypical or overlapping. This study aimed to develop and temporally validate a pretreatment multiphasic CT-based fusion model combining deep learning (DL) predictions with quantitative enhancement features for pediatric HB–FNH differentiation and to evaluate the potential value of model assistance for junior-radiologist interpretation. Methods: This retrospective study included 612 children who underwent pretreatment multiphasic CT between January 2011 and September 2025, including 523 with HB and 89 with FNH. A chronological split on July 1, 2023 assigned 491 patients to model development and 121 patients to temporal testing. Three phase-specific DL models based on 2.5D ResNet-18 were trained using precontrast, arterial-phase, and portal venous-phase images, and their predicted probabilities were averaged to generate DL-3Phase. Quantitative enhancement features from standardized manual region-of-interest attenuation measurements were used to train a regularized logistic regression model, termed the quantitative enhancement feature (QEF) model. DL+QEF was prespecified as the unweighted average of the DL-3Phase and QEF model probabilities. Performance was assessed using the area under the receiver operating characteristic curve (AUC), diagnostic accuracy metrics, calibration, decision curve analysis, and comparison with radiologist interpretation. Results: In the temporal test cohort, DL+QEF achieved an AUC of 0.980, an accuracy of 94.2%, an HB sensitivity of 94.9%, and an FNH specificity of 92.9%. DL+QEF showed better discrimination than DL-3Phase and the best-performing single-phase DL model, and combined the high HB sensitivity of DL-3Phase with the high FNH specificity of the QEF model. In the pathology-confirmed test subset, the AUC was 0.972 and accuracy was 92.9%. Junior-radiologist accuracy was 88.4% during unaided reading and 95.0% during model-assisted reading (exact McNemar p = 0.0078). In reader-defined atypical cases, DL+QEF had higher accuracy than the junior radiologist (90.2% vs. 68.3%). Conclusion: The pretreatment multiphasic CT-based DL+QEF model showed favorable diagnostic performance for pediatric HB–FNH differentiation and may serve as an adjunct to CT interpretation, with potential utility in reader-defined atypical or diagnostically uncertain cases.

  • Validation of Feature-Tracking Cardiac CT for Left Ventricular Strain Assessment in Pediatric Acute Myocarditis: Comparison With Cardiac MRI

    by Lixin Yang, Yongli Cao, Yun Peng

    Objective: This study aimed to validate feature-tracking cardiac CT (FT-CCT) for left ventricular (LV) strain assessment against cardiac MRI (CMR) in pediatric acute myocarditis, evaluating its potential as a pragmatic solution when CMR is delayed after a clinically indicated coronary CT angiography (CCTA). Materials and Methods: Forty-five children with acute myocarditis underwent CCTA and CMR. Global longitudinal (GLS), circumferential (GCS), and radial strain were measured. Intermodality agreement (Bland-Altman, ICC), diagnostic performance for detecting late gadolinium enhancement (LGE) (ROC analysis, DeLong test), and heart rate influence were assessed. Results: FT-CCT showed excellent agreement with CMR for LV ejection fraction (bias: -0.1%) and strain (ICCs: 0.750-0.854), independent of heart rate. For detecting LGE, CCTA-derived GCS and GLS demonstrated diagnostic performance equivalent to CMR (AUCs: 0.716 vs. 0.718, P =0.974; 0.705 vs. 0.703, P =0.972). CCTA-derived GLS provided high specificity (93.1%) and PPV (77.8%), serving as a robust “rule-in” tool. Measurements were highly reproducible (ICCs: 0.746-0.809). Conclusion: FT-CCT applied to clinically indicated CCTA provides a heart rate-robust, reproducible alternative to CMR for LV strain assessment in pediatric myocarditis. Its high specificity and diagnostic equivalence support its role as a complementary tool for initial myocardial injury detection and risk stratification when CMR is not immediately available.

  • Feasibility study of the FRACTURE sequence in evaluating pediatric skull base bone lesions

    by Guangheng Yin, Chunlei Du, Yanqiu Lv, Xiaojian Yang, Haoyan Li, Yun Peng, Jihang Sun

    Objectives This study investigated the feasibility of a fast field echo resembling a CT using a restricted echo-spacing (FRACTURE) sequence as a radiation-free alternative to CT for evaluating pediatric skull base lesions. Materials and methods In this prospective study (October 2023–December 2024), 40 pediatric patients (mean age, 7.7 ± 4.0 years) with suspected skull base lesions underwent both 256-slice CT and 3.0 T MRI, including a 3D FRACTURE sequence. Two pediatric radiologists independently assessed image quality for bone and soft-tissue visualization. Bone edge sharpness was objectively quantified using the edge rise slope (ERS). Diagnostic accuracy and treatment-planning consistency were evaluated by two radiologists and two surgeons by comparing “FRACTURE combined with conventional MRI” with CT. Results CT showed slightly higher scores for bone visualization than FRACTURE (5.00 ± 0.00 vs. 4.83 ± 0.47; p = 0.001), while both were diagnostically sufficient. FRACTURE provided significantly superior soft-tissue visualization compared with CT (5.00 ± 0.00 vs. 1.85 ± 0.36; p < 0.001). FRACTURE achieved the highest edge sharpness (ERS: 474.20 ± 69.76), exceeding CT (413.45 ± 188.73) and conventional 3D T1-weighted imaging (226.50 ± 47.04) (p < 0.05). Inter-rater agreement was perfect for diagnosis (ICC = 1.0), and treatment-planning consistency was high (Kappa = 0.892) between FRACTURE-based and CT-based protocols. Conclusion The FRACTURE sequence provides CT-like bony delineation with superior soft-tissue visualization and sharper bony edges, while completely eliminating ionizing radiation exposure. FRACTURE represents a feasible and reliable alternative to CT for the diagnosis and preoperative treatment planning of pediatric skull base lesions. Key Points Question Can the 3D FRACTURE MRI sequence replace CT for the evaluation and preoperative planning of pediatric skull base lesions while avoiding ionizing radiation? Findings FRACTURE provides CT‑comparable bone depiction and superior soft‑tissue visualization for evaluating pediatric skull base lesions. Clinical relevance The FRACTURE-based MRI protocol enables comprehensive evaluation of both bony and soft tissue structures and may serve as a radiation-free alternative to CT for preoperative assessment and surgical planning of pediatric skull base lesions. Graphical Abstract

  • Open Access

    Improving image quality and diagnostic confidence for PRETEXT staging in pediatric hepatoblastoma using thin-slice and low-energy virtual monochromatic images in dual-energy CT with deep learning image reconstruction algorithm

    by Guangheng Yin, Tingting Guo, Jun Feng, Haoyan Li, Yaoyao Song, Yunxian Zhang, Yun Peng, Jihang Sun

    Background: Hepatoblastoma is the most common pediatric hepatic tumor, for which surgery is the primary treatment option. The PRETEXT (Pretreatment Extent of Disease) staging system, based on CT images, is a crucial basis for surgical planning. Therefore, improving the image quality and diagnostic confidence of PRETEXT staging impacts the overall therapeutic outcomes in pediatric hepatoblastoma. Objective: To investigate whether thin-slice 40 keV dual-energy CT (DECT) images combined with a deep learning image reconstruction (DLIR) algorithm can improve image quality and diagnostic confidence for the evaluation of PRETEXT staging for pediatric hepatoblastoma. Methods: This single-center retrospective study included 53 pediatric patients (mean age, 3.54 ± 2.26 years) with pathologically confirmed hepatoblastoma who underwent contrast-enhanced abdominal DECT. From the raw data, three distinct image series were reconstructed with a slice thickness of 0.625 mm for comparison: (A) standard-energy 68 keV VMI (virtual monoenergetic image) with 50% adaptive statistical iterative reconstruction-V (ASIR-V50%); (B) 68 keV VMI with high-level DLIR (DLIR-H); and (C) low-energy 40 keV VMI with DLIR-H. Objective image quality was quantified by the contrast-to-noise ratio (CNR) and Edge Rise Slope (ERS) of hepatic veins. Two independent radiologists performed PRETEXT staging and subjectively assessed image noise, hepatic vein visualization, and diagnostic confidence using a 5-point Likert scale. Results: The final PRETEXT staging results showed no statistically significant difference among the three image groups. However, objectively, the 40 keV DLIR-H images demonstrated significantly superior ERS (83.73 ± 46.50), indicating the sharpest vessel boundaries ( p < 0.001), and CNR values for the hepatic veins. Subjectively, the 40 keV DLIR-H images received the highest scores for hepatic vein visualization and diagnostic confidence ( p < 0.001), and was the only group consistently deemed sufficient to meet all diagnostic requirements for staging. Conclusion: The 0.625 mm thin-slice 40 keV VMI in DECT combined with DLIR-H reconstruction provides superior image quality and significantly enhances the diagnostic confidence for PRETEXT staging, and may be considered for routine clinical use.

  • Open Access

    Predicting brain age in children aged 2–6 years with autism spectrum disorders using routine T1‐ and T2‐weighted magnetic resonance imaging

    by Zunying Hu, Rongjia Xiang, Huanyu Luo, Di Hu, Huiying Kang, Huanjie Li, Xin Fan, Yun Peng

    Importance: Early childhood (ages 2–6 years) represents a dynamic phase of brain maturation and a critical window for the emergence of neurodevelopmental disorders, such as autism spectrum disorder (ASD). However, the maturational patterns of the brain during this period remain underexplored, especially regarding the utility of routine clinical imaging. Objective: To develop a brain age prediction model using routine magnetic resonance imaging (MRI) and characterize maturational deviations in children with ASD. Methods: We retrospectively collected MRI data from 2010 typically developing children (TDC) and 822 children with ASD (aged 2–6 years). A brain age prediction model based on T1‐ and T2‐weighted MRI was developed using machine learning algorithms in the TDC cohort and subsequently applied to the ASD cohort. Model performance was assessed using the mean absolute error (MAE) and Pearson's correlation coefficient (PCC). Brain age difference (BAD) was compared between the two groups, followed by age‐matched analyses and age‐stratified comparisons. Results: The Ridge regression model demonstrated a robust performance in the TDC testing set (MAE = 0.526 years, PCC = 0.812) and showed comparable predictive performance in the ASD cohort (MAE = 0.497 years, PCC = 0.775). Age‐matched analysis revealed significantly delayed brain maturation in ASD patients compared with TDC patients ( P < 0.001). Stratified analysis identified nominal delays in ASD subgroups aged 3–4 years and 4–5 years, with a trend toward relatively advanced predicted brain age by ages 5–6 years. Interpretation: This routine MRI‐based brain age prediction model demonstrated good performance, with low prediction error and high correlation between predicted and chronological age, in estimating the brain age of TDC and ASD. It revealed a dynamic, age‐related pattern in children with ASD, highlighting developmental heterogeneity across early childhood.


  • Open Access

    A comparative study on the risk of acute kidney injury in children induced by iso-osmolarity and low-osmolarity contrast media

    by Fang Hu, Chen Wang, Ruohua Yan, Xiaohang Liu, Jihang Sun, Yun Peng, Xiaoxia Peng

    To compare the risk of contrast-associated acute kidney injury (CA-AKI) caused by iso-osmolarity contrast media (IOCM) and low-osmolarity contrast media (L

  • Open Access

    Resting-state fMRI dynamic functional network in young children with Tourette syndrome

    by Haode Wang, Yue Liu, Chen Zhang, Jingtao Lian, Lei Yang, Yun Peng

    Introduction: Tourette syndrome (TS) is a neurodevelopmental disorder characterized by involuntary motor and phonic tics, with diagnosis often delayed due to the 1-year symptom duration criterion. This study aimed to explore early neuroimaging biomarkers of TS in young children, by investigating spatiotemporal alterations in dynamic brain network connectivity in 4-6-year-old children with TS. Methods: This retrospective case-control study collected resting-state functional magnetic resonance imaging (fMRI) data from 24 children aged 4-6 years, including 12 drug-naive TS patients and 12 matched healthy controls (N group). Group Independent Component Analysis (GICA) and Independent Vector Analysis (IVA) were used to assess group differences in temporal and spatial dynamic functional network connectivity (FNC), respectively. Correlations between these connectivity alterations and Yale Global Tic Severity Scale (YGTSS) scores as well as disease duration were analyzed. Results: Statistically significant between-group differences were found in temporal dynamic FNC ( p < 0.05), with marginal differences observed in spatial dynamic connectivity ( p < 0.1), primarily involving the ventral default mode network (VDMN), primary visual network (PVN), and precuneus network (PCN). The N group showed a wider range and higher strength of FNC values, while the TS group exhibited abnormally enhanced connectivity in the insula region, which was positively correlated with disease duration. Discussion: This study revealed abnormal temporal and spatial dynamic brain network connectivity in young children at the early stage of TS, particularly in insula-related circuits. These findings provide novel insights into the early neuropathological mechanisms of TS and support the potential of dynamic FNC metrics as early imaging biomarkers for TS in young children.


  • Open Access

    Feasibility of single-phase DECT as an alternative to triple-phase CT for imaging-defined risk factors assessment in neuroblastoma for dose reduction

    by Ruifang Sun, Haoyan Li, Bei Wang, Huiying Kang, Runtong Lu, Zhenpeng Chen, Yun Peng, Jihang Sun

  • Top Cited Papers
    Open Access

    Hierarchical maturation of structural brain connectomes from birth to childhood

    by Tengda Zhao, Minhui Ouyang, Xiao-Jing Shou, Shanbin Zhang, Jiatong Ju, Xuhong Liao, Meizhen Han, Lianglong Sun, Xiaoyue Wang, Yunman Xia, et al.

    The postnatal white matter connectome undergoes profound reorganization, yet the topological principles governing its spatiotemporal maturation remain largely unknown. Using connectome mapping, machine learning, and neurobiological annotation, we show hierarchical network development from birth to childhood and its association with neurobiological signatures. We identify two cardinal topological transformations that change rapidly during infancy and continue to refine into childhood, as characterized by nonlinear global increases in network efficiency and robustness to nodal attack, and regional reorganization with accelerated hub consolidation and prolonged modular reconfiguration, predominantly involving the prefrontal and insular cortices. Early developmental trajectories of these association cortices predict late childhood network architecture through local microstructural maturation of connected white matter tracts. These patterns align with well-established multiscale cortical hierarchies, including anatomical, evolutionary, and energy metabolism axes. Our findings reveal critical neurotopological milestones after postnatal development and establish a unified multiscale framework linking macroscale network dynamics to biologically constrained rules.