Peng Ji

Dr. Peng Ji


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
23 August 2024 in Journal of Bone Oncology
Verified
Journal Article
Open access
YXYong Xu
Yong Xu
CMChengjie Meng
Chengjie Meng
DCDan Chen
Dan Chen
YCYongsheng Cao
Yongsheng Cao
XWXin Wang
Xin Wang
PJPeng Ji
Peng Ji
Variability exists in the subjective delineation of tumor areas in MRI scans of patients with spinal bone metastases. This research aims to investigate the efficacy of the nnUNet radiomics model for automatic segmentation and identification of spinal bone metastases. A cohort of 118 patients diagnosed with spinal bone metastases at our institution between January 2020 and December 2023 was enrolled. They were randomly divided into a training set (n = 78) and a test set (n = 40). The nnUNet radiomics segmentation model was developed, employing manual delineations of tumor areas by physicians as the reference standard. Both methods were utilized to compute tumor area measurements, and the segmentation performance and consistency of the nnUNet model were assessed. The nnUNet model demonstrated effective localization and segmentation of metastases, including smaller lesions. The Dice coefficients for the training and test sets were 0.926 and 0.824, respectively. Within the test set, the Dice coefficients for lumbar and thoracic vertebrae were 0.838 and 0.785, respectively. Strong linear correlation was observed between the nnUNet model segmentation and physician-delineated tumor areas in 40 patients (R 2 = 0.998, P < 0.001). The nnUNet model exhibits efficacy in automatically localizing and segmenting spinal bone metastases in MRI scans.

12 March 2026 in Frontiers in Neurology
Verified
Journal Article
Open access
PDF file
XWXin Wang
Xin Wang
DCDan Chen
Dan Chen
KCKavimbi Chipusu
Kavimbi Chipusu
MAMuhammad Awais Ashraf
Muhammad Awais Ashraf
PJPeng Ji
Peng Ji
Background: Intracranial aneurysm (IA) is a focal cerebral artery dilatation affecting 2–5% of the population, with rupture leading to high mortality and disability. Early, accurate classification from computed tomography angiography (CTA) is crucial for management but is challenged by small datasets and limited interpretability. We evaluate a hybrid deep transfer learning framework with integrated Grad-CAM to improve both discrimination and explainability in CTA-based IA classification. Methods: In this retrospective study, 83 eligible patients from two centers underwent CTA. We employed stratified 5-fold cross-validation to compare: a baseline deep learning model (DL), a transfer learning-enhanced model (DL + TL), and radiologist assessment. Both AI models used a hybrid ResNet-18 architecture with LASSO feature selection and logistic regression. Performance was assessed using AUC, accuracy, calibration, decision curve analysis, NRI, and IDI. Interpretability was quantified via Grad-CAM using Intersection-over-Union (IoU) and Dice similarity coefficient. Results: The DL + TL model achieved superior performance with a mean AUC of 0.853 (95% CI: 0.789–0.912) and accuracy of 84.0%, outperforming both DL (AUC: 0.744, p = 0.012) and radiologists (AUC: 0.731, p = 0.008). Grad-CAM analysis showed DL + TL had significantly higher attention precision (IoU: 0.68 vs. 0.45 for DL, p < 0.001) and was rated more clinically relevant by blinded radiologists (4.2/5 vs. 2.8/5). Conclusion: Integrating transfer learning with quantitative interpretability assessment improves both accuracy and transparency of IA classification in limited-data settings. This framework offers a validated, interpretable approach for neurovascular imaging, pending further multi-center validation.

12 March 2026 in Biomedical Engineering / Biomedizinische Technik
Verified
Journal Article
Open access
PDF file
WLWeiwei Lu
Weiwei Lu
FWFeng Wang
Feng Wang
LLLi Li
Li Li
DCDan Chen
Dan Chen
PJPeng Ji
Peng Ji
Objectives: Hypertensive intracerebral hemorrhage (HICH) is a frequently encountered and highly lethal cerebrovascular disorder, and postoperative rebleeding remains one of its most feared complications. Methods: We developed a nomogram featuring a hybrid architecture that integrates radiomics-derived signatures and deep learning representations from CT imaging together with routine clinical parameters, with the goal of enhancing the individualized prediction of rebleeding risk following surgical intervention in HICH patients. A total of 151 individuals diagnosed with HICH were prospectively enrolled and randomly assigned to a training set (n=105) and a validation set (n=46) following a 7:3 ratio. Results: The resulting model outperformed single-domain approaches relying solely on traditional clinical indicators or deep learning features. In the training cohort, the nomogram yielded an AUC of 0.993 (95 % CI: 0.982–1.000), while in the internal testing cohort, the AUC reached 0.860 (95 % CI: 0.745–0.974). The model highlighted several key predictors associated with postoperative rebleeding. Conclusions: Overall, the integrated nomogram, embedding clinical data, radiomic phenotypes, and deep learning markers, exhibited robust predictive capability in assessing rebleeding risk among patients with HICH. Ongoing research is needed to further refine and validate the model in broader clinical settings.