Chunfeng Hu

Dr. Chunfeng Hu


Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
21 January 2024 in European Journal of Radiology Open
Verified
Journal Article
Open access
BLBo Li
Bo Li
JSJie Su
Jie Su
KLKai Liu
Kai Liu
CHChunfeng Hu
Chunfeng Hu
Programmed cell death protein-1 ligand (PD-L1) is an important prognostic predictor for immunotherapy of non-small cell lung cancer (NSCLC). This study aimed to develop a non-invasive deep learning and radiomics model based on positron emission tomography and computed tomography (PET/CT) to predict PD-L1 expression in NSCLC. A total of 136 patients with NSCLC between January 2021 and September 2022 were enrolled in this study. The patients were randomly divided into the training dataset and the validation dataset in a ratio of 7:3. Radiomics feature and deep learning feature were extracted from their PET/CT images. The Mann-whitney U-test, Least Absolute Shrinkage and Selection Operator algorithm and Spearman correlation analysis were used to select the top significant features. Then we developed a radiomics model, a deep learning model, and a fusion model based on the selected features. The performance of three models were compared by the area under the curve (AUC), sensitivity, specificity, accuracy, positive predictive value, and negative predictive value. Of the patients, 42 patients were PD-L1 negative and 94 patients were PD-L1 positive. A total of 2446 radiomics features and 4096 deep learning features were extracted per patient. In the training dataset, the fusion model achieved a highest AUC (0.954, 95% confident internal [CI]: 0.890–0.986) compared with the radiomics model (0.829, 95%CI: 0.738–0.898) and the deep learning model (0.935, 95%CI: 0.865–0.975). In the validation dataset, the AUC of the fusion model (0.910, 95% CI: 0.779–0.977) was also higher than that of the radiomics model (0.785, 95% CI: 0.628–0.897) and the deep learning model (0.867, 95% CI: 0.724–0.952). The PET/CT-based deep learning radiomics model can predict the PD-L1 expression accurately in NSCLC patients, and provides a non-invasive tool for clinicians to select positive PD-L1 patients.

1 January 2016 in Medicine
Verified
Journal Article
Open access
SHShuguang Han
Shuguang Han
XWXiaopeng Wang
Xiaopeng Wang
KXKai Xu
Kai Xu
CHChunfeng Hu
Chunfeng Hu
Crossed cerebellar diaschisis (CCD) describes a depression of oxidative metabolism glucose and blood flow in the cerebellum secondary to a supratentorial lesion in the contralateral cerebral hemisphere. PET/MR has the potential to become a powerful tool for demonstrating and imaging intracranial lesions .We herein report 3 cases of CCD imaging using a tri-modality PET/CT–MR set-up for investigating the value of adding MRI rather than CT to PET in clinical routine. We describe 3 patients with CCD and neurological symptoms in conjunction with abnormal cerebral fluorodeoxyglucose (FDG) positron emission tomography/computed tomography-magnetic resonance imaging (PET/CT–MR) manifestations including arterial spin-labeling (ASL) and T2-weighted images. In all, 18FDG-PET/CT detected positive FDG uptake in supratentorial lesions, and hypometabolism with atrophy in the contralateral cerebellum. More than that, hybrid PET/MRI provided a more accurate anatomic localization and ASL indicated disruption of the cortico-ponto-cerebellar pathway. Using pathology or long-term clinical follow-up to confirm the PET and ASL findings, the supratentorial lesions of the 3 patients were respectively diagnosed with cerebral infarction, recurrent glioma, and metastasis. The reports emphasize the significance of multimodality radiological examinations. Multimodality imaging contributes to proper diagnosis, management, and follow-up of supratentorial lesions with CCD.

1 December 2024 in Quantitative Imaging in Medicine and Surgery
Verified
Journal Article
Open access
PDF file
XLXiaole Li
Xiaole Li
ZWZishuo Wang
Zishuo Wang
SWSiyi Wang
Siyi Wang
WCWensu Chen
Wensu Chen
CLChengzong Li
Chengzong Li
CHChunfeng Hu
Chunfeng Hu
Background: Radiofrequency catheter ablation (RFCA) represents an important treatment option for atrial fibrillation (AF); however, the recurrence rate following surgery is relatively high. This study aimed to predict the recurrence of AF after RFCA using interpretable machine learning models that combined the triglyceride-glucose (TyG) index and the quantification of left atrial epicardial and pericoronary adipose tissue. Methods: This retrospective study included 325 patients with AF who underwent their first successful RFCA, among whom 79 had confirmed recurrence. The preoperative clinical data of patients were collected, the TyG index was calculated, and computed tomography (CT) image features were quantitatively measured. Multivariate Cox regression analysis was used to identify the independent risk factors for RFCA recurrence, and adjustments being made for various confounding factors. Post-hoc subgroup analysis was conducted to evaluate the predictive value of the TyG index for recurrence in different patient subgroups. Prediction models based on six machine learning algorithms were constructed. The optimal model’s features were evaluated using Shapley additive explanations (SHAP). Results: After adjustment were made for various confounding factors such as comorbidities of AF, Cox regression showed that the volume of left atrial epicardial adipose tissue (LA-EAT), LA-EAT attenuation, left circumflex coronary artery fat attenuation index (LCX-FAI), and the TyG index were independent risk factors for recurrence after RFCA (P<0.001). The support vector machine (SVM) model based on these combined indicators had the best predictive performance, with an area under the curve of 0.793 [95% confidence interval (CI): 0.782–0.805] in the validation set, while its accuracy and positive predictive value were 0.804 and 0.710, respectively. The predictive efficiency of the TyG index appeared to be independent of type 2 diabetes mellitus (T2DM) status (Pinteraction=0.660). Conclusions: The SVM model that integrated the TyG index and quantitative CT imaging variables demonstrated good predictive ability for post-RFCA recurrence in patients with AF. Furthermore, the TyG index appeared capable of predicting recurrence independently of T2DM status.

20 March 2024 in Journal of Cardiothoracic Surgery
Verified
Journal Article
Open access
PDF file
YLYu Li
Yu Li
YSYi-Bing Shi
Yi-Bing Shi
CHChunfeng Hu
Chunfeng Hu
Several studies to date have reported on the development of positron emission tomography (PET)/computed tomography (CT)-based models intended to effectively distinguish between benign and malignant pulmonary nodules (PNs). This meta-analysis was designed with the goal of clarifying the utility of these PET/CT-based conventional parameter models as diagnostic tools in the context of the differential diagnosis of PNs. Relevant studies published through September 2023 were identified by searching the Web of Science, PubMed, and Wanfang databases, after which Stata v 12.0 was used to conduct pooled analyses of the resultant data. This meta-analysis included a total of 13 retrospective studies that analyzed 1,731 and 693 malignant and benign PNs, respectively. The respective pooled sensitivity, specificity, PLR, and NLR values for the PET/CT-based studies developed in these models were 88% (95%CI: 0.86–0.91), 78% (95%CI: 0.71–0.85), 4.10 (95%CI: 2.98–5.64), and 0.15 (95%CI: 0.12–0.19). Of these endpoints, the pooled analyses of model sensitivity (I2 = 69.25%), specificity (I2 = 78.44%), PLR (I2 = 71.42%), and NLR (I2 = 67.18%) were all subject to significant heterogeneity. The overall area under the curve value (AUC) value for these models was 0.91 (95%CI: 0.88–0.93). When differential diagnosis was instead performed based on PET results only, the corresponding pooled sensitivity, specificity, PLR, and NLR values were 92% (95%CI: 0.85–0.96), 51% (95%CI: 0.37–0.66), 1.89 (95%CI: 1.36–2.62), and 0.16 (95%CI: 0.07–0.35), with all four being subject to significant heterogeneity (I2 = 88.08%, 82.63%, 80.19%, and 86.38%). The AUC for these pooled analyses was 0.82 (95%CI: 0.79–0.85). These results suggest that PET/CT-based models may offer diagnostic performance superior to that of PET results alone when distinguishing between benign and malignant PNs.

26 August 2026 in Frontiers in Cardiovascular Medicine
Verified
Journal Article
Open access
PDF file
HYHui Yan
Hui Yan
XLXiao-Le Li
Xiao-Le Li
JMJun-Hao Mei
Jun-Hao Mei
LZLei Zhou
Lei Zhou
SGShu-Hao Guo
Shu-Hao Guo
HXHui Xue
Hui Xue
Objective: To develop and validate a prediction framework integrating clinical data, left atrium and pulmonary vein morphology, and radiomic features to identify patients at high risk of atrial fibrillation (AF) recurrence after radiofrequency ablation (RFA). Methods: Patients with AF who underwent RFA at three centers between August 2018 and October 2024 were retrospectively screened. Patients from two centers were divided into training and internal validation cohorts, and patients from the third center formed the external validation cohort. Clinical and CTA-derived morphological variables and radiomic features from the left atrium and epicardial adipose tissue were analyzed. Clinical, radiomic, and fusion models were evaluated using five machine-learning algorithms. Training performance was estimated from five-fold out-of-fold predictions. Discrimination, calibration, clinical utility, pairwise AUROC differences, and model contributions were assessed using ROC analysis, calibration plots, decision curve analysis, DeLong tests, and SHAP. Results: Of 877 patients, 449 formed the training cohort, 192 the internal validation cohort, and 236 the external validation cohort; recurrence occurred in 23.6%, 30.2%, and 35.2%, respectively. The optimal clinical GBDT, radiomic RF, and fusion RF models achieved AUROCs of 0.739, 0.922, and 0.947 in the training cohort; 0.726, 0.837, and 0.839 in internal validation; and 0.722, 0.837, and 0.848 in external validation. Radiomic and fusion models outperformed the clinical model in both validation cohorts, whereas fusion did not significantly outperform radiomic (DeLong P = 0.95 internally and P = 0.43 externally). Decision curves showed net benefit across relevant threshold ranges, while calibration varied across models and cohorts. Conclusion: Radiomic models substantially improved post-RFA recurrence discrimination over the clinical model. The fusion model achieved the numerically highest external AUROC, but did not significantly outperform radiomic alone in either validation cohort. These findings support radiomic-based risk stratification while underscoring the need for prospective calibration and validation.

3 January 2026 in Journal of Cardiovascular Computed Tomography
Verified
Journal Article
Closed access
HZHe Zhang
He Zhang
SZShuai Zhang
Shuai Zhang
ASAiyun Sun
Aiyun Sun
DZDapeng Zhang
Dapeng Zhang
JLJuan Long
Juan Long
YMYankai Meng
Yankai Meng