Siqi Hu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Siqi Hu has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Qiong Zou
Department of Nuclear Medicine, The Third Affiliated Hospital of Sun Yat-sen University, Guangzhou, China
3 shared publications - Yong Zhang
Department of Nuclear Medicine, The Third Affiliated Hospital of Sun Yat-sen University, Guangzhou, China
3 shared publications - Hong Zhang
Department of Nuclear Medicine, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, China
2 shared publications - Ju Jiao
Department of Nuclear Medicine The Third Affiliated Hospital of Sun Yat‐Sen University Guangzhou China
2 shared publications - Yujie Xie
Department of Nuclear Medicine The Third Affiliated Hospital of Sun Yat‐Sen University Guangzhou China
2 shared publications - Lei Xu
Department of Radiation Oncology, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Sciences, Jinan, Shandong, China
1 shared publication
Latest Publications
- Open Access
- 1 July 2025
- Published by AME Publishing Company in Quantitative Imaging in Medicine and Surgery
- Vol. 15 (7) , 6217-6233
Preliminary study on the ability of 18F-fluorodeoxyglucose positron emission tomography/computed tomography radiomics to predict vessels that encapsulate tumor clusters and prognosis in hepatocellular carcinoma
Background: Recently, a novel vascular pattern characterized by vessels encapsulating tumor clusters (VETC) was reported to be related to poor clinical outcomes in patients with hepatocellular carcinoma (HCC). The objective of this study was to preliminarily assess the ability of metabolic parameters and radiomics features derived from 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) to preoperatively predict VETC and prognosis in HCC patients. Methods: A total of 149 patients diagnosed with HCC from two institutions (The Third Affiliated Hospital of Sun Yat-sen University and Sun Yat-sen Memorial Hospital) were retrospectively enrolled and subsequently divided into a training cohort (n=103) and a test cohort (n=46) as external validation. The correlation between traditional image features on computed tomography (CT)/magnetic resonance imaging (MRI) and 18F-FDG PET/CT and VETC status were evaluated and compared. Radiomics features were extracted from 18F-FDG PET/CT images, followed by calculation of a radiomics score (Radscore). Univariate and multivariate logistic regression analyses were used to screen out the independent indicators. A nomogram model was developed based on Radscore and clinical indicators, and a clinical model was developed based on clinical indicators. The performance of the nomogram, clinical model, Radscore, as well as traditional PET parameter tumor-to-liver ratio (TLR) were evaluated using receiver operating characteristic (ROC) curves and decision curve analysis (DCA). Disease-free survival (DFS) and overall survival (OS) rates were assessed using Kaplan-Meier survival analysis. Results: The difference in FDG parameter TLR between VETC-positive and VETC-negative HCC was found to be statistically significant (PConclusions: FDG metabolism is significantly associated with VETC status in HCC patients. A comprehensive nomogram model based on PET/CT radiomics and clinical indicators has potential for preoperative prediction of VETC as well as patient prognosis.
- 1 July 2025
- Published by AME Publishing Company in Quantitative Imaging in Medicine and Surgery
- Vol. 15 (7) , 6217-6233
Open AccessPreliminary study on the ability of 18F-fluorodeoxyglucose positron emission tomography/computed tomography radiomics to predict vessels that encapsulate tumor clusters and prognosis in hepatocellular carcinoma
Background: Recently, a novel vascular pattern characterized by vessels encapsulating tumor clusters (VETC) was reported to be related to poor clinical outcomes in patients with hepatocellular carcinoma (HCC). The objective of this study was to preliminarily assess the ability of metabolic parameters and radiomics features derived from 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) to preoperatively predict VETC and prognosis in HCC patients. Methods: A total of 149 patients diagnosed with HCC from two institutions (The Third Affiliated Hospital of Sun Yat-sen University and Sun Yat-sen Memorial Hospital) were retrospectively enrolled and subsequently divided into a training cohort (n=103) and a test cohort (n=46) as external validation. The correlation between traditional image features on computed tomography (CT)/magnetic resonance imaging (MRI) and 18F-FDG PET/CT and VETC status were evaluated and compared. Radiomics features were extracted from 18F-FDG PET/CT images, followed by calculation of a radiomics score (Radscore). Univariate and multivariate logistic regression analyses were used to screen out the independent indicators. A nomogram model was developed based on Radscore and clinical indicators, and a clinical model was developed based on clinical indicators. The performance of the nomogram, clinical model, Radscore, as well as traditional PET parameter tumor-to-liver ratio (TLR) were evaluated using receiver operating characteristic (ROC) curves and decision curve analysis (DCA). Disease-free survival (DFS) and overall survival (OS) rates were assessed using Kaplan-Meier survival analysis. Results: The difference in FDG parameter TLR between VETC-positive and VETC-negative HCC was found to be statistically significant (PConclusions: FDG metabolism is significantly associated with VETC status in HCC patients. A comprehensive nomogram model based on PET/CT radiomics and clinical indicators has potential for preoperative prediction of VETC as well as patient prognosis.
- 12 November 2022
- Published by Springer Nature in Abdominal Radiology
- Vol. 48 (2) , 532-542
18F-FDG PET/CT-based radiomics nomogram for preoperative prediction of macrotrabecular-massive hepatocellular carcinoma: a two-center study
Purpose To explore the potential of β-2-[18F] fluoro-2-deoxy-d-glucose positron emission tomography/computed tomography (18F-FDG PET/CT) in the evaluation of macrotrabecular-massive (MTM) hepatocellular carcinoma (HCC) and to apply radiomics approach to build a radiomics nomogram for predicting MTM-HCC. Methods This study included 140 (training cohort:101; validation cohort:39) HCC patients who underwent preoperative 18F-FDG PET/CT at two institutions. The clinical features and tumor FDG metabolism measured by the tumor-to-liver ratio (TLR) via 18F-FDG PET/CT were retrospectively collected. Radiomics features were extracted from 18F-FDG PET/CT images and a radiomics score (Rad-score) was calculated. A radiomics nomogram was then constructed by combining Rad-score and independent clinical features and was assessed with a calibration curve. The performance of the radiomics nomogram, Rad-score and TLR was evaluated by receiver operating characteristic (ROC) curves and decision curve analysis (DCA). Results A total of six top weighted radiomics features were selected from PET/CT images by the least absolute shrinkage and selection operator (LASSO) regression algorithm and were used to construct a Rad-score. Multivariate analysis identified Rad-score (OR = 2.183, P = 0.004), age ≤ 50 years (OR = 3.136, P = 0.036), AST > 40U/L (OR = 0.270, P = 0.017) and TLR (OR = 1.641, P = 0.049) as independent predictors of MTM-HCC. The radiomics nomogram had a higher area under the curves (AUCs) than the Rad-score and TLR for predicting MTM-HCC in both training (0.849 [95% CI 0.774–0.924] vs. 0.764 [95% CI 0.669–0.843], 0.763 [95% CI 0.668–0.842]) and validation (0.749 [95% CI 0.584–0.873] vs. 0.690 [95% CI 0.522–0.828], 0.541 [95% CI 0.374–0.701]) cohorts. DCA showed the radiomics nomogram to be more clinically useful than Rad-score and TLR. Conclusions Tumor FDG metabolism is significantly associated with MTM-HCC. A 18F-FDG PET/CT-based radiomics nomogram may be useful for preoperatively predicting the MTM subtype in primary HCC patients, contributing to pretreatment decision-making.
- 12 November 2022
- Published by Springer Nature in Abdominal Radiology
- Vol. 48 (2) , 532-542
18F-FDG PET/CT-based radiomics nomogram for preoperative prediction of macrotrabecular-massive hepatocellular carcinoma: a two-center study
Purpose To explore the potential of β-2-[18F] fluoro-2-deoxy-d-glucose positron emission tomography/computed tomography (18F-FDG PET/CT) in the evaluation of macrotrabecular-massive (MTM) hepatocellular carcinoma (HCC) and to apply radiomics approach to build a radiomics nomogram for predicting MTM-HCC. Methods This study included 140 (training cohort:101; validation cohort:39) HCC patients who underwent preoperative 18F-FDG PET/CT at two institutions. The clinical features and tumor FDG metabolism measured by the tumor-to-liver ratio (TLR) via 18F-FDG PET/CT were retrospectively collected. Radiomics features were extracted from 18F-FDG PET/CT images and a radiomics score (Rad-score) was calculated. A radiomics nomogram was then constructed by combining Rad-score and independent clinical features and was assessed with a calibration curve. The performance of the radiomics nomogram, Rad-score and TLR was evaluated by receiver operating characteristic (ROC) curves and decision curve analysis (DCA). Results A total of six top weighted radiomics features were selected from PET/CT images by the least absolute shrinkage and selection operator (LASSO) regression algorithm and were used to construct a Rad-score. Multivariate analysis identified Rad-score (OR = 2.183, P = 0.004), age ≤ 50 years (OR = 3.136, P = 0.036), AST > 40U/L (OR = 0.270, P = 0.017) and TLR (OR = 1.641, P = 0.049) as independent predictors of MTM-HCC. The radiomics nomogram had a higher area under the curves (AUCs) than the Rad-score and TLR for predicting MTM-HCC in both training (0.849 [95% CI 0.774–0.924] vs. 0.764 [95% CI 0.669–0.843], 0.763 [95% CI 0.668–0.842]) and validation (0.749 [95% CI 0.584–0.873] vs. 0.690 [95% CI 0.522–0.828], 0.541 [95% CI 0.374–0.701]) cohorts. DCA showed the radiomics nomogram to be more clinically useful than Rad-score and TLR. Conclusions Tumor FDG metabolism is significantly associated with MTM-HCC. A 18F-FDG PET/CT-based radiomics nomogram may be useful for preoperatively predicting the MTM subtype in primary HCC patients, contributing to pretreatment decision-making.
- 30 November 2021
- Published by Springer Nature in European Journal of Nuclear Medicine and Molecular Imaging
- Vol. 49 (5) , 1523-1534
Machine learning-based prediction of invisible intraprostatic prostate cancer lesions on 68 Ga-PSMA-11 PET/CT in patients with primary prostate cancer
Purpose 68 Ga-PSMA PET/CT has high specificity and sensitivity for the detection of both intraprostatic tumor focal lesions and metastasis. However, approximately 10% of primary prostate cancer are invisible on PSMA-PET (exhibit no or minimal uptake). In this work, we investigated whether machine learning-based radiomics models derived from PSMA-PET images could predict invisible intraprostatic lesions on 68 Ga-PSMA-11 PET in patients with primary prostate cancer. Methods In this retrospective study, patients with or without prostate cancer who underwent 68 Ga-PSMA PET/CT and presented negative on PSMA-PET image at either of two different institutions were included: institution 1 (between 2017 and 2020) for the training set and institution 2 (between 2019 and 2020) for the external test set. Three random forest (RF) models were built using selected features extracted from standard PET images, delayed PET images, and both standard and delayed PET images. Then, subsequent tenfold cross-validation was performed. In the test phase, the three RF models and PSA density (PSAD, cut-off value: 0.15 ng/ml/ml) were tested with the external test set. The area under the receiver operating characteristic curve (AUC) was calculated for the models and PSAD. The AUCs of the radiomics model and PSAD were compared. Results A total of 64 patients (39 with prostate cancer and 25 with benign prostate disease) were in the training set, and 36 (21 with prostate cancer and 15 with benign prostate disease) were in the test set. The average AUCs of the three RF models from tenfold cross-validation were 0.87 (95% CI: 0.72, 1.00), 0.86 (95% CI: 0.63, 1.00), and 0.91 (95% CI: 0.69, 1.00), respectively. In the test set, the AUCs of the three trained RF models and PSAD were 0.903 (95% CI: 0.830, 0.975), 0.856 (95% CI: 0.748, 0.964), 0.925 (95% CI:0.838, 1.00), and 0.662 (95% CI: 0.510, 0.813). The AUCs of the three radiomics models were higher than that of PSAD (0.903, 0.856, and 0.925 vs. 0.662, respectively; P = .007, P = .045, and P = .005, respectively). Conclusion Random forest models developed by 68 Ga-PSMA-11 PET-based radiomics features were proven useful for accurate prediction of invisible intraprostatic lesion on 68 Ga-PSMA-11 PET in patients with primary prostate cancer and showed better diagnostic performance compared with PSAD.
- 30 November 2021
- Published by Springer Nature in European Journal of Nuclear Medicine and Molecular Imaging
- Vol. 49 (5) , 1523-1534
Machine learning-based prediction of invisible intraprostatic prostate cancer lesions on 68 Ga-PSMA-11 PET/CT in patients with primary prostate cancer
Purpose 68 Ga-PSMA PET/CT has high specificity and sensitivity for the detection of both intraprostatic tumor focal lesions and metastasis. However, approximately 10% of primary prostate cancer are invisible on PSMA-PET (exhibit no or minimal uptake). In this work, we investigated whether machine learning-based radiomics models derived from PSMA-PET images could predict invisible intraprostatic lesions on 68 Ga-PSMA-11 PET in patients with primary prostate cancer. Methods In this retrospective study, patients with or without prostate cancer who underwent 68 Ga-PSMA PET/CT and presented negative on PSMA-PET image at either of two different institutions were included: institution 1 (between 2017 and 2020) for the training set and institution 2 (between 2019 and 2020) for the external test set. Three random forest (RF) models were built using selected features extracted from standard PET images, delayed PET images, and both standard and delayed PET images. Then, subsequent tenfold cross-validation was performed. In the test phase, the three RF models and PSA density (PSAD, cut-off value: 0.15 ng/ml/ml) were tested with the external test set. The area under the receiver operating characteristic curve (AUC) was calculated for the models and PSAD. The AUCs of the radiomics model and PSAD were compared. Results A total of 64 patients (39 with prostate cancer and 25 with benign prostate disease) were in the training set, and 36 (21 with prostate cancer and 15 with benign prostate disease) were in the test set. The average AUCs of the three RF models from tenfold cross-validation were 0.87 (95% CI: 0.72, 1.00), 0.86 (95% CI: 0.63, 1.00), and 0.91 (95% CI: 0.69, 1.00), respectively. In the test set, the AUCs of the three trained RF models and PSAD were 0.903 (95% CI: 0.830, 0.975), 0.856 (95% CI: 0.748, 0.964), 0.925 (95% CI:0.838, 1.00), and 0.662 (95% CI: 0.510, 0.813). The AUCs of the three radiomics models were higher than that of PSAD (0.903, 0.856, and 0.925 vs. 0.662, respectively; P = .007, P = .045, and P = .005, respectively). Conclusion Random forest models developed by 68 Ga-PSMA-11 PET-based radiomics features were proven useful for accurate prediction of invisible intraprostatic lesion on 68 Ga-PSMA-11 PET in patients with primary prostate cancer and showed better diagnostic performance compared with PSAD.