Wanmin Liu

Dr. Wanmin Liu

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
8 December 2023 in Phenomics
Verified
Journal Article
Open access
PDF file
JWJianmin Wu
Jianmin Wu
WLWanmin Liu
Wanmin Liu
XQXinyao Qiu
Xinyao Qiu
JLJing Li
Jing Li
KSKairong Song
Kairong Song
LCLei Chen
Lei Chen
It is widely recognized that tumor immune microenvironment (TIME) plays a crucial role in tumor progression, metastasis, and therapeutic response. Despite several noninvasive strategies have emerged for cancer diagnosis and prognosis, there are still lack of effective radiomic-based model to evaluate TIME status, let alone predict clinical outcome and immune checkpoint inhibitor (ICIs) response for hepatocellular carcinoma (HCC). In this study, we developed a radiomic model to evaluate TIME status within the tumor and predict prognosis and immunotherapy response. A total of 301 patients who underwent magnetic resonance imaging (MRI) examinations were enrolled in our study. The intra-tumoral expression of 17 immune-related molecules were evaluated using co-detection by indexing (CODEX) technology, and we construct Immunoscore (IS) with the least absolute shrinkage and selection operator (LASSO) algorithm and Cox regression method to evaluate TIME. Of 6115 features extracted from MRI, five core features were filtered out, and the Radiomic Immunoscore (RIS) showed high accuracy in predicting TIME status in testing cohort (area under the curve = 0.753). More importantly, RIS model showed the capability of predicting therapeutic response to anti-programmed cell death 1 (PD-1) immunotherapy in an independent cohort with advanced HCC patients (area under the curve = 0.731). In comparison with previously radiomic-based models, our integrated RIS model exhibits not only higher accuracy in predicting prognosis but also the potential guiding significance to HCC immunotherapy.

7 May 2024 in Abdominal Radiology
Verified
Journal Article
Closed access
PDF file
HCHuilin Chen
Huilin Chen
HDHui Dong
Hui Dong
RHRuilin He
Ruilin He
MGMengting Gu
Mengting Gu
XZXingyu Zhao
Xingyu Zhao
WLWanmin Liu
Wanmin Liu

30 August 2022 in Frontiers in Oncology
Verified
Journal Article
Open access
SZSisi Zhang
Sisi Zhang
LHLei Huo
Lei Huo
JZJuan Zhang
Juan Zhang
YFYayuan Feng
Yayuan Feng
YLYiping Liu
Yiping Liu
WLWanmin Liu
Wanmin Liu
Purpose: The present study aimed to develop and validate a preoperative model based on gadobenate-enhanced magnetic resonance imaging (MRI) for predicting microvascular invasion (MVI) in patients with hepatocellular carcinoma (HCC) size of ≤5 cm. In order to provide preoperative guidance for clinicians to optimize treatment options.Methods: 164 patients with pathologically confirmed HCC and preoperative gadobenate-enhanced MRI from July 2016 to December 2020 were retrospectively included. Univariate and multivariate logistic regression (forward LR) analyses were used to determine the predictors of MVI and the model was established. Four-fold cross validation was used to verify the model, which was visualized by nomograms. The predictive performance of the model was evaluated based on discrimination, calibration, and clinical utility.Results: Elevated alpha-fetoprotein (HR 1.849, 95% CI: 1.193, 2.867, P=0.006), atypical enhancement pattern (HR 3.441, 95% CI: 1.523, 7.772, P=0.003), peritumoral hypointensity on HBP (HR 7.822, 95% CI: 3.317, 18.445, P<0.001), and HBP hypointensity (HR 3.258, 95% CI: 1.381, 7.687, P=0.007) were independent risk factors to MVI and constituted the HBP model. The mean area under the curve (AUC), sensitivity, specificity, and accuracy values for the HBP model were as follows: 0.830 (95% CI: 0.784, 0.876), 0.71, 0.78, 0.81 in training set; 0.826 (95% CI:0.765, 0.887), 0.8, 0.7, 0.79 in test set. The decision curve analysis (DCA) curve showed that the HBP model achieved great clinical benefits.Conclusion: In conclusion, the HBP imaging features of Gd-BOPTA-enhanced MRI play an important role in predicting MVI for HCC. A preoperative model, mainly based on HBP imaging features of gadobenate-enhanced MRI, was able to excellently predict the MVI for HCC size of ≤5cm. The model may help clinicians preoperatively assess the risk of MVI in HCC patients so as to guide clinicians to optimize treatment options.

14 October 2025 in Cancers
Verified
Journal Article
Open access
PDF file
RHRuilin He
Ruilin He
HCHuilin Chen
Huilin Chen
WZWenjie Zou
Wenjie Zou
MGMengting Gu
Mengting Gu
XZXingyu Zhao
Xingyu Zhao
WLWanmin Liu
Wanmin Liu
Background: Microvascular invasion (MVI) is a critical prognostic factor in hepatocellular carcinoma (HCC), but preoperative three-class prediction remains challenging. Radiomics and clinical biomarkers may enable more accurate and individualized assessment. Aim: The aim of this study was to develop and validate a Transformer-based deep learning framework that integrates radiomic and clinical features for direct three-class MVI classification in HCC patients. Methods: This retrospective study included 437 patients with pathologically confirmed hepatocellular carcinoma (HCC) and microvascular invasion (MVI) status from two campuses of a single institution. Patients from Hospital A (n = 305) were randomly divided into training and internal test cohorts, while patients from Hospital B (n = 132) were used as an independent external validation cohort. Radiomic features were extracted from preoperative Gd-BOPTA-enhanced MRI, and clinical laboratory data were collected. A two-stage feature selection strategy, combining univariate statistical testing and recursive feature elimination, was applied. A Transformer-based model was built to classify three MVI categories (M0, M1, M2), and its performance was evaluated in both the internal test cohort and the external validation cohort. Results were compared with those from traditional machine learning models, including Random Forest, Logistic Regression, XGBoost, and LightGBM. Results: On the internal test set (n = 76, Hospital A), the model achieved an accuracy of 0.733 (95% CI: 0.64–0.83), a weighted F1-score of 0.733, and a macro-average AUC of 0.880 (95% CI: 0.807–0.953). The sensitivity and specificity for M1 were 0.56 (95% CI: 0.31–0.78) and 0.86 (95% CI: 0.74–0.94), respectively; for high-risk M2 cases, the sensitivity was 0.73 (95% CI: 0.64–0.81) and the specificity was 0.91 (95% CI: 0.85–0.96). On the external validation set (n = 132, Hospital B), performance remained stable with an accuracy of 0.758, a weighted F1-score of 0.768, and a macro-average AUC of 0.886 (95% CI: 0.833–0.940). Conclusions: This Transformer-based model enables accurate and objective three-class MVI prediction using multi-modal features, supporting individualized surgical planning and improved clinical outcomes. In particular, the ability to preoperatively identify high-risk M2 patients may inform surgical margin design, guide adjuvant therapy strategies, and influence liver transplantation eligibility.

28 July 2025 in Academic Radiology
Verified
Journal Article
Closed access
WZWenjie Zou
Wenjie Zou
MGMengting Gu
Mengting Gu
HCHuilin Chen
Huilin Chen
RHRuilin He
Ruilin He
XZXingyu Zhao
Xingyu Zhao
WLWanmin Liu
Wanmin Liu

23 November 2022 in Frontiers in Oncology
Verified
Journal Article
Open access
SZSisi Zhang
Sisi Zhang
LHLei Huo
Lei Huo
YFYayuan Feng
Yayuan Feng
JZJuan Zhang
Juan Zhang
YWYuxian Wu
Yuxian Wu
WLWanmin Liu
Wanmin Liu
Purpose: The present study aimed to determine the reliable imaging features to distinguish atypical hepatocellular carcinoma (HCC) with peripheral rim-like enhancement from intrahepatic mass-forming cholangiocarcinoma (IMCC) on contrast-enhanced magnetic resonance imaging (MRI).Methods: A total of 168 patients (130 male, 57.10 ± 10.53 years) pathological confirmed HCC or IMCC who underwent contrast-enhanced MRI between July 2019 and February 2022 were retrospectively included. Univariate and multivariate logistic regression analyses were used to determine independent differential factors for distinguishing HCC from IMCC, and the model was established. Bootstrap resampling 1000 times was used to verify the model, which was visualized by nomograms. The predictive performance of the model was evaluated based on discrimination, calibration, and clinical utility.Results: Radiological capsule (OR 0.024, 95% CI: 0.006, 0.095, P<0.001), heterogeneous signal intensity (SI) on T1WI (OR 0.009, 95%CI: 0.001,0.056, P<0.001) were independent differential factors for predicting HCC over IMCC. A lobulated contour (OR 11.732, 95%CI: 2.928,47.007, P = 0.001), target sign on DP (OR 14.269, 95%CI: 2.849,82.106, P = 0.007), bile duct dilatation (OR 12.856, 95%CI: 2.013, P = 0.001) were independent differential factors for predicting IMCCs over HCCs. The independent differential factors constituted a model to distinguish atypical HCCs and IMCCs. The area under receiver operating characteristic (ROC) curve, sensitivity, and specificity values of the model were 0.964(0.940,0.987), 0.88, and 0.906, indicating that the model had an excellent differential diagnostic performance. The decision curve analysis (DCA) curve showed that the model obtained a better net clinical benefit.Conclusion: The present study identified reliable imaging features for distinguishing atypical HCCs with peripheral rim-like enhancement from IMCCs on contrast-enhanced MRI. Our findings may help radiologists provide clinicians with more accurate preoperative imaging diagnoses to select appropriate treatment options.