Qiu-Ping Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Qiu-Ping Liu has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Yu-Dong Zhang
Department of Radiology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China
4 shared publications - Xun Xu
The First Affiliated Hospital of Nanjing Medical University, Nanjing, China
3 shared publications - Jinrong Qu
Department of Radiology, The Affiliated Cancer Hospital of Zhengzhou University & Henan Cancer Hospital, Zhengzhou, China.
2 shared publications - Kai-Lan Yang
Department of Radiology, Affiliated Cancer Hospital of Zhengzhou University & Henan Cancer Hospital, Zhengzhou, China
2 shared publications - Shu Wen Sun
The First Affiliated Hospital of Nanjing Medical University, Nanjing, China
2 shared publications - Xi-Sheng Liu
Department of Radiology, The First Affiliated Hospital with Nanjing Medical University, Nanjing, China
2 shared publications
Latest Publications
- 11 April 2025
- Published by Springer Nature in Abdominal Radiology
- Vol. 50 (11) , 5175-5186
Comparison of different machine learning methods in the prediction of early recurrence in HCC patients with Gd-EOB-DTPA-MRI
Purpose To develop machine learning models that are driven by Gd-EOB-DTPA-MRI features for the preoperative prediction of early recurrence in HCC and compare them to the previously proposed ERASL-pre method. Methods This retrospective study consisted of 311 consecutive patients who underwent curative hepatic resection between January 2013 and July 2021. Among them, 131 patients with early recurrence of HCC and 180 patients without early recurrence of HCC. The MR images were independently reviewed by two radiologists. Logistic regression, classification tree, random forest, extreme gradient boosting (XGBoost), support vector machines (SVM), and neural network (Nnet) were the six machine learning algorithms used. The baseline model was ERASL-pre. Different models’ discrimination, calibration, and overall performance were evaluated and compared. Results The baseline ERASL-pre obtained AUCs of 0.703 and 0.716, respectively. In comparison to ERASL-pre, the AUCs for logistic regression, random forest, and SVM were higher but not substantially different. XGBoost produced AUCs for Readers 1 and 2 of 0.720 and 0.685, respectively. Nnet achieved marginally lower but not statistically different AUCs in comparison to ERASL-pre, whereas the classification tree achieved the lowest AUCs. The logistic regression model had the optimal overall net benefit across the majority of the range of reasonable threshold probabilities. Good agreement was observed between prediction and observation in the ERASL-pre and the logistic regression model for both readers. Conclusion The logistic regression model performed better in predicting an early recurrence of HCC with Gd-EOB-DTPA MRI. In addition, the model is more sensitive than the baseline ERASL-pre model. Graphical Abstract
- 11 April 2025
- Published by Springer Nature in Abdominal Radiology
- Vol. 50 (11) , 5175-5186
Comparison of different machine learning methods in the prediction of early recurrence in HCC patients with Gd-EOB-DTPA-MRI
Purpose To develop machine learning models that are driven by Gd-EOB-DTPA-MRI features for the preoperative prediction of early recurrence in HCC and compare them to the previously proposed ERASL-pre method. Methods This retrospective study consisted of 311 consecutive patients who underwent curative hepatic resection between January 2013 and July 2021. Among them, 131 patients with early recurrence of HCC and 180 patients without early recurrence of HCC. The MR images were independently reviewed by two radiologists. Logistic regression, classification tree, random forest, extreme gradient boosting (XGBoost), support vector machines (SVM), and neural network (Nnet) were the six machine learning algorithms used. The baseline model was ERASL-pre. Different models’ discrimination, calibration, and overall performance were evaluated and compared. Results The baseline ERASL-pre obtained AUCs of 0.703 and 0.716, respectively. In comparison to ERASL-pre, the AUCs for logistic regression, random forest, and SVM were higher but not substantially different. XGBoost produced AUCs for Readers 1 and 2 of 0.720 and 0.685, respectively. Nnet achieved marginally lower but not statistically different AUCs in comparison to ERASL-pre, whereas the classification tree achieved the lowest AUCs. The logistic regression model had the optimal overall net benefit across the majority of the range of reasonable threshold probabilities. Good agreement was observed between prediction and observation in the ERASL-pre and the logistic regression model for both readers. Conclusion The logistic regression model performed better in predicting an early recurrence of HCC with Gd-EOB-DTPA MRI. In addition, the model is more sensitive than the baseline ERASL-pre model. Graphical Abstract
- Open Access
- 4 November 2024
- Published by Springer Nature in Abdominal Radiology
- Vol. 50 (9) , 4063-4075
Liver tumor imaging staging: a multi-institutional study of a preoperative staging tool for hepatocellular carcinoma
Background & aims The current staging system has limitations in preoperatively assessing hepatocellular carcinoma (HCC) and in precise detailed treatment allocation. This study aims to propose a new Liver Tumor Imaging Staging (LTIS) method for HCC. Methods 1295 patients who underwent CT or MRI and curative liver resection during January 2012 and October 2020 were retrospectively recruited from three independent institutions. All images were interpreted by two abdominal and a board-certified radiologist. LTIS was designed to discriminate low-grade (absence of microvascular invasion [MVI] and Edmondson-Steiner grade III/IV), intermediate (MVI + or Edmondson-Steiner grade III/IV but not both) and high-grade HCC (MVI + and Edmondson-Steiner grade III/IV) upon CT and MRI. Model was constructed in 578 derivation cohort (center 1) and validated in internal center 1 test cohort (n = 291), and external center 2 (n = 226) and center 3 (n = 200), respectively. Cronbach’s alpha statistics were determined to assess interobserver agreement. Net clinical benefit of LTIS on recurrence-free survival (RFS) and overall survival (OS) was analyzed with a Cox proportional hazards model. Results LTIS shows good inter-reader agreements in both CT and MRI datasets, with a Cronbach’s alpha coefficient of 0.86 and 0.85, respectively. In independent test, LTIS achieved agreement of 73.2% (281/384), 18.9% (100/528), and 69.2% (265/383) for determining low, intermediate, and high-grade HCCs with “ground truth” results. In the Cox analysis, LTIS was comparable to “ground truth” grade for predicting RFS (hazards ratio (HR), 1.30 vs. ground truth grade, 1.36 and 1.56) and OS (HR, 1.76 vs. ground truth grade, 2.00 and 3.03) of patients after surgery. In patients conventionally classified as having low-grade tumors (serum α-fetoprotein < 400 ng/mL, stage T1), 47.4% and 35.6% were reclassified as high-grade tumors upon LTIS restaging. The resulting LTIS subgroups showed a significant difference in RFS and OS at Kaplan-Meier analysis (Log-rank test, p < 0.001). Conclusion LTIS provides a potential noninvasive way to precisely stage HCC using CT and MRI.
- 4 November 2024
- Published by Springer Nature in Abdominal Radiology
- Vol. 50 (9) , 4063-4075
Open AccessLiver tumor imaging staging: a multi-institutional study of a preoperative staging tool for hepatocellular carcinoma
Background & aims The current staging system has limitations in preoperatively assessing hepatocellular carcinoma (HCC) and in precise detailed treatment allocation. This study aims to propose a new Liver Tumor Imaging Staging (LTIS) method for HCC. Methods 1295 patients who underwent CT or MRI and curative liver resection during January 2012 and October 2020 were retrospectively recruited from three independent institutions. All images were interpreted by two abdominal and a board-certified radiologist. LTIS was designed to discriminate low-grade (absence of microvascular invasion [MVI] and Edmondson-Steiner grade III/IV), intermediate (MVI + or Edmondson-Steiner grade III/IV but not both) and high-grade HCC (MVI + and Edmondson-Steiner grade III/IV) upon CT and MRI. Model was constructed in 578 derivation cohort (center 1) and validated in internal center 1 test cohort (n = 291), and external center 2 (n = 226) and center 3 (n = 200), respectively. Cronbach’s alpha statistics were determined to assess interobserver agreement. Net clinical benefit of LTIS on recurrence-free survival (RFS) and overall survival (OS) was analyzed with a Cox proportional hazards model. Results LTIS shows good inter-reader agreements in both CT and MRI datasets, with a Cronbach’s alpha coefficient of 0.86 and 0.85, respectively. In independent test, LTIS achieved agreement of 73.2% (281/384), 18.9% (100/528), and 69.2% (265/383) for determining low, intermediate, and high-grade HCCs with “ground truth” results. In the Cox analysis, LTIS was comparable to “ground truth” grade for predicting RFS (hazards ratio (HR), 1.30 vs. ground truth grade, 1.36 and 1.56) and OS (HR, 1.76 vs. ground truth grade, 2.00 and 3.03) of patients after surgery. In patients conventionally classified as having low-grade tumors (serum α-fetoprotein < 400 ng/mL, stage T1), 47.4% and 35.6% were reclassified as high-grade tumors upon LTIS restaging. The resulting LTIS subgroups showed a significant difference in RFS and OS at Kaplan-Meier analysis (Log-rank test, p < 0.001). Conclusion LTIS provides a potential noninvasive way to precisely stage HCC using CT and MRI.
- Open Access
- 22 April 2023
- Published by Elsevier in JHEP Reports
- Vol. 5 (7) , 100763
Immuno-genomic-radiomics to predict response of biliary tract cancer to camrelizumab plus GEMOX in a single-arm phase II trial
- 22 April 2023
- Published by Elsevier in JHEP Reports
- Vol. 5 (7) , 100763
Open AccessImmuno-genomic-radiomics to predict response of biliary tract cancer to camrelizumab plus GEMOX in a single-arm phase II trial
- 16 December 2021
- Published by Springer Nature in Abdominal Radiology
- Vol. 47 (2) , 651-663
Radiomics analysis of pretreatment MRI in predicting tumor response and outcome in hepatocellular carcinoma with transarterial chemoembolization: a two-center collaborative study
Background and objective To develop a machine-learning model by integrating clinical and imaging modalities for predicting tumor response and survival of hepatocellular carcinoma (HCC) with transarterial chemoembolization (TACE). Methods 140 HCC patients with TACE were retrospectively included from two centers. Tumor response were evaluated using modified Response Evaluation Criteria in Solid Tumors (mRECIST) criteria. Response-related radiomics scores (Rad-scores) were constructed on T2-weighted images (T2WI) and dynamic contrast-enhanced (DCE) imaging separately, and then integrated with conventional clinic-radiological variables into a logistic regression (LR) model for predicting tumor response. LR model was trained in 94 patients in center 1 and independently tested in 46 patients in center 2. Results Among 4 MRI sequences, T2WI achieved better performance than DCE (area under the curve [AUC] 0.754 vs 0.602 to 0.752). LR model by combining Rad-score on T2WI with Barcelona Clinic Liver Cancer (BCLC) stage and albumin-bilirubin (ALBI) grade resulted in an AUC of 0.813 in training and 0.781 in test for predicting tumor response. In survival analysis, progression-free survival (PFS) and overall survival (OS) presented significant difference between LR-predicted responders and non-responders. The ALBI grade and BCLC stage were independent predictors of PFS; and LR-predicted response, ALBI grade, satellite node, and BCLC stage were independent predictors of OS. The resulting Cox model produced concordance-indexes of 0.705 and 0.736 for predicting PFS and OS, respectively. Conclusions The model combined MRI radiomics with clinical factors demonstrated favorable performance for predicting tumor response and clinical outcomes, thus may help personalized clinical management.
- 16 December 2021
- Published by Springer Nature in Abdominal Radiology
- Vol. 47 (2) , 651-663
Radiomics analysis of pretreatment MRI in predicting tumor response and outcome in hepatocellular carcinoma with transarterial chemoembolization: a two-center collaborative study
Background and objective To develop a machine-learning model by integrating clinical and imaging modalities for predicting tumor response and survival of hepatocellular carcinoma (HCC) with transarterial chemoembolization (TACE). Methods 140 HCC patients with TACE were retrospectively included from two centers. Tumor response were evaluated using modified Response Evaluation Criteria in Solid Tumors (mRECIST) criteria. Response-related radiomics scores (Rad-scores) were constructed on T2-weighted images (T2WI) and dynamic contrast-enhanced (DCE) imaging separately, and then integrated with conventional clinic-radiological variables into a logistic regression (LR) model for predicting tumor response. LR model was trained in 94 patients in center 1 and independently tested in 46 patients in center 2. Results Among 4 MRI sequences, T2WI achieved better performance than DCE (area under the curve [AUC] 0.754 vs 0.602 to 0.752). LR model by combining Rad-score on T2WI with Barcelona Clinic Liver Cancer (BCLC) stage and albumin-bilirubin (ALBI) grade resulted in an AUC of 0.813 in training and 0.781 in test for predicting tumor response. In survival analysis, progression-free survival (PFS) and overall survival (OS) presented significant difference between LR-predicted responders and non-responders. The ALBI grade and BCLC stage were independent predictors of PFS; and LR-predicted response, ALBI grade, satellite node, and BCLC stage were independent predictors of OS. The resulting Cox model produced concordance-indexes of 0.705 and 0.736 for predicting PFS and OS, respectively. Conclusions The model combined MRI radiomics with clinical factors demonstrated favorable performance for predicting tumor response and clinical outcomes, thus may help personalized clinical management.