Radiomics Analysis Based on Contrast-Enhanced MRI for Prediction of Therapeutic Response to Transarterial Chemoembolization in Hepatocellular Carcinoma

PurposeTo investigate the role of contrast-enhanced magnetic resonance imaging (CE-MRI) radiomics for pretherapeutic prediction of the response to transarterial chemoembolization (TACE) in patients with hepatocellular carcinoma (HCC).MethodsOne hundred and twenty-two HCC patients (objective response, n = 63; non-response, n = 59) who received CE-MRI examination before initial TACE were retrospectively recruited and randomly divided into a training cohort (n = 85) and a validation cohort (n = 37). All HCCs were manually segmented on arterial, venous and delayed phases of CE-MRI, and total 2367 radiomics features were extracted. Radiomics models were constructed based on each phase and their combination using logistic regression algorithm. A clinical-radiological model was built based on independent risk factors identified by univariate and multivariate logistic regression analyses. A combined model incorporating the radiomics score and selected clinical-radiological predictors was constructed, and the combined model was presented as a nomogram. Prediction models were evaluated by receiver operating characteristic curves, calibration curves, and decision curve analysis.ResultsAmong all radiomics models, the three-phase radiomics model exhibited better performance in the training cohort with an area under the curve (AUC) of 0.838 (95% confidence interval (CI), 0.753 - 0.922), which was verified in the validation cohort (AUC, 0.833; 95% CI, 0.691 - 0.975). The combined model that integrated the three-phase radiomics score and clinical-radiological risk factors (total bilirubin, tumor shape, and tumor encapsulation) showed excellent calibration and predictive capability in the training and validation cohorts with AUCs of 0.878 (95% CI, 0.806 - 0.950) and 0.833 (95% CI, 0.687 - 0.979), respectively, and showed better predictive ability (P = 0.003) compared with the clinical-radiological model (AUC, 0.744; 95% CI, 0.642 - 0.846) in the training cohort. A nomogram based on the combined model achieved good clinical utility in predicting the treatment efficacy of TACE.ConclusionCE-MRI radiomics analysis may serve as a promising and noninvasive tool to predict therapeutic response to TACE in HCC, which will facilitate the individualized follow-up and further therapeutic strategies guidance in HCC patients.

Download Full-text

Predictive model for microvascular invasion of hepatocellular carcinoma among candidates for either hepatectomy or liver transplantation.

Journal of Clinical Oncology ◽

10.1200/jco.2017.35.15_suppl.4079 ◽

2017 ◽

Vol 35 (15_suppl) ◽

pp. 4079-4079

Author(s):

Hidetoshi Nitta ◽

Marc Antoine Allard ◽

Mylene Sebagh ◽

Gabriella Pittau ◽

Oriana Ciacio ◽

...

Keyword(s):

Hepatocellular Carcinoma ◽

Liver Transplantation ◽

Predictive Model ◽

Validation Cohort ◽

Microvascular Invasion ◽

Roc Curve Analysis ◽

Training Cohort ◽

Contrast Enhanced Ct ◽

Contrast Enhanced ◽

Enhanced Ct

4079 Background: Microvascular invasion (MVI) is the strongest prognostic factor following surgery of hepatocellular carcinoma (HCC). However, it is usually not available on the preoperative setting. A predictive model of MVI in patients scheduled for hepatic resection (HR) or liver transplantation (LT) would thus help guiding treatment strategy. The aim of this study was to develop a predictive model for MVI of HCC before either HR or LT. Methods: HCC patients who consecutively performed HR or LT from January 1994 to June 2016 at a single institution were subdivided into a training and validation cohort. Risk factors for MVI in the training cohort were used to develop a predictive model for MVI, to be validated in the validation cohort. The outcomes of the HR and LT patients with high or low MVI probability based on the model, were compared using propensity score matching (PSM). Cut-off values for continuous factors were determined based on ROC curve analysis. Results: A total of 910 patients (425 HR, 485 LT) were included in the training (n = 637) and validation (n = 273) cohorts. In the training cohort, multivariate analysis demonstrated that alpha-fetoprotein ≥100ng/ml ( p < 0.0001), largest tumor size ≥40mm ( p = 0.0002), non-boundary HCC type on contrast-enhanced CT ( p = 0.001), neutrophils-to-lymphocytes ratio ≥3.2 ( p = 0.002), aspartate aminotransferase ≥62U/l ( p = 0.02) were independently associated with MVI. Combinations of these 5 factors varied the MVI probability from 15.5% to 91.1%. This predictive model achieved a good c-index of 0.76 in the validation cohort. In PSM (109 HR, 109 LT), there was no difference in survival between HR and LT patients among the high MVI probability (≥50%) patients, (5y-OS; 46.3% vs 42.2%, p = 0.77, 5y-RFS; 54.0% vs 28.8%, p = 0.21). Among the low probability ( < 50%), survival was significantly decreased following HR compared with LT (5y-OS; 54.1% vs 78.8%, p = 0.007, 5y-RFS; 17.3% vs 86.1%, p< 0.0001). Conclusions: This model developed from preoperative data allows reliable prediction of MVI, and may thus help with preoperative decisions about the suitability of HR or LT in patients with HCC.

Download Full-text

A novel pretreatment model identifying high-risk of refractoriness after transcatheter arterial chemoembolization in unresectable hepatocellular carcinoma.

Journal of Clinical Oncology ◽

10.1200/jco.2020.38.15_suppl.e16641 ◽

2020 ◽

Vol 38 (15_suppl) ◽

pp. e16641-e16641

Author(s):

Xin Yin ◽

Ke Shu Hu ◽

Shen Xin Lu ◽

Bei Tang ◽

Zhenggang Ren

Keyword(s):

Hepatocellular Carcinoma ◽

Logistic Regression ◽

Confidence Interval ◽

Clinical Decision Making ◽

Transcatheter Arterial Chemoembolization ◽

Validation Cohort ◽

Treatment Model ◽

Training Cohort ◽

Pre Treatment ◽

Arterial Chemoembolization

e16641 Background: Refractoriness to transcatheter arterial chemoembolization is common during the therapeutic process of hepatocellular carcinoma, which is an intractable issue and may compromise the prognosis. We aim to establish a pre-treatment model to identify patients with high risks of refractoriness. Methods: From 2010 to 2016, 824 patients who had initially underwent at least two sessions of transcatheter arterial chemoembolization in Zhongshan Hospital, Fudan University were retrospectively enrolled. These patients were randomly allocated into a training cohort and a validation cohort. The pre-treatment scoring model was established based on the clinical and radiological variables using logistic regression and nomogram. The discrimination and calibration of the model were also evaluated. Results: Logistic regression identified vascularization pattern, ALBI grade, serum alpha-fetoprotein level, serum γ- glutamyl transpeptidase level and major tumor size as the key parameters related to refractoriness. The p-TACE model was established using these variables (risk score range: 0-19.5). Patients were divided into six risk subgroups based on their scores ( < 4, ≥4, ≥7, ≥10, ≥13, ≥16). The discriminative ability, as determined by the area under receiver operating characteristic curve was 0.784 (95% confidence interval: 0.741-0.827) in the training cohort and 0.743 (95% confidence interval: 0.696-0.789) in the validation cohort. Moreover, satisfactory calibration was confirmed by Hosmer-Lemeshow test with P values of 0.767 and 0.913 in the training cohort and validation cohort. Conclusions: This study presents a pre-treatment model to identify patients with high risks of refractoriness after transcatheter arterial chemoembolization and shed light on clinical decision making.

Download Full-text

A Predictive Model of Live Birth Based on Obesity and Metabolic Parameters in Patients With PCOS Undergoing Frozen-Thawed Embryo Transfer

Frontiers in Endocrinology ◽

10.3389/fendo.2021.799871 ◽

2022 ◽

Vol 12 ◽

Author(s):

Xiaohua Jiang ◽

Ruijun Liu ◽

Ting Liao ◽

Ye He ◽

Caihua Li ◽

...

Keyword(s):

Risk Factors ◽

Logistic Regression ◽

Embryo Transfer ◽

Live Birth ◽

Goodness Of Fit ◽

Validation Cohort ◽

Advanced Age ◽

Training Cohort ◽

Frozen Thawed Embryo Transfer ◽

Thawed Embryo Transfer

AimsTo determine the clinical predictors of live birth in women with polycystic ovary syndrome (PCOS) undergoing frozen-thawed embryo transfer (F-ET), and to determine whether these parameters can be used to develop a clinical nomogram model capable of predicting live birth outcomes for these women.MethodsIn total, 1158 PCOS patients that were clinically pregnant following F-ET treatment were retrospectively enrolled in this study and randomly divided into the training cohort (n = 928) and the validation cohort (n = 230) at an 8:2 ratio. Relevant risk factors were selected via a logistic regression analysis approach based on the data from patients in the training cohort, and odds ratios (ORs) were calculated. A nomogram was constructed based on relevant risk factors, and its performance was assessed based on its calibration and discriminative ability.ResultsIn total, 20 variables were analyzed in the present study, of which five were found to be independently associated with the odds of live birth in univariate and multivariate logistic regression analyses, including advanced age, obesity, total cholesterol (TC), triglycerides (TG), and insulin resistance (IR). Having advanced age (OR:0.499, 95% confidence interval [CI]: 0.257 – 967), being obese (OR:0.506, 95% CI: 0.306 - 0.837), having higher TC levels (OR: 0.528, 95% CI: 0.423 - 0.660), having higher TG levels (OR: 0.585, 95% CI: 0.465 - 737), and exhibiting IR (OR:0.611, 95% CI: 0.416 - 0.896) were all independently associated with a reduced chance of achieving a live birth. A predictive nomogram incorporating these five variables was found to be well-calibrated and to exhibit good discriminatory capabilities, with an area under the curve (AUC) for the training group of 0.750 (95% CI, 0.709 - 0.788). In the independent validation cohort, this model also exhibited satisfactory goodness-of-fit and discriminative capabilities, with an AUC of 0.708 (95% CI, 0.615 - 0.781).ConclusionsThe nomogram developed in this study may be of value as a tool for predicting the odds of live birth for PCOS patients undergoing F-ET, and has the potential to improve the efficiency of pre-transfer management.

Download Full-text

Development and Validation of a Combined Model for Preoperative Prediction of Lymph Node Metastasis in Peripheral Lung Adenocarcinoma

Frontiers in Oncology ◽

10.3389/fonc.2021.675877 ◽

2021 ◽

Vol 11 ◽

Author(s):

Qi Li ◽

Xiao-qun He ◽

Xiao Fan ◽

Chao-nan Zhu ◽

Jun-wei Lv ◽

...

Keyword(s):

Risk Factors ◽

Lymph Node ◽

Lymph Node Metastasis ◽

Tumor Size ◽

Validation Cohort ◽

Morphological Features ◽

Combined Model ◽

Training Cohort ◽

Node Metastasis ◽

Peripheral Lung

BackgroundBased on the “seed and soil” theory proposed by previous studies, we aimed to develop and validate a combined model of machine learning for predicting lymph node metastasis (LNM) in patients with peripheral lung adenocarcinoma (PLADC).MethodsRadiomics models were developed in a primary cohort of 390 patients (training cohort) with pathologically confirmed PLADC from January 2016 to August 2018. The patients were divided into the LNM (−) and LNM (+) groups. Thereafter, the patients were subdivided according to TNM stages N0, N1, N2, and N3. Radiomic features from unenhanced computed tomography (CT) were extracted. Radiomic signatures of the primary tumor (R1) and adjacent pleura (R2) were built as predictors of LNM. CT morphological features and clinical characteristics were compared between both groups. A combined model incorporating R1, R2, and CT morphological features, and clinical risk factors was developed by multivariate analysis. The combined model’s performance was assessed by receiver operating characteristic (ROC) curve. An internal validation cohort containing 166 consecutive patients from September 2018 to November 2019 was also assessed.ResultsThirty-one radiomic features of R1 and R2 were significant predictors of LNM (all P < 0.05). Sex, smoking history, tumor size, density, air bronchogram, spiculation, lobulation, necrosis, pleural effusion, and pleural involvement also differed significantly between the groups (all P < 0.05). R1, R2, tumor size, and spiculation in the combined model were independent risk factors for predicting LNM in patients with PLADC, with area under the ROC curves (AUCs) of 0.897 and 0.883 in the training and validation cohorts, respectively. The combined model identified N0, N1, N2, and N3, with AUCs ranging from 0.691–0.927 in the training cohort and 0.700–0.951 in the validation cohort, respectively, thereby indicating good performance.ConclusionCT phenotypes of the primary tumor and adjacent pleura were significantly associated with LNM. A combined model incorporating radiomic signatures, CT morphological features, and clinical risk factors can assess LNM of patients with PLADC accurately and non-invasively.

Download Full-text

Prognostic Performance of Albumin–Bilirubin Grade With Artificial Intelligence for Hepatocellular Carcinoma Treated With Transarterial Chemoembolization Combined With Sorafenib

Frontiers in Oncology ◽

10.3389/fonc.2020.525461 ◽

2020 ◽

Vol 10 ◽

Author(s):

Bin-Yan Zhong ◽

Zhi-Ping Yan ◽

Jun-Hui Sun ◽

Lei Zhang ◽

Zhong-Heng Hou ◽

...

Keyword(s):

Risk Factors ◽

Hepatocellular Carcinoma ◽

Transarterial Chemoembolization ◽

Validation Cohort ◽

Survival Prediction ◽

Ann Model ◽

Training Cohort ◽

Prognostic Performance ◽

Independent Risk Factors ◽

Artificial Neural Network Ann

PurposeTo establish albumin-bilirubin (ALBI) grade-based and Child-Turcotte-Pugh (CTP) grade-based nomograms, as well as to develop an artificial neural network (ANN) model to compare the prognostic performance and discrimination of these two grades for hepatocellular carcinoma (HCC) treated with transarterial chemoembolization (TACE) combined with sorafenib as an initial treatment.MethodsThis multicenter retrospective study included patients from three hospitals between January 2013 and August 2018. In the training cohort, independent risk factors associated with overall survival (OS) were identified by univariate and multivariate analyses. The nomograms and ANN were established and then validated in two validation cohorts.ResultsA total of 504 patients (319, 61, and 124 patients from hospitals A, B, and C, respectively) were included. The median OS was 15.2, 26.9, and 14.8 months in the training cohort and validation cohorts 1 and 2, respectively (P = 0.218). In the training cohort, both ALBI grade and CTP grade were identified as independent risk factors. The ALBI grade-based and CTP grade-based nomograms were established separately and showed similar prognostic performance and discrimination when validated in the validation cohorts (C-index in validation cohort 1: 0.799 vs. 0.779, P = 0.762; in validation cohort 2: 0.700 vs. 0.693, P = 0.803). The ANN model showed that the ALBI grade had higher importance in survival prediction than the CTP grade.ConclusionsThe ALBI grade and CTP grade have comparable prognostic performance for HCC patients treated with TACE combined with sorafenib. ALBI grades 1 and 2 have the potential to act as a stratification factor for clinical trials on the combination therapy of TACE and systemic therapy.

Download Full-text

Preoperative and Postoperative Nomograms in Predicting Early Recurrence of Hepatocellular Carcinoma Without Macrovascular Invasion After Curative Resection

10.21203/rs.3.rs-891054/v1 ◽

2021 ◽

Author(s):

Yanfang Zhang ◽

Liangliang Xu ◽

Mingqing Xu ◽

Hong Tang

Keyword(s):

Risk Factors ◽

Hepatocellular Carcinoma ◽

Validation Cohort ◽

Predictive Performance ◽

Early Recurrence ◽

Tumor Diameter ◽

Training Cohort ◽

Factors Associated ◽

Tumor Number ◽

Before And After

Abstract This study aimed to establish pre- and postoperative nomograms in predicting postoperative early recurrence (ER) for hepatocellular carcinoma (HCC) without macrovascular invasion. The patients who underwent curative LR for HCC from January 2012 to December 2016 in our center were divided into training and internal prospective validation cohorts. Nomograms were constructed based on the independent risk factors derived from multivariate logistic regression analyses in training cohort. The predictive performance of nomograms was validated by internal prospective validation cohort. A total of 698 patients fulfilled with eligible criteria. Among them, 265 out of 482 patients (55.0%) in training cohort and 120 out 216 (55.6%) patients in validation cohort developed ER. The preoperative risk factors associated with ER were age, alpha fetoprotein (AFP), tumor diameter, tumor number; the postoperative risk factors associated with ER were age, tumor diameter, tumor number, microvasular invasion (MVI) and differentiation. The pre- and postoperative nomograms based on these factors showed good accuracy with C-indices of 0.712 and 0.850 in training cohort, and 0.754 and 0.857 in validation cohort, respectively. The calibration curves showed optimal agreement between the prediction by the nomograms and actual observation. The area under the receiver operating characteristic curves of pre- and postoperative nomograms were 0.721 and 0.848 in training cohort, and 0.754 and 0.844 in validation cohort, respectively. Present nomograms showed good performance in predicting ER for HCC without macrovascular invasion before and after surgery, which were helpful for doctors in designation of treatments and selection of patients for regularly surveillance or administration of neoadjuvant therapies.

Download Full-text

Radiomics Based on Contrast-Enhanced MRI in Differentiation Between Fat-Poor Angiomyolipoma and Hepatocellular Carcinoma in Noncirrhotic Liver: A Multicenter Analysis

Frontiers in Oncology ◽

10.3389/fonc.2021.744756 ◽

2021 ◽

Vol 11 ◽

Author(s):

Xiangtian Zhao ◽

Yukun Zhou ◽

Yuan Zhang ◽

Lujun Han ◽

Li Mao ◽

...

Keyword(s):

Hepatocellular Carcinoma ◽

Diagnostic Accuracy ◽

Sensitivity And Specificity ◽

Validation Cohort ◽

Characteristic Curve ◽

External Validation ◽

Arterial Phase ◽

Combined Model ◽

Internal Validation ◽

Contrast Enhanced

ObjectiveThis study aims to develop and externally validate a contrast-enhanced magnetic resonance imaging (CE-MRI) radiomics-based model for preoperative differentiation between fat-poor angiomyolipoma (fp-AML) and hepatocellular carcinoma (HCC) in patients with noncirrhotic livers and to compare the diagnostic performance with that of two radiologists.MethodsThis retrospective study was performed with 165 patients with noncirrhotic livers from three medical centers. The dataset was divided into a training cohort (n = 99), a time-independent internal validation cohort (n = 24) from one center, and an external validation cohort (n = 42) from the remaining two centers. The volumes of interest were contoured on the arterial phase (AP) images and then registered to the venous phase (VP) and delayed phase (DP), and a total of 3,396 radiomics features were extracted from the three phases. After the joint mutual information maximization feature selection procedure, four radiomics logistic regression classifiers, including the AP model, VP model, DP model, and combined model, were built. The area under the receiver operating characteristic curve (AUC), diagnostic accuracy, sensitivity, and specificity of each radiomics model and those of two radiologists were evaluated and compared.ResultsThe AUCs of the combined model reached 0.789 (95%CI, 0.579–0.999) in the internal validation cohort and 0.730 (95%CI, 0.563–0.896) in the external validation cohort, higher than the AP model (AUCs, 0.711 and 0.638) and significantly higher than the VP model (AUCs, 0.594 and 0.610) and the DP model (AUCs, 0.547 and 0.538). The diagnostic accuracy, sensitivity, and specificity of the combined model were 0.708, 0.625, and 0.750 in the internal validation cohort and 0.619, 0.786, and 0.536 in the external validation cohort, respectively. The AUCs for the two radiologists were 0.656 and 0.594 in the internal validation cohort and 0.643 and 0.500 in the external validation cohort. The AUCs of the combined model surpassed those of the two radiologists and were significantly higher than that of the junior one in both validation cohorts.ConclusionsThe proposed radiomics model based on triple-phase CE-MRI images was proven to be useful for differentiating between fp-AML and HCC and yielded comparable or better performance than two radiologists in different centers, with different scanners and different scanning parameters.

Download Full-text

Nomogram for Perinatal Prediction of Intrapartum Fever: A Case-control Study

10.21203/rs.3.rs-144513/v1 ◽

2021 ◽

Author(s):

Zhenfei Jiang ◽

Xiaoyi Hu ◽

Huabei Zeng ◽

Xinghe Wang ◽

Cheng Tan ◽

...

Keyword(s):

Risk Factors ◽

Logistic Regression ◽

Vaginal Delivery ◽

Validation Cohort ◽

Multivariate Logistic Regression Analysis ◽

Labor Analgesia ◽

Multivariate Logistic Regression Model ◽

Multivariate Logistic Regression ◽

Clinical Trial Registration ◽

Training Cohort

Abstract Objective: To explore the risk factors of intrapartum fever and develop a nomogram to predict the incidence of intrapartum fever.Methods: The general demographic characteristics and perinatal factors of 696 parturient who underwent vaginal delivery in the Affiliated Hospital of Xuzhou Medical University from May 2019 to April 2020 were retrospectively analyzed. 487 patients collected from May 2019 to October 2019 were formed into a training cohort. A multivariate logistic regression model was used to identify the independent risk factors associated with intrapartum fever during vaginal delivery, then a nomogram was developed to predict the occurrence. 209 cases collected from January 2020 to April 2020 were formed into a validation cohort to verify the nomogram.Results: Intrapartum fever was found in 72 of 487 parturient (14.78%) in the training cohort, and the incidence of intrapartum fever in the validation cohort was 14.83% (31/209). Multivariate logistic regression analysis showed that primiparas (Odds Ratio [OR]2.433; 95% confidence interval [CI]1.149-5.150), epidural labor analgesia (OR2.890; 95%CI 1.225-6.818), premature rupture of membranes (OR2.366; 95%CI 1.130-4.954), second stage of labor ≥120min (OR4.363; 95%CI 1.419-13.410), amniotic fluid pollution Ⅲ degree (OR10.391; 95%CI 3.299-32.729), fetal weight ≥4000g (OR7.492; 95%CI 2.115-26.542) were significantly related to intrapartum fever. According to clinical experience and previous studies, the duration of epidural labor analgesia also seemed to be a meaningful factor for intrapartum fever, so these 7 variables were incorporated to develop a nomogram, which achieved good area under ROC curve of 0.855 in the training cohort and 0.808 in the validation cohort, and it had a well-fitted calibration curve, which showed an excellent diagnostic performance.Conclusion: We constructed a model to predict the occurrence of fever during childbirth and developed an accessible nomogram. The nomogram can help doctors assess the risk of fever during childbirth, so as to lead to reasonable treatment measures.Clinical Trial Registration: (www.chictr.org.cn ChiCTR2000035593)

Download Full-text

Nomogram for perinatal prediction of intrapartum fever: a retrospective case–control study

BMC Pregnancy and Childbirth ◽

10.1186/s12884-021-03891-6 ◽

2021 ◽

Vol 21 (1) ◽

Author(s):

Zhenfei Jiang ◽

Xiaoyi Hu ◽

Huabei Zeng ◽

Xinghe Wang ◽

Cheng Tan ◽

...

Keyword(s):

Risk Factors ◽

Logistic Regression ◽

Pregnant Women ◽

Validation Cohort ◽

Vaginal Birth ◽

Labour Analgesia ◽

Trial Registration ◽

Multivariate Logistic Regression ◽

Training Cohort ◽

Link Type

Abstract Objective To explore the risk factors for intrapartum fever and to develop a nomogram to predict the incidence of intrapartum fever. Methods The general demographic characteristics and perinatal factors of 696 parturients who underwent vaginal birth at the Affiliated Hospital of Xuzhou Medical University from May 2019 to April 2020 were retrospectively analysed. Data was collected from May 2019 to October 2019 on 487 pregnant women who formed a training cohort. A multivariate logistic regression model was used to identify the independent risk factors associated with intrapartum fever during vaginal birth, and a nomogram was developed to predict the occurrence. To verify the nomogram, data was collected from January 2020 to April in 2020 from 209 pregnant women who formed a validation cohort. Results The incidence of intrapartum fever in the training cohort was found in 72 of the 487 parturients (14.8%), and the incidence of intrapartum fever in the validation cohort was 31 of the 209 parturients (14.8%). Multivariate logistic regression analysis showed that the following factors were significantly related to intrapartum fever: primiparas (odds ratio [OR] 2.43; 95% confidence interval [CI] 1.15–5.15), epidural labour analgesia (OR 2.89; 95% CI 1.23–6.82), premature rupture of membranes (OR 2.37; 95% CI 1.13–4.95), second stage of labour ≥ 120 min (OR 4.36; 95% CI 1.42–13.41), amniotic fluid pollution degree III (OR 10.39; 95% CI 3.30–32.73), and foetal weight ≥ 4000 g (OR 7.49; 95% CI 2.12–26.54). Based on clinical experience and previous studies, the duration of epidural labour analgesia also appeared to be a meaningful factor for intrapartum fever; therefore, these seven variables were used to develop a nomogram to predict intrapartum fever in parturients. The nomogram achieved a good area under the ROC curve of 0.86 and 0.81 in the training and in the validation cohorts, respectively. Additionally, the nomogram had a well-fitted calibration curve, which also showed excellent diagnostic performance. Conclusion We constructed a model to predict the occurrence of fever during childbirth and developed an accessible nomogram to help doctors assess the risk of fever during childbirth. Such assessment may be helpful in implementing reasonable treatment measures. Trial registration Clinical Trial Registration: (www.chictr.org.cnChiCTR2000035593)

Download Full-text

Contrast-Enhanced CT-Based Radiomics Analysis in Predicting Lymphovascular Invasion in Esophageal Squamous Cell Carcinoma

Frontiers in Oncology ◽

10.3389/fonc.2021.644165 ◽

2021 ◽

Vol 11 ◽

Author(s):

Yang Li ◽

Meng Yu ◽

Guangda Wang ◽

Li Yang ◽

Chongfei Ma ◽

...

Keyword(s):

Squamous Cell Carcinoma ◽

Logistic Regression ◽

Esophageal Squamous Cell Carcinoma ◽

Lymphovascular Invasion ◽

Combined Model ◽

Training Cohort ◽

Clinical Model ◽

Contrast Enhanced Ct ◽

Contrast Enhanced ◽

Enhanced Ct

ObjectivesTo develop a radiomics model based on contrast-enhanced CT (CECT) to predict the lymphovascular invasion (LVI) in esophageal squamous cell carcinoma (ESCC) and provide decision-making support for clinicians.Patients and MethodsThis retrospective study enrolled 334 patients with surgically resected and pathologically confirmed ESCC, including 96 patients with LVI and 238 patients without LVI. All enrolled patients were randomly divided into a training cohort and a testing cohort at a ratio of 7:3, with the training cohort containing 234 patients (68 patients with LVI and 166 without LVI) and the testing cohort containing 100 patients (28 patients with LVI and 72 without LVI). All patients underwent preoperative CECT scans within 2 weeks before operation. Quantitative radiomics features were extracted from CECT images, and the least absolute shrinkage and selection operator (LASSO) method was applied to select radiomics features. Logistic regression (Logistic), support vector machine (SVM), and decision tree (Tree) methods were separately used to establish radiomics models to predict the LVI status in ESCC, and the best model was selected to calculate Radscore, which combined with two clinical CT predictors to build a combined model. The clinical model was also developed by using logistic regression. The receiver characteristic curve (ROC) and decision curve (DCA) analysis were used to evaluate the model performance in predicting the LVI status in ESCC.ResultsIn the radiomics model, Sphericity and gray-level non-uniformity (GLNU) were the most significant radiomics features for predicting LVI. In the clinical model, the maximum tumor thickness based on CECT (cThick) in patients with LVI was significantly greater than that in patients without LVI (P<0.001). Patients with LVI had higher clinical N stage based on CECT (cN stage) than patients without LVI (P<0.001). The ROC analysis showed that both the radiomics model (AUC values were 0.847 and 0.826 in the training and testing cohort, respectively) and the combined model (0.876 and 0.867, respectively) performed better than the clinical model (0.775 and 0.798, respectively), with the combined model exhibiting the best performance.ConclusionsThe combined model incorporating radiomics features and clinical CT predictors may potentially predict the LVI status in ESCC and provide support for clinical treatment decisions.

Download Full-text