Computed tomography-based radiomics analysis to predict lymphovascular invasion in esophageal squamous cell carcinoma

2021 ◽  
Author(s):  
Hui Peng ◽  
Qiuxing Yang ◽  
Ting Xue ◽  
Qiaoling Chen ◽  
Manman Li ◽  
...  
Keyword(s):  
Squamous Cell Carcinoma ◽  
Esophageal Squamous Cell Carcinoma ◽  
Cell Carcinoma ◽  
Lymphovascular Invasion ◽  
Validation Cohort ◽  
Regression Method ◽  
Training Cohort ◽  
Volume Model ◽  
Single Slice ◽  
Full Volume

Objective The present study explored the value of preoperative CT radiomics in predicting lymphovascular invasion (LVI) in esophageal squamous cell carcinoma (ESCC). Methods A retrospective analysis of 294 pathologically confirmed ESCC patients undergoing surgical resection and their preoperative chest-enhanced CT arterial images were used to delineate the target area of the lesion. All patients were randomly divided into a training cohort and a validation cohort at a ratio of 7:3. Radiomics features were extracted from single-slice, three-slice, and full-volume regions of interest (ROIs). The least absolute shrinkage and selection operator (LASSO) regression method was applied to select valuable radiomics features. Radiomics models were constructed using logistic regression method and were validated using leave group out cross-validation (LGOCV) method. The performance of the three models was evaluated using the receiver characteristic curve (ROC) and decision curve analysis (DCA). Results A total of 1218 radiomics features were separately extracted from single-slice ROIs, three-slice ROIs, and full-volume ROIs, and 16, 13 and 18 features, respectively, were retained after optimization and screening to construct a radiomics prediction model. The results showed that the AUC of the full-volume model was higher than that of the single-slice and three-slice models. According to LGOCV, the full-volume model showed the highest mean AUC for the training cohort and the validation cohort. Conclusion The full-volume radiomics model has the best predictive performance and thus can be used as an auxiliary method for clinical treatment decision making. Advances in knowledge: LVI is considered to be an important initial step for tumor dissemination. CT radiomics features correlate with LVI in ESCC and can be used as potential biomarkers for predicting LVI in ESCC.

scholarly journals A Radiomics Nomogram for Non-Invasive Prediction of Progression-Free Survival in Esophageal Squamous Cell Carcinoma

2021 ◽  
Author(s):  
Ting Yan ◽  
lili liu ◽  
Meilan Peng ◽  
Zhenpeng Yan ◽  
Qingyu Wang ◽  
...  
Keyword(s):  
Squamous Cell Carcinoma ◽  
Esophageal Squamous Cell Carcinoma ◽  
Cell Carcinoma ◽  
Squamous Cell ◽  
Validation Cohort ◽  
Progression Free Survival ◽  
Tnm Staging ◽  
Free Survival ◽  
Training Cohort ◽  
Radiomics Signature

Abstract Objectives: To construct a prognostic model for preoperative prediction based on computed tomography (CT) images of esophageal squamous cell carcinoma (ESCC). Methods: Radiomics signature was constructed using the least absolute shrinkage and selection operator (LASSO) with high throughput radiomics features that extracted from the CT images of 272 patients (204 in training and 68 in validation cohort), who were pathologically confirmed ESCC. Multivariable logistic regression was adopted to build the radiomics signature and another predictive nomogram model, which was composed with radiomics signature, traditional TNM stage and clinical features. Then its performance was assessed by the calibration and decision curve analysis (DCA). Results: 16 radiomics features were selected from 954 to build a radiomics signature，which were significantly associated with progression-free survival (PFS) (p<0.001). The area under the curve (AUC) of performance was 0.891 (95% CI: 0.845-0.936) for training cohort and 0.706 (95% CI: 0.583-0.829) for validation cohort. The radscore of signatures’ combination showed significant discrimination for survival status in both two cohort. Kaplan-Meier survival curve further confirmed the radscore has a better prognostic performance in training cohort. Radiomics nomogram combined radscore with TNM staging showed significant improvement over TNM staging alone in training cohort (C-index, 0.802 vs 0.628; p<0.05), and it is the same with clinical data (C-index, 0.798 vs 0.660; p<0.05). Findings were confirmed in the validation cohort. DCA showed CT-based radiomics model will receive benefit when the threshold probability was between 0 and 0.9. Heat maps revealed associations between radiomics features and tumor stages.Conclusions: Multiparametric CT-based radiomics nomograms provided improved prognostic ability in ESCC.

scholarly journals The value of complete blood count for the prognosis analysis of preoperative esophageal squamous cell carcinoma

BMC Cancer ◽  
2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Xiang Lv ◽  
Songtao Han ◽  
Bin Xu ◽  
Yuqin Deng ◽  
Yangchun Feng
Keyword(s):  
Squamous Cell Carcinoma ◽  
Esophageal Squamous Cell Carcinoma ◽  
Cell Carcinoma ◽  
Squamous Cell ◽  
Prognostic Model ◽  
Blood Count ◽  
Validation Cohort ◽  
Complete Blood Count ◽  
Training Cohort ◽  
Cox Regression Analysis

Abstract Objective To investigate the predictive value of preoperative complete blood count for the survival of patients with esophageal squamous cell carcinoma. Methods A total of 1587 patients with pathologically confirmed esophageal squamous cell carcinoma who underwent esophagectomy in the Cancer Hospital Affiliated to Xinjiang Medical University from January 2010 to December 2019 were collected by retrospective study. A total of 359 patients were as the validation cohort from January 2015 to December 2016, and the remaining 1228 patients were as the training cohort. The relevant clinical data were collected by the medical record system, and the patients were followed up by the hospital medical record follow-up system. The follow-up outcome was patient death. The survival time of all patients was obtained. The Cox proportional hazards regression model and nomogram were established to predict the survival prognosis of esophageal squamous cell carcinoma by the index, their cut-off values obtained the training cohort by the ROC curve. The Kaplan-Meier survival curve was established to express the overall survival rate. The 3-year and 5-year calibration curves and C-index were used to determine the accuracy and discrimination of the prognostic model. The decision curve analysis was used to predict the potential of clinical application. Finally, the validation cohort was used to verify the results of the training cohort. Results The cut-off values of NLR, NMR, LMR, RDW and PDW in complete blood count of the training cohort were 3.29, 12.77, 2.95, 15.05 and 13.65%, respectively. All indicators were divided into high and low groups according to cut-off values. Univariate Cox regression analysis model showed that age (≥ 60), NLR (≥3.29), LMR (< 2.95), RDW (≥15.05%) and PDW (≥13.65%) were risk factors for the prognosis of esophageal squamous cell carcinoma; multivariate Cox regression analysis model showed that age (≥ 60), NLR (≥3.29) and LMR (< 2.95) were independent risk factors for esophageal squamous cell carcinoma. Kaplan-Meier curve indicated that age <  60, NLR < 3.52 and LMR ≥ 2.95 groups had higher overall survival (p <  0.05). The 3-year calibration curve indicated that its predictive probability overestimate the actual probability. 5-year calibration curve indicated that its predictive probability was consistent with the actual probability. 5 c-index was 0.730 and 0.737, respectively, indicating that the prognostic model had high accuracy and discrimination. The decision curve analysis indicated good potential for clinical application. The validation cohort also proved the validity of the prognostic model. Conclusion NLR and LMR results in complete blood count results can be used to predict the survival prognosis of patients with preoperative esophageal squamous cell carcinoma.

scholarly journals Serum Autoantibodies against STIP1 as a Potential Biomarker in the Diagnosis of Esophageal Squamous Cell Carcinoma

2017 ◽  
Vol 2017 ◽  
pp. 1-9 ◽  
Author(s):  
Yi-Wei Xu ◽  
Can-Tong Liu ◽  
Xin-Yi Huang ◽  
Li-Sheng Huang ◽  
Yu-Hao Luo ◽  
...  
Keyword(s):  
Squamous Cell Carcinoma ◽  
Esophageal Squamous Cell Carcinoma ◽  
Cell Carcinoma ◽  
Squamous Cell ◽  
Validation Cohort ◽  
Early Stage ◽  
Enzyme Linked Immunosorbent Assay ◽  
Characteristic Analysis ◽  
Training Cohort ◽  
Sensitivity Specificity

Esophageal squamous cell carcinoma (ESCC) remains one of the leading causes of cancer-related mortality around the world. The identification of novel serum biomarkers is required for early detection of ESCC. This study was designed to elucidate whether autoantibodies against STIP1 could be a diagnostic biomarker in ESCC. An enzyme-linked immunosorbent assay was performed to detect serum levels of STIP1 autoantibodies in a training cohort (148 ESCC patients and 111 controls) and a validation cohort (60 ESCC patients and 40 controls). Mann–Whitney’s U test showed that ESCC patients in two cohorts have higher levels of autoantibodies against STIP1 when compared to controls (P<0.001). According to receiver operating characteristic analysis, the sensitivity, specificity, and area under the curve (AUC) of autoantibodies against STIP1 in ESCC were 41.9%, 90.1%, and 0.682 in the training cohort and 40.0%, 92.5%, and 0.710 in the validation cohort, respectively. Moreover, detection of autoantibodies against STIP1 could discriminate early-stage ESCC patients from controls, with sensitivity, specificity, and AUC of 35.7%, 90.1%, and 0.684 in the training cohort and 38.5%, 92.5%, and 0.756 in the validation cohort, respectively. Our findings indicated that autoantibodies against STIP1 might be a useful biomarker for early-stage ESCC detection.

scholarly journals A Radiomics Nomogram for Non-Invasive Prediction of Progression-Free Survival in Esophageal Squamous Cell Carcinoma

2021 ◽  
Author(s):  
Ting Yan ◽  
Lili Liu ◽  
Meilan Peng ◽  
Zhenpeng Yan ◽  
Qingyu Wang ◽  
...  
Keyword(s):  
Squamous Cell Carcinoma ◽  
Esophageal Squamous Cell Carcinoma ◽  
Cell Carcinoma ◽  
Squamous Cell ◽  
Validation Cohort ◽  
Progression Free Survival ◽  
Tnm Staging ◽  
Free Survival ◽  
Training Cohort ◽  
Radiomics Signature

Abstract To construct a prognostic model for preoperative prediction on computed tomography (CT) images of esophageal squamous cell carcinoma (ESCC), we constructed radiomics signature with high throughput radiomics features extracted from CT images of 272 patients (204 in training and 68 in validation cohort). Multivariable logistic regression was adopted to build the radiomics signature and another predictive nomogram model, which was composed with radiomics signature, traditional TNM stage and clinical features. 16 radiomics features were selected from 954 to build a radiomics signature，which were significantly associated with progression-free survival (PFS) (p<0.001). The area under the curve (AUC) of performance was 0.891 (95% CI: 0.845-0.936) for training cohort and 0.706 (95% CI: 0.583-0.829) for validation cohort. The radscore of signatures’ combination showed significant discrimination for survival status. Radiomics nomogram combined radscore with TNM staging showed significant improvement over TNM staging alone in training cohort (C-index, 0.802 vs 0.628; p<0.05), and it is the same with clinical data (C-index, 0.798 vs 0.660; p<0.05), which were confirmed in validation cohort. DCA showed the model will receive benefit when the threshold probability was between 0 and 0.9. Collectively, multiparametric CT-based radiomics nomograms provided improved prognostic ability in ESCC.

Establishment and Validation of a Prognostic Model in Patients with Stage T1-3N0M0 of Esophageal Squamous Cell Carcinoma (ESCC): An Observational Study from Two Centers

2020 ◽  
Author(s):  
Lei-Lei Wu ◽  
Yu-Xuan Ji ◽  
Yan Zheng ◽  
Xuan Liu ◽  
Yang-Yu Huang ◽  
...  
Keyword(s):  
Squamous Cell Carcinoma ◽  
High Risk ◽  
Esophageal Squamous Cell Carcinoma ◽  
Cell Carcinoma ◽  
Squamous Cell ◽  
Prognostic Model ◽  
Validation Cohort ◽  
External Validation ◽  
Training Cohort ◽  
Stage T1

Abstract PURPOSE: To explore the postoperative prognosis of patients diagnosed with esophageal squamous cell carcinoma (ESCC) of stage T1-3N0M0 using a survival prognostic model (SPM). PATIENTS AND METHODS: Patients diagnosed with stage T1-3N0M0 ESCC from two cancer centers—Sun Yat-sen University Cancer Center (SYSUCC-A/ training cohort: N = 555), SYSUCC-B/ internal validation cohort: N = 241) and Henan Cancer Hospital (HNCH/ external validation cohort: N = 170)—that had undergone esophagectomy between 1995 and 2015 were enrolled in this study. The primary clinical endpoint was overall survival (OS). We have identified and integrated significant prognostic factors for OS by univariate and multivariate Cox regression methods applied in the training cohort to build a SPM that could be validated in the validation cohorts.RESULTS: The OS evaluation by the SPM was comparable in three cohorts (SYSUCC-A: C-index 0.654, SYSUCC-B: C-index 0.630, HNCH: C-index 0.688). Discretization of patients was done using a fixed survival score cutoff of 136.434 based on our SPM determined from the training cohort divided into low- and high-risk subgroups with stratified OS in the validation cohort (SYSUCC-A: hazard ratio [HR] 1.009, 95% confidence intervals [CI], 1.006–1.011, P < 0.001; SYSUCC-B: HR 1.009, 95% CI, 1.004–1.013, P ˂ 0.001; HNCH: HR 1.010, 95% CI 1.005-1.015, P = 0.0017). The 48-month OS in the low-risk subgroup vs. that in the high-risk subgroup was 80.8% vs. 60.9% for SYSUCC-A, 86.4% vs. 60.7% for SYSUCC-B, and 89.7% vs. 64.1% for HNCH. CONCLUSION: We have established and validated a novel SPM that can predict the OS for T1-3N0M0 ESCC patients and could help clinicians to detect subgroups of patients with poor prognosis.

scholarly journals Comprehensive Analysis of the Functions, Prognostic and Diagnostic Values of RNA Binding Proteins in Head and Neck Squamous Cell Carcinoma

2021 ◽  
Author(s):  
Xueping Ke ◽  
Zhen Fu ◽  
Jingjing Yang ◽  
Shijin Yu ◽  
Tingyuan Yan ◽  
...  
Keyword(s):  
Squamous Cell Carcinoma ◽  
Logistic Regression ◽  
Regression Analysis ◽  
Cell Carcinoma ◽  
Prognostic Model ◽  
Rna Binding ◽  
Cox Regression ◽  
Validation Cohort ◽  
Characteristic Curve ◽  
Training Cohort

Abstract Background: Increasing evidence has suggested that RNA binding protein (RBP) dysregulation plays an important part in tumorigenesis. Here, we sought to explore the potential molecular functions and clinical significance of RBP and develop diagnostic and prognostic signatures based on RBP in patients with head and neck squamous cell carcinoma (HNSCC). Methods: The Limma package was applied to identify the differently expressed RBPs between HNSCC and normal samples with |log2 fold change (FC)|≥1 and false discovery rate (FDR)<0.05. the immunohistochemistry images from the Human Protein Atlas database The diagnostic signature based on RBP was built by LASSO-logistic regression and random forest and the prognostic signature based on RBP was constructed by LASSO and stepwise Cox regression analysis in training cohort and validated in validation cohort. All these analyses were performed using the R software.Results: A total of 84 aberrantly expressed RBPs were obtained, comprising 41 up-regulated and 43 down-regulated RBPs. Seven RBP genes (CPEB3, PDCD4, ENDOU, PARP12, DNMT3B, IGF2BP1, EXO1) were identified as diagnostic related hub gene and were used to establish a diagnostic RBP signature risk score (DRBPS) model by the coefficients in LASSO-logistic regression analysis and shown high specificity and sensitivity in the training (area under the receiver operating characteristic curve [AUC] = 0.998), and in all validation cohorts (AUC > 0.95 for all). Similarly, seven RBP genes (MKRN3, ZC3H12D, EIF5A2, AFF3, SIDT1, RBM24 and NR0B1) were identified as prognosis associated hub genes by least absolute shrinkage and selection operator (LASSO) and stepwise multiple Cox regression analyses and were used to construct the prognostic model named as PRBPS. The area under the curve of the time-dependent receiver operator characteristic curve of the prognostic model were 0.664 at 3 years and 0.635 at 5 years in training cohort and 0.720, 0.777 in the validation cohort, showing a favorable predictive effificacy for prognosis in HNSCC.Conclusions: Our results demonstrate the values of consideration of RBP in the diagnosis and prognosis for HNSCC and provide a novel insights to understand potential role of dysregulated RBP in HNSCC.

Sign in / Sign up

Export Citation Format

Share Document