Dataset Information

An artificial neural network-based radiomics model for predicting the radiotherapy response of advanced esophageal squamous cell carcinoma patients: a multicenter study.

ABSTRACT: Radiotherapy benefits patients with advanced esophageal squamous cell carcinoma (ESCC) in terms of symptom relief and long-term survival. In contrast, a substantial proportion of ESCC patients have not benefited from radiotherapy. This study aimed to establish and validate an artificial neural network-based radiomics model for the pretreatment prediction of the radiotherapy response of advanced ESCC by using integrated data combined with feasible baseline characteristics of computed tomography. A total of 248 patients with advanced ESCC who underwent baseline CT and received radiotherapy were enrolled in this study and were analyzed by two types of radiomics models, machine learning and deep learning. As a result, the Att. Resnet50 pretrained network model indicated superior performance, with AUCs of 0.876, 0.802 and 0.732 in the training, internal validation, and external validation cohorts, respectively. Similarly, our Att. Resnet50 pretrained network model showed excellent calibration and significant clinical benefit according to the C index and decision curve analysis. Herein, a novel pretreatment radiomics model was established based on deep learning methods and could be used for radiotherapy response prediction in advanced ESCC patients, thus providing reliable evidence for therapeutic decision-making.

SUBMITTER: Xie Y

PROVIDER: S-EPMC10226996 | biostudies-literature | 2023 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

An artificial neural network-based radiomics model for predicting the radiotherapy response of advanced esophageal squamous cell carcinoma patients: a multicenter study.

Xie Yuchen Y Liu Qiang Q Ji Chao C Sun Yuchen Y Zhang Shuliang S Hua Mingyu M Liu Xueting X Pan Shupei S Hu Weibin W Ma Yanfang Y Wang Ying Y Zhang Xiaozhi X

Scientific reports 20230529 1

Radiotherapy benefits patients with advanced esophageal squamous cell carcinoma (ESCC) in terms of symptom relief and long-term survival. In contrast, a substantial proportion of ESCC patients have not benefited from radiotherapy. This study aimed to establish and validate an artificial neural network-based radiomics model for the pretreatment prediction of the radiotherapy response of advanced ESCC by using integrated data combined with feasible baseline characteristics of computed tomography. ...[more]

PMID: 37248363

Similar Datasets

Project description: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.

Project description:BackgroundBecause of the superficial and infiltrative spreading patterns of esophageal squamous cell carcinoma (ESCC), an accurate assessment of tumor extent is challenging using imaging-based clinical staging. Radiomics features extracted from pretreatment computed tomography (CT) or magnetic resonance imaging have shown promise in identifying tumor characteristics. Accurate staging is essential for planning cancer treatment, especially for deciding whether to offer surgery or radiotherapy (chemotherapy) in patients with locally advanced ESCC. Thus, this study aimed to evaluate the predictive potential of contrast-enhanced CT-based radiomics as a non-invasive approach for estimating pathological tumor extent in ESCC patients.MethodsPatients who underwent esophagectomy between October 2011 and September 2017 were retrospectively studied and included 116 patients with pathologically confirmed ESCC. Contrast-enhanced CT from the neck to the abdomen was performed in all patients during the 2 weeks before the operation. Radiomics features were extracted from segmentations, which were contoured by radiologists. Cluster analysis was performed to obtain clusters with similar radiomics characteristics, and chi-squared tests were used to assess differences in clinicopathological features and survival among clusters. Furthermore, a least absolute shrinkage and selection operator was performed to select radiomics features and construct a radiomics model. Receiver operating characteristic analysis was used to evaluate the predictive ability of the radiomics signatures.ResultsAll 116 ESCC patients were divided into two groups according to the cluster analysis. The chi-squared test showed that cluster-based radiomics features were significantly correlated with T stage (p = 0.0254) and tumor length (p = 0.0002). Furthermore, CT radiomics signatures exhibited favorable predictive performance for T stage (area under the curve [AUC] = 0.86, sensitivity = 0.77, and specificity = 0.87) and tumor length (AUC = 0.95, sensitivity = 0.92, and specificity = 0.91).ConclusionsCT contrast radiomics is a simple and non-invasive method that shows promise for predicting pathological T stage and tumor length preoperatively in ESCC patients and may aid in the accurate assessments of patients in combination with the existing examinations.

Project description:Lessons learnedRadiotherapy plus anti-PD-1 antibody as first-line therapy is safe and feasible in locally advanced esophageal squamous cell carcinoma (ESCC). Tumor-infiltrating and peripheral lymphocytes were associated with patient survival. Further studies combining chemoradiotherapy with immunotherapy in locally advanced ESCC and exploration of predictive biomarkers are warranted.BackgroundWe conducted a phase Ib study of radiotherapy plus programmed cell death protein 1 (PD-1) monoclonal antibody camrelizumab as first-line treatment for locally advanced esophageal squamous cell carcinoma (ESCC).MethodsWe planned to enroll 20 patients with newly diagnosed locally advanced ESCC. Patients received 60 Gy radiation (2.0 Gy/fraction, 5 fractions/week), with camrelizumab (200 mg every 2 weeks) starting with radiotherapy and continuing for 32 weeks (i.e., for 16 cycles). The primary endpoints were safety and feasibility. Secondary endpoints were rates of radiologic and pathologic response, overall survival (OS), and progression-free survival (PFS). Study data were collected by the week during radiotherapy (RT), every month during the maintenance camrelizumab treatment, and every 3 months after treatment. Tumor microenvironment and peripheral blood were monitored at baseline and after 40 Gy radiation for association with efficacy.ResultsTwenty patients were enrolled and received treatment. One patient (patient 10) was excluded upon discovery of a second tumor in the bladder during treatment, leaving 19 patients for analysis. Toxicity was deemed tolerable. Fourteen (74%) patients had assessed objective response. At a median follow-up time of 31.0 months (95% confidence interval [CI], 27.0-35.1), median OS and PFS times were 16.7 months (95% CI, 5.9-27.9) and 11.7 months (95% CI, 0-30.3), respectively. OS and PFS rates at 24 months were 31.6% and 35.5%, respectively. Kaplan-Meier analysis revealed associations between the following factors and OS/PFS: tumor programmed cell death ligand 1 (PD-L1) expression, PD-1+ CD8+ , PD-1+ CD4+ T cells, and PD-L1+ CD4+ T cells; peripheral blood CD4+ , CD8+ , CD4+ regulatory T cells, and their subsets.ConclusionRadiotherapy plus camrelizumab had manageable toxicity and antitumor efficacy for locally advanced ESCC. Several biomarkers were associated with clinical benefit and deserve further study.

Project description:BackgroundTo develop and validate an online individualized model for predicting local recurrence-free survival (LRFS) in esophageal squamous cell carcinoma (ESCC) treated by definitive chemoradiotherapy (dCRT).MethodsESCC patients from three hospitals were randomly stratified into the training set (715) and the internal testing set (179), and patients from the other hospital as the external testing set (120). The important radiomic features extracted from contrast-enhanced computed tomography (CECT)-based subregions clustered from the whole volume of tumor and peritumor were selected and used to construct the subregion-based radiomic signature by using COX proportional hazards model, which was compared with the tumor-based radiomic signature. The clinical model and the radiomics model combing the clinical factors and the radiomic signature were further constructed and compared, which were validated in two testing sets.ResultsThe subresion-based radiomic signature showed better prognostic performance than the tumor-based radiomic signature (training: 0.642 vs. 0.621, internal testing: 0.657 vs. 0.638, external testing: 0.636 vs. 0.612). Although the tumor-based radiomic signature, the subregion-based radiomic signature, the tumor-based radiomics model, and the subregion-based radiomics model had better performance compared to the clinical model, only the subregion-based radiomics model showed a significant advantage (p < 0.05; training: 0.666 vs. 0.616, internal testing: 0.689 vs. 0.649, external testing: 0.642 vs. 0.604). The clinical model and the subregion-based radiomics model were visualized as the nomograms, which are available online and could interactively calculate LRFS probability.ConclusionsWe established and validated a CECT-based online radiomics nomogram for predicting LRFS in ESCC received dCRT, which outperformed the clinical model and might serve as a powerful tool to facilitate individualized treatment.Trial registrationThis retrospective study was approved by the ethics committee (KY20222145-C-1).

Dataset Information

An artificial neural network-based radiomics model for predicting the radiotherapy response of advanced esophageal squamous cell carcinoma patients: a multicenter study.

Publications

An artificial neural network-based radiomics model for predicting the radiotherapy response of advanced esophageal squamous cell carcinoma patients: a multicenter study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets