scholarly journals Pretreatment Prediction of Relapse Risk in Patients with Osteosarcoma Using Radiomics Nomogram Based on CT: A Retrospective Multicenter Study

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Jin Liu ◽  
Tao Lian ◽  
Haimei Chen ◽  
Xiaohong Wang ◽  
Xianyue Quan ◽  
...  
Keyword(s):  
Risk Factors ◽  
Multicenter Study ◽  
Cox Regression ◽  
Validation Cohort ◽  
External Validation ◽  
Training Cohort ◽  
Relapse Risk ◽  
Significant Difference ◽  
Prediction Of Relapse ◽  
Radiomics Signature

Objective. To develop and externally validate a CT-based radiomics nomogram for pretreatment prediction of relapse in osteosarcoma patients within one year. Materials and Methods. In this multicenter retrospective study, a total of 80 patients (training cohort: 63 patients from three hospitals; validation cohort: 17 patients from three other hospitals) with osteosarcoma, undergoing pretreatment CT between August 2010 and December 2018, were identified from multicenter databases. Radiomics features were extracted and selected from tumor regions on CT image, and then, the radiomics signature was constructed. The radiomics nomogram that incorporated the radiomics signature and clinical-based risk factors was developed to predict relapse risk with a multivariate Cox regression model using the training cohort and validated using the external validation cohort. The performance of the nomogram was assessed concerning discrimination, calibration, reclassification, and clinical usefulness. Results. Kaplan-Meier curves based on the radiomics signature showed a significant difference between the high-risk and the low-risk groups in both training and validation cohorts ( P < 0.001 and P = 0.015 , respectively). The radiomics nomogram achieved good discriminant results in the training cohort ( C -index: 0.779) and the validation cohort ( C -index: 0.710) as well as good calibration. Decision curve analysis revealed that the proposed model significantly improved the clinical benefit compared with the clinical-based nomogram ( P < 0.001 ). Conclusions. This multicenter study demonstrates that a radiomics nomogram incorporated the radiomics signature and clinical-based risk factors can increase the predictive value of the osteosarcoma relapse risk, which supports the clinical application in different institutions.

scholarly journals Preoperative Assessment for Event-Free Survival With Hepatoblastoma in Pediatric Patients by Developing a CT-Based Radiomics Model

2021 ◽  
Vol 11 ◽  
Author(s):  
Yi Jiang ◽  
Jingjing Sun ◽  
Yuwei Xia ◽  
Yan Cheng ◽  
Linjun Xie ◽  
...  
Keyword(s):  
Risk Factors ◽  
Clinical Decision Making ◽  
Validation Cohort ◽  
External Validation ◽  
Multivariable Analysis ◽  
Tumor Diameter ◽  
Event Free Survival ◽  
Free Survival ◽  
Training Cohort ◽  
Radiomics Signature

Objective: To explore a CT-based radiomics model for preoperative prediction of event-free survival (EFS) in patients with hepatoblastoma and to compare its performance with that of a clinicopathologic model.Patients and Methods: Eighty-eight patients with histologically confirmed hepatoblastoma (mean age: 2.28 ± 2.72 years) were recruited from two institutions between 2002 and 2019 for this retrospective study. They were divided into a training cohort (65 patients from institution A) and a validation cohort (23 patients from institution B). Radiomics features were extracted manually from pretreatment CT images in the portal venous (PV) phase. The least absolute shrinkage and selection operator (LASSO) Cox regression model was applied to construct a “radiomics signature” and radiomics score (Rad-score) for EFS prediction. Then, a nomogram incorporating the Rad-score, updated staging system, and significant variables of clinicopathologic risk (age, alpha-fetoprotein (AFP) level, histology subtype, tumor diameter) as the radiomic model, clinicopathologic model, and combined clinicopathologic-radiomic model were built for EFS estimation in the training cohort, the performance of which was assessed in an external-validation cohort with respect to clinical usefulness, discrimination, and calibration.Results: Nine survival-relevant features were selected for a radiomics signature and Rad-score building. Multivariable analysis revealed that histology subtype (P = 0.01), PV (P = 0.001) invasion, and metastasis (P = 0.047) were independent risk factors of EFS. Patients were divided into low- and high-risk groups based on the Rad-score with a cutoff of 0.08 according to survival outcome. The radiomics signature-incorporated nomogram showed good performance (P &lt; 0.001) for EFS estimation (C-Index: 0.810; 95% CI: 0.738–0.882), which was comparable with that of the clinicopathological model for EFS estimation (C-Index: 0.81 vs. 0.85). The radiomics-based nomogram failed to show incremental prognostic value compared with that using the clinicopathologic model. The combined model (radiomics signature plus clinicopathologic parameters) showed significant improvement in the discriminatory accuracy, along with good calibration and greater net clinical benefit, of EFS (C-Index: 0.88; 95% CI: 0.829–0.933).Conclusion: The radiomics signature can be used as a prognostic indicator for EFS in patients with hepatoblastoma. A combination of the radiomics signature and clinicopathologic risk factors showed better performance in terms of EFS prediction in patients with hepatoblastoma, which enabled precise clinical decision-making.

scholarly journals Establishment and Validation of an Integrated Model to Predict Postoperative Recurrence in Patients With Atypical Meningioma

2021 ◽  
Vol 11 ◽  
Author(s):  
Xiao-Yong Chen ◽  
Jin-Yuan Chen ◽  
Yin-Xing Huang ◽  
Jia-Heng Xu ◽  
Wei-Wei Sun ◽  
...  
Keyword(s):  
Cox Regression ◽  
Validation Cohort ◽  
Clinical Laboratory ◽  
External Validation ◽  
Postoperative Recurrence ◽  
Integrated Model ◽  
Atypical Meningioma ◽  
Tumor Diameter ◽  
Roc Curve Analysis ◽  
Training Cohort

BackgroundThis study aims to establish an integrated model based on clinical, laboratory, radiological, and pathological factors to predict the postoperative recurrence of atypical meningioma (AM).Materials and MethodsA retrospective study of 183 patients with AM was conducted. Patients were randomly divided into a training cohort (n = 128) and an external validation cohort (n = 55). Univariable and multivariable Cox regression analyses, the least absolute shrinkage and selection operator (LASSO) regression analysis, time-dependent receiver operating characteristic (ROC) curve analysis, and evaluation of clinical usage were used to select variables for the final nomogram model.ResultsAfter multivariable Cox analysis, serum fibrinogen &gt;2.95 g/L (hazard ratio (HR), 2.43; 95% confidence interval (CI), 1.05–5.63; p = 0.039), tumor located in skull base (HR, 6.59; 95% CI, 2.46-17.68; p &lt; 0.001), Simpson grades III–IV (HR, 2.73; 95% CI, 1.01–7.34; p = 0.047), tumor diameter &gt;4.91 cm (HR, 7.10; 95% CI, 2.52–19.95; p &lt; 0.001), and mitotic level ≥4/high power field (HR, 2.80; 95% CI, 1.16–6.74; p = 0.021) were independently associated with AM recurrence. Mitotic level was excluded after LASSO analysis, and it did not improve the predictive performance and clinical usage of the model. Therefore, the other four factors were integrated into the nomogram model, which showed good discrimination abilities in training cohort (C-index, 0.822; 95% CI, 0.759–0.885) and validation cohort (C-index, 0.817; 95% CI, 0.716–0.918) and good match between the predicted and observed probability of recurrence-free survival.ConclusionOur study established an integrated model to predict the postoperative recurrence of AM.

scholarly journals ANVCFV Score System: Assessment for Probability of New Vertebral Compression Fractures after Percutaneous Vertebroplasty in Patients with Vertebral Compression Fractures

2015 ◽  
Vol 6;18 (6;11) ◽  
pp. E1047-E1057
Author(s):  
Gao-Jun Teng
Keyword(s):  
Risk Factors ◽  
Cox Regression ◽  
Validation Cohort ◽  
Percutaneous Vertebroplasty ◽  
Vertebral Compression Fractures ◽  
Score System ◽  
Training Cohort ◽  
Compression Fractures ◽  
Independent Risk Factors ◽  
Risk Score System

Background: Percutaneous vertebroplasty (PVP) is widely used for the treatment of painful vertebral compression fractures (VCFs). However, new VCFs occur frequently after PVP. Objectives: We aim to establish an objective risk score system to assess the possibility of new vertebral fractures in patients with VCFs undergoing PVP. Study Design: This study was a retrospective study, and it was approved by the Institutional Review Board of our 2 institutions. Setting: This study consists of patients from 2 large academic centers. Methods: Patients with VCFs who underwent their first PVP and met the inclusion criteria between January 2007 and December 2013 at Hospital A (training cohort) and Hospital B (validation cohort) were included. In the training cohort, the independent risk factors for new VCFs after PVP were identified by multivariate stepwise backward Cox regression analysis from the risk factors selected by univariate analysis and Harrell’s C-statistics and used to develop the score system (assessment for new VCFs after PVP [ANVCFV]) to predict the probability of new VCFs. Results: In total, 397 patients (training cohort: n = 241; validation cohort: n = 156) were included in this study. In the training cohort, the ANVCFV score was developed based on 5 independent risk factors for the new VCFs after PVP, including lower computed tomography (CT) values, pre-existing old VCFs, intradiscal cement leakage, more than one vertebra treated, and superior or inferior marginal cement distribution in the vertebra. The patients were divided into 2 groups by the ANVCFV score of -1.5 to 8.5 vs. > 8.5 points in the probability of new VCFs (median fracture-free time: 1846 vs. 732 days; P < 0.001) in the training cohort. The accuracy of this score system was 77.4% for the training cohort and 85.3% for the validation cohort. Limitations: The main limitations of this study are that it is a retrospective study and that there is a significant difference of the treated vertebrae of PVP per session between the 2 cohorts. Conclusion: Patients who underwent their first PVP with an ANVCFV score > 8.5 points may exhibit an increased chance of suffering from new VCFs. Key words: Vertebral compression fracture, percutaneous vertebroplasty, newly developed, risk factors, risk score system, Cox regression model, accuracy, validation

scholarly journals A radiomics nomogram for the prediction of overall survival in patients with hepatocellular carcinoma after hepatectomy

2020 ◽  
Vol 20 (1) ◽  
Author(s):  
Qinqin Liu ◽  
Jing Li ◽  
Fei Liu ◽  
Weilin Yang ◽  
Jingjing Ding ◽  
...  
Keyword(s):  
Hepatocellular Carcinoma ◽  
Overall Survival ◽  
Cox Regression ◽  
Validation Cohort ◽  
Cox Model ◽  
Accurate Estimation ◽  
Training Cohort ◽  
Dismal Prognosis ◽  
Texture Parameters ◽  
Radiomics Signature

Abstract Background Hepatocellular carcinoma (HCC) is associated with a dismal prognosis, and prediction of the prognosis of HCC can assist in therapeutic decision-makings. An increasing number of studies have shown that the texture parameters of images can reflect the heterogeneity of tumors, and may have the potential to predict the prognosis of patients with HCC after surgical resection. The aim of this study was to investigate the prognostic value of computed tomography (CT) texture parameters in patients with HCC after hepatectomy and to develop a radiomics nomogram by combining clinicopathological factors and the radiomics signature. Methods In all, 544 eligible patients were enrolled in this retrospective study and were randomly divided into the training cohort (n = 381) and the validation cohort (n = 163). The tumor regions of interest (ROIs) were delineated, and the corresponding texture parameters were extracted. The texture parameters were selected by using the least absolute shrinkage and selection operator (LASSO) Cox model in the training cohort, and a radiomics signature was established. Then, the radiomics signature was further validated as an independent risk factor for overall survival (OS). The radiomics nomogram was established based on the Cox regression model. The concordance index (C-index), calibration plot and decision curve analysis (DCA) were used to evaluate the performance of the radiomics nomogram. Results The radiomics signature was formulated based on 7 OS-related texture parameters, which were selected in the training cohort. In addition, the radiomics nomogram was developed based on the following five variables: α-fetoprotein (AFP), platelet-to-lymphocyte ratio (PLR), largest tumor size, microvascular invasion (MVI) and radiomics score (Rad-score). The nomogram displayed good accuracy in predicting OS (C-index = 0.747) in the training cohort and was confirmed in the validation cohort (C-index = 0.777). The calibration plots also showed excellent agreement between the actual and predicted survival probabilities. The DCA indicated that the radiomics nomogram showed better clinical utility than the clinicopathologic nomogram. Conclusion The radiomics signature is a potential prognostic biomarker of HCC after hepatectomy. The radiomics nomogram that integrated the radiomics signature can provide a more accurate estimation of OS than the clinicopathologic nomogram for HCC patients after hepatectomy.

scholarly journals Computed Tomography-Based Radiomics Nomogram: Potential to Predict Local Recurrence of Gastric Cancer After Radical Resection

2021 ◽  
Vol 11 ◽  
Author(s):  
Liebin Huang ◽  
Bao Feng ◽  
Yueyue Li ◽  
Yu Liu ◽  
Yehang Chen ◽  
...  
Keyword(s):  
Risk Factors ◽  
Gastric Cancer ◽  
Computed Tomography ◽  
Validation Cohort ◽  
Radical Resection ◽  
Curve Analysis ◽  
Internal Validation ◽  
Training Cohort ◽  
Clinical Model ◽  
Radiomics Signature

ObjectiveAccurate prediction of postoperative recurrence risk of gastric cancer (GC) is critical for individualized precision therapy. We aimed to investigate whether a computed tomography (CT)-based radiomics nomogram can be used as a tool for predicting the local recurrence (LR) of GC after radical resection.Materials and Methods342 patients (194 in the training cohort, 78 in the internal validation cohort, and 70 in the external validation cohort) with pathologically proven GC from two centers were included. Radiomics features were extracted from the preoperative CT imaging. The clinical model, radiomics signature, and radiomics nomogram, which incorporated the radiomics signature and independent clinical risk factors, were developed and verified. Furthermore, the performance of these three models was assessed by using the area under the curve (AUC) of receiver operating characteristic (ROC) curve analysis and decision curve analysis (DCA).ResultsThe radiomics signature, which was comprised of two selected radiomics features, namely, contrast_GLCM and dissimilarity_GLCM, showed better performance than the clinical model in predicting the LR of GC, with AUC values of 0.83 in the training cohort, 0.84 in the internal validation cohort, and 0.73 in the external cohort, respectively. By integrating the independent clinical risk factors (N stage, bile acid duodenogastric reflux and nodular or irregular outer layer of the gastric wall) into the radiomics signature, the radiomics nomogram achieved the highest accuracy in predicting LR, with AUC values of 0.89, 0.89 and 0.80 in the three cohorts, respectively. DCA in the validation cohort showed that radiomics nomogram added more net benefit than the clinical model within the range of 0.01-0.98.ConclusionThe CT-based radiomics nomogram has the potential to predict the LR of GC after radical resection.

scholarly journals Development and Validation of a Nomogram for Preoperative Prediction of Lymph Node Metastasis in Lung Adenocarcinoma Based on Radiomics Signature and Deep Learning Signature

2021 ◽  
Vol 11 ◽  
Author(s):  
Jia Ran ◽  
Ran Cao ◽  
Jiumei Cai ◽  
Tao Yu ◽  
Dan Zhao ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Regression Analysis ◽  
Deep Learning ◽  
Prediction Model ◽  
Validation Cohort ◽  
External Validation ◽  
Training Cohort ◽  
Preoperative Prediction ◽  
Lemeshow Test ◽  
Radiomics Signature

Background and PurposeThe preoperative LN (lymph node) status of patients with LUAD (lung adenocarcinoma) is a key factor for determining if systemic nodal dissection is required, which is usually confirmed after surgery. This study aimed to develop and validate a nomogram for preoperative prediction of LN metastasis in LUAD based on a radiomics signature and deep learning signature.Materials and MethodsThis retrospective study included a training cohort of 200 patients, an internal validation cohort of 40 patients, and an external validation cohort of 60 patients. Radiomics features were extracted from conventional CT (computed tomography) images. T-test and Extra-trees were performed for feature selection, and the selected features were combined using logistic regression to build the radiomics signature. The features and weights of the last fully connected layer of a CNN (convolutional neural network) were combined to obtain a deep learning signature. By incorporating clinical risk factors, the prediction model was developed using a multivariable logistic regression analysis, based on which the nomogram was developed. The calibration, discrimination and clinical values of the nomogram were evaluated.ResultsMultivariate logistic regression analysis showed that the radiomics signature, deep learning signature, and CT-reported LN status were independent predictors. The prediction model developed by all the independent predictors showed good discrimination (C-index, 0.820; 95% CI, 0.762 to 0.879) and calibration (Hosmer-Lemeshow test, P=0.193) capabilities for the training cohort. Additionally, the model achieved satisfactory discrimination (C-index, 0.861; 95% CI, 0.769 to 0.954) and calibration (Hosmer-Lemeshow test, P=0.775) when applied to the external validation cohort. An analysis of the decision curve showed that the nomogram had potential for clinical application.ConclusionsThis study presents a prediction model based on radiomics signature, deep learning signature, and CT-reported LN status that can be used to predict preoperative LN metastasis in patients with LUAD.

scholarly journals Radiomic nomogram based on MRI to predict grade of branching type intraductal papillary mucinous neoplasms of the pancreas: a multicenter study

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Sijia Cui ◽  
Tianyu Tang ◽  
Qiuming Su ◽  
Yajie Wang ◽  
Zhenyu Shu ◽  
...  
Keyword(s):  
Calibration Curve ◽  
Main Pancreatic Duct ◽  
Validation Cohort ◽  
External Validation ◽  
High Grade ◽  
Intraductal Papillary Mucinous Neoplasms ◽  
Training Cohort ◽  
Independent Validation ◽  
Medical Centers ◽  
Mucinous Neoplasms

Abstract Background Accurate diagnosis of high-grade branching type intraductal papillary mucinous neoplasms (BD-IPMNs) is challenging in clinical setting. We aimed to construct and validate a nomogram combining clinical characteristics and radiomic features for the preoperative prediction of low and high-grade in BD-IPMNs. Methods Two hundred and two patients from three medical centers were enrolled. The high-grade BD-IPMN group comprised patients with high-grade dysplasia and invasive carcinoma in BD-IPMN (n = 50). The training cohort comprised patients from the first medical center (n = 103), and the external independent validation cohorts comprised patients from the second and third medical centers (n = 48 and 51). Within 3 months prior to surgery, all patients were subjected to magnetic resonance examination. The volume of interest was delineated on T1-weighted (T1-w) imaging, T2-weighted (T2-w) imaging, and contrast-enhanced T1-weighted (CET1-w) imaging, respectively, on each tumor slice. Quantitative image features were extracted using MITK software (G.E.). The Mann-Whitney U test or independent-sample t-test, and LASSO regression, were applied for data dimension reduction, after which a radiomic signature was constructed for grade assessment. Based on the training cohort, we developed a combined nomogram model incorporating clinical variables and the radiomic signature. Decision curve analysis (DCA), a receiver operating characteristic curve (ROC), a calibration curve, and the area under the ROC curve (AUC) were used to evaluate the utility of the constructed model based on the external independent validation cohorts. Results To predict tumor grade, we developed a nine-feature-combined radiomic signature. For the radiomic signature, the AUC values of high-grade disease were 0.836 in the training cohort, 0.811 in external validation cohort 1, and 0.822 in external validation cohort 2. The CA19–9 level and main pancreatic duct size were identified as independent parameters of high-grade of BD-IPMNs using multivariate logistic regression analysis. The CA19–9 level and main pancreatic duct size were then used to construct the radiomic nomogram. Using the radiomic nomogram, the high-grade disease-associated AUC values were 0.903 (training cohort), 0.884 (external validation cohort 1), and 0.876 (external validation cohort 2). The clinical utility of the developed nomogram was verified using the calibration curve and DCA. Conclusions The developed radiomic nomogram model could effectively distinguish high-grade patients with BD-IPMNs preoperatively. This preoperative identification might improve treatment methods and promote personalized therapy in patients with BD-IPMNs.

scholarly journals Development and Validation of Nomogram to Preoperatively Predict Intraoperative Cerebrospinal Fluid Leakage in Endoscopic Pituitary Surgery: A Retrospective Cohort Study

2021 ◽  
Vol 11 ◽  
Author(s):  
Xiangming Cai ◽  
Junhao Zhu ◽  
Jin Yang ◽  
Chao Tang ◽  
Feng Yuan ◽  
...  
Keyword(s):  
Risk Factors ◽  
Cerebrospinal Fluid ◽  
Prediction Model ◽  
Calibration Curve ◽  
Validation Cohort ◽  
Laboratory Data ◽  
Pituitary Surgery ◽  
Cerebrospinal Fluid Leakage ◽  
Training Cohort ◽  
Preoperative Prediction

BackgroundPituitary adenomas (PAs) are the most common tumor of the sellar region. PA resection is the preferred treatment for patients with clear indications for surgery. Intraoperative cerebrospinal fluid (iCSF) leakage is a major complication of PA resection surgery. Risk factors for iCSF leakage have been studied previously, but a predictive nomogram has not yet been developed. We constructed a nomogram for preoperative prediction of iCSF leakage in endoscopic pituitary surgery.MethodsA total of 232 patients who underwent endoscopic PA resection at the Department of Neurosurgery in Jinling Hospital between January of 2018 and October of 2020 were enrolled in this retrospective study. Patients treated by a board-certified neurosurgeon were randomly classified into a training cohort or a validation cohort 1. Patients treated by other qualified neurosurgeons were included in validation cohort 2. A range of demographic, clinical, radiological, and laboratory data were acquired from the medical records. The Least Absolute Shrinkage and Selection Operator (LASSO) algorithm and uni- and multivariate logistic regression were utilized to analyze these features and develop a nomogram model. We used a receiver operating characteristic (ROC) curve and calibration curve to evaluate the predictive performance of the nomogram model.ResultsVariables were comparable between the training cohort and validation cohort 1. Tumor height and albumin were included in the final prediction model. The area under the curve (AUC) of the nomogram model was 0.733, 0.643, and 0.644 in training, validation 1, and validation 2 cohorts, respectively. The calibration curve showed satisfactory homogeneity between the predicted probability and actual observations. Nomogram performance was stable in the subgroup analysis.ConclusionsTumor height and albumin were the independent risk factors for iCSF leakage. The prediction model developed in this study is the first nomogram developed as a practical and effective tool to facilitate the preoperative prediction of iCSF leakage in endoscopic pituitary surgery, thus optimizing treatment decisions.

Prognostic Nomogram Incorporating Immunohistochemical Results for the Overall Survival of Patients with Bladder Cancer.

2020 ◽  
Author(s):  
Tianwei Wang ◽  
Yunyan Wang
Keyword(s):  
Risk Factors ◽  
Overall Survival ◽  
Bladder Cancer ◽  
Risk Model ◽  
Cox Regression ◽  
Validation Cohort ◽  
Multivariable Analysis ◽  
Clinical Information ◽  
Internal Validation ◽  
Cox Regression Analysis

Abstract Objectives: In this study, we want to combine GATA3, VEGF, EGFR and Ki67 with clinical information to develop and validate a prognostic nomogram for bladder cancer.Methods: A total of 188 patients with clinical information and immunohistochemistry were enrolled in this study, from 1996 to 2018. Univariable and multivariable cox regression analysis was applied to identify risk factors for nomogram of overall survival (OS). The calibration of the nomogram was performed and the Area Under Curve (AUC) was calculated to assess the performance of the nomogram. Internal validation was performed with the validation cohort., the calibration curve and the AUC were calculated simultaneously.Results: Univariable and multivariable analysis showed that age (HR: 2.229; 95% CI: 1.162-4.274; P=0.016), histology (HR: 0.320; 95% CI: 0.136-0.751; P=0.009), GATA3 (HR: 0.348; 95% CI: 0.171-0.709; P=0.004), VEGF (HR: 2.295; 95% CI: 1.225-4.301; P=0.010) and grade (HR: 4.938; 95% CI: 1.339-18.207; P=0.016) remained as independent risk factors for OS. The age, histology, grade, GATA3 and VEGF were included to build the nomogram. The accuracy of the risk model was further verified with the C-index. The C-index were 0.65 (95% CI, 0.58-0.72) and 0.58 (95% CI, 0.46-0.70) in the training and validation cohort respectively. Conclusions: A combination of clinical variables with immunohistochemical results based nomogram would predict the overall survival of patients with bladder cancer.

scholarly journals Machine Learning Based on a Multiparametric and Multiregional Radiomics Signature Predicts Radiotherapeutic Response in Patients with Glioblastoma

2020 ◽  
Vol 2020 ◽  
pp. 1-12
Author(s):  
Zi-Qi Pan ◽  
Shu-Jun Zhang ◽  
Xiang-Lian Wang ◽  
Yu-Xin Jiao ◽  
Jian-Jian Qiu
Keyword(s):  
Machine Learning ◽  
Risk Factors ◽  
Cox Regression ◽  
Clinical Risk Factors ◽  
Cox Regression Analysis ◽  
Clinical Risk ◽  
Independent Test ◽  
Independent Test Dataset ◽  
Multiple Regions ◽  
Radiomics Signature

Background and Objective. Although radiotherapy has become one of the main treatment methods for cancer, there is no noninvasive method to predict the radiotherapeutic response of individual glioblastoma (GBM) patients before surgery. The purpose of this study is to develop and validate a machine learning-based radiomics signature to predict the radiotherapeutic response of GBM patients. Methods. The MRI images, genetic data, and clinical data of 152 patients with GBM were analyzed. 122 patients from the TCIA dataset (training set: n = 82 ; validation set: n = 40 ) and 30 patients from local hospitals were used as an independent test dataset. Radiomics features were extracted from multiple regions of multiparameter MRI. Kaplan-Meier survival analysis was used to verify the ability of the imaging signature to predict the response of GBM patients to radiotherapy before an operation. Multivariate Cox regression including radiomics signature and preoperative clinical risk factors was used to further improve the ability to predict the overall survival (OS) of individual GBM patients, which was presented in the form of a nomogram. Results. The radiomics signature was built by eight selected features. The C -index of the radiomics signature in the TCIA and independent test cohorts was 0.703 ( P < 0.001 ) and 0.757 ( P = 0.001 ), respectively. Multivariate Cox regression analysis confirmed that the radiomics signature (HR: 0.290, P < 0.001 ), age (HR: 1.023, P = 0.01 ), and KPS (HR: 0.968, P < 0.001 ) were independent risk factors for OS in GBM patients before surgery. When the radiomics signature and preoperative clinical risk factors were combined, the radiomics nomogram further improved the performance of OS prediction in individual patients ( C ‐ index = 0.764 and 0.758 in the TCIA and test cohorts, respectively). Conclusion. This study developed a radiomics signature that can predict the response of individual GBM patients to radiotherapy and may be a new supplement for precise GBM radiotherapy.

Sign in / Sign up

Export Citation Format

Share Document