Dataset Information

Prediction of tumor response via a pretreatment MRI radiomics-based nomogram in HCC treated with TACE.

ABSTRACT:

Objectives

To develop and validate a pre-transcatheter arterial chemoembolization (TACE) MRI-based radiomics model for predicting tumor response in intermediate-advanced hepatocellular carcinoma (HCC) patients.

Materials

Ninety-nine intermediate-advanced HCC patients (69 for training, 30 for validation) treated with TACE were enrolled. MRI examinations were performed before TACE, and the efficacy was evaluated according to the mRECIST criterion 3 months after TACE. A total of 396 radiomics features were extracted from T2-weighted pre-TACE images, and least absolute shrinkage and selection operator (LASSO) regression was applied to feature selection and model construction. The performance of the model was evaluated by receiver operating characteristic (ROC) curves, calibration curves, and decision curves.

Results

The AFP value, Child-Pugh score, and BCLC stage showed a significant difference between the TACE response (TR) and non-TACE response (nTR) patients. Six radiomics features were selected by LASSO and the radiomics score (Rad-score) was calculated as the sum of each feature multiplied by the non-zero coefficient from LASSO. The AUCs of the ROC curve based on Rad-score were 0.812 and 0.866 in the training and validation cohorts, respectively. To improve the diagnostic efficiency, the Rad-score was further integrated with the above clinical indicators to form a novel predictive nomogram. Results suggested that the AUC increased to 0.861 and 0.884 in the training and validation cohorts, respectively. Decision curve analysis showed that the radiomics nomogram was clinically useful.

Conclusion

The radiomics and clinical indicator-based predictive nomogram can well predict TR in intermediate-advanced HCC and can further be applied for auxiliary diagnosis of clinical prognosis.

Key points

• The therapeutic outcome of TACE varies greatly even for patients with the same clinicopathologic features. • Radiomics showed excellent performance in predicting the TACE response. • Decision curves demonstrated that the novel predictive model based on the radiomics signature and clinical indicators has great clinical utility.

SUBMITTER: Kong C

PROVIDER: S-EPMC8452577 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Background and purpose: Adaptive radiotherapy (ART) can compensate for the dosimetric impacts induced by anatomic and geometric variations in patients with nasopharyngeal carcinoma (NPC); Yet, the need for ART can only be assessed during the radiation treatment and the implementation of ART is resource intensive. Therefore, we aimed to determine tumoral biomarkers using pre-treatment MR images for predicting ART eligibility in NPC patients prior to the start of treatment. Methods: Seventy patients with biopsy-proven NPC (Stage II-IVB) in 2015 were enrolled into this retrospective study. Pre-treatment contrast-enhanced T1-w (CET1-w), T2-w MR images were processed and filtered using Laplacian of Gaussian (LoG) filter before radiomic features extraction. A total of 479 radiomics features, including the first-order (n = 90), shape (n = 14), and texture features (n = 375), were initially extracted from Gross-Tumor-Volume of primary tumor (GTVnp) using CET1-w, T2-w MR images. Patients were randomly divided into a training set (n = 51) and testing set (n = 19). The least absolute shrinkage and selection operator (LASSO) logistic regression model was applied for radiomic model construction in training set to select the most predictive features to predict patients who were replanned and assessed in the testing set. A double cross-validation approach of 100 resampled iterations with 3-fold nested cross-validation was employed in LASSO during model construction. The predictive performance of each model was evaluated using the area under the receiver operator characteristic (ROC) curve (AUC). Results: In the present cohort, 13 of 70 patients (18.6%) underwent ART. Average AUCs in training and testing sets were 0.962 (95%CI: 0.961-0.963) and 0.852 (95%CI: 0.847-0.857) with 8 selected features for CET1-w model; 0.895 (95%CI: 0.893-0.896) and 0.750 (95%CI: 0.745-0.755) with 6 selected features for T2-w model; and 0.984 (95%CI: 0.983-0.984) and 0.930 (95%CI: 0.928-0.933) with 6 selected features for joint T1-T2 model, respectively. In general, the joint T1-T2 model outperformed either CET1-w or T2-w model alone. Conclusions: Our study successfully showed promising capability of MRI-based radiomics features for pre-treatment identification of ART eligibility in NPC patients.

Project description:BackgroundWe aimed to evaluate the value of using preoperative magnetic resonance imaging (MRI) features and clinical indicators to predict the early response of hepatocellular carcinoma (HCC) to transcatheter arterial chemoembolization (TACE). We also aimed to establish a preoperative prediction model.MethodsWe retrospectively reviewed data of 111 patients with HCC who underwent magnetic resonance imaging (MRI) before the first TACE and underwent MRI or computed tomography between 30 and 60 days after TACE. We used the modified response evaluation criteria in solid tumors for evaluating the TACE response. We used univariate and multivariate logistic regression analyses to identify independent predictors based on MRI features and clinical indicators. Moreover, receiver operating characteristic (ROC) curve analyses were performed to assess the diagnostic performance of the prediction model and each independent predictor.ResultsAmong the 111 included patients, 85 were men (76.6%). Patient age was 31-86 years (average age, 61.08 ± 11.50 years). After the first treatment session, 56/111 (50.5%) patients showed an objective response (complete response + partial response), whereas the remaining showed non-response (stable disease + local progressive disease). In the univariate analysis, we identified irregular margins, number of nodules, and satellite nodules as predictors of early objective response. However, in the multivariate logistic regression analysis, irregular margins, number of nodules and pretreatment platelet were identified as the independent predictors of early objective response. A combined prediction model was then established, which factored in irregular margins, the number of nodules, and the pretreatment platelet count. This model showed good diagnostic performance (area under the ROC curve = 0.755), with the sensitivity, specificity, positive predictive value, and negative predictive value being 78.6%, 69.1%, 72.1%, and 76.0%, respectively.ConclusionsIrregular margins, the number of nodules and the pretreatment platelet count are independent predictors of the early response of HCC to TACE. Our clinical combined model can provide a superior predictive power to a single indicator.