Applying arterial enhancement fraction (AEF) texture features to predict the tumor response in hepatocellular carcinoma (HCC) treated with Transarterial chemoembolization (TACE)

18F-FDG PET/CT-Based Radiomics Nomogram for Prediction of Bone Marrow Involvement in Pediatric Neuroblastoma: A Two-Center Study

RATIONALE AND OBJECTIVES

To assess the predictive ability of an 18F-FDG PET/CT-based radiomics nomogram for bone marrow involvement in pediatric neuroblastoma.

MATERIALS AND METHODS

A total of 241 neuroblastoma patients who underwent 18F-FDG PET/CT at two medical centers were retrospectively evaluated. Data from center A (n = 200) were randomized into a training cohort (n = 140) and an internal validation cohort (n = 60), while data from center B (n = 41) constituted the external validation cohort. For each patient, two regions of interest were defined using the tumor and axial skeleton. The clinical factors and radiomics features were derived to construct the clinical and radiomics models. The radiomics nomogram was built by combining clinical factors and radiomics features. The area under the receiver operating characteristic curves (AUCs) were used to assess the performance of the models.

RESULTS

Radiomics models created from tumor and axial skeleton achieved AUCs of 0.773 and 0.900, and the clinical model had an AUC of 0.858 in the training cohort. By incorporating clinical risk factors and axial skeleton-based radiomics features, the AUC of the radiomics nomogram in the training cohort, internal validation cohort, and external validation cohort was 0.932, 0.887, and 0.733, respectively.

CONCLUSION

The axial skeleton-based radiomics model performed better than the tumor-based radiomics model in predicting bone marrow involvement. Moreover, the radiomics nomogram showed that combining axial skeleton-based radiomics features with clinical risk factors improved their performance.

Radiomics features of computed tomography and magnetic resonance imaging for predicting response to transarterial chemoembolization in hepatocellular carcinoma: a meta-analysis

Purpose

To examine the methodological quality of radiomics-related studies and evaluate the ability of radiomics to predict treatment response to transarterial chemoembolization (TACE) for hepatocellular carcinoma (HCC).

Methods

A systematic review was performed on radiomics-related studies published until October 15, 2022, predicting the effectiveness of TACE for HCC. Methodological quality and risk of bias were assessed using the Radiomics Quality Score (RQS) and Quality Assessment of Diagnostic Accuracy Studies-2 tools, respectively. Pooled sensitivity, pooled specificity, and area under the curve (AUC) were determined to evaluate the utility of radiomics in predicting the response to TACE for HCC.

Results

In this systematic review, ten studies were eligible, and six of these studies were used in our meta-analysis. The RQS ranged from 7-21 (maximum possible score: 36). The pooled sensitivity and specificity were 0.89 (95% confidence interval (CI) = 0.79-0.95) and 0.82 (95% CI = 0.64-0.92), respectively. The overall AUC was 0.93 (95% CI = 0.90-0.95).

Conclusion

Radiomics-related studies evaluating the efficacy of TACE in patients with HCC revealed promising results. However, prospective and multicenter trials are warranted to make radiomics more feasible and acceptable.

A novel method for predicting hepatocellular carcinoma response to chemoembolization using an intraprocedural CT hepatic arteriography-based enhancement mapping: a proof-of-concept analysis

BACKGROUND

To evaluate the feasibility of a novel approach for predicting hepatocellular carcinoma (HCC) response to drug-eluting beads transarterial chemoembolization (DEB-TACE) using computed tomography hepatic arteriography enhancement mapping (CTHA-EM) method.

METHODS

This three-institution retrospective study included 29 patients with 46 HCCs treated with DEB-TACE between 2017 and 2020. Pre- and posttreatment CTHA-EM images were generated using a prototype deformable registration and subtraction software. Relative tumor enhancement (T_Post/pre-RE) defined as the ratio of tumor enhancement to normal liver tissue was calculated to categorize tumor response as residual (T_Post-RE > 1) versus non-residual (T_Post-RE ≤ 1) enhancement, which was blinded compared to the response assessment on first follow-up imaging using modified RECIST criteria. Additionally, for tumors with residual enhancement, CTHA-EM was evaluated to identify its potential feeding arteries.

RESULTS

CTHA-EM showed residual enhancement in 18/46 (39.1%) and non-residual enhancement in 28/46 (60.9%) HCCs, with significant differences on T_Post-RE (3.05 ± 2.4 versus 0.48 ± 0.23, respectively; p < 0.001). The first follow-up imaging showed non-complete response (partial response or stable disease) in 19/46 (41.3%) and complete response in 27/46 (58.7%) HCCs. CTHA-EM had a response prediction sensitivity of 94.7% (95% CI, 74.0-99.9) and specificity of 100% (95% CI, 87.2-100). Feeding arteries to the residual enhancement areas were demonstrated in all 18 HCCs (20 arteries where DEB-TACE was delivered, 2 newly developed collaterals following DEB-TACE).

CONCLUSION

CTHA-EM method was highly accurate in predicting initial HCC response to DEB-TACE and identifying feeding arteries to the areas of residual arterial enhancement.

Diagnostic Value of 18F-FDG PET/CT-Based Radiomics Nomogram in Bone Marrow Involvement of Pediatric Neuroblastoma

OBJECTIVES

To develop and validate an ¹⁸F-FDG PET/CT-based radiomics nomogram and evaluate the value of the ¹⁸F-FDG PET/CT-based radiomics nomogram for the diagnosis of bone marrow involvement (BMI) in pediatric neuroblastoma.

MATERIALS AND METHODS

A total of 144 patients with neuroblastoma (100 in the training cohort and 44 in the validation cohort) were retrospectively included. The PET/CT images of patients were visually assessed. The results of bone marrow aspirates or biopsies were used as the gold standard for BMI. Radiomics features and conventional PET parameters were extracted using the 3D slicer. Features were selected by the least absolute shrinkage and selection operator regression, and radiomics signature was constructed. Univariate and multivariate logistic regression analyses were applied to identify the independent clinical risk factors and construct the clinical model. Other different models, including the conventional PET model, combined PET-clinical model and combined radiomics model, were built using logistic regression. The combined radiomics model was based on clinical factors, conventional PET parameters and radiomics signature, which was presented as a radiomics nomogram. The diagnostic performance of the different models was evaluated by receiver operating characteristic (ROC) curves and decision curve analysis (DCA).

RESULTS

By visual assessment, BMI was observed in 80 patients. Four conventional PET parameters (SUVmax, SUVmean, metabolic tumor volume, and total lesion glycolysis) were extracted. And 15 radiomics features were selected to build the radiomics signature. The 11q aberration, neuron-specific enolase and vanillylmandelic acid were identified as the independent clinical risk factors to establish the clinical model. The radiomics nomogram incorporating the radiomics signature, the independent clinical risk factors and SUVmean demonstrated the best diagnostic value for identifying BMI, with an area under the curve (AUC) of 0.963 and 0.931 in the training and validation cohorts, respectively. And the DCA demonstrated that the radiomics nomogram was clinically useful.

CONCLUSION

The ¹⁸F-FDG PET/CT-based radiomics nomogram which incorporates radiomics signature, independent clinical risk factors and conventional PET parameters could improve the diagnostic performance for BMI of pediatric neuroblastoma without additional medical costs and radiation exposure.

Arterial enhancement fraction in evaluating the therapeutic effect and survival for hepatocellular carcinoma patients treated with DEB-TACE

BACKGROUND

Arterial enhancement fraction (AEF), derived from triphasic CT scans, is considered to indirectly reflect the ratio of hepatic arterial perfusion to total perfusion. The purpose of this study was to retrospectively investigate the relationship between AEF and treatment response and survival in hepatocellular carcinoma (HCC) patients treated with drug-eluting bead (DEB) TACE.

METHODS

AEF of primary lesion (AEF_pre) and residual tumor (AEF_post) in 158 HCC patients were obtained from triphasic liver CT examinations pre- and post-treatment. Wilcoxon-signed rank test was used to compare the AEF_pre and AEF_post for different response groups. Survival curves for overall survival (OS) in patients with different AEF were created by using Kaplan-Meier method. Cox regression analyses were used to determine the association between AEF and OS.

RESULTS

There was no correlation between AEF_pre and treatment response. After DEB-TACE, AEF_post was significantly lower than AEF_pre either in the partial response group (38.9% vs. 52.7%, p <  0.001) or in the stable disease group (49.3% vs. 52.1%, p = 0.029). In the progression disease group, AEF_post was numerically higher than AEF_pre (55.5% vs. 53.0%, p = 0.604). Cox regression analyses showed that risk of death increased in patients with AEF_pre > 57.95% (HR = 1.66, p = 0.019) or AEF_post > 54.85% (HR = 2.47, p <  0.001), and the risk reduced in patients with any reduction in tumor AEF (decrease ratio ≥ 0) and with increased AEF but not exceeding the ratio of 0.102 (increase ratio <  0.102) (HR = 0.32, p <  0.001).

CONCLUSIONS

The change in AEF of viable tumor is correlated with response of HCC to DEB-TACE. In addition, the AEF could be a helpful predictor in future studies on the embolization treatment for HCC.