Clinical-radiomics predictors to identify the suitability of transarterial chemoembolization treatment in intermediate-stage hepatocellular carcinoma: A multicenter study

Radiomics as a tool for prognostic prediction in transarterial chemoembolization for hepatocellular carcinoma: a systematic review and meta-analysis

INTRODUCTION

Transarterial chemoembolization (TACE) is one of the predominant locoregional therapeutic modalities for addressing hepatocellular carcinoma (HCC). However, achieving precise prognostic predictions and effective patient selection remains a challenging pursuit. The primary objective of this systematic review and meta-analysis is to evaluate the efficacy of radiomics in forecasting the prognosis associated with TACE treatment.

METHODS

A comprehensive exploration of pertinent original studies was undertaken, encompassing databases of PubMed, Web of Science and Embase. The studies' quality was meticulously evaluated employing the quality assessment of diagnostic accuracy studies 2 (QUADAS-2), the radiomics quality score (RQS) and the METhodological RadiomICs Score (METRICS). Pooled statistics, along with 95% confidence intervals (95% CI), were computed for sensitivity, specificity, positive likelihood ratio (PLR), and negative likelihood ratio (NLR). Additionally, a summary receiver operating characteristic curve (sROC) was generated. To discern potential sources of heterogeneity, meta-regression and subgroup analyses were performed.

RESULTS

The systematic review incorporated 29 studies, comprising a total of 5483 patients, with 14 studies involving 2691 patients qualifying for inclusion in the meta-analysis. The assessed studies exhibited commendable quality with regard to bias risk, with mean RQS of 12.90 ± 5.13 (35.82% ± 14.25%) and mean METRICS of 62.98% ± 14.58%. The pooled sensitivity was 0.83 (95% CI: 0.78-0.87), specificity was 0.86 (95% CI: 0.79-0.92), PLR was 6.13 (95% CI: 3.79-9.90), and NLR was 0.20 (95% CI: 0.15-0.27). The area under the sROC was 0.90 (95% CI: 0.87-0.93). Significant heterogeneity within all the included studies was observed, while meta-regression and subgroup analyses revealed homogeneous and promising findings in subgroups where principal methodological variables such as modeling algorithms, imaging modalities, and imaging phases were specified.

CONCLUSION

Radiomics models have exhibited robust predictive capabilities concerning prognosis subsequent to TACE, thereby presenting promising prospects for clinical translation.

Conversion therapy for advanced hepatocellular carcinoma in the era of precision medicine: Current status, challenges and opportunities

Hepatocellular carcinoma (HCC), the most prevalent malignancy of the digestive tract, is characterized by a high mortality rate and poor prognosis, primarily due to its initial diagnosis at an advanced stage that precludes any surgical intervention. Recent advancements in systemic therapies have significantly improved oncological outcomes for intermediate and advanced-stage HCC, and the combination of locoregional and systemic therapies further facilitates tumor downstaging and increases the likelihood of surgical resectability for initially unresectable cases following conversion therapies. This shift toward high conversion rates with novel, multimodal treatment approaches has become a principal pathway for prolonged survival in patients with advanced HCC. However, the field of conversion therapy for HCC is marked by controversies, including the selection of potential surgical candidates, formulation of conversion therapy regimens, determination of optimal surgical timing, and application of adjuvant therapy post-surgery. Addressing these challenges and refining clinical protocols and research in HCC conversion therapy is essential for setting the groundwork for future advancements in treatment strategies and clinical research. This narrative review comprehensively summarizes the current strategies and clinical experiences in conversion therapy for advanced-stage HCC, emphasizing the unresolved issues and the path forward in the context of precision medicine. This work not only provides a comprehensive overview of the evolving landscape of treatment modalities for conversion therapy but also paves the way for future studies and innovations in this field.

Machine Learning Combined with Radiomics Facilitating the Personal Treatment of Malignant Liver Tumors

In the realm of managing malignant liver tumors, the convergence of radiomics and machine learning has redefined the landscape of medical practice. The field of radiomics employs advanced algorithms to extract thousands of quantitative features (including intensity, texture, and structure) from medical images. Machine learning, including its subset deep learning, aids in the comprehensive analysis and integration of these features from diverse image sources. This potent synergy enables the prediction of responses of malignant liver tumors to various treatments and outcomes. In this comprehensive review, we examine the evolution of the field of radiomics and its procedural framework. Furthermore, the applications of radiomics combined with machine learning in the context of personalized treatment for malignant liver tumors are outlined in aspects of surgical therapy and non-surgical treatments such as ablation, transarterial chemoembolization, radiotherapy, and systemic therapies. Finally, we discuss the current challenges in the amalgamation of radiomics and machine learning in the study of malignant liver tumors and explore future opportunities.