Radiomics analysis of pretreatment MRI in predicting tumor response and outcome in hepatocellular carcinoma with transarterial chemoembolization: a two-center collaborative 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.

The conditional recurrence-free survival after R0 hepatectomy for locally advanced intrahepatic cholangiocarcinoma: A competing risk analysis based on inflammation-nutritional status

Background

Conditional survival analysis can serve as a dynamic prognostic metric, which helps to estimate the real-time survival probability over time. The present study conducted a conditional recurrence-free survival (CRFS) analysis for locally advanced intrahepatic cholangiocarcinoma (ICC) after R0 hepatectomy from an inflammatory-nutritional perspective using the competing risk method.

Methods

We extracted the medical data of 164 locally advanced ICC patients after R0 resection from Sun Yat-sen University Cancer Center. The calculation formula of the CRFS rate is CRFS(y/x) = RFS(y + x)/RFS(x). Univariable and multivariable COX regression analysis and competing risk analysis were conducted to identify RFS indicators.

Results

Considering death before recurrence as a competing risk factor, the conditional RFS rates every 6 months gradually increased over time. The 24-month RFS rate increased from 29.2 % to 49.9 %, 68.5 %, and 85.1 % given 6, 12, and 18-month already recurrence-free survival, respectively. Both in multivariate COX regression analysis and competing risk analysis, tumor diameter and number, lymph node metastasis, aggregate systemic inflammation index score (AISI), and albumin-bilirubin score (ALBI) all remained significant. For both AISI and ALBI variables, the CRFS rates in the low-value set were higher than those of the high-value set.

Conclusions

Conditional RFS rates of locally advanced ICC after R0 hepatectomy dynamically increased over time, which contributed to reducing survivors' psychological distress and facilitating personalized follow-up schedules. In addition, a person's inflammatory and nutritional status significantly impact the recurrence risk. Oncologists should consider the role of inflammation-nutritional status when making decisions for patients with locally advanced ICC.

Predicting Survival Using Whole-Liver MRI Radiomics in Patients with Hepatocellular Carcinoma After TACE Refractoriness

PURPOSE

To develop a model based on whole-liver radiomics features of pre-treatment enhanced MRI for predicting the prognosis of hepatocellular carcinoma (HCC) patients undergoing continued transarterial chemoembolization (TACE) after TACE-resistance.

MATERIALS AND METHODS

Data from 111 TACE-resistant HCC patients between January 2014 and March 2018 were retrospectively collected. At a ratio of 7:3, patients were randomly assigned to developing and validation cohorts. The whole-liver were manually segmented, and the radiomics signature was extracted. The tumor and liver radiomics score (TLrad-score) was calculated. Models were trained by machine learning algorithms and their predictive efficacies were compared.

RESULTS

Tumor stage, tumor burden, body mass index, alpha-fetoprotein, and vascular invasion were revealed as independent risk factors for survival. The model trained by Random Forest algorithms based on tumor burden, whole-liver radiomics signature, and clinical features had the highest predictive efficacy, with c-index values of 0.85 and 0.80 and areas under the ROC curve of 0.96 and 0.83 in the developing cohort and validation cohort, respectively. In the high-rad-score group (TLrad-score > - 0.34), the median overall survival (mOS) was significantly shorter than in the low-rad-score group (17 m vs. 37 m, p < 0.001). A shorter mOS was observed in patients with high tumor burden compared to those with low tumor burden (14 m vs. 29 m, p = 0.007).

CONCLUSION

The combined radiomics model from whole-liver signatures may effectively predict survival for HCC patients continuing TACE after TACE refractoriness. The TLrad-score and tumor burden are potential prognostic markers for TACE therapy following TACE-resistance.

Radiomics analysis based on contrast-enhanced MRI for predicting short-term efficacy of drug-eluting beads transarterial chemoembolization in hepatocellular carcinoma

OBJECTIVE

We developed and validated a clinical-radiomics model for preoperative prediction of the short-term efficacy of initial drug-eluting beads transarterial chemoembolization (D-TACE) treatment in patients with hepatocellular carcinoma (HCC).

METHODS

In this retrospective cohort study of 113 patients with intermediate and advanced HCC, 5343 features were extracted based on three sequences of the arterial phase (AP), diffusion-weighted imaging, and T2-weighted images based on contrast-enhanced magnetic resonance imaging, and minimum redundancy maximum correlation and least absolute shrinkage and selection operator (LASSO) regression were applied for feature selection and model construction. Multifactor logistic regression was used to build a clinical-imaging model based on clinical factors and a clinical-radiomics model. The area under the curve (AUC) and calibration curves were used to assess model performance, and the clinical value of the model was analyzed using decision curve analysis. The relationship between the actual and predicted short-term efficacy of the combined model and progression-free survival (PFS) was evaluated using Kaplan-Meier survival curves and log-rank tests.

RESULTS

A total of 34 radiomics features were selected by LASSO, and the clinical-radiomics model had the best predictive performance (AUC = 0.902 and AUC = 0.845 for the training and testing sets, respectively), and the model based on AP had the best predictive performance among the four radiomics models (AUC = 0.89 for the training set and AUC = 0.85 for the testing set); the multifactorial logistic regression results showed that microsphere type (p = 0.042) and AP Rad-score (p = 0.01) were associated with short-term efficacy. In addition, a difference in PFS was observed in patients with HCC with different short-term efficacies predicted by the combined model. Moreover, prognosis was better in the objective versus non-objective response group.

CONCLUSIONS

The combined clinical-radiomics model is an effective predictor of the short-term efficacy of initial D-TACE in patients with HCC, contributing to clinical and economic benefits for patients.

Ethiodized oil as an imaging biomarker after conventional transarterial chemoembolization

Conventional transarterial chemoembolization (cTACE) utilizing ethiodized oil as a chemotherapy carrier has become a standard treatment for intermediate-stage hepatocellular carcinoma (HCC) and has been adopted as a bridging and downstaging therapy for liver transplantation. Water-in-oil emulsion made up of ethiodized oil and chemotherapy solution is retained in tumor vasculature resulting in high tissue drug concentration and low systemic chemotherapy doses. The density and distribution pattern of ethiodized oil within the tumor on post-treatment imaging are predictive of the extent of tumor necrosis and duration of response to treatment. This review describes the multiple roles of ethiodized oil, particularly in its role as a biomarker of tumor response to cTACE. CLINICAL RELEVANCE: With the increasing complexity of locoregional therapy options, including the use of combination therapies, treatment response assessment has become challenging; Ethiodized oil deposition patterns can serve as an imaging biomarker for the prediction of treatment response, and perhaps predict post-treatment prognosis. KEY POINTS: • Treatment response assessment after locoregional therapy to hepatocellular carcinoma is fraught with multiple challenges given the varied post-treatment imaging appearance. • Ethiodized oil is unique in that its' radiopacity can serve as an imaging biomarker to help predict treatment response. • The pattern of deposition of ethiodozed oil has served as a mechanism to detect portions of tumor that are undertreated and can serve as an adjunct to enhancement in order to improve management in patients treated with intraarterial embolization with ethiodized oil.

Prognostic nomogram model for selecting between transarterial chemoembolization plus lenvatinib, with and without PD-1 inhibitor in unresectable hepatocellular carcinoma

OBJECTIVES

To establish and verify a prognostic nomogram model for selecting in unresectable hepatocellular carcinoma (uHCC) treated by transarterial chemoembolization plus lenvatinib (TACE-L) with or without PD-1 inhibitor.

METHODS

Data of 241 uHCC patients who underwent TACE-L (n = 128) and TACE-L plus PD-1 inhibitor (TACE-L-P, n = 113) were retrospectively reviewed. The differences in tumour responses, progression-free survival (PFS), overall survival (OS), and adverse events (AEs) between two groups were compared, and a prognostic nomogram model was established based on independent clinical-radiologic factors and confirmed by Cox regression analysis for predicting PFS and OS. The treatment selection for uHCC patients was stratified by the nomogram score.

RESULTS

Compared to TACE-L, TACE-L-P presented prolonged PFS (14.0 vs. 9.0 months, P < .001), longer OS (24.0 vs. 15.0 months, P < .001), and a better overall objective response rate (54.0% vs. 32.8%, P = .001). There was no significant difference between the rate of AEs in the TACE-L-P and the TACE-L (56.64% vs. 46.09%, P = .102) and the rate of grade ≥ 3 AEs (11.50% vs. 9.38%, P = .588), respectively. The nomogram model presented good discrimination, with a C-index of 0.790 for predicting PFS and 0.749 for predicting OS. Patients who underwent TACE-L and obtained a nomogram score >9 demonstrated improved 2-year PFS when transferred to TACE-L-P, and those with a nomogram ≤25 had better 2-year OS when transferred to TACE-L-P.

CONCLUSIONS

TACE-L-P showed significant improvements in efficiency and safety for uHCC patients compared with TACE-L. The nomogram was useful for stratifying treatment decisions and selecting a suitable population for uHCC patients.

ADVANCES IN KNOWLEDGE

Prognostic nomogram model is of great value in predicting individualized survival benefits for uHCC patients after TACE-L or/and TACE-L-P. And the nomogram was helpful for selection between TACE-L-P and TACE-L among uHCC patients.

The Role of Artificial Intelligence and Texture Analysis in Interventional Radiological Treatments of Liver Masses: A Narrative Review

Liver lesions, including both benign and malignant tumors, pose significant challenges in interventional radiological treatment planning and prognostication. The emerging field of artificial intelligence (AI) and its integration with texture analysis techniques have shown promising potential in predicting treatment outcomes, enhancing precision, and aiding clinical decision-making. This comprehensive review aims to summarize the current state-of-the-art research on the application of AI and texture analysis in determining treatment response, recurrence rates, and overall survival outcomes for patients undergoing interventional radiological treatment for liver lesions. Furthermore, the review addresses the challenges associated with the implementation of AI and texture analysis in clinical practice, including data acquisition, standardization of imaging protocols, and model validation. Future directions and potential advancements in this field are discussed. Integration of multi-modal imaging data, incorporation of genomics and clinical data, and the development of predictive models with enhanced interpretability are proposed as potential avenues for further research. In conclusion, the application of AI and texture analysis in predicting outcomes of interventional radiological treatment for liver lesions shows great promise in augmenting clinical decision-making and improving patient care. By leveraging these technologies, clinicians can potentially enhance treatment planning, optimize intervention strategies, and ultimately improve patient outcomes in the management of liver lesions.

Radiomics in CT and MR imaging of the liver and pancreas: tools with potential for clinical application

Radiomics allows the extraction of quantitative imaging features from clinical magnetic resonance imaging (MRI) and computerized tomography (CT) studies. The advantages of radiomics have primarily been exploited in oncological applications, including better characterization and staging of oncological lesions and prediction of patient outcomes and treatment response. The potential introduction of radiomics in the clinical setting requires the establishment of a standardized radiomics pipeline and a quality assurance program. Radiomics and texture analysis of the liver have improved the differentiation of hypervascular lesions such as adenomas, focal nodular hyperplasia, and hepatocellular carcinoma (HCC) during the arterial phase, and in the pretreatment determination of HCC prognostic factors (e.g., tumor grade, microvascular invasion, Ki-67 proliferation index). Radiomics of pancreatic CT and MR images has enhanced pancreatic ductal adenocarcinoma detection and its differentiation from pancreatic neuroendocrine tumors, mass-forming chronic pancreatitis, or autoimmune pancreatitis. Radiomics can further help to better characterize incidental pancreatic cystic lesions, accurately discriminating benign from malignant intrapancreatic mucinous neoplasms. Nonetheless, despite their encouraging results and exciting potential, these tools have yet to be implemented in the clinical setting. This non-systematic review will describe the essential steps in the implementation of the radiomics and feature extraction workflow from liver and pancreas CT and MRI studies for their potential clinical application. A succinct overview of reported radiomics applications in the liver and pancreas and the challenges and limitations of their implementation in the clinical setting is also discussed, concluding with a brief exploration of the future perspectives of radiomics in the gastroenterology 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.

CT-based radiomics nomogram for prediction of survival after transarterial chemoembolization with drug-eluting beads in patients with hepatocellular carcinoma and portal vein tumor thrombus

OBJECTIVES

To develop and validate a CT-based radiomics model for the prediction of the overall survival (OS) of patients with hepatocellular carcinoma (HCC) and portal vein tumor thrombus (PVTT) treated with drug-eluting beads transarterial chemoembolization (DEB-TACE).

METHODS

Patients were retrospectively enrolled from two institutions for the constitution of training (n = 69) and validation (n = 31) cohorts with a median follow-up of 15 months. A total of 396 radiomics features were extracted from each baseline CT image. Features selected by variable importance and minimal depth were used for random survival forest model construction. The performance of the model was assessed using the concordance index (C-index), calibration curves, integrated discrimination index (IDI), net reclassification index (NRI), and decision curve analysis.

RESULTS

Type of PVTT and tumor number were proved to be significant clinical indicators for OS. Arterial phase images were used to extract radiomics features. Three radiomics features were selected for model construction. The C-index for the radiomics model was 0.759 in the training cohort and 0.730 in the validation cohort. To improve the predictive performance, clinical indicators were integrated into the radiomics model to form a combined model with a C-index of 0.814 in the training cohort and 0.792 in the validation cohort. The IDI was significant in both cohorts for the combined model versus the radiomics model in predicting 12-month OS.

CONCLUSIONS

Type of PVTT and tumor number affected the OS of HCC patients with PVTT treated with DEB-TACE. Moreover, the combined clinical-radiomics model had a satisfactory performance.

CLINICAL RELEVANCE STATEMENT

A CT-based radiomics nomogram, which consisted of 3 radiomics features and 2 clinical indicators, was recommended to predict 12-month overall survival of patients with hepatocellular carcinoma and portal vein tumor thrombus initially treated with drug-eluting beads transarterial chemoembolization.

KEY POINTS

• Type of portal vein tumor thrombus and tumor number were significant predictors of the OS. • Integrated discrimination index and net reclassification index provided a quantitative evaluation of the incremental impact added by new indicators for the radiomics model. • A nomogram based on a radiomics signature and clinical indicators showed satisfactory performance in predicting OS after DEB-TACE.

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

BACKGROUND

Although transarterial chemoembolization (TACE) is the first-line therapy for intermediate-stage hepatocellular carcinoma (HCC), it is not suitable for all patients. This study aimed to determine how to select patients who are not suitable for TACE as the first treatment choice.

METHODS

A total of 243 intermediate-stage HCC patients treated with TACE at three centers were retrospectively enrolled, of which 171 were used for model training and 72 for testing. Radiomics features were screened using the Spearman correlation analysis and the least absolute shrinkage and selection operator (LASSO) algorithm. Subsequently, a radiomics model was established using extreme gradient boosting (XGBoost) with 5-fold cross-validation. The Shapley additive explanations (SHAP) method was used to visualize the radiomics model. A clinical model was constructed using univariate and multivariate logistic regression. The combined model comprising the radiomics signature and clinical factors was then established. This model's performance was evaluated by discrimination, calibration, and clinical application. Generalization ability was evaluated by the testing cohort. Finally, the model was used to analyze overall and progression-free survival of different groups.

RESULTS

A third of the patients (81/243) were unsuitable for TACE treatment. The combined model had a high degree of accuracy as it identified TACE-unsuitable cases, at a sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) of 0.759, 0.885, 0.906 [95% confidence interval (CI): 0.859-0.953] in the training cohort and 0.826, 0.776, and 0.894 (95% CI: 0.815-0.972) in the testing cohort, respectively.

CONCLUSIONS

The high degree of accuracy of our clinical-radiomics model makes it clinically useful in identifying intermediate-stage HCC patients who are unsuitable for TACE treatment.

Machine Learning Models in Prediction of Treatment Response After Chemoembolization with MRI Clinicoradiomics Features

PURPOSE

To evaluate machine learning models, created with radiomics and clinicoradiomics features, ability to predict local response after TACE.

MATERIALS AND METHODS

188 treatment-naïve patients (150 responders, 38 non-responders) with HCC who underwent TACE were included in this retrospective study. Laboratory, clinical and procedural information were recorded. Local response was evaluated by European Association for the Study of the Liver criteria at 3-months. Radiomics features were extracted from pretreatment pre-contrast enhanced T1 (T1WI) and late arterial-phase contrast-enhanced T1 (CE-T1) MRI images. After data augmentation, data were split into training and test sets (70/30). Intra-class correlations, Pearson's correlation coefficients were analyzed and followed by a sequential-feature-selection (SFS) algorithm for feature selection. Support-vector-machine (SVM) models were trained with radiomics and clinicoradiomics features of T1WI, CE-T1 and the combination of both datasets, respectively. Performance metrics were calculated with the test sets. Models' performances were compared with Delong's test.

RESULTS

1128 features were extracted. In feature selection, SFS algorithm selected 18, 12, 24 and 8 features in T1WI, CE-T1, combined datasets and clinical features, respectively. The SVM models area-under-curve was 0.86 and 0.88 in T1WI; 0.76, 0.71 in CE-T1 and 0.82, 0.91 in the combined dataset, with and without clinical features, respectively. The only significant change was observed after inclusion of clinical features in the combined dataset (p = 0.001). Higher WBC and neutrophil levels were significantly associated with lower treatment response in univariant analysis (p = 0.02, for both).

CONCLUSION

Machine learning models created with clinical and MRI radiomics features, may have promise in predicting local response after TACE.

LEVEL OF EVIDENCE

Level 4, Case-control study.

A Cox Nomogram for Assessing Recurrence Free Survival in Hepatocellular Carcinoma Following Surgical Resection Using Dynamic Contrast-Enhanced MRI Radiomics

BACKGROUND

The prognosis of hepatocellular carcinoma (HCC) is difficult to predict and carries high mortality. This study utilized radiomic techniques with clinical examinations to assess recurrence in HCC.

PURPOSE

To develop a Cox nomogram to assess the risk of postoperative recurrence in HCC using radiomic features of three volumes of interest (VOIs) in preoperative dynamic contrast-enhanced MRI (DCE-MRI), along with clinical findings.

STUDY TYPE

Retrospective.

SUBJECTS

249 patients with pathologically proven HCCs undergoing surgical resection at three institutions were selected.

FIELD STRENGTH/SEQUENCE

Fat saturated T2-weighted, Fat saturated T1-weighted, and DCE-MRI performed at 1.5 T and 3.0 T.

ASSESSMENT

Three VOIs were generated; the tumor VOI corresponds to the area from the tumor core to the outer perimeter of the tumor, the tumor +10 mm VOI represents the area from the tumor perimeter to 10 mm distal to the tumor in all directions, finally, the background liver parenchyma VOI represents the hepatic tissue outside the tumor. Three models were generated. The total radiomic model combined information from the three listed VOI's above. The clinical-radiological model combines physical examination findings with imaging characteristics such as tumor size, margin features, and metastasis. The combined radiomic model includes features from both models listed above and showed the highest reliability for assessing 24-month survival for HCC.

STATISTICAL TESTS

The least absolute shrinkage and selection operator (LASSO) Cox regression, univariable, and multivariable Cox regression, Kmeans clustering, and Kaplan-Meier analysis. The discrimination performance of each model was quantified by the C-index. A P value <0.05 was considered statistically significant.

RESULTS

The combined radiomic model, which included features from the radiomic VOI's and clinical imaging provided the highest performance (C-index: training cohort = 0.893, test cohort = 0.851, external cohort = 0.797) in assessing the survival of HCC.

CONCLUSION

The combined radiomic model provides superior ability to discern the possibility of recurrence-free survival in HCC over the total radiomic and the clinical-radiological models.

EVIDENCE LEVEL

4.

TECHNICAL EFFICACY

Stage 2.

Using Machine Learning to Predict Response to Image-guided Therapies for Hepatocellular Carcinoma

Interventional oncology is a rapidly growing field with advances in minimally invasive image-guided local-regional treatments for hepatocellular carcinoma (HCC), including transarterial chemoembolization, transarterial radioembolization, and thermal ablation. However, current standardized clinical staging systems for HCC are limited in their ability to optimize patient selection for treatment as they rely primarily on serum markers and radiologist-defined imaging features. Given the variation in treatment responses, an updated scoring system that includes multidimensional aspects of the disease, including quantitative imaging features, serum markers, and functional biomarkers, is needed to optimally triage patients. With the vast amounts of numerical medical record data and imaging features, researchers have turned to image-based methods, such as radiomics and artificial intelligence (AI), to automatically extract and process multidimensional data from images. The synthesis of these data can provide clinically relevant results to guide personalized treatment plans and optimize resource utilization. Machine learning (ML) is a branch of AI in which a model learns from training data and makes effective predictions by teaching itself. This review article outlines the basics of ML and provides a comprehensive overview of its potential value in the prediction of treatment response in patients with HCC after minimally invasive image-guided therapy.

Intratumoral and peritumoral radiomics based on contrast-enhanced MRI for preoperatively predicting treatment response of transarterial chemoembolization in hepatocellular carcinoma

BACKGROUND

Noninvasive and precise methods to estimate treatment response and identify hepatocellular carcinoma (HCC) patients who could benefit from transarterial chemoembolization (TACE) are urgently required. The present study aimed to investigate the ability of intratumoral and peritumoral radiomics based on contrast-enhanced magnetic resonance imaging (CE-MRI) to preoperatively predict tumor response to TACE in HCC patients.

METHODS

A total of 138 patients with HCC who received TACE were retrospectively included and randomly divided into training and validation cohorts at a ratio of 7:3. Total 1206 radiomics features were extracted from arterial, venous, and delayed phases images. The inter- and intraclass correlation coefficients, the spearman's rank correlation test, and the gradient boosting decision tree algorithm were used for radiomics feature selection. Radiomics models on intratumoral region (TR) and peritumoral region (PTR) (3 mm, 5 mm, and 10 mm) were established using logistic regression. Three integrated radiomics models, including intratumoral and peritumoral region (T-PTR) (3 mm), T-PTR (5 mm), and T-PTR (10 mm) models, were constructed using TR and PTR radiomics scores. A clinical-radiological model and a combined model incorporating the optimal radiomics score and selected clinical-radiological predictors were constructed, and the combined model was presented as a nomogram. The discrimination, calibration, and clinical utilities were evaluated by receiver operating characteristic curve, calibration curve, and decision curve analysis, respectively.

RESULTS

The T-PTR radiomics models performed better than the TR and PTR models, and the T-PTR (3 mm) radiomics model demonstrated preferable performance with the AUCs of 0.884 (95%CI, 0.821-0.936) and 0.911 (95%CI, 0.825-0.975) in both training and validation cohorts. The T-PTR (3 mm) radiomics score, alkaline phosphatase, tumor size, and satellite nodule were fused to construct a combined nomogram. The combined nomogram [AUC: 0.910 (95%CI, 0.854-0.958) and 0.918 (95%CI, 0.831-0.986)] outperformed the clinical-radiological model [AUC: 0.789 (95%CI, 0.709-0.863) and 0.782 (95%CI, 0.660-0.902)] in the both cohorts and achieved good calibration capability and clinical utility.

CONCLUSIONS

CE-MRI-based intratumoral and peritumoral radiomics approach can provide an effective tool for the precise and individualized estimation of treatment response for HCC patients treated with TACE.

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.

Radiomic advances in the transarterial chemoembolization related therapy for hepatocellular carcinoma

Radiomics is a hot topic in the research on customized oncology treatment, efficacy evaluation, and tumor prognosis prediction. To achieve the goal of mining the heterogeneity information within the tumor tissue, the image features concealed within the tumoral images are turned into quantifiable data features. This article primarily describes the research progress of radiomics and clinical-radiomics combined model in the prediction of efficacy, the choice of treatment modality, and survival in transarterial chemoembolization (TACE) and TACE combination therapy for hepatocellular carcinoma.

Machine-Learning-Based Radiomic Features on Pre-Ablation MRI as Predictors of Pathologic Response in Patients with Hepatocellular Carcinoma Who Underwent Hepatic Transplant

Background: The aim was to investigate the role of pre-ablation tumor radiomics in predicting pathologic treatment response in patients with early-stage hepatocellular carcinoma (HCC) who underwent liver transplant. Methods: Using data collected from 2005–2015, we included adult patients who (1) had a contrast-enhanced MRI within 3 months prior to ablation therapy and (2) underwent liver transplantation. Demographics were obtained for each patient. The treated hepatic tumor volume was manually segmented on the arterial phase T1 MRI images. A vector with 112 radiomic features (shape, first-order, and texture) was extracted from each tumor. Feature selection was employed through minimum redundancy and maximum relevance using a training set. A random forest model was developed based on top radiomic and demographic features. Model performance was evaluated by ROC analysis. SHAP plots were constructed in order to visualize feature importance in model predictions. Results: Ninety-seven patients (117 tumors, 31 (32%) microwave ablation, 66 (68%) radiofrequency ablation) were included. The mean model for end-stage liver disease (MELD) score was 10.5 ± 3. The mean follow-up time was 336.2 ± 179 days. Complete response on pathology review was achieved in 62% of patients at the time of transplant. Incomplete pathologic response was associated with four features: two first-order and two GLRM features using univariate logistic regression analysis (p < 0.05). The random forest model included two radiomic features (diagnostics maximum and first-order maximum) and four clinical features (pre-procedure creatinine, pre-procedure albumin, age, and gender) achieving an AUC of 0.83, a sensitivity of 82%, a specificity of 67%, a PPV of 69%, and an NPV of 80%. Conclusions: Pre-ablation MRI radiomics could act as a valuable imaging biomarker for the prediction of tumor pathologic response in patients with HCC.

Association of Multi-Phasic MR-Based Radiomic and Dosimetric Features with Treatment Response in Unresectable Hepatocellular Carcinoma Patients following Novel Sequential TACE-SBRT-Immunotherapy

This study aims to investigate the association of pre-treatment multi-phasic MR-based radiomics and dosimetric features with treatment response to a novel sequential trans-arterial chemoembolization (TACE) plus stereotactic body radiotherapy (SBRT) plus immunotherapy regimen in unresectable Hepatocellular Carcinoma (HCC) sub-population. Twenty-six patients with unresectable HCC were retrospectively analyzed. Radiomic features were extracted from 42 lesions on arterial phase (AP) and portal-venous phase (PVP) MR images. Delta-phase (DeltaP) radiomic features were calculated as AP-to-PVP ratio. Dosimetric data of the tumor was extracted from dose-volume-histograms. A two-sided independent Mann-Whitney U test was used to assess the clinical association of each feature, and the classification performance of each significant independent feature was assessed using logistic regression. For the 3-month timepoint, four DeltaP-derived radiomics that characterize the temporal change in intratumoral randomness and uniformity were the only contributors to the treatment response association (p-value = 0.038-0.063, AUC = 0.690-0.766). For the 6-month timepoint, DeltaP-derived radiomic features (n = 4) maintained strong clinical associations with the treatment response (p-value = 0.047-0.070, AUC = 0.699-0.788), additional AP-derived radiomic features (n = 4) that reflect baseline tumoral arterial-enhanced signal pattern and tumor morphology (n = 1) that denotes initial tumor burden were shown to have strong associations with treatment response (p-value = 0.028-0.074, AUC = 0.719-0.773). This pilot study successfully demonstrated associations of pre-treatment multi-phasic MR-based radiomics with tumor response to the novel treatment regimen.

Radiomics: A radiological evidence-based artificial intelligence technique to facilitate personalized precision medicine in hepatocellular carcinoma

The high postoperative recurrence rates in hepatocellular carcinoma (HCC) remain a major hurdle in its management. Appropriate staging and treatment selection may alleviate the extent of fatal recurrence. However, effective methods to preoperatively evaluate pathophysiologic and molecular characteristics of HCC are lacking. Imaging plays a central role in HCC diagnosis and stratification due to the non-invasive diagnostic criteria. Vast and crucial information is hidden within image data. Other than providing a morphological sketch for lesion diagnosis, imaging could provide new insights to describe the pathophysiological and genetic landscape of HCC. Radiomics aims to facilitate diagnosis and prognosis of HCC using artificial intelligence techniques to harness the immense information contained in medical images. Radiomics produces a set of archetypal and robust imaging features that are correlated to key pathological or molecular biomarkers to preoperatively risk-stratify HCC patients. Inferred with outcome data, comprehensive combination of radiomic, clinical and/or multi-omics data could also improve direct prediction of response to treatment and prognosis. The evolution of radiomics is changing our understanding of personalized precision medicine in HCC management. Herein, we review the key techniques and clinical applications in HCC radiomics and discuss current limitations and future opportunities to improve clinical decision making.

A radiomics nomogram for predicting cytokeratin 19-positive hepatocellular carcinoma: a two-center study

Objectives

We aimed to construct and validate a radiomics-based nomogram model derived from gadoxetic acid-enhanced magnetic resonance (MR) images to predict cytokeratin (CK) 19-positive (+) hepatocellular carcinoma (HCC) and patients' prognosis.

Methods

A two-center and time-independent cohort of 311 patients were retrospectively enrolled (training cohort, n = 168; internal validation cohort, n = 72; external validation cohort, n = 71). A total of 2286 radiomic features were extracted from multisequence MR images with the uAI Research Portal (uRP), and a radiomic feature model was established. A combined model was established by incorporating the clinic-radiological features and the fusion radiomics signature using logistic regression analysis. Receiver operating characteristic curve (ROC) was used to evaluate the predictive efficacy of these models. Kaplan-Meier survival analysis was used to assess 1-year and 2-year progression-free survival (PFS) and overall survival (OS) in the cohort.

Results

By combining radiomic features extracted in DWI phase, arterial phase, venous and delay phase, the fusion radiomics signature achieved AUCs of 0.865, 0.824, and 0.781 in the training, internal, and external validation cohorts. The final combined clinic-radiological model showed higher AUC values in the three datasets compared with the fusion radiomics model. The nomogram based on the combined model showed satisfactory prediction performance in the training (C-index, 0.914), internal (C-index, 0.855), and external validation (C-index, 0.795) cohort. The 1-year and 2-year PFS and OS of the patients in the CK19+ group were 76% and 73%, and 78% and 68%, respectively. The 1-year and 2-year PFS and OS of the patients in the CK19-negative (-) group were 81% and 77%, and 80% and 74%, respectively. Kaplan-Meier survival analysis showed no significant differences in 1-year PFS and OS between the groups (P = 0.273 and 0.290), but it did show differences in 2-year PFS and OS between the groups (P = 0.032 and 0.040). Both PFS and OS were lower in CK19+ patients.

Conclusion

The combined model based on clinic-radiological radiomics features can be used for predicting CK19+ HCC noninvasively to assist in the development of personalized treatment.

A comparative study between deep learning and radiomics models in grading liver tumors using hepatobiliary phase contrast-enhanced MR images

Purpose

To compare a deep learning model with a radiomics model in differentiating high-grade (LR-3, LR-4, LR-5) liver imaging reporting and data system (LI-RADS) liver tumors from low-grade (LR-1, LR-2) LI-RADS tumors based on the contrast-enhanced magnetic resonance images.

Methods

Magnetic resonance imaging scans of 361 suspected hepatocellular carcinoma patients were retrospectively reviewed. Lesion volume segmentation was manually performed by two radiologists, resulting in 426 lesions from the training set and 83 lesions from the test set. The radiomics model was constructed using a support vector machine (SVM) with pre-defined features, which was first selected using Chi-square test, followed by refining using binary least absolute shrinkage and selection operator (LASSO) regression. The deep learning model was established based on the DenseNet. Performance of the models was quantified by area under the receiver-operating characteristic curve (AUC), accuracy, sensitivity, specificity and F1-score.

Results

A set of 8 most informative features was selected from 1049 features to train the SVM classifier. The AUCs of the radiomics model were 0.857 (95% confidence interval [CI] 0.816–0.888) for the training set and 0.879 (95% CI 0.779–0.935) for the test set. The deep learning method achieved AUCs of 0.838 (95% CI 0.799–0.871) for the training set and 0.717 (95% CI 0.601–0.814) for the test set. The performance difference between these two models was assessed by t-test, which showed the results in both training and test sets were statistically significant.

Conclusion

The deep learning based model can be trained end-to-end with little extra domain knowledge, while the radiomics model requires complex feature selection. However, this process makes the radiomics model achieve better performance in this study with smaller computational cost and more potential on model interpretability.