CT radiomics for prediction of microvascular invasion in hepatocellular carcinoma: A systematic review and meta-analysis

The Application Status of Radiomics-Based Machine Learning in Intrahepatic Cholangiocarcinoma: Systematic Review and Meta-Analysis

BACKGROUND

Over the past few years, radiomics for the detection of intrahepatic cholangiocarcinoma (ICC) has been extensively studied. However, systematic evidence is lacking in the use of radiomics in this domain, which hinders its further development.

OBJECTIVE

To address this gap, our study delved into the status quo and application value of radiomics in ICC and aimed to offer evidence-based support to promote its systematic application in this field.

METHODS

PubMed, Web of Science, Cochrane Library, and Embase were comprehensively retrieved to determine relevant original studies. The study quality was appraised through the Radiomics Quality Score. In addition, subgroup analyses were undertaken according to datasets (training and validation sets), imaging sources, and model types.

RESULTS

Fifty-eight studies encompassing 12,903 patients were eligible, with an average Radiomics Quality Score of 9.21. Radiomics-based machine learning (ML) was mainly used to diagnose ICC (n=30), microvascular invasion (n=8), gene mutations (n=5), perineural invasion (PNI; n=2), lymph node (LN) positivity (n=2), and tertiary lymphoid structures (TLSs; n=2), and predict overall survival (n=6) and recurrence (n=9). The C-index, sensitivity (SEN), and specificity (SPC) of the ML model developed using clinical features (CFs) for ICC detection were 0.762 (95% CI 0.728-0.796), 0.72 (95% CI 0.66-0.77), and 0.72 (95% CI 0.66-0.78), respectively, in the validation dataset. In contrast, the C-index, SEN, and SPC of the radiomics-based ML model for detecting ICC were 0.853 (95% CI 0.824-0.882), 0.80 (95% CI 0.73-0.85), and 0.88 (95% CI 0.83-0.92), respectively. The C-index, SEN, and SPC of ML constructed using both radiomics and CFs for diagnosing ICC were 0.912 (95% CI 0.889-0.935), 0.77 (95% CI 0.72-0.81), and 0.90 (95% CI 0.86-0.92). The deep learning-based model that integrated both radiomics and CFs yielded a notably higher C-index of 0.924 (0.863-0.984) in the task of detecting ICC. Additional analyses showed that radiomics demonstrated promising accuracy in predicting overall survival and recurrence, as well as in diagnosing microvascular invasion, gene mutations, PNI, LN positivity, and TLSs.

CONCLUSIONS

Radiomics-based ML demonstrates excellent accuracy in the clinical diagnosis of ICC. However, studies involving specific tasks, such as diagnosing PNI and TLSs, are still scarce. The limited research on deep learning has hindered both further analysis and the development of subgroup analyses across various models. Furthermore, challenges such as data heterogeneity and interpretability caused by segmentation and imaging parameter variations require further optimization and refinement. Future research should delve into the application of radiomics to enhance its clinical use. Its integration into clinical practice holds great promise for improving decision-making, boosting diagnostic and treatment accuracy, minimizing unnecessary tests, and optimizing health care resource usage.

Development and Validation of a Pre-Transplant Risk Score (LT-MVI Score) to Predict Microvascular Invasion in Hepatocellular Carcinoma Candidates for Liver Transplantation

Background/Objectives: MVI is a relevant prognostic factor among patients with hepatocellular carcinoma (HCC) receiving liver transplantation (LT). The preoperative assessment of the risk for MVI is relevant to pre-LT patient management and selection. The objective of this study was to create and validate a model to predict microvascular invasion (MVI) based on preoperative variables in the LT setting. Methods: A total of 2170 patients from 11 collaborative centers in Europe, Asia, and the US, who received transplants between 1 January 2000 and 31 December 2017, were enrolled in the study. The entire cohort was split into a training and a validation set (70/30% of the initial cohort, respectively) using random selection. Results: MVI was reported in 586 (27.0%) explanted specimens. Using the training set data, multivariable logistic regression identified three preoperative parameters associated with MVI: α-fetoprotein (lnAFP; odds ratio [OR] = 1.19; 95% confidence interval [CI] = 1.13-1.27), imaging tumor burden score (lnTBS; OR = 1.66; 95%CI = 1.39-1.99), and a fast-track approach before LT due to the availability of a live donation (OR = 1.99; 95%CI = 1.56-2.53). In the validation set, the LT-MVI c-index was 0.74, versus 0.69 for the MVI score proposed by Endo et al. (Brier Skill Score +75%). The new score had a relevant net reclassification index (overall value = 0.61). Stratifying the validation set into three risk categories (0-50th, 51st-75th, and >75th score percentiles), a very good stratification was observed in terms of disease-free (5-year: 89.3, 75.5, and 50.7%, respectively) and overall survival (5-year: 79.5, 72.6, and 53.7%, respectively). Conclusions: The preoperative assessment of MVI using the proposed score demonstrated very good accuracy in predicting MVI after LT.

Real-world efficacy of radiomics versus clinical predictors for microvascular invasion in patients with hepatocellular carcinoma: Large cohort study

AIM

Microvascular invasion (MVI) affects the prognosis and treatment of hepatocellular carcinoma (HCC); however, its preoperative diagnosis is challenging. Analysis of computed tomography (CT) images using radiomics can detect MVI, but its effectiveness depends on the imaging conditions. We compared the efficacies of radiomics, clinical, and combined models for predicting MVI in HCC using nonstandardized scanning protocols.

METHODS

This multicenter study included 533 patients who underwent hepatic resection for HCC. Patients were divided randomly into training (n = 426) and test groups (n = 107). We manually extracted 3D CT features in hepatic arterial, portal venous, and venous phases. The radiomics model was trained by machine learning. A logistic regression model was developed based on clinical information, and a fused model was created integrating clinical information and radiomics prediction score (Rad_Score). We calculated areas under the receiver operating characteristic curves (AUCs) for the radiomics, clinical, and mixed models in the test groups.

RESULTS

The clinical model incorporated hepatitis B virus surface antigen, tumor diameter, and log-transformed α-fetoprotein and des-gamma-carboxyprothrombin. The AUCs of the radiomics and clinical models were comparable (p = 0.76). Rad_Score was not an independent significant factor in the fused model (p = 0.40) and its addition did not improve the accuracy of the clinical model alone (p = 0.51).

CONCLUSIONS

A clinical model is as effective as a CT radiomics model for predicting MVI status in patients with HCC based on real-world scanning data, and integration of both models does not improve the predictive performance compared with a clinical model alone.

Chinese expert consensus on the diagnosis and treatment of hepatocellular carcinoma with microvascular invasion (2024 edition)

Background

Hepatocellular carcinoma (HCC) is one of the most common malignant tumors in China. Surgical resection is the preferred treatment for HCC, but the postoperative recurrence and metastasis rates are high. Current evidence shows that microvascular invasion (MVI) is an independent risk factor for postoperative recurrence and metastasis, but there are still many controversies about the diagnosis, classification, prediction, and treatment of MVI worldwide.

Methods

Systematic literature reviews to identify knowledge gaps and support consensus statements and a modified Delphi method to develop evidence- and expert-based guidelines and finalization of the clinical consensus statements based on recommendations from a panel of experts.

Results

After many discussions and revisions, the Chinese Association of Liver Cancer of the Chinese Medical Doctor Association organized domestic experts in related fields to form the "Chinese expert consensus on the diagnosis and treatment of hepatocellular carcinoma with microvascular invasion (2024 edition)" which included eight recommendations to better guide the prediction, diagnosis and treatment of HCC patients with MVI. The MVI pathological grading criteria as outlined in the "Guidelines for Pathological Diagnosis of Primary Liver Cancer" and the Eastern Hepatobiliary Surgery Hospital (EHBH) nomogram for predicting MVI are highly recommended.

Conclusions

We present an expert consensus on the diagnosis and treatment of MVI and potentially improve recurrence-free survival (RFS) and overall survival (OS) for HCC patients with MVI.

MRI-based radiomic models for the preoperative prediction of extramural venous invasion in rectal cancer: A systematic review and meta-analysis

AIM

To estimate the diagnostic value of magnetic resonance imaging (MRI)-based radiomic models in detecting the extramural venous invasion (EMVI) of rectal cancer.

MATERIALS AND METHODS

Appropriate studies in multiple electronic databases were systematically retrieved. The Quality Assessment of Diagnostic Accuracy Studies 2 and Radiomics Quality Score (RQS) were used to evaluate the eligible studies' methodology quality. Summary accuracy metrics were calculated, and the publication bias was detected using Deek's funnel plot. The sensitivity and meta-regression analysis were performed to investigate the causes of heterogeneity.

RESULTS

For the seven eligible studies, which included 1175 patients, the pooled sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, and diagnostic odds ratio were 0.80 (95 % CI, 0.70-0.88), 0.89 (95 % CI, 0.84-0.92), 7.0 (95 % CI, 4.7, 10.4), 0.22 (95 % CI, 0.14, 0.34), and 32 (95 % CI, 16, 65), respectively. The area under the receiver operating characteristic curve (AUC) was 0.91 (95 % CI, 0.88, 0.93). Moderate heterogeneity was found due to I2 values of 38.63 % and 32.29 % in sensitivity and specificity, respectively. Meta-regression analysis suggested that the patient enrollment, number of patients, segmentation method, and RQS score were the source of the heterogeneity. The head-to-head analysis suggested that radiomics model had a higher sensitivity for detection of EMVI than subjective evaluation by radiologist (0.47 vs. 0.73, p ≤ 0.001).

CONCLUSION

Our study suggests that MRI-based radiomic models have good diagnostic value in detecting EMVI for rectal cancer patients. Nevertheless, more prospective and high-quality studies with larger sample sizes are needed in the future to validate these results.

Contrast-enhanced CT radiomics features to preoperatively identify differences between tumor and proximal tumor-adjacent and tumor-distant tissues of resectable esophageal squamous cell carcinoma

BACKGROUND

Esophagectomy is the main treatment for esophageal squamous cell carcinoma (ESCC), and patients with histopathologically negative margins still have a relatively higher recurrence rate. Contrast-enhanced CT (CECT) radiomics might noninvasively obtain potential information about the internal heterogeneity of ESCC and its adjacent tissues. This study aimed to develop CECT radiomics models to preoperatively identify the differences between tumor and proximal tumor-adjacent and tumor-distant tissues in ESCC to potentially reduce tumor recurrence.

METHODS

A total of 529 consecutive patients with ESCC from Centers A (n = 447) and B (n = 82) undergoing preoperative CECT were retrospectively enrolled in this study. Radiomics features of the tumor, proximal tumor-adjacent (PTA) and proximal tumor-distant (PTD) tissues were individually extracted by delineating the corresponding region of interest (ROI) on CECT and applying the 3D-Slicer radiomics module. Patients with pairwise tissues (ESCC vs. PTA, ESCC vs. PTD, and PTA vs. PTD) from Center A were randomly assigned to the training cohort (TC, n = 313) and internal validation cohort (IVC, n = 134). Univariate analysis and the least absolute shrinkage and selection operator were used to select the core radiomics features, and logistic regression was performed to develop radiomics models to differentiate individual pairwise tissues in TC, validated in IVC and the external validation cohort (EVC) from Center B. Diagnostic performance was assessed using area under the receiver operating characteristics curve (AUC) and accuracy.

RESULTS

With the chosen 20, 19 and 5 core radiomics features in TC, 3 individual radiomics models were developed, which exhibited excellent ability to differentiate the tumor from PTA tissue (AUC: 0.965; accuracy: 0.965), the tumor from PTD tissue (AUC: 0.991; accuracy: 0.958), and PTA from PTD tissue (AUC: 0.870; accuracy: 0.848), respectively. In IVC and EVC, the models also showed good performance in differentiating the tumor from PTA tissue (AUCs: 0.956 and 0.962; accuracy: 0.956 and 0.937), the tumor from PTD tissue (AUCs: 0.990 and 0.974; accuracy: 0.952 and 0.970), and PTA from PTD tissue (AUCs: 0.806 and 0.786; accuracy: 0.760 and 0.786), respectively.

CONCLUSION

CECT radiomics models could differentiate the tumor from PTA tissue, the tumor from PTD tissue, and PTA from PTD tissue in ESCC.

A Systematic Review and Meta-Analysis of MRI Radiomics for Predicting Microvascular Invasion in Patients with Hepatocellular Carcinoma

BACKGROUND

The prediction power of MRI radiomics for microvascular invasion (MVI) in patients with hepatocellular carcinoma (HCC) remains uncertain.

OBJECTIVE

To investigate the prediction performance of MRI radiomics for MVI in HCC.

METHODS

Original studies focusing on preoperative prediction performance of MRI radiomics for MVI in HCC, were systematically searched from databases of PubMed, Embase, Web of Science and Cochrane Library. Radiomics quality score (RQS) and risk of bias of involved studies were evaluated. Meta-analysis was carried out to demonstrate the value of MRI radiomics for MVI prediction in HCC. Influencing factors of the prediction performance of MRI radiomics were identified by subgroup analyses.

RESULTS

13 studies classified as type 2a or above according to the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis statement were eligible for this systematic review and meta-analysis. The studies achieved an average RQS of 14 (ranging from 11 to 17), accounting for 38.9% of the total points. MRI radiomics achieved a pooled sensitivity of 0.82 (95%CI: 0.78 - 0.86), specificity of 0.79 (95%CI: 0.76 - 0.83) and area under the summary receiver operator characteristic curve (AUC) of 0.88 (95%CI: 0.84 - 0.91) to predict MVI in HCC. Radiomics models combined with clinical features achieved superior performances compared to models without the combination (AUC: 0.90 vs 0.85, P < 0.05).

CONCLUSION

MRI radiomics has the potential for preoperative prediction of MVI in HCC. Further studies with high methodological quality should be designed to improve the reliability and reproducibility of the radiomics models for clinical application. The systematic review and meta-analysis was registered prospectively in the International Prospective Register of Systematic Reviews (No. CRD42022333822).