Quantitative assessment of HCC wash-out on CT is a predictor of early complete response to TACE

Assessing microvascular invasion in HBV-related hepatocellular carcinoma: an online interactive nomogram integrating inflammatory markers, radiomics, and convolutional neural networks

Objective

The early recurrence of hepatocellular carcinoma (HCC) correlates with decreased overall survival. Microvascular invasion (MVI) stands out as a prominent hazard influencing post-resection survival status and metastasis in patients with HBV-related HCC. The study focused on developing a web-based nomogram for preoperative prediction of MVI in HBV-HCC.

Materials and methods

173 HBV-HCC patients from 2017 to 2022 with complete preoperative clinical data and Gadopentetate dimeglumine-enhanced magnetic resonance images were randomly divided into two groups for the purpose of model training and validation, using a ratio of 7:3. MRI signatures were extracted by pyradiomics and the deep neural network, 3D ResNet. Clinical factors, blood-cell-inflammation markers, and MRI signatures selected by LASSO were incorporated into the predictive nomogram. The evaluation of the predictive accuracy involved assessing the area under the receiver operating characteristic (ROC) curve (AUC), the concordance index (C-index), along with analyses of calibration and decision curves.

Results

Inflammation marker, neutrophil-to-lymphocyte ratio (NLR), was positively correlated with independent MRI radiomics risk factors for MVI. The performance of prediction model combined serum AFP, AST, NLR, 15 radiomics features and 7 deep features was better than clinical and radiomics models. The combined model achieved C-index values of 0.926 and 0.917, with AUCs of 0.911 and 0.907, respectively.

Conclusion

NLR showed a positive correlation with MRI radiomics and deep learning features. The nomogram, incorporating NLR and MRI features, accurately predicted individualized MVI risk preoperatively.

An interpretable machine learning model based on contrast-enhanced CT parameters for predicting treatment response to conventional transarterial chemoembolization in patients with hepatocellular carcinoma

OBJECTIVE

To explore the potential of pre-therapy computed tomography (CT) parameters in predicting the treatment response to initial conventional TACE (cTACE) in intermediate-stage hepatocellular carcinoma (HCC) and develop an interpretable machine learning model.

METHODS

This retrospective study included 367 patients with intermediate-stage HCC who received cTACE as first-line therapy from three centers. We measured the mean attenuation values of target lesions on multi-phase contrast-enhanced CT and further calculated three CT parameters, including arterial (AER), portal venous (PER), and arterial portal venous (APR) enhancement ratios. We used logistic regression analysis to select discriminative features and trained three machine learning models via 5-fold cross-validation. The performance in predicting treatment response was evaluated in terms of discrimination, calibration, and clinical utility. Afterward, a Shapley additive explanation (SHAP) algorithm was leveraged to interpret the outputs of the best-performing model.

RESULTS

The mean diameter, ECOG performance status, and cirrhosis were the important clinical predictors of cTACE treatment response, by multiple logistic regression. Adding the CT parameters to clinical variables showed significant improvement in performance (net reclassification index, 0.318, P < 0.001). The Random Forest model (hereafter, RF-combined model) integrating CT parameters and clinical variables demonstrated the highest performance on external validation dataset (AUC of 0.800). The decision curve analysis illustrated the optimal clinical benefits of RF-combined model. This model could successfully stratify patients into responders and non-responders with distinct survival (P = 0.001).

CONCLUSION

The RF-combined model can serve as a robust and interpretable tool to identify the appropriate crowd for cTACE sessions, sparing patients from receiving ineffective and unnecessary treatments.

Automated CT LI-RADS v2018 scoring of liver observations using machine learning: A multivendor, multicentre retrospective study

Background & Aims

Assessment of computed tomography (CT)/magnetic resonance imaging Liver Imaging Reporting and Data System (LI-RADS) v2018 major features leads to substantial inter-reader variability and potential decrease in hepatocellular carcinoma diagnostic accuracy. We assessed the performance and added-value of a machine learning (ML)-based algorithm in assessing CT LI-RADS major features and categorisation of liver observations compared with qualitative assessment performed by a panel of radiologists.

Methods

High-risk patients as per LI-RADS v2018 with pathologically proven liver lesions who underwent multiphase contrast-enhanced CT at diagnosis between January 2015 and March 2019 in seven centres in five countries were retrospectively included and randomly divided into a training set (n = 84 lesions) and a test set (n = 345 lesions). An ML algorithm was trained to classify non-rim arterial phase hyperenhancement, washout, and enhancing capsule as present, absent, or of uncertain presence. LI-RADS major features and categories were compared with qualitative assessment of two independent readers. The performance of a sequential use of the ML algorithm and independent readers were also evaluated in a triage and an add-on scenario in LR-3/4 lesions. The combined evaluation of three other senior readers was used as reference standard.

Results

A total of 318 patients bearing 429 lesions were included. Sensitivity and specificity for LR-5 in the test set were 0.67 (95% CI, 0.62-0.72) and 0.91 (95% CI, 0.87-0.96) respectively, with 242 (70.1%) lesions accurately categorised. Using the ML algorithm in a triage scenario improved the overall performance for LR-5. (0.86 and 0.93 sensitivity, 0.82 and 0.76 specificity, 78% and 82.3% accuracy for the two independent readers).

Conclusions

Quantitative assessment of CT LI-RADS v2018 major features is feasible and diagnoses LR-5 observations with high performance especially in combination with the radiologist's visual analysis in patients at high-risk for HCC.

Impact and implications

Assessment of CT/MRI LI-RADS v2018 major features leads to substantial inter-reader variability and potential decrease in hepatocellular carcinoma diagnostic accuracy. Rather than replacing radiologists, our results highlight the potential benefit from the radiologist-artificial intelligence interaction in improving focal liver lesions characterisation by using the developed algorithm as a triage tool to the radiologist's visual analysis. Such an AI-enriched diagnostic pathway may help standardise and improve the quality of analysis of liver lesions in patients at high risk for HCC, especially in non-expert centres in liver imaging. It may also impact the clinical decision-making and guide the clinician in identifying the lesions to be biopsied, for instance in patients with multiple liver focal lesions.

Added value of CE-CT radiomics to predict high Ki-67 expression in hepatocellular carcinoma

BACKGROUND

This study aimed to develop a computed tomography (CT) model to predict Ki-67 expression in hepatocellular carcinoma (HCC) and to examine the added value of radiomics to clinico-radiological features.

METHODS

A total of 208 patients (training set, n = 120; internal test set, n = 51; external validation set, n = 37) with pathologically confirmed HCC who underwent contrast-enhanced CT (CE-CT) within 1 month before surgery were retrospectively included from January 2014 to September 2021. Radiomics features were extracted and selected from three phases of CE-CT images, least absolute shrinkage and selection operator regression (LASSO) was used to select features, and the rad-score was calculated. CE-CT imaging and clinical features were selected using univariate and multivariate analyses, respectively. Three prediction models, including clinic-radiologic (CR) model, rad-score (R) model, and clinic-radiologic-radiomic (CRR) model, were developed and validated using logistic regression analysis. The performance of different models for predicting Ki-67 expression was evaluated using the area under the receiver operating characteristic curve (AUROC) and decision curve analysis (DCA).

RESULTS

HCCs with high Ki-67 expression were more likely to have high serum α-fetoprotein levels (P = 0.041, odds ratio [OR] 2.54, 95% confidence interval [CI]: 1.04-6.21), non-rim arterial phase hyperenhancement (P = 0.001, OR 15.13, 95% CI 2.87-79.76), portal vein tumor thrombus (P = 0.035, OR 3.19, 95% CI: 1.08-9.37), and two-trait predictor of venous invasion (P = 0.026, OR 14.04, 95% CI: 1.39-144.32). The CR model achieved relatively good and stable performance compared with the R model (AUC, 0.805 [95% CI: 0.683-0.926] vs. 0.678 [95% CI: 0.536-0.839], P = 0.211; and 0.805 [95% CI: 0.657-0.953] vs. 0.667 [95% CI: 0.495-0.839], P = 0.135) in the internal and external validation sets. After combining the CR model with the R model, the AUC of the CRR model increased to 0.903 (95% CI: 0.849-0.956) in the training set, which was significantly higher than that of the CR model (P = 0.0148). However, no significant differences were found between the CRR and CR models in the internal and external validation sets (P = 0.264 and P = 0.084, respectively).

CONCLUSIONS

Preoperative models based on clinical and CE-CT imaging features can be used to predict HCC with high Ki-67 expression accurately. However, radiomics cannot provide added value.

Soft Reconstruction Kernels Improve HCC Imaging on a Photon-Counting Detector CT

RATIONALE AND OBJECTIVES

Hepatocellular carcinoma (HCC) is the only tumor entity that allows non-invasive diagnosis based on imaging without further histological proof. Therefore, excellent image quality is of utmost importance for HCC diagnosis. Novel photon-counting detector (PCD) CT improves image quality via noise reduction and higher spatial resolution, inherently providing spectral information. The aim of this study was to investigate these improvements for HCC imaging with triple-phase liver PCD-CT in a phantom and patient population study focusing on identification of the optimal reconstruction kernel.

MATERIALS AND METHODS

Phantom experiments were performed to analyze objective quality characteristics of the regular body and quantitative reconstruction kernels, each with four sharpness levels (36-40-44-48). For 24 patients with viable HCC lesions on PCD-CT, virtual monoenergetic images at 50 keV were reconstructed using these kernels. Quantitative image analysis included contrast-to-noise ratio (CNR) and edge sharpness. Three raters performed qualitative analyses evaluating noise, contrast, lesion conspicuity, and overall image quality.

RESULTS

In all contrast phases, the CNR was highest using the kernels with a sharpness level of 36 (all p < 0.05), with no significant influence on lesion sharpness. Softer reconstruction kernels were also rated better regarding noise and image quality (all p < 0.05). No significant differences were found in image contrast and lesion conspicuity. Comparing body and quantitative kernels with equal sharpness levels, there was no difference in image quality criteria, neither regarding in vitro nor in vivo analysis.

CONCLUSION

Soft reconstruction kernels yield the best overall quality for the evaluation of HCC in PCD-CT. As the image quality of quantitative kernels with potential for spectral post-processing is not restricted compared to regular body kernels, they should be preferred.

The Role of Immediate Post-Procedural Cone-Beam Computed Tomography (CBCT) in Predicting the Early Radiologic Response of Hepatocellular Carcinoma (HCC) Nodules to Drug-Eluting Bead Transarterial Chemoembolization (DEB-TACE)

The purpose of this study was to evaluate the efficacy of unenhanced cone-beam computed tomography (CBCT) performed at the end of drug-eluting bead transarterial chemoembolization (DEB-TACE) in predicting HCC nodules’ early radiologic response to treatment, assessed using mRECIST criteria with a 30−60 day four-phase contrast-enhanced CT follow-up. Fifty-nine patients (81 lesions) subjected to DEB-TACE as exclusive treatment for HCC lesions (naive/relapse) between February 2020 and October 2021 were prospectively enrolled. In a post-interventional unenhanced CBCT procedure, two experienced radiologists evaluated for each lesion the overall intensity of the contrast media deposit, the homogeneity of the enhancement, and the presence of smooth and complete margins. The univariate analysis found that lesions with complete response (CR+) had a significantly higher incidence of clear and complete margins than CR− lesions (76.9% vs. 17.2%, p = 0.003) and a higher intensity score (67.3% vs. 27.6%, p = 0.0009). A Dmax <30 mm was significantly more common among CR+ than CR− lesions (92.3% vs. 69%, p = 0.01). These features were confirmed as significant predictors for CR+ by multivariate binary logistic regression. The homogeneity of the enhancement did not affect the DEB-TACE outcome. Post-interventional unenhanced CBCT is effective in predicting early radiological response to DEB-TACE, since the presence of an intense contrast media deposit with clear and complete margins in treated HCC lesions is associated with CR.

Rim Enhancement after Technically Successful Transarterial Chemoembolization in Hepatocellular Carcinoma: A Potential Mimic of Incomplete Embolization or Reactive Hyperemia?

Contrast enhancement at the margins/rim of embolization areas in hepatocellular-carcinoma (HCC) lesions treated with transarterial chemoembolization (TACE) might be an early prognostic indicator for HCC recurrence. The aim of this study was to evaluate the predictive value of rim perfusion for TACE recurrence as determined by perfusion CT (PCT). A total of 52 patients (65.6 ± 9.3 years) underwent PCT directly before, immediately after (within 48 h) and at follow-up (95.3 ± 12.5 days) after TACE. Arterial-liver perfusion (ALP), portal-venous perfusion (PVP) and hepatic-perfusion index (HPI) were evaluated in normal liver parenchyma, and on the embolization rim as well as the tumor bed. A total of 42 lesions were successfully treated, and PCT measurements showed no residually vascularized tumor areas. Embolization was not entirely successful in 10 patients with remaining arterialized focal nodular areas (ALP 34.7 ± 10.1 vs. 4.4 ± 5.3 mL/100 mL/min, p < 0.0001). Perfusion values at the TACE rim were lower in responders compared to normal adjacent liver parenchyma and edges of incompletely embolized tumors (ALP liver 16.3 ± 10.1 mL/100 mL/min, rim responder 8.8 ± 8.7 mL/100 mL/min, rim non-responder 23.4 ± 8.6 mL/100 mL/min, p = 0.005). At follow-up, local tumor relapse was observed in 17/42, and 15/42 showed no recurrence (ALP 39.1 ± 10.1 mL/100 mL/min vs. 10.0 ± 7.4 mL/100 mL/min, p = 0.0008); four patients had de novo disseminated disease and six patients were lost in follow-up. Rim perfusion was lower compared to adjacent recurring HCC and not different between groups. HCC lesions showed no rim perfusion after TACE, neither immediately after nor at follow-up at three months, both for mid-term responders and mid-term relapsing HCCs, indicating that rim enhancement is not a sign of reactive hyperemia and not predictive of early HCC recurrence.

Quantitative washout in patients with hepatocellular carcinoma undergoing TACE: an imaging biomarker for predicting prognosis?

BACKGROUND

The delayed percentage attenuation ratio (DPAR) was recently identified as a novel predictor of an early complete response in patients with hepatocellular carcinoma (HCC) undergoing transarterial chemoembolization (TACE). In this study, we aimed to validate the role of DPAR as a predictive biomarker for short-, mid-, and long-term outcomes after TACE.

METHODS

We retrospectively reviewed laboratory and imaging data for 103 treatment-naïve patients undergoing initial TACE treatment at our tertiary care center between January 2016 and November 2020. DPAR and other washin and washout indices were quantified in the triphasic computed tomography performed before the initial TACE. The correlation of DPAR and radiologic response was investigated. Furthermore, the influence of DPAR on the 6-, 12-, 18-, and 24-month survival rates and the median overall survival (OS) was compared to other established washout indices and estimates of tumor burden and remnant liver function.

RESULTS

The DPAR was significantly of the target lesions (TLs) with objective response to TACE after the initial TACE session was significantly higher compared to patients with stable disease (SD) or progressive disease (PD) (125 (IQR 118-134) vs 110 (IQR 103-116), p < 0.001). Furthermore, the DPAR was significantly higher in patients who survived the first 6 months after TACE (122 vs. 115, p = 0.04). In addition, the number of patients with a DPAR > 120 was significantly higher in this group (n = 38 vs. n = 8; p = 0.03). However, no significant differences were observed in the 12-, 18-, and 24-month survival rates after the initial TACE. Regarding the median OS, no significant difference was observed for patients with a high DPAR compared to those with a low DPAR (18.7 months vs. 12.7 months, p = 0.260).

CONCLUSIONS

Our results confirm DPAR as the most relevant washout index for predicting the short-term outcome of patients with HCC undergoing TACE. However, DPAR and the other washout indices were not predictive of mid- and long-term outcomes.

Drug-Eluting Bead Transarterial Chemoembolization Combined with FOLFOX-Based Hepatic Arterial Infusion Chemotherapy for Large or Huge Hepatocellular Carcinoma

PURPOSE

To evaluate the safety and efficacy of drug-eluting bead transarterial chemoembolization (DEB-TACE) combined with oxaliplatin plus fluorouracil and leucovorin (FOLFOX)-based hepatic arterial infusion chemotherapy (D-TACE-HAIC) for unresectable large (5.1-10 cm) or huge (>10 cm) hepatocellular carcinoma (HCC).

METHODS

This retrospective study evaluated consecutive patients with unresectable large or huge HCC who underwent D-TACE-HAIC (D-TACE-HAIC group) or DEB-TACE (DEB-TACE group) from January 2017 to December 2020. At imaging, tumor infiltrating appearance was classified into smooth tumor margin, non-smooth tumor margin, and macrovascular invasion. Adverse events, objective response rate (ORR), progression-free survival (PFS), and overall survival (OS) were compared between the two groups.

RESULTS

A total of 133 patients (mean age, 53 years ± 12; 117 men) were included: 69 underwent D-TACE-HAIC and 64 underwent DEB-TACE. The patients who underwent D-TACE-HAIC had higher ORR (71.0% vs 53.1%; P = 0.033), longer PFS (median, 9.3 vs 6.3 months; P = 0.005), and better OS (median, 19.0 vs 14.0 months; P = 0.008) than those who underwent DEB-TACE. In subgroup analysis, patients with non-smooth tumor margin (median, 20.8 vs 13.0 months; P = 0.031) or macrovascular invasion (median, 15.0 vs 11.0 months; P = 0.015) had significantly longer OS in D-TACE-HAIC group than in DEB-TACE group; but in patients with smooth tumor margin, OS between the two groups was similar (median, 37.0 vs 35.0 months; P = 0.458). DEB-TACE, non-smooth tumor margin, and macrovascular invasion were independent prognostic factors for poor OS in uni- and multivariable analyses. The incidence of grade 3/4 adverse events was not statistically different between the two groups (37.7% vs 28.1%; P = 0.242).

CONCLUSION

D-TACE-HAIC was tolerable and led to better OS than DEB-TACE in patients with large or huge HCC, especially in those with non-smooth tumor margin or macrovascular invasion.

Lipiodol Deposition and Washout in Primary and Metastatic Liver Tumors After Chemoembolization

BACKGROUND/AIM

Lipiodol is the key component of conventional trans-arterial chemoembolization. Our aim was to evaluate lipiodol deposition and washout rate after conventional trans-arterial chemoembolization in intrahepatic cholangiocarcinoma and hepatic metastases originating from neuroendocrine tumors and colorectal carcinoma.

PATIENTS AND METHODS

This was a retrospective analysis of 44 patients with intrahepatic cholangiocarcinoma and liver metastasis from neuroendocrine tumors or colorectal carcinoma who underwent conventional trans-arterial chemoembolization. Lipiodol volume (cm³) was analyzed on non-contrast computed tomography imaging obtained within 24 h post conventional trans-arterial chemoembolization, and 40-220 days after conventional trans-arterial chemoembolization using volumetric image analysis software. Tumor response was assessed on contrast-enhanced magnetic resonance imaging 1 month after conventional trans-arterial chemoembolization.

RESULTS

The washout rate was longer for neuroendocrine tumors compared to colorectal carcinoma, with half-lives of 54.61 days (p<0.00001) and 19.39 days (p<0.001), respectively, with no exponential washout among intrahepatic cholangiocarcinomas (p=0.83). The half-life for lipiodol washout was longer in tumors larger than 300 cm³ compared to smaller tumors (25.43 vs. 22.71 days). Lipiodol wash out half-life was 54.76 days (p<0.01) and 29.45 days (p<0.00001) for tumors with a contrast enhancement burden of 60% or more and less than 60%, respectively. A negative exponential relationship for lipiodol washout was observed in non-responders (p<0.00001).

CONCLUSION

Lipiodol washout is a time-dependent process, and occurs faster in colorectal carcinoma tumors, tumors smaller than 300 cm³, tumors with baseline contrast enhancement burden of less than 60%, and non-responding target lesions.