Application of CT-based radiomics in predicting portal pressure and patient outcome in portal hypertension

Development of a non-invasive diagnostic model for high-risk esophageal varices based on radiomics of spleen CT

PURPOSE

To evaluate the diagnostic performance of radiomics models derived from multi-phase spleen CT for high-risk esophageal varices (HREV) in cirrhotic patients.

METHODS

We retrospectively selected cirrhotic patients with esophageal varices from two hospitals from September 2019 to September 2023. Patients underwent non-contrast and contrast-enhanced CT scans and were categorized into HREV and non-HREV groups based on endoscopic evaluations. Radiomics features were extracted from spleen CT images in non-contrast, arterial, and portal venous phases, with feature selection via lasso regression and Pearson's correlation. Ten machine learning models were developed to diagnose HREV, evaluated by area under the curve (AUC). The AUC values of the three groups of models were statistically compared by the Kruskal-Wallis H test and Bonferroni-corrected Mann-Whitney U test. A p-value less than 0.05 was considered statistically significant.

RESULTS

Among 233 patients, 11, 6, and 11 features were selected from non-contrast, arterial, and portal venous phases, respectively. Significant differences in AUC values were observed across phases (p < 0.05), and the arterial phase models showed the highest AUC values. The best model in arterial phase was the logical regression model, whose AUC value was 0.85, sensitivity was 83.3%, specificity was 80% and F1 score was 0.81.

CONCLUSION

Radiomics models based on spleen CT, especially the arterial phase models, demonstrate high diagnostic accuracy for HREV, offering the potential for early detection and intervention.

Recent Advances in the Pathogenesis and Clinical Evaluation of Portal Hypertension in Chronic Liver Disease

In chronic liver disease, hepatic stellate cell activation and degeneration of liver sinusoidal endothelial cells lead to structural changes, which are secondary to fibrosis and the presence of regenerative nodules in the sinusoids, and to functional changes, which are related to vasoconstriction. The combination of such changes increases intrahepatic vascular resistance and causes portal hypertension. The subsequent increase in splanchnic and systemic hyperdynamic circulation further increases the portal blood flow, thereby exacerbating portal hypertension. In clinical practice, the hepatic venous pressure gradient is the gold-standard measure of portal hypertension; a value of ≥10 mm Hg is defined as clinically significant portal hypertension, which is severe and is associated with the risk of liver-related events. Hepatic venous pressure gradient measurement is somewhat invasive, so evidence on the utility of risk stratification by elastography and serum biomarkers is needed. The various stages of cirrhosis are associated with different outcomes. In viral hepatitis-related cirrhosis, viral suppression or elimination by nucleos(t)ide analog or direct-acting antivirals results in recompensation of liver function and portal pressure. However, careful follow-up should be continued, because some cases have residual clinically significant portal hypertension even after achieving sustained virologic response. In this study, we reviewed the current and future prospects for portal hypertension.

Machine Learning Radiomics Signature for Differentiating Lymphoma versus Benign Splenomegaly on CT

BACKGROUND

We aimed to develop and validate a preoperative CT-based radiomics signature for differentiating lymphoma versus benign splenomegaly.

METHODS

We retrospectively analyzed CT studies from 139 patients (age range 26-93 years, 43% female) between 2011 and 2019 with histopathological diagnosis of the spleen (19 lymphoma, 120 benign) and divided them into developing (n = 79) and testing (n = 60) datasets. The volumetric radiomic features were extracted from manual segmentation of the whole spleen on venous-phase CT imaging using PyRadiomics package. LASSO regression was applied for feature selection and development of the radiomic signature, which was interrogated with the complete blood cell count and differential count. All p values < 0.05 were considered to be significant.

RESULTS

Seven features were selected for constructing the radiomic signature after feature selection, including first-order statistics (10th percentile and Robust Mean Absolute Deviation), shape-based (Surface Area), and texture features (Correlation, MCC, Small Area Low Gray-level Emphasis and Low Gray-level Zone Emphasis). The radiomic signature achieved an excellent diagnostic accuracy of 97%, sensitivity of 89%, and specificity of 98%, distinguishing lymphoma versus benign splenomegaly in the testing dataset. The radiomic signature significantly correlated with the platelet and segmented neutrophil percentage.

CONCLUSIONS

CT-based radiomics signature can be useful in distinguishing lymphoma versus benign splenomegaly and can reflect the changes in underlying blood profiles.

Multi-organ Radiomics-Based Prediction of Future Remnant Liver Hypertrophy Following Portal Vein Embolization

BACKGROUND

Portal vein embolization (PVE) is used to induce remnant liver hypertrophy prior to major hepatectomy. The purpose of this study was to evaluate the predictive value of baseline computed tomography (CT) data for future remnant liver (FRL) hypertrophy after PVE.

METHODS

In this retrospective study, all consecutive patients undergoing right-sided PVE with or without hepatic vein embolization between 2018 and 2021 were included. CT volumetry was performed before and after PVE to assess standardized FRL volume (sFRLV). Radiomic features were extracted from baseline CT after segmenting liver (without tumor), spleen and bone marrow. For selecting features that allow classification of response (hypertrophy ≥ 1.33), a stepwise dimension reduction was performed. Logistic regression models were fitted and selected features were tested for their predictive value. Decision curve analysis was performed on the test dataset.

RESULTS

A total of 53 patients with liver tumor were included in this study. sFRLV increased significantly after PVE, with a mean hypertrophy of FRL of 1.5 ± 0.3-fold. sFRLV hypertrophy ≥ 1.33 was reached in 35 (66%) patients. Three independent radiomic features, i.e. liver-, spleen- and bone marrow-associated, differentiated well between responders and non-responders. A logistic regression model revealed the highest accuracy (area under the curve 0.875) for the prediction of response, with sensitivity of 1.0 and specificity of 0.5. Decision curve analysis revealed a positive net benefit when applying the model.

CONCLUSIONS

This proof-of-concept study provides first evidence of a potential predictive value of baseline multi-organ radiomics CT data for FRL hypertrophy after PVE.

Radiomics Applications in Spleen Imaging: A Systematic Review and Methodological Quality Assessment

The spleen, often referred to as the "forgotten organ", plays numerous important roles in various diseases. Recently, there has been an increased interest in the application of radiomics in different areas of medical imaging. This systematic review aims to assess the current state of the art and evaluate the methodological quality of radiomics applications in spleen imaging. A systematic search was conducted on PubMed, Scopus, and Web of Science. All the studies were analyzed, and several characteristics, such as year of publication, research objectives, and number of patients, were collected. The methodological quality was evaluated using the radiomics quality score (RQS). Fourteen articles were ultimately included in this review. The majority of these articles were published in non-radiological journals (78%), utilized computed tomography (CT) for extracting radiomic features (71%), and involved not only the spleen but also other organs for feature extraction (71%). Overall, the included papers achieved an average RQS total score of 9.71 ± 6.37, corresponding to an RQS percentage of 27.77 ± 16.04. In conclusion, radiomics applications in spleen imaging demonstrate promising results in various clinical scenarios. However, despite all the included papers reporting positive outcomes, there is a lack of consistency in the methodological approaches employed.

Conventional and artificial intelligence-based imaging for biomarker discovery in chronic liver disease

Chronic liver diseases, resulting from chronic injuries of various causes, lead to cirrhosis with life-threatening complications including liver failure, portal hypertension, hepatocellular carcinoma. A key unmet medical need is robust non-invasive biomarkers to predict patient outcome, stratify patients for risk of disease progression and monitor response to emerging therapies. Quantitative imaging biomarkers have already been developed, for instance, liver elastography for staging fibrosis or proton density fat fraction on magnetic resonance imaging for liver steatosis. Yet, major improvements, in the field of image acquisition and analysis, are still required to be able to accurately characterize the liver parenchyma, monitor its changes and predict any pejorative evolution across disease progression. Artificial intelligence has the potential to augment the exploitation of massive multi-parametric data to extract valuable information and achieve precision medicine. Machine learning algorithms have been developed to assess non-invasively certain histological characteristics of chronic liver diseases, including fibrosis and steatosis. Although still at an early stage of development, artificial intelligence-based imaging biomarkers provide novel opportunities to predict the risk of progression from early-stage chronic liver diseases toward cirrhosis-related complications, with the ultimate perspective of precision medicine. This review provides an overview of emerging quantitative imaging techniques and the application of artificial intelligence for biomarker discovery in chronic liver disease.

Computed Tomography-Based Texture Features for the Risk Stratification of Portal Hypertension and Prediction of Survival in Patients With Cirrhosis: A Preliminary Study

Objective

Clinical evidence suggests that the risk stratification of portal hypertension (PH) plays a vital role in disease progression and patient outcomes. However, the gold standard for stratifying PH [portal vein pressure (PVP) measurement] is invasive and therefore not suitable for routine clinical practice. This study is aimed to stratify PH and predict patient outcomes using liver or spleen texture features based on computed tomography (CT) images non-invasively.

Methods

A total of 114 patients with PH were included in this retrospective study and divided into high-risk PH (PVP ≥ 20 mm Hg, n = 57) or low-risk PH (PVP &lt; 20 mm Hg, n = 57), a progression-free survival (PFS) group (n = 14), or a non-PFS group (n = 51) based on patients with rebleeding or death after the transjugular intrahepatic portosystemic shunt (TIPS) procedure. All patients underwent contrast-enhanced CT, and the laboratory data were recorded. Texture features of the liver or spleen were obtained by a manual drawing of the region of interest (ROI) and were performed in the portal venous phase. Logistic regression analysis was applied to select the significant features related to high-risk PH, and PFS-related features were determined by the Cox proportional hazards model and Kaplan-Meier analysis. Receiver operating characteristic (ROC) curves were used to test the diagnostic capacity of each feature.

Results

Five texture features (one first-order feature from the liver and four wavelet features from the spleen) and the international normalized ratio (INR) were identified as statistically significant for stratifying PH (p &lt; 0.05). The best performance was achieved by the spleen-derived feature of wavelet.LLH_ngtdm_Busyness, with an AUC of 0.72. The only log.sigma.3.0.mm.3D_firstorder_RobustMeanAbsoluteDeviation feature from the liver was associated with PFS with a C-index of 0.72 (95% CI 0.566–0.885), which could stratify patients with PH into high- or low-risk groups. The 1-, 2-, and 3-year survival probabilities were 66.7, 50, and 33.3% for the high-risk group and 93.2, 91.5, and 84.4% for the low-risk group, respectively (p &lt; 0.05).

Conclusion

CT-based texture features from the liver or spleen may have the potential to stratify PH and predict patient survival.

CT-Based Radiomics Score Can Accurately Predict Esophageal Variceal Rebleeding in Cirrhotic Patients

Purpose: This study aimed to develop a radiomics score (Rad-score) extracted from liver and spleen CT images in cirrhotic patients to predict the probability of esophageal variceal rebleeding. Methods: In total, 173 cirrhotic patients were enrolled in this retrospective study. A total of 2,264 radiomics features of the liver and spleen were extracted from CT images. Least absolute shrinkage and selection operator (LASSO) Cox regression was used to select features and generate the Rad-score. Then, the Rad-score was evaluated by the concordance index (C-index), calibration curves, and decision curve analysis (DCA). Kaplan-Meier analysis was used to assess the risk stratification ability of the Rad-score. Results: Rad-score_Liver, Rad-score_Spleen, and Rad-score_Liver-Spleen were independent risk factors for EV rebleeding. The Rad-score_Liver-Spleen, which consisted of ten features, showed good discriminative performance, with C-indexes of 0.853 [95% confidence interval (CI), 0.776-0.904] and 0.822 (95% CI, 0.749-0.875) in the training and validation cohorts, respectively. The calibration curve showed that the predicted probability of rebleeding was very close to the actual probability. DCA verified the usefulness of the Rad-score_Liver-Spleen in clinical practice. The Rad-score_Liver-Spleen showed good performance in stratifying patients into high-, intermediate- and low-risk groups in both the training and validation cohorts. The C-index of the Rad-score_Liver-Spleen in the hepatitis B virus (HBV) cohort was higher than that in the non-HBV cohort. Conclusion: The radiomics score extracted from liver and spleen CT images can predict the risk of esophageal variceal rebleeding and stratify cirrhotic patients accordingly.

Artificial intelligence in the diagnosis of cirrhosis and portal hypertension

Clinically significant portal hypertension is associated with an increased risk of developing gastroesophageal varices and hepatic decompensation. Hepatic venous pressure gradient measurement and esophagogastroduodenoscopy are the gold-standard methods for assessing clinically significant portal hypertension and gastroesophageal varices, respectively. However, invasiveness, cost, and feasibility limit their widespread use, especially if repeated and serial evaluations are required to assess the efficacy of pharmacotherapy. Artificial intelligence describes a range of techniques that allow machines to perform tasks typically thought to require human reasoning and problem-solving skills. Artificial intelligence has made great strides in the field of medicine, and is also involved in portal hypertension diagnosis. Artificial intelligence tools will potentially transform our practice by leveraging massive amounts of data to personalize care to the right patient, in the right amount, at the right time. This review focuses on the recent advances in artificial intelligence for the noninvasive diagnosis of portal hypertension and gastroesophageal varices and monitoring of risk assessment of its complications in clinical practice.

Spleen Radiomics Signature: A Potential Biomarker for Prediction of Early and Late Recurrences of Hepatocellular Carcinoma After Resection

OBJECTIVES

To explore the usefulness of spleen radiomics features based on contrast-enhanced computed tomography (CECT) in predicting early and late recurrences of hepatocellular carcinoma (HCC) patients after curative resection.

METHODS

This retrospective study included 237 HCC patients who underwent CECT and curative resection between January 2006 to January 2016. Radiomic features were extracted from CECT images, and then the spleen radiomics signatures and the tumor radiomics signatures were built. Cox regression analysis was performed to identify the independent risk factors of early and late recurrences. Then, multiple models were built to predict the recurrence-free survival of HCC after resection, and the incremental value of the radiomics signature to the clinicopathologic model was assessed and validated. Kaplan-Meier survival analysis was used to assess the association of the models with RFS.

RESULTS

The spleen radiomics signature was independent risk factor of early recurrence of HCC. The mixed model that integrated microvascular invasion, tumor radiomics signature and spleen radiomics signature for the prediction of early recurrence achieved the highest C-index of 0.780 (95% CI: 0.728,0.831) in the primary cohort and 0.776 (95% CI: 0.716,0.836) in the validation cohort, and presented better predictive performance than clinicopathological model and combined model. In the analysis of late recurrence, the spleen radiomics signature was the only prognostic factor associated with late recurrence of HCC.

CONCLUSIONS

The identified spleen radiomics signatures are prognostic factors of both early and late recurrences of HCC patients after surgery and improve the predictive performance of model for early recurrence.

A novel radiomics-platelet nomogram for the prediction of gastroesophageal varices needing treatment in cirrhotic patients

BACKGROUND AND AIMS

Highly accurate noninvasive methods for predicting gastroesophageal varices needing treatment (VNT) are desired. Radiomics is a newly emerging technology of image analysis. This study aims to develop and validate a novel noninvasive method based on radiomics for predicting VNT in cirrhosis.

METHODS

In this retrospective-prospective study, a total of 245 cirrhotic patients were divided as the training set, internal validation set and external validation set. Radiomics features were extracted from portal-phase computed tomography (CT) images of each patient. A radiomics signature (Rad score) was constructed with the least absolute shrinkage and selection operator algorithm and tenfold cross-validation in the training set. Combined with independent risk factors, a radiomics nomogram was built with a multivariate logistic regression model.

RESULTS

The Rad score, consisting of 14 features from the gastroesophageal region and 5 from the splenic hilum region, was effective for VNT classification. The diagnostic performance was further improved by combining the Rad score with platelet counts, achieving an AUC of 0.987 (95% CI 0.969-1.00), 0.973 (95% CI 0.939-1.00) and 0.947 (95% CI 0.876-1.00) in the training set, internal validation set and external validation set, respectively. In efficacy and safety assessment, the radiomics nomogram could spare more than 40% of endoscopic examinations with a low risk of missing VNT (< 5%), and no more than 8.3% of unnecessary endoscopic examinations still be performed.

CONCLUSIONS

In this study, we developed and validated a novel, diagnostic radiomics-based nomogram which is a reliable and noninvasive method to predict VNT in cirrhotic patients.

CLINICAL TRIALS REGISTRATION

NCT04210297.

Noninvasive imaging assessment of portal hypertension

Portal hypertension (PH) is a spectrum of complications of chronic liver disease (CLD) and cirrhosis, with manifestations including ascites, gastroesophageal varices, splenomegaly, hypersplenism, hepatic hydrothorax, hepatorenal syndrome, hepatopulmonary syndrome and portopulmonary hypertension. PH can vary in severity and is diagnosed via invasive hepatic venous pressure gradient measurement (HVPG), which is considered the reference standard. Accurate diagnosis of PH and assessment of severity are highly relevant as patients with clinically significant portal hypertension (CSPH) are at higher risk for developing acute variceal bleeding and mortality. In this review, we discuss current and upcoming noninvasive imaging methods for diagnosis and assessment of severity of PH.