CT-Based Radiomics Nomogram: A Potential Tool for Differentiating Hepatocellular Adenoma From Hepatocellular Carcinoma in the Noncirrhotic Liver

Systematic review and meta-analysis on the classification metrics of machine learning algorithm based radiomics in hepatocellular carcinoma diagnosis

The aim of this systematic review and meta-analysis is to evaluate the performance of classification metrics of machine learning-driven radiomics in diagnosing hepatocellular carcinoma (HCC). Following the PRISMA guidelines, a comprehensive search was conducted across three major scientific databases-PubMed, ScienceDirect, and Scopus-from 2018 to 2022. The search yielded a total of 436 articles pertinent to the application of machine learning and deep learning for HCC prediction. These studies collectively reflect the burgeoning interest and rapid advancements in employing artificial intelligence (AI)-driven radiomics for enhanced HCC diagnostic capabilities. After the screening process, 34 of these articles were chosen for the study. The area under curve (AUC), accuracy, specificity, and sensitivity of the proposed and basic models were assessed in each of the studies. Jamovi (version 1.1.9.0) was utilised to carry out a meta-analysis of 12 cohort studies to evaluate the classification accuracy rate. The risk of bias was estimated, and Logistic Regression was found to be the most suitable classifier for binary problems, with least absolute shrinkage and selection operator (LASSO) as the feature selector. The pooled proportion for HCC prediction classification was high for all performance metrics, with an AUC value of 0.86 (95 % CI: 0.83-0.88), accuracy of 0.83 (95 % CI: 0.78-0.88), sensitivity of 0.80 (95 % CI: 0.75-0.84) and specificity of 0.84 (95 % CI: 0.80-0.88). The performance of feature selectors, classifiers, and input features in detecting HCC and related factors was evaluated and it was observed that radiomics features extracted from medical images were adequate for AI to accurately distinguish the condition. HCC based radiomics has favourable predictive performance especially with addition of clinical features that may serve as tool that support clinical decision-making.

Comparing Texture Analysis of Apparent Diffusion Coefficient MRI in Hepatocellular Adenoma and Hepatocellular Carcinoma

AIM

This study aimed to assess the effectiveness of using MRI-apparent diffusion coefficient (ADC) map-driven radiomics to differentiate between hepatocellular adenoma (HCA) and hepatocellular carcinoma (HCC) features.

MATERIALS AND METHODS

The study involved 55 patients with liver tumors (20 with HCA and 35 with HCC), featuring 106 lesions equally distributed between hepatic carcinoma and hepatic adenoma who underwent texture analysis on ADC map MR images. The analysis identified several imaging features that significantly differed between the HCA and HCC groups. Four classification models were compared for distinguishing HCA from HCC including linear support vector machine (linear-SVM), radial basis function SVM (RBF-SVM), random forest (RF), and k-nearest neighbor (KNN).

RESULTS

The k-nearest neighbor (KNN) classifier displayed the top accuracy (0.89) and specificity (0.90). Linear-SVM and KNN classifiers showcased the leading sensitivity (0.88) for both, with the KNN classifier achieving the highest precision (0.9). In comparison, the conventional interpretation had lower sensitivity (70.1%) and specificity (77.9%).

CONCLUSION

The study found that utilizing ADC maps for texture analysis in MR images is a viable method to differentiate HCA from HCC, yielding promising results in identified texture features.

Differential diagnosis of hepatocellular carcinoma and intrahepatic cholangiocarcinoma based on spatial and channel attention mechanisms

BACKGROUND

The pre-operative non-invasive differential diagnosis of hepatocellular carcinoma (HCC) and intrahepatic cholangiocarcinoma (ICC) mainly depends on imaging. However, the accuracy of conventional imaging and radiomics methods in differentiating between the two carcinomas is unsatisfactory. In this study, we aimed to establish a novel deep learning model based on computed tomography (CT) images to provide an effective and non-invasive pre-operative differential diagnosis method for HCC and ICC.

MATERIALS AND METHODS

We retrospectively investigated the CT images of 395 HCC patients and 99 ICC patients who were diagnosed based on pathological analysis. To differentiate between HCC and ICC we developed a deep learning model called CSAM-Net based on channel and spatial attention mechanisms. We compared the proposed CSAM-Net with conventional radiomic models such as conventional logistic regression, least absolute shrinkage and selection operator regression, support vector machine, and random forest models.

RESULTS

With respect to differentiating between HCC and ICC, the CSAM-Net model showed area under the receiver operating characteristic curve (AUC) values of 0.987 (accuracy = 0.939), 0.969 (accuracy = 0.914), and 0.959 (accuracy = 0.912) for the training, validation, and test sets, respectively, which were significantly higher than those of the conventional radiomics models (0.736-0.913 [accuracy = 0.735-0.912], 0.602-0.828 [accuracy = 0.647-0.818], and 0.638-0.845 [accuracy = 0.618-0.849], respectively. The decision curve analysis showed a high net benefit of the CSAM-Net model, which suggests potential efficacy in differentiating between HCC and ICC in the diagnosis of liver cancers.

CONCLUSIONS

The proposed CSAM-Net model based on channel and spatial attention mechanisms provides an effective and non-invasive tool for the differential diagnosis of HCC and ICC on CT images, and has potential applications in diagnosis of liver cancers.

Applications of Dynamic Contrast-Enhanced Ultrasound in Differential Diagnosis of Hepatocellular Carcinoma and Intrahepatic Cholangiocarcinoma in Non-cirrhotic Liver

OBJECTIVE

The aim of the work described here was to investigate the value of dynamic contrast enhanced ultrasound (DCE-US) and quantitative analysis in pre-operative differential diagnosis of intrahepatic cholangiocarcinoma (ICC) and hepatocellular carcinoma (HCC) in non-cirrhotic liver.

METHODS

In this retrospective study, patients with histopathologically proven ICC and HCC lesions in non-cirrhotic liver were included. All patients underwent contrast-enhanced ultrasound (CEUS) examinations with an Acuson Sequoia unit (Siemens Healthineers, Mountain View, CA, USA) unit or LOGIQ E20 (GE Healthcare, Milwaukee, WI, USA) within 1 wk before surgery. SonoVue (Bracco, Milan, Italy) was used as the contrast agent. B-mode ultrasound (BMUS) features and CEUS enhancement patterns were analyzed. DCE-US analysis was performed by VueBox software (Bracco). Two regions of interest (ROIs) were set in the center of the focal liver lesions and their surrounding liver parenchyma. Time-intensity curves (TICs) were generated, and quantitative perfusion parameters were obtained and compared between the ICC and HCC groups using the Student t-test or Mann-Whitney U-test.

RESULTS

From November 2020 to February 2022, patients with histopathologically confirmed ICC (n = 30) and HCC (n = 24) lesions in non-cirrhotic liver were included. During the arterial phase (AP) of CEUS, ICC lesions exhibited heterogeneous hyperenhancement (13/30, 43.3%), heterogeneous hypo-enhancement (2/30, 6.7 %) and rim-like hyperenhancement (15/30, 50.0%), whereas all HCC lesions exhibited heterogeneous hyperenhancement (24/24, 100.0%) (p < 0.05). Subsequently, most of the ICC lesions exhibited AP wash-out (83.3%, 25/30), whereas a few cases exhibited wash-out in the portal venous phase (PVP) (15.7%, 5/30). In contrast, HCC lesions exhibited AP wash-out (41.7%, 10/24), PVP wash-out (41.7%, 10/24) and a small part of late phase wash-out (16.7%, 4/24) (p < 0.05). Compared with those of HCC lesions, TICs of ICCs revealed earlier and lower enhancement during the AP, faster decline during the PVP and reduced area under the curve. The combined area under the receiver operating characteristic curve (AUROC) of all significant parameters was 0.946, with 86.7% sensitivity, 95.8% specificity and 90.7% accuracy in differential diagnosis between ICC and HCC lesions in non-cirrhotic liver, which improved the diagnostic efficacy of CEUS (58.3% sensitivity, 90.0% specificity and 75.9% accuracy).

CONCLUSION

ICC and HCC lesions in non-cirrhotic liver might exhibit some overlap of CEUS features in diagnosis. DCE-US with quantitative analysis would be helpful in pre-operative differential diagnosis.

Strategy for Accurate Diagnosis by Contrast-Enhanced Ultrasound of Focal Liver Lesions in Patients Not at High Risk for Hepatocellular Carcinoma: A Preliminary Study

OBJECTIVE

To develop an effective strategy for accurate diagnosis of focal liver lesions (FLLs) in patients with non-high risk for hepatocellular carcinoma (HCC).

METHODS

From January 2012 to December 2015, consecutive patients with non-high risk for HCC who underwent contrast-enhanced ultrasound (CEUS) were included in this retrospective double-reader study. All patients were stratified into 2 different risks (intermediate, low-risk) groups according to criteria based on clinical characteristics, known as clinical risk stratification criteria. For the intermediate-risk group, the CEUS criteria for identifying benign lesions and HCCs were constructed based on selected CEUS features. The diagnostic performance of the clinical risk stratification criteria, and CEUS criteria for identifying benign lesions and HCCs was evaluated.

RESULTS

This study included 348 FLLs in 348 patients. The sensitivity and specificity of the clinical risk stratification criteria for malignancy was 97.8 and 69.8%. Patients were classified as intermediate risk if they were male, or older than 40 years of age, or HBcAb positive, or having positive tumor markers. Otherwise, patients were classified as low risk. Among the 348 patients, 327 were in the intermediate-risk group and 21 were in the low-risk group. In the intermediate-risk group, the CEUS criteria for identifying benign lesions were any of the following features: 1) hyper/isoenhancement in the arterial phase without washout, 2) nonenhancement in all phases, 3) peripheral discontinuous globular enhancement in the arterial phase, 4) centrifugal enhancement or peripheral enhancement followed by no central enhancement, or 5) enhanced septa. The accuracy, sensitivity, and specificity of the CEUS criteria for identifying benign lesions were 94.5, 83.0, and 99.6%, respectively. Arterial phase hyperenhancement followed by mild and late washout (>60 seconds) was more common in HCC patients than in non-HCC patients (P < .001). Using arterial phase hyperenhancement followed by mild and late washout as the CEUS criteria for identifying HCCs, the sensitivity and specificity were 52.6 and 95.3%, but unfortunately, the positive predictive value was only 82.0%. For the low-risk group, no further analysis was performed due to the small sample size.

CONCLUSIONS

Initial clinical risk stratification followed by assessment of certain CEUS features appears to be a promising strategy for the accurate diagnosis of FLLs in patients not at high risk for HCC.

Radiomics in the diagnosis and treatment of hepatocellular carcinoma

Hepatocellular carcinoma (HCC) is a common malignant tumor. At present, early diagnosis of HCC is difficult and therapeutic methods are limited. Radiomics can achieve accurate quantitative evaluation of the lesions without invasion, and has important value in the diagnosis and treatment of HCC. Radiomics features can predict the development of cancer in patients, serve as the basis for risk stratification of HCC patients, and help clinicians distinguish similar diseases, thus improving the diagnostic accuracy. Furthermore, the prediction of the treatment outcomes helps determine the treatment plan. Radiomics is also helpful in predicting the HCC recurrence, disease-free survival and overall survival. This review summarized the role of radiomics in the diagnosis, treatment and prognosis of HCC.

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.

Current status and future perspectives of radiomics in hepatocellular carcinoma

Given the frequent co-existence of an aggressive tumor and underlying chronic liver disease, the management of hepatocellular carcinoma (HCC) patients requires experienced multidisciplinary team discussion. Moreover, imaging plays a key role in the diagnosis, staging, restaging, and surveillance of HCC. Currently, imaging assessment of HCC entails the assessment of qualitative characteristics which are prone to inter-reader variability. Radiomics is an emerging field that extracts high-dimensional mineable quantitative features that cannot be assessed visually with the naked eye from medical imaging. The main potential applications of radiomic models in HCC are to predict histology, response to treatment, genetic signature, recurrence, and survival. Despite the encouraging results to date, there are challenges and limitations that need to be overcome before radiomics implementation in clinical practice. The purpose of this article is to review the main concepts and challenges pertaining to radiomics, and to review recent studies and potential applications of radiomics in HCC.

The Role of Radiomics and AI Technologies in the Segmentation, Detection, and Management of Hepatocellular Carcinoma

Hepatocellular carcinoma (HCC) is the most common primary hepatic neoplasm. Thanks to recent advances in computed tomography (CT) and magnetic resonance imaging (MRI), there is potential to improve detection, segmentation, discrimination from HCC mimics, and monitoring of therapeutic response. Radiomics, artificial intelligence (AI), and derived tools have already been applied in other areas of diagnostic imaging with promising results. In this review, we briefly discuss the current clinical applications of radiomics and AI in the detection, segmentation, and management of HCC. Moreover, we investigate their potential to reach a more accurate diagnosis of HCC and to guide proper treatment planning.

Pattern Classification for Ovarian Tumors by Integration of Radiomics and Deep Learning Features

BACKGROUND

Ovarian tumor is a common female genital tumor, among which malignant tumors have a poor prognosis. The survival rate of 70% of patients with ovarian cancer is less than 5 years, while benign ovarian tumor is better, so the early diagnosis of ovarian cancer is important for the treatment and prognosis of patients.

OBJECTIVES

Our aim is to establish a classification model for ovarian tumors.

METHODS

We extracted radiomics and deep learning features from patients'CT images. The four-step feature selection algorithm proposed in this paper was used to obtain the optimal combination of features, then, a classification model was developed by combining those selected features and support vector machine. The receiver operating characteristic curve and an area under the curve (AUC) analysis were used to evaluate the performance of the classification model in both the training and test cohort.

RESULTS

The classification model, which combined radiomics features with deep learning features, demonstrated better classification performance with respect to the radiomics features model alone in training cohort (AUC 0.9289 vs. 0.8804, P < 0.0001, accuracy 0.8970 vs. 0.7993, P < 0.0001), and significantly improve the performance in the test cohort (AUC 0.9089 vs. 0.8446, P = 0.001, accuracy 0.8296 vs. 0.7259, P < 0.0001).

CONCLUSION

The experiments showed that deep learning features play an active role in the construction of classification model, and the proposed classification model achieved excellent classification performance, which can potentially become a new auxiliary diagnostic tool.

Imaging Features of Hepatocellular Carcinoma in the Non-Cirrhotic Liver with Sonazoid-Enhanced Contrast-Enhanced Ultrasound

Purpose: To investigate the Sonazoid-enhanced contrast-enhanced ultrasound (CEUS) features of hepatocellular carcinoma (HCC) in a non-cirrhosis liver background, in comparison to those in liver cirrhosis. Methods: In this retrospective study, 19 patients with surgery and histopathologically proven HCC lesions in non-cirrhosis liver background were included regarding Sonazoid-enhanced CEUS characteristics. Two radiologists evaluated the CEUS features of HCC lesions according to the WFUMB (World Federation of Societies for Ultrasound in Medicine and Biology) guidelines criteria. Thirty-six patients with HCC lesions in liver cirrhosis were included as a control group. Final diagnoses were confirmed by surgery and histopathological results. Results: Liver background of the non-cirrhosis group including normal liver (n = 7), liver fibrosis (n = 11), and alcoholic liver disease (n = 1). The mean size of non-cirrhosis HCC lesions was 60.8 ± 46.8 mm (ranging from 25 to 219 mm). During the arterial phase of Sonazoid-enhanced CEUS, most HCCs in non-cirrhotic liver (94.7%, 18/19) and in cirrhotic liver (83.3%, 30/36) presented non-rim hyperenhancement. During the portal venous phase, HCC lesions in the non-cirrhosis liver group showed relatively early washout (68.4%, 13/19) (p = 0.090). Meanwhile, HCC lesions in liver cirrhosis background showed isoenhancement (55.6%, 20/36). All lesions in the non-cirrhotic liver group showed hypoenhancement in the late phase and the Kupffer phase (100%, 19/19). Five cases of HCC lesions in liver cirrhosis showed isoenhancement during the late phase and hypoenhancement during the Kupffer phase (13.9%, 5/36). The rest of the cirrhotic HCC lesions showed hypoenhancement during the late phase and the Kupffer phase (86.1%, 31/36). Additional hypoenhanced lesions were detected in three patients in the non-cirrhosis liver group and eight patients in the liver cirrhosis group (mean size: 13.0 ± 5.6 mm), which were also suspected to be HCC lesions. Conclusions: Heterogeneous hyperenhancement during the arterial phase as well as relatively early washout are characteristic features of HCC in the non-cirrhotic liver on Sonazoid-enhanced CEUS.

Contrast-Enhanced Ultrasound Using Perfluorobutane: Impact of Proposed Modified LI-RADS Criteria on Hepatocellular Carcinoma Detection

BACKGROUND. Contrast-enhanced ultrasound (CEUS) LI-RADS version 2017 (v2017) applies only to CEUS examinations performed using pure blood pool agents, noting that future versions will address combined blood pool and Kupffer cell agents such as perfluorobutane. Such agents may improve hepatocellular carcinoma (HCC) detection by visualization of a defect in the Kupffer phase (obtained ≥ 10 minutes after injection). OBJECTIVE. The purpose of our study was to compare the diagnostic performance of the LR-5 category for HCC detection in at-risk patients between CEUS LI-RADS v2017 and proposed modified criteria for CEUS examinations performed using perfluorobutane. METHODS. This retrospective study included 293 patients at risk for HCC (259 men, 34 women; mean age, 55 ± 12 [SD] years) who underwent CEUS using perfluorobutane from March 1, 2020, to October 30, 2020, showing a total of 304 observations (274 HCC, 14 non-HCC malignancy, and 16 benign lesions). Two readers independently assessed examinations and assigned categories using both CEUS LI-RADS v2017 and the proposed modified criteria. In the modified criteria, observations 10 mm or greater with not rim arterial phase hyperenhancement (APHE), no washout, and a Kupffer defect were upgraded from LR-4 to LR-5, and observations 10 mm or greater with not rim APHE, early washout, and a mild Kupffer defect were reassigned from LR-M to LR-5. Interreader agreement was assessed, and consensus interpretations were reached. Diagnostic performance was evaluated. RESULTS. Interreader agreement for LI-RADS category assignments, expressed using kappa coefficients, was 0.839 for CEUS LI-RADS v2017 and 0.854 for the modified criteria. Modified criteria upgraded 35 observations from LR-4 to LR-5 on the basis of a Kupffer defect, of which 34 were HCC and one was benign. Modified criteria reassigned 22 observations from LR-M to LR-5 on the basis of a mild Kupffer defect, of which all were HCC. LR-5 using modified criteria, compared with CEUS LI-RADS v2017, had significantly increased sensitivity (89% vs 69%, p < .001), a nonsignificant decrease in specificity (83% vs 87%, p > .99), and significantly increased accuracy (89% vs 71%, p < .001) for HCC. CONCLUSION. When using perfluorobutane for CEUS in at-risk patients, modified criteria incorporating Kupffer defects significantly improve sensitivity without significant loss of specificity in HCC detection. CLINICAL IMPACT. Future CEUS LI-RADS updates seeking to address the use of combined blood pool and Kupffer cell agents should consider adoption of the explored criteria.

Clinical application of deep learning and radiomics in hepatic disease imaging: a systematic scoping review

OBJECTIVE

Artificial intelligence (AI) has begun to play a pivotal role in hepatic imaging. This systematic scoping review summarizes the latest progress of AI in evaluating hepatic diseases based on computed tomography (CT) and magnetic resonance (MR) imaging.

METHODS

We searched PubMed and Web of Science for publications, using terms related to deep learning, radiomics, imaging methods (CT or MR), and the liver. Two reviewers independently selected articles and extracted data from each eligible article. The Quality Assessment of Diagnostic Accuracy Studies-AI (QUADAS-AI) tool was used to assess the risk of bias and concerns regarding applicability.

RESULTS

The screening identified 45 high-quality publications from 235 candidates, including 8 on diffuse liver diseases and 37 on focal liver lesions. Nine studies used deep learning and 36 studies used radiomics. All 45 studies were rated as low risk of bias in patient selection and workflow, but 36 (80%) were rated as high risk of bias in the index test because they lacked external validation. In terms of concerns regarding applicability, all 45 studies were rated as low concerns. These studies demonstrated that deep learning and radiomics can evaluate liver fibrosis, cirrhosis, portal hypertension, and a series of complications caused by cirrhosis, predict the prognosis of malignant hepatic tumors, and differentiate focal hepatic lesions.

CONCLUSIONS

The latest studies have shown that deep learning and radiomics based on hepatic CT and MR imaging have potential application value in the diagnosis, treatment evaluation, and prognosis prediction of common liver diseases. The AI methods may become useful tools to support clinical decision-making in the future.

ADVANCES IN KNOWLEDGE

Deep learning and radiomics have shown their potential in the diagnosis, treatment evaluation, and prognosis prediction of a series of common diffuse liver diseases and focal liver lesions.

The latest application progress of radiomics in prediction and diagnosis of liver diseases

INTRODUCTION

Early detection and individualized treatment of patients with liver disease is the key to survival. Radiomics can extract high-throughput quantitative features by multimode imaging, which has good application prospects for the diagnosis, staging and prognosis of benign and malignant liver diseases. Therefore, this paper summarizes the current research status in the field of liver disease, in order to help these patients achieve personalized and precision medical care.

AREAS COVERED

This paper uses several keywords on the PubMed database to search the references, and reviews the workflow of traditional radiomics, as well as the characteristics and influencing factors of different imaging modes. At the same time, the references on the application of imaging in different benign and malignant liver diseases were also summarized.

EXPERT OPINION

For patients with liver disease, the traditional imaging evaluation can only provide limited information. Radiomics exploits the characteristics of high-throughput and high-dimensional extraction, enabling liver imaging capabilities far beyond the scope of traditional visual image analysis. Recent studies have demonstrated the prospect of this technology in personalized diagnosis and treatment decision in various fields of the liver. However, further clinical validation is needed in its application and practice.

Differentiation of hepatocellular adenoma by subtype and hepatocellular carcinoma in non-cirrhotic liver by fractal analysis of perfusion MRI

Background

To investigate whether fractal analysis of perfusion differentiates hepatocellular adenoma (HCA) subtypes and hepatocellular carcinoma (HCC) in non-cirrhotic liver by quantifying perfusion chaos using four-dimensional dynamic contrast-enhanced magnetic resonance imaging (4D-DCE-MRI).

Results

A retrospective population of 63 patients (47 female) with histopathologically characterized HCA and HCC in non-cirrhotic livers was investigated. Our population consisted of 13 hepatocyte nuclear factor (HNF)-1α-inactivated (H-HCAs), 7 β-catenin-exon-3-mutated (b^ex3-HCAs), 27 inflammatory HCAs (I-HCAs), and 16 HCCs. Four-dimensional fractal analysis was applied to arterial, portal venous, and delayed phases of 4D-DCE-MRI and was performed in lesions as well as remote liver tissue. Diagnostic accuracy of fractal analysis was compared to qualitative MRI features alone and their combination using multi-class diagnostic accuracy testing including kappa-statistics and area under the receiver operating characteristic curve (AUC). Fractal analysis allowed quantification of perfusion chaos, which was significantly different between lesion subtypes (multi-class AUC = 0.90, p < 0.001), except between I-HCA and HCC. Qualitative MRI features alone did not allow reliable differentiation between HCA subtypes and HCC (κ = 0.35). However, combining qualitative MRI features and fractal analysis reliably predicted the histopathological diagnosis (κ = 0.89) and improved differentiation of high-risk lesions (i.e., HCCs, b^ex3-HCAs) and low-risk lesions (H-HCAs, I-HCAs) from sensitivity and specificity of 43% (95% confidence interval [CI] 23–66%) and 47% (CI 32–64%) for qualitative MRI features to 96% (CI 78–100%) and 68% (CI 51–81%), respectively, when adding fractal analysis.

Conclusions

Combining qualitative MRI features with fractal analysis allows identification of HCA subtypes and HCCs in patients with non-cirrhotic livers and improves differentiation of lesions with high and low risk for malignant transformation.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13244-022-01223-6.

A Computed Tomography Nomogram for Assessing the Malignancy Risk of Focal Liver Lesions in Patients With Cirrhosis: A Preliminary Study

Purpose

The detection and characterization of focal liver lesions (FLLs) in patients with cirrhosis is challenging. Accurate information about FLLs is key to their management, which can range from conservative methods to surgical excision. We sought to develop a nomogram that incorporates clinical risk factors, blood indicators, and enhanced computed tomography (CT) imaging findings to predict the nature of FLLs in cirrhotic livers.

Method

A total of 348 surgically confirmed FLLs were included. CT findings and clinical data were assessed. All factors with P < 0.05 in univariate analysis were included in multivariate analysis. ROC analysis was performed, and a nomogram was constructed based on the multivariate logistic regression analysis results.

Results

The FLLs were either benign (n = 79) or malignant (n = 269). Logistic regression evaluated independent factors that positively affected malignancy. AFP (OR = 10.547), arterial phase hyperenhancement (APHE) (OR = 740.876), washout (OR = 0.028), satellite lesions (OR = 15.164), ascites (OR = 156.241), and nodule-in-nodule architecture (OR =27.401) were independent predictors of malignancy. The combined predictors had excellent performance in differentiating benign and malignant lesions, with an AUC of 0.959, a sensitivity of 95.24%, and a specificity of 87.5% in the training cohort and AUC of 0.981, sensitivity of 94.74%, and specificity of 93.33% in the test cohort. The C-index was 96.80%, and calibration curves showed good agreement between the nomogram predictions and the actual data.

Conclusions

The nomogram showed excellent discrimination and calibration for malignancy risk prediction, and it may aid in making FLLs treatment decisions.

Radiomics Analysis of Gd-EOB-DTPA Enhanced Hepatic MRI for Assessment of Functional Liver Reserve

Rationale and Objectives To evaluate the effectiveness of radiomics analysis based on Gd-EOB-DTPA enhanced hepatic MRI for functional liver reserve assessment in HCC patients. Materials and Methods Radiomics features were extracted from Gd-EOB-DTPA enhanced MRI images in 60 HCC patients. Boruta algorithm was performed to select features associated with indocyanine green retention rate at 15 min (ICG R15). Prediction and classification model were built by performing Random Forest regression analysis. Pearson correlation analysis and AUC of ROC were used to assess performance of the two models. Results A total of 165 radiomics features were extracted. Six radiomics features were selected to build the prediction model. A Predicted value of ICG R15 for each patient was calculated by the prediction model. Pearson correlation analysis revealed that predicted values were significantly associated with actual values of ICG R15 (R value = 0.90, p < 0.001). Nine radiomics features were selected to build the classification model. AUC of ROC revealed favorable performance of the classification model for identifying patients with ICG R15 <10% (AUC: 0.906, 95%CI: 0.900-0.913), <15% (AUC: 0.954, 95%CI: 0.950-0.958), and <20% (AUC: 0.996, 95%CI: 0.995-0.996). Conclusion Radiomics analysis of Gd-EOB-DTPA enhanced hepatic MRI can be used for assessment of functional liver reserve in HCC patients.

A deep learning radiomics model may help to improve the prediction performance of preoperative grading in meningioma

PURPOSE

This study aimed to investigate the clinical usefulness of the enhanced-T1WI-based deep learning radiomics model (DLRM) in differentiating low- and high-grade meningiomas.

METHODS

A total of 132 patients with pathologically confirmed meningiomas were consecutively enrolled (105 in the training cohort and 27 in the test cohort). Radiomics features and deep learning features were extracted from T1 weighted images (T1WI) (both axial and sagittal) and the maximum slice of the axial tumor lesion, respectively. Then, the synthetic minority oversampling technique (SMOTE) was utilized to balance the sample numbers. The optimal discriminative features were selected for model building. LightGBM algorithm was used to develop DLRM by a combination of radiomics features and deep learning features. For comparison, a radiomics model (RM) and a deep learning model (DLM) were constructed using a similar method as well. Differentiating efficacy was determined by using the receiver operating characteristic (ROC) analysis.

RESULTS

A total of 15 features were selected to construct the DLRM with SMOTE, which showed good discrimination performance in both the training and test cohorts. The DLRM outperformed RM and DLM for differentiating low- and high-grade meningiomas (training AUC: 0.988 vs. 0.980 vs. 0.892; test AUC: 0.935 vs. 0.918 vs. 0.718). The accuracy, sensitivity, and specificity of the DLRM with SMOTE were 0.926, 0.900, and 0.924 in the test cohort, respectively.

CONCLUSION

The DLRM with SMOTE based on enhanced T1WI images has favorable performance for noninvasively individualized prediction of meningioma grades, which exhibited favorable clinical usefulness superior over the radiomics features.

Radiomics in hepatocellular carcinoma: A state-of-the-art review

Hepatocellular carcinoma (HCC) is the most common cancer and the second major contributor to cancer-related mortality. Radiomics, a burgeoning technology that can provide invisible high-dimensional quantitative and mineable data derived from routine-acquired images, has enormous potential for HCC management from diagnosis to prognosis as well as providing contributions to the rapidly developing deep learning methodology. This article aims to review the radiomics approach and its current state-of-the-art clinical application scenario in HCC. The limitations, challenges, and thoughts on future directions are also summarized.

Predicting microvascular invasion in hepatocellular carcinoma: a deep learning model validated across hospitals

BACKGROUND

The accuracy of estimating microvascular invasion (MVI) preoperatively in hepatocellular carcinoma (HCC) by clinical observers is low. Most recent studies constructed MVI predictive models utilizing radiological and/or radiomics features extracted from computed tomography (CT) images. These methods, however, rely heavily on human experiences and require manual tumor contouring. We developed a deep learning-based framework for preoperative MVI prediction by using CT images of arterial phase (AP) with simple tumor labeling and without the need of manual feature extraction. The model was further validated on CT images that were originally scanned at multiple different hospitals.

METHODS

CT images of AP were acquired for 309 patients from China Medical University Hospital (CMUH). Images of 164 patients, who took their CT scanning at 54 different hospitals but were referred to CMUH, were also collected. Deep learning (ResNet-18) and machine learning (support vector machine) models were constructed with AP images and/or patients' clinical factors (CFs), and their performance was compared systematically. All models were independently evaluated on two patient cohorts: validation set (within CMUH) and external set (other hospitals). Subsequently, explainability of the best model was visualized using gradient-weighted class activation map (Grad-CAM).

RESULTS

The ResNet-18 model built with AP images and patients' clinical factors was superior than other models achieving a highest AUC of 0.845. When evaluating on the external set, the model produced an AUC of 0.777, approaching its performance on the validation set. Model interpretation with Grad-CAM revealed that MVI relevant imaging features on CT images were captured and learned by the ResNet-18 model.

CONCLUSIONS

This framework provide evidence showing the generalizability and robustness of ResNet-18 in predicting MVI using CT images of AP scanned at multiple different hospitals. Attention heatmaps obtained from model explainability further confirmed that ResNet-18 focused on imaging features on CT overlapping with the conditions used by radiologists to estimate MVI clinically.

Application of artificial intelligence in preoperative imaging of hepatocellular carcinoma: Current status and future perspectives

Hepatocellular carcinoma (HCC) is the most common primary malignant liver tumor in China. Preoperative diagnosis of HCC is challenging because of atypical imaging manifestations and the diversity of focal liver lesions. Artificial intelligence (AI), such as machine learning (ML) and deep learning, has recently gained attention for its capability to reveal quantitative information on images. Currently, AI is used throughout the entire radiomics process and plays a critical role in multiple fields of medicine. This review summarizes the applications of AI in various aspects of preoperative imaging of HCC, including segmentation, differential diagnosis, prediction of histopathology, early detection of recurrence after curative treatment, and evaluation of treatment response. We also review the limitations of previous studies and discuss future directions for diagnostic imaging of HCC.

Non-cirrhotic hepatocellular carcinoma in chronic viral hepatitis: Current insights and advancements

Primary liver cancers carry significant morbidity and mortality. Hepatocellular carcinoma (HCC) develops within the hepatic parenchyma and is the most common malignancy originating from the liver. Although 80% of HCCs develop within background cirrhosis, 20% may arise in a non-cirrhotic milieu and are referred to non-cirrhotic-HCC (NCHCC). NCHCC is often diagnosed late due to lack of surveillance. In addition, the rising prevalence of non-alcoholic fatty liver disease and diabetes mellitus have increased the risk of developing HCC on non-cirrhotic patients. Viral infections such as chronic Hepatitis B and less often chronic hepatitis C with advance fibrosis are associated with NCHCC. NCHCC individuals may have Hepatitis B core antibodies and occult HBV infection, signifying the role of Hepatitis B infection in NCHCC. Given the effectiveness of current antiviral therapies, surgical techniques and locoregional treatment options, nowadays such patients have more options and potential for cure. However, these lesions need early identification with diagnostic models and multiple surveillance strategies to improve overall outcomes. Better understanding of the NCHCC risk factors, tumorigenesis, diagnostic tools and treatment options are critical to improving prognosis and overall outcomes on these patients. In this review, we aim to discuss NCHCC epidemiology, risk factors, and pathogenesis, and elaborate on NCHCC diagnosis and treatment strategies.