Computer-aided diagnosis program for classifying the risk of hepatocellular carcinoma on MR images following liver imaging reporting and data system (LI-RADS)

Automated Assessment of T2-Weighted MRI to Differentiate Malignant and Benign Primary Solid Liver Lesions in Noncirrhotic Livers Using Radiomics

RATIONALE AND OBJECTIVES

Distinguishing malignant from benign liver lesions based on magnetic resonance imaging (MRI) is an important but often challenging task, especially in noncirrhotic livers. We developed and externally validated a radiomics model to quantitatively assess T2-weighted MRI to distinguish the most common malignant and benign primary solid liver lesions in noncirrhotic livers.

MATERIALS AND METHODS

Data sets were retrospectively collected from three tertiary referral centers (A, B, and C) between 2002 and 2018. Patients with malignant (hepatocellular carcinoma and intrahepatic cholangiocarcinoma) and benign (hepatocellular adenoma and focal nodular hyperplasia) lesions were included. A radiomics model based on T2-weighted MRI was developed in data set A using a combination of machine learning approaches. The model was internally evaluated on data set A through cross-validation, externally validated on data sets B and C, and compared to visual scoring of two experienced abdominal radiologists on data set C.

RESULTS

The overall data set included 486 patients (A: 187, B: 98, and C: 201). The radiomics model had a mean area under the curve (AUC) of 0.78 upon internal validation on data set A and a similar AUC in external validation (B: 0.74 and C: 0.76). In data set C, the two radiologists showed moderate agreement (Cohen's κ: 0.61) and achieved AUCs of 0.86 and 0.82.

CONCLUSION

Our T2-weighted MRI radiomics model shows potential for distinguishing malignant from benign primary solid liver lesions. External validation indicated that the model is generalizable despite substantial MRI acquisition protocol differences. Pending further optimization and generalization, this model may aid radiologists in improving the diagnostic workup of patients with liver lesions.

Evidence Supporting Diagnostic Value of Liver Imaging Reporting and Data System for CT- and MR Imaging-based Diagnosis of Hepatocellular Carcinoma: A Systematic Review and Meta-analysis

Background

Based on the Liver Imaging Data and Reporting System (LI-RADS) guidelines, Hepatocellular Carcinoma (HCC) can be diagnosed using imaging criteria in patients at risk of HCC.

Objective

This study aimed to assess the diagnostic value of LI-RADS in high-risk patients with HCC.

Material and Methods

This systematic review is conducted on international databases, including Google Scholar, Web of Science, PubMed, Embase, PROQUEST, and Cochrane Library, with appropriate keywords. Using the binomial distribution formula, the variance of each study was calculated, and all the data were analyzed using STATA version 16. The pooled sensitivity and specificity were determined using a random-effects meta-analysis approach. Also, we used the chi-squared test and I2 index to calculate heterogeneity among studies, and Funnel plots and Egger tests were used for evaluating publication bias.

Results

The pooled sensitivity was estimated at 0.80 (95% CI 0.76-0.84). According to different types of Liver Imaging Reporting and Data Systems (LI-RADS), the highest pooled sensitivity was in version 2018 (0.83 (95% CI 0.79-0.87) (I2: 80.6%, P of chi 2 test for heterogeneity <0.001 and T2: 0.001). The pooled specificity was estimated as 0.89 (95% CI 0.87-0.92). According to different types of LI-RADS, the highest pooled specificity was in version 2014 (93.0 (95% CI 89.0-96.0) (I2: 81.7%, P of chi 2 test for heterogeneity <0.001 and T2: 0.001).

Conclusion

LI-RADS can assist radiologists in achieving the required sensitivity and specificity in high-risk patients suspected to have HCC. Therefore, this strategy can serve as an appropriate tool for identifying HCC.

A novel computer-aided diagnostic system for accurate detection and grading of liver tumors

Liver cancer is a major cause of morbidity and mortality in the world. The primary goals of this manuscript are the identification of novel imaging markers (morphological, functional, and anatomical/textural), and development of a computer-aided diagnostic (CAD) system to accurately detect and grade liver tumors non-invasively. A total of 95 patients with liver tumors (M = 65, F = 30, age range = 34–82 years) were enrolled in the study after consents were obtained. 38 patients had benign tumors (LR1 = 19 and LR2 = 19), 19 patients had intermediate tumors (LR3), and 38 patients had hepatocellular carcinoma (HCC) malignant tumors (LR4 = 19 and LR5 = 19). A multi-phase contrast-enhanced magnetic resonance imaging (CE-MRI) was collected to extract the imaging markers. A comprehensive CAD system was developed, which includes the following main steps: i) estimation of morphological markers using a new parametric spherical harmonic model, ii) estimation of textural markers using a novel rotation invariant gray-level co-occurrence matrix (GLCM) and gray-level run-length matrix (GLRLM) models, and iii) calculation of the functional markers by estimating the wash-in/wash-out slopes, which enable quantification of the enhancement characteristics across different CE-MR phases. These markers were subsequently processed using a two-stages random forest-based classifier to classify the liver tumor as benign, intermediate, or malignant and determine the corresponding grade (LR1, LR2, LR3, LR4, or LR5). The overall CAD system using all the identified imaging markers achieved a sensitivity of 91.8%±0.9%, specificity of 91.2%±1.9%, and F\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$_{1}$$\end{document}1 score of 0.91±0.01, using the leave-one-subject-out (LOSO) cross-validation approach. Importantly, the CAD system achieved overall accuracies of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$88\%\pm 5\%$$\end{document}88%±5%, 85%±2%, 78%±3%, 83%±4%, and 79%±3% in grading liver tumors into LR1, LR2, LR3, LR4, and LR5, respectively. In addition to LOSO, the developed CAD system was tested using randomly stratified 10-fold and 5-fold cross-validation approaches. Alternative classification algorithms, including support vector machine, naive Bayes classifier, k-nearest neighbors, and linear discriminant analysis all produced inferior results compared to the proposed two stage random forest classification model. These experiments demonstrate the feasibility of the proposed CAD system as a novel tool to objectively assess liver tumors based on the new comprehensive imaging markers. The identified imaging markers and CAD system can be used as a non-invasive diagnostic tool for early and accurate detection and grading of liver cancer.

Role of imaging in management of hepatocellular carcinoma: surveillance, diagnosis, and treatment response

Imaging plays a notable role in hepatocellular carcinoma (HCC) surveillance, diagnosis, and treatment response assessment. Whereas HCC surveillance among at-risk patients, including those with cirrhosis, has traditionally been ultrasound-based, there are increasing data showing that this strategy is operator-dependent and has insufficient sensitivity when used alone. Several novel blood-based and imaging modalities are currently being evaluated to increase sensitivity for early HCC detection. Multi-phase computed tomography (CT) or contrast-enhanced magnetic resonance imaging (MRI) should be performed in patients with positive surveillance tests to confirm a diagnosis of HCC and perform cancer staging, as needed. HCC is a unique cancer in that most cases can be diagnosed radiographically without histological confirmation when demonstrating characteristic features such as arterial phase hyperenhancement and delayed phase washout. The Liver Imaging Reporting and Data System offers a standardized nomenclature for reporting CT or MRI liver findings among at-risk patients. Finally, cross-sectional imaging plays a critical role for assessing response to any HCC therapy as well as monitoring for HCC recurrence in those who achieve complete response.

Impact of margin status on long-term results of liver resection for hepatocellular carcinoma: single-center time-to-recurrence analysis

Occult metastasis from the initial tumor and a de novo second primary hepatocellular carcinoma (HCC) were recognized as the main causes for the onset of early and late HCC recurrence, after liver resection (LR). This study aims to compare the time to recurrence after LR for HCC in which a margin ≤ 1 mm or > 1 mm was achieved. A single-center retrospective study involving 256 patients was conducted from June 2005 to June 2019. HCC patients resected with a radical surgical approach were investigated and stratified into groups A (resection margins ≤ 1 mm) and B (> 1 mm), as measured on final pathologic assessment. Kaplan-Meier estimators were used to estimate the probability of recurrence, and the log-rank test was used to compare groups. Uni- and multivariable (stepwise) Cox regression models were used to assess the effect of several HCC pathological characteristics. Twenty patients were excluded for the presence of microscopic tumor invasion at pathologic analysis (R1); 236 patients underwent radical (R0) LR, and were included in the study and divided into group A (n = 61, 26%), and group B (n = 175, 74%). No differences between the two groups were detected regarding: epidemiology, tumor characteristics, type of LR, and follow-up. The estimated probability of recurrence for group A and group B at 12 and 24 months was 27% and 38%, and, 33% and 46%, respectively. Univariate and multivariable Cox regression model estimates showed that tumor grading (HR 2.1, 95% CI 1.2-3.4, p = 0.006), number of nodules (HR 1.2, 95% CI 1.0-1.4, p = 0.015), and extension of the resection (HR 1.8, 95% CI 1.0-1.1, p = 0.047) were independent risk factors for HCC recurrence, with no significant effect of margin status on time to recurrence. A R0 approach that considers a margin of resection > 1 mm does not improve the likelihood of HCC recurrence. Otherwise, our experience confirms that biologic tumor characteristics are the principal factors predictive of local and systemic recurrence.

Radiomics-based classification of hepatocellular carcinoma and hepatic haemangioma on precontrast magnetic resonance images

Background

To evaluate the feasibility of using radiomics with precontrast magnetic resonance imaging for classifying hepatocellular carcinoma (HCC) and hepatic haemangioma (HH).

Methods

This study enrolled 369 consecutive patients with 446 lesions (a total of 222 HCCs and 224 HHs). A training set was constituted by randomly selecting 80% of the samples and the remaining samples were used to test. On magnetic resonance (MR) images of HCC and HH obtained with in-phase, out-phase, T2-weighted imaging (T2WI), and diffusion-weighted imaging (DWI) sequences, we outlined the target lesions and extracted 1029 radiomics features, which were classified as first-, second-, higher-order statistics and shape features. Then, the variance threshold, select k best, and least absolute shrinkage and selection operator algorithms were explored for dimensionality reduction of the features. We used four classifiers (decision tree, random forest, K nearest neighbours, and logistic regression) to identify HCC and HH on the basis of radiomics features. Two abdominal radiologists also performed the conventional qualitative analysis for classification of HCC and HH. Diagnostic performances of radiomics and radiologists were evaluated by receiver operating characteristic (ROC) analysis.

Results

Valuable radiomics features for building a radiomics signature were extracted from in-phase (n = 22), out-phase (n = 24), T2WI (n = 34) and DWI (n = 24) sequences. In comparison, the logistic regression classifier showed better predictive ability by combining four sequences. In the training set, the area under the ROC curve (AUC) was 0.86 (sensitivity: 0.76; specificity: 0.78), and in the testing set, the AUC was 0.89 (sensitivity: 0.822; specificity: 0.714). The diagnostic performance for the optimal radiomics-based combined model was significantly higher than that for the less experienced radiologist (2-years experience) (AUC = 0.702, p < 0.05), and had no statistic difference with the experienced radiologist (10-years experience) (AUC = 0.908, p>0.05).

Conclusions

We developed and validated a radiomics signature as an adjunct tool to distinguish HCC and HH by combining in-phase, out-phase, T2W, and DW MR images, which outperformed the less experienced radiologist (2-years experience), and was nearly equal to the experienced radiologist (10-years experience).

Hepatocellular carcinoma: Can LI-RADS v2017 with gadoxetic-acid enhancement magnetic resonance and diffusion-weighted imaging improve diagnostic accuracy?

BACKGROUND

The Liver Imaging Reporting and Data System (LI-RADS), supported by the American College of Radiology (ACR), has been developed for standardizing the acquisition, interpretation, reporting, and data collection of liver imaging examinations in patients at risk for hepatocellular carcinoma (HCC). Diffusion-weighted imaging (DWI), which is described as an ancillary imaging feature of LI-RADS, can improve the diagnostic efficiency of LI-RADS v2017 with gadoxetic acid-enhanced magnetic resonance imaging (MRI) for HCC.

AIM

To determine whether the use of DWI can improve the diagnostic efficiency of LI-RADS v2017 with gadoxetic acid-enhanced magnetic resonance MRI for HCC.

METHODS

In this institutional review board-approved study, 245 observations of high risk of HCC were retrospectively acquired from 203 patients who underwent gadoxetic acid-enhanced MRI from October 2013 to April 2018. Two readers independently measured the maximum diameter and recorded the presence of each lesion and assigned scores according to LI-RADS v2017. The test was used to determine the agreement between the two readers with or without DWI. In addition, the sensitivity (SE), specificity (SP), accuracy (AC), positive predictive value (PPV), and negative predictive value (NPV) of LI-RADS were calculated. Youden index values were used to compare the diagnostic performance of LI-RADS with or without DWI.

RESULTS

Almost perfect interobserver agreement was obtained for the categorization of observations with LI-RADS (kappa value: 0.813 without DWI and 0.882 with DWI). For LR-5, the diagnostic SE, SP, and AC values were 61.2%, 92.5%, and 71.4%, respectively, with or without DWI; for LR-4/5, they were 73.9%, 80%, and 75.9% without DWI and 87.9%, 80%, and 85.3% with DWI; for LR-4/5/M, they were 75.8%, 58.8%, and 70.2% without DWI and 87.9%, 58.8%, and 78.4% with DWI; for LR- 4/5/TIV, they were 75.8%, 75%, and 75.5% without DWI and 89.7%, 75%, and 84.9% with DWI. The Youden index values of the LI-RADS classification without or with DWI were as follows: LR-4/5: 0.539 vs 0.679; LR-4/5/M: 0.346 vs 0.467; and LR-4/5/TIV: 0.508 vs 0.647.

CONCLUSION

LI-RADS v2017 has been successfully applied with gadoxetate-enhanced MRI for patients at high risk for HCC. The addition of DWI significantly increases the diagnostic efficiency for HCC.