The role of ancillary features for diagnosing hepatocellular carcinoma on CT: based on the Liver Imaging Reporting
1Department of Radiology, Beijing Friendship Hospital, Capital Medical University, 95 YongAn Road, Beijing, 100050, PR China.
Insights
Incorporating ancillary features into the Liver Imaging Reporting and Data System (LI-RADS) version 2017 on CT scans significantly enhances the diagnosis of hepatocellular carcinoma (HCC). This improved performance is particularly notable for LR-3 lesions, boosting accuracy and sensitivity.
Area of Science:
- Radiology
- Hepatology
- Oncology
Background:
- Hepatocellular carcinoma (HCC) is a significant global health concern, necessitating accurate diagnostic tools.
- The Liver Imaging Reporting and Data System (LI-RADS) is a standardized system for reporting imaging findings in patients at risk for HCC.
- Computed tomography (CT) is a primary imaging modality for HCC surveillance and diagnosis.
Purpose of the Study:
- To evaluate the diagnostic performance of LI-RADS version 2017 for HCC detection using CT.
- To compare the diagnostic accuracy of LI-RADS using only major features versus a combination of major and ancillary features.
Main Methods:
- Retrospective analysis of 205 patients at high risk for HCC, including 147 with HCC, 35 with non-HCC malignancy, and 37 with benign lesions.
- Evaluation of LI-RADS diagnostic performance based on major features alone and in combination with ancillary features on CT.
- Comparison of sensitivity, specificity, positive predictive value, negative predictive value, and accuracy between the two approaches.
Main Results:
- Using both major and ancillary features improved specificity, positive predictive value, and accuracy for LR-5 predictions of HCC compared to major features alone.
- Combining major and ancillary features increased sensitivity, negative predictive value, and accuracy for LR-4/5 predictions of HCC while maintaining high specificity.
- Ancillary features led to a category adjustment in 8.7% of lesions, indicating their impact on classification.
Conclusions:
- The integration of ancillary features into the LI-RADS v2017 algorithm on CT enhances the diagnostic performance for hepatocellular carcinoma.
- This improvement is particularly beneficial for classifying LR-3 lesions, leading to more accurate HCC diagnosis.
- Ancillary features provide valuable supplementary information for the LI-RADS classification of liver lesions.
Aim:
To investigate the diagnostic performance of Liver Imaging Reporting and Data System (LI-RADS) version 2017 for diagnosing hepatocellular carcinoma (HCC), by using major features only and combined major and ancillary features on computed tomography (CT).
Materials And Methods:
A total of 147 HCC, 35 non-HCC malignancy, and 37 benign lesions in 205 patients at high risk of HCC were evaluated retrospectively, and the diagnostic performance of LI-RADS for diagnosing HCC were compared between using major features only and adopting major and ancillary features in combination.
Results:
When using LR-5 as a predictor for diagnosing HCC, the diagnostic specificity (90.3% versus 91.7%), positive predictive value (92.3% versus 93.3%), and accuracy (68% versus 68.8%) were increased based on major and ancillary features in combination than just using major features on CT. When using LR-4/5 as a predictor for diagnosing HCC, the diagnostic sensitivity (78.9% versus 85.7%), negative predictive value (64.4% versus 72%), and accuracy (78.5% versus 82.2%) were increased while preserving a high specificity (77.8% versus 75%), according to major and ancillary features in combination rather than just using major features on CT. The LI-RADS categories of 8.7% (19/219) lesions were adjusted by adding the ancillary features on CT.
Conclusion:
Adding the ancillary features visible on CT can improve the diagnostic performance of the LI-RADS v2017 algorithm for diagnosing HCC, especially for LR-3 lesions.
More Related Videos
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
06:11Laparoscopic Anatomical Resection of the Right Anterior Lobe Based on the Laennec Capsule Technique
Published on: May 2, 2025