Dataset Information

Diagnostic Performance of LI-RADS v2018 versus KLCA-NCC 2018 Criteria for Hepatocellular Carcinoma Using Magnetic Resonance Imaging with Hepatobiliary Agent: A Systematic Review and Meta-Analysis of Comparative Studies.

ABSTRACT:

Background/aims

To compare the performance of the Liver Imaging Reporting and Data System (LI-RADS) v2018 and Korean Liver Cancer Association-National Cancer Center (KLCA-NCC) 2018 criteria for diagnosing hepatocellular carcinoma (HCC) using magnetic resonance imaging (MRI) with hepatobiliary agent (HBA).

Methods

We searched the MEDLINE and EMBASE for studies from January 1, 2018, to October 20, 2021, that compared the diagnostic performance of two imaging criteria on HBA-MRI. A bivariate random-effects model was fitted to calculate the per-observation sensitivity and specificity, and the estimates of paired data were compared. Subgroup analysis was performed based on the observation size. Meta-regression analysis was also performed for study heterogeneity.

Results

Of the six studies included, the pooled sensitivity of the definite HCC category of the KLCA-NCC criteria (82%; 95% confidence interval [CI], 74% to 90%; I²=84%) was higher than that of LR-5 of LI-RADS v2018 (65%; 95% CI, 52% to 77%; I²=96%) for diagnosing HCC (p<0.001), while the specificity was lower for KLCA-NCC criteria (87%; 95% CI, 84% to 91%; I²=0%) than LI-RADS v2018 (93%; 95% CI, 91% to 96%; I²=0%) (p=0.017). For observations sized ≥20 mm, the sensitivity was higher for KLCA-NCC 2018 than for LI-RADS v2018 (84% vs 74%, p=0.012), with no significant difference in specificity (81% vs 85%, p=0.451). The reference standard was a significant factor contributing to the heterogeneity of sensitivities.

Conclusions

The definite HCC category of KLCA-NCC 2018 provided a higher sensitivity and lower specificity than the LR-5 of LI-RADS v2018 for diagnosing HCC using MRI with HBA.

SUBMITTER: Shin J

PROVIDER: S-EPMC10191791 | biostudies-literature | 2023 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Diagnostic Performance of LI-RADS v2018 versus KLCA-NCC 2018 Criteria for Hepatocellular Carcinoma Using Magnetic Resonance Imaging with Hepatobiliary Agent: A Systematic Review and Meta-Analysis of Comparative Studies.

Shin Jaeseung J Lee Sunyoung S Yoon Ja Kyung JK Son Won Jeong WJ Roh Yun Ho YH Chung Yong Eun YE Choi Jin-Young JY Park Mi-Suk MS

Gut and liver 20221101 3

<h4>Background/aims</h4>To compare the performance of the Liver Imaging Reporting and Data System (LI-RADS) v2018 and Korean Liver Cancer Association-National Cancer Center (KLCA-NCC) 2018 criteria for diagnosing hepatocellular carcinoma (HCC) using magnetic resonance imaging (MRI) with hepatobiliary agent (HBA).<h4>Methods</h4>We searched the MEDLINE and EMBASE for studies from January 1, 2018, to October 20, 2021, that compared the diagnostic performance of two imaging criteria on HBA-MRI. A b ...[more]

PMID: 36317516

Similar Datasets

Project description:ObjectiveTo evaluate the performance of the 2018 Korean Liver Cancer Association-National Cancer Center (KLCA-NCC) Practice Guidelines (hereafter, PG) for the diagnosis of hepatocellular carcinoma (HCC) using gadoxetic acid-enhanced MRI, compared to the Liver Imaging-Reporting and Data System (LI-RADS) version 2018 (hereafter, v2018).Materials and methodsFrom January 2013 to October 2015, treatment-naïve hepatic lesions (≥ 1 cm) on gadoxetic acid-enhanced MRI in consecutive patients with chronic hepatitis B or cirrhosis were retrospectively evaluated. For each lesion, three radiologists independently analyzed the imaging features and classified the lesions into categories according to the 2018 KLCA-NCC PG and LI-RADS v2018. The imaging features and categories were determined by consensus. Generalized estimating equation (GEE) models were used to compare the per-lesion diagnostic performance of the 2018 KLCA-NCC PG and LI-RADS v2018 using the consensus data.ResultsIn total, 422 lesions (234 HCCs, 45 non-HCC malignancies, and 143 benign lesions) from 387 patients (79% male; mean age, 59 years) were included. In all lesions, the definite HCC (2018 KLCA-NCC PG) had a higher sensitivity and lower specificity than LR-5 (LI-RADS v2018) (87.2% [204/234] vs. 80.8% [189/234], p < 0.001; 86.2% [162/188] vs. 91.0% [171/188], p = 0.002). However, in lesions of size ≥ 2 cm, the definite HCC had a higher sensitivity than the LR-5 (86.8% [164/189] vs. 82.0 (155/189), p = 0.002) without a reduction in the specificity (80.0% [48/60] vs. 83.3% [50/60], p = 0.15). In all lesions, the sensitivity and specificity of the definite/probable HCC (2018 KLCA-NCC PG) and LR-5/4 did not differ significantly (89.7% [210/234] vs. 91.5% [214/234], p = 0.204; 83.5% [157/188] vs. 79.3% [149/188], p = 0.071).ConclusionFor the diagnosis of HCC of size ≥ 2 cm, the definite HCC (2018 KLCA-NCC PG) had a higher sensitivity than LR-5, without a reduction in specificity. The definite/probable HCC (2018 KLCA-NCC PG) had a similar sensitivity and specificity to that those of the LR-5/4.

Project description:Background & aimsAssessment 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.MethodsHigh-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.ResultsA 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).ConclusionsQuantitative 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 implicationsAssessment 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.

Project description:ObjectiveTo develop a domain-specific large language model (LLM) for LI-RADS v2018 categorization of hepatic observations based on free-text descriptions extracted from MRI reports.Material and methodsThis retrospective study included 291 small liver observations, divided into training (n = 141), validation (n = 30), and test (n = 120) datasets. Of these, 120 were fictitious, and 171 were extracted from 175 MRI reports from a single institution. The algorithm's performance was compared to two independent radiologists and one hepatologist in a human replacement scenario, and considering two combined strategies (double reading with arbitration and triage). Agreement on LI-RADS category and dichotomic malignancy (LR-4, LR-5, and LR-M) were estimated using linear-weighted κ statistics and Cohen's κ, respectively. Sensitivity and specificity for LR-5 were calculated. The consensus agreement of three other radiologists served as the ground truth.ResultsThe model showed moderate agreement against the ground truth for both LI-RADS categorization (κ = 0.54 [95% CI: 0.42-0.65]) and the dichotomized approach (κ = 0.58 [95% CI: 0.42-0.73]). Sensitivity and specificity for LR-5 were 0.76 (95% CI: 0.69-0.86) and 0.96 (95% CI: 0.91-1.00), respectively. When the chatbot was used as a triage tool, performance improved for LI-RADS categorization (κ = 0.86/0.87 for the two independent radiologists and κ = 0.76 for the hepatologist), dichotomized malignancy (κ = 0.94/0.91 and κ = 0.87) and LR-5 identification (1.00/0.98 and 0.85 sensitivity, 0.96/0.92 and 0.92 specificity), with no statistical significance compared to the human readers' individual performance. Through this strategy, the workload decreased by 45%.ConclusionLI-RADS v2018 categorization from unlabelled MRI reports is feasible using our LLM, and it enhances the efficiency of data curation.Critical relevance statementOur proof-of-concept study provides novel insights into the potential applications of LLMs, offering a real-world example of how these tools could be integrated into a local workflow to optimize data curation for research purposes.Key pointsAutomatic LI-RADS categorization from free-text reports would be beneficial to workflow and data mining. LiverAI, a GPT-4-based model, supported various strategies improving data curation efficiency by up to 60%. LLMs can integrate into workflows, significantly reducing radiologists' workload.

Dataset Information

Diagnostic Performance of LI-RADS v2018 versus KLCA-NCC 2018 Criteria for Hepatocellular Carcinoma Using Magnetic Resonance Imaging with Hepatobiliary Agent: A Systematic Review and Meta-Analysis of Comparative Studies.

Background/aims

Methods

Results

Conclusions

Publications

Diagnostic Performance of LI-RADS v2018 versus KLCA-NCC 2018 Criteria for Hepatocellular Carcinoma Using Magnetic Resonance Imaging with Hepatobiliary Agent: A Systematic Review and Meta-Analysis of Comparative Studies.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets