Diagnostic accuracy and inter-reader reliability of the MRI Liver Imaging Reporting and Data System (version 2018) risk stratification and management system
Bibliographic record
Abstract
Background: Hepatocellular carcinoma (HCC) can be diagnosed non-invasively, provided certain imaging criteria are met. However, the recent Liver Imaging Reporting and Data System (LI-RADS) version 2018 has not been widely validated. Objectives: This study aimed to evaluate the diagnostic accuracy and reader reliability of the LI-RADS version 2018 lexicon amongst fellowship trained radiologists compared with an expert consensus reference standard. Method: This retrospective study was conducted between 2018 and 2020. A total of 50 contrast enhanced liver magnetic resonance imaging (MRI) studies evaluating focal liver observations in patients with cirrhosis, hepatitis B virus (HBV) or prior HCC were acquired. The standard of reference was a consensus review by three fellowship-trained radiologists. Diagnostic accuracy including sensitivity, specificity, positive predictive value (PPV), negative predictive values (NPV) and area under the curve (AUC) values were calculated per LI-RADS category for each reader. Kappa statistics were used to measure reader agreement. Results: Readers demonstrated excellent specificities (88% – 100%) and NPVs (85% – 100%) across all LI-RADS categories. Sensitivities were variable, ranging from 67% to 83% for LI-RADS 1, 29% to 43% for LI-RADS 2, 100% for LI-RADS 3, 70% to 80% for LI-RADS 4 and 80% to 84% for LI-RADS 5. Readers showed excellent accuracy for differentiating benign and malignant liver lesions with AUC values > 0.90. Overall inter-reader agreement was ‘good’ (kappa = 0.76, p < 0.001). Pairwise inter-reader agreement was ‘very good’ (kappa ≥ 0.90, p < 0.001). Conclusion: The LI-RADS version 2018 demonstrates excellent specificity, NPV and AUC values for risk stratification of liver observations by radiologists. Liver Imaging Reporting and Data System can reliably differentiate benign from malignant lesions when used in conjunction with corresponding LI-RADS management recommendations.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.014 | 0.035 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".