Combining CEUS and CT/MRI LI-RADS major imaging features: diagnostic accuracy for classification of indeterminate liver observations in patients at risk for HCC
Bibliographic record
Abstract
PURPOSE: To determine the diagnostic accuracy of combining CEUS and CT/MRI LI-RADS major imaging features for the improved categorization of liver observations indeterminate on both CT/MRI and CEUS. MATERIALS AND METHODS: A retrospective analysis using a database from a prospective study conducted at 11 centers in North America and Europe from 2018 to 2022 included a total of 109 participants at risk for HCC who had liver observations with indeterminate characterization (LR3, LR-4, and LR-M) on both CEUS and CT/MRI. The individual CEUS and CT/MRI LI-RADS major features were extracted from the original study and analyzed in various combinations. Reference standards included biopsy, explant histology, and follow-up CT/MRI. The diagnostic performance of the combinations of LI-RADS major features for definitive diagnosis of HCC was calculated. A reverse, stepwise logistical regression sub-analysis was also performed. RESULTS: This study included 114 observations indeterminate on both CT/MRI and CEUS. These observations were categorized as LR-3 (n = 37), LR-4 (n = 41), and LR-M (n = 36) on CT/MRI and LR-3 (n = 48), LR-4 (n = 36), LR-M (n = 29), and LR-TIV (n = 1) on CEUS. Of them, 43.0% (49/114) were confirmed as HCC, 37.3% (43/114) non-malignant, and 19.3% (22/114) non-hepatocellular malignancies. The highest diagnostic accuracy among the combinations of imaging features was achieved in CT/MRI LR-3 observations, where the combination of CEUS arterial phase hyper-enhancement (APHE) + CT/MRI APHE had 96.7% specificity, 75.0% positive predictive value (PPV), and 86.5% accuracy for HCC. CONCLUSION: The combination of LI-RADS major features on CT/MRI and CEUS showed higher specificity, PPV, and accuracy compared to individual modalities' assessments, particularly for CT/MRI LR-3 observations.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".