Radiomic Analysis of Contrast-Enhanced CT Predicts Glypican 3-PositiveHepatocellular Carcinoma
Bibliographic record
Abstract
BACKGROUND: The Glypican 3 (GPC3)-positive expression in Hepatocellular Carcinoma (HCC) is associated with a worse prognosis. Moreover, GPC3 has emerged as an immunotherapeutic target in advanced unresectable HCC systemic therapy. It is significant to diagnose GPC3-positive HCCs before therapy. Regarding imaging diagnosis of HCC, dynamic contrast-enhanced CT is more common than MRI in many regions. OBJECTIVE: The aim of this study was to construct and validate a radiomics model based on contrast-enhanced CT to predict the GPC3 expression in hepatocellular carcinoma. METHODS: This retrospective study included 141 (training cohort: n = 100; validation cohort: n = 41) pathologically confirmed HCC patients. Radiomics features were extracted from the Artery Phase (AP) images of contrast-enhanced CT. Logistic regression with the Least Absolute Shrinkage and Selection Operator (LASSO) regularization was used to select features to construct radiomics score (Rad-score). A final combined model, including the Rad-score of the selected features and clinical risk factors, was established. Receiver Operating Characteristic (ROC) curve analysis, Delong test, and Decision Curve Analysis (DCA) were used to assess the predictive performance of the clinical and radiomics models. RESULTS: 5 features were selected to construct the AP radiomics model of contrast-enhanced CT. The radiomics model of AP from contrast-enhanced CT was superior to the clinical model of AFP in training cohorts (P < 0.001), but not superior to the clinical model in validation cohorts (P = 0.151). The combined model (AUC = 0.867 vs. 0.895), including AP Rad-score and serum Alpha-Fetoprotein (AFP) levels, improved the predictive performance more than the AFP model (AUC = 0.651 vs. 0.718) in the training and validation cohorts. The combined model, with a higher decision curve indicating more net benefit, exhibited a better predictive performance than the AP radiomics model. DCA revealed that at a range threshold probability approximately above 60%, the combined model added more net benefit compared to the AP radiomics model of contrastenhanced CT. CONCLUSION: A combined model including AP Rad-score and serum AFP levels based on contrast-enhanced CT could preoperatively predict GPC3-positive expression in HCC.
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 | 0.003 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.003 | 0.003 |
| Bibliometrics | 0.002 | 0.003 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 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".