Ensemble Tabnet Predicting a T-Cell/MHC-I-Based Immune Profile Biomarker for Colorectal Liver Metastases from CT Images
Bibliographic record
Abstract
Colorectal cancer liver metastases (CLM) are the most common type of distant metastases originating from the abdomen and are characterized by a high recurrence rate after curative resection. It has been previously reported that CLM presenting a low cluster of differentiation 3 (CD3) positive T-cell infiltration density concurrent with a high major histocompatibility complex class I (MHC-I) expression were associated with poor clinical outcomes. In this study, we attempt to noninvasively predict whether a CLM exhibits the CD3LowMHCHighimmunological profile using preoperative CT images. To this end, we propose an ensemble network combining multiple Attentive Interpre table Tabular learning (TabNet) models, trained using CT-derived radiomic features. A total of 160 CLM were included in this study and randomly divided between a training set (n=130) and a hold-out test set (n=30). The proposed model yielded good prediction performance on the test set with an accuracy of 70.0% [95% confidence interval 53.6%-86.4%] and an area under the curve of 69.4% [52.9%-85.9%]. It also outperformed other off-the-shelf machine learning models. We finally demonstrated that the predicted immune profile was associated with a shorter disease-specific survival (p = .023) and time-to-recurrence (p = .020), showing the value of assessing the immune response.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| 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".