Quantification of Human Epidermal Growth Factor Receptor 2 Immunohistochemistry Using the Ventana Image Analysis System
Bibliographic record
Abstract
The use of computer-based image analysis for scoring human epidermal growth factor receptor 2 (HER2) immunohistochemistry (IHC) has gained a lot of interest recently. We investigated the performance of the Ventana Image Analysis System (VIAS) in HER2 quantification by IHC and its correlation with fluorescence in situ hybridization (FISH). We specifically compared the 3+ IHC results using the manufacturer's machine score cutoffs versus laboratory-defined cutoffs with the FISH assay. Using the manufacturer's 3+ cutoff (VIAS score; 2.51 to 3.5), 181/536 (33.7%) were scored 3+, and FISH was positive in 147/181 (81.2%), 2 (1.1%) were equivocal, and 32 (17.6%) were FISH (-). Using the laboratory-defined 3+ cutoff (VIAS score 3.5), 52 (28.7%) cases were downgraded to 2+, of which 29 (55.7%) were FISH (-), and 23 (44.2%) were FISH (+). With the revised cutoff, there were improvements in the concordance rate from 89.1% to 97.0% and in the positive predictive value from 82.1% to 97.6%. The false-positive rate for 3+ decreased from 9.0% to 0.8%. Six of 175 (3.4%) IHC (-) cases were FISH (+). Three cases with a VIAS score 3.5 showed polysomy of chromosome 17. In conclusion, the VIAS may be a valuable tool for assisting pathologists in HER2 scoring; however, the positive cutoff defined by the manufacturer is associated with a high false-positive rate. This study highlights the importance of instrument validation/calibration to reduce false-positive results.
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 | 0.004 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.007 | 0.001 |
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".