PS2 - 205 Application of Computer-Assisted Diagnostics for Immunohistochemistry Analysis of Gliomas
Bibliographic record
Abstract
In the current practice of pathology, the identification of cell markers and their respective distribution represents an indispensable dialogue for diagnostic, predictive, therapeutic, and research purposes. Early immunohistochemical protocols were limited to direct, fluorescent labeled antibodies, yielding quick results but lacking sensitivity. More recently, the use of indirect techniques –utilization of enzyme labels–and various detection systems have continued to advance the complexity of IHC, increasing both its specificity and sensitivity of detecting one or multiple antigen(s) (Ag) simultaneously. As such, IHC has become an affordable, powerful, and readily available means for the identification of candidate biomarkers (mostly lineage markers) in formalin-fixed, paraffin-embedded (FFPE) tissue samples. Pathologists are now asked to “quantify” expression levels of differential prognostic markers–at microscopic level–using this arguably “non-quantitative” technique. Conventionally, histological grading relies mainly on manual counting of positively immunostained cells, a labour intensive protocol that may be associated with subjectivity, intra- and inter- observer variation and reproducibility issues. The subjectivity and lack of reproducibility has prompted the use of computer-assisted or fully automated image analysis technologies. Digital image acquisition systems are becoming commonplace and as such, the demand for complex assessments of digital images of histological slides must be matched with quantitative platforms. In this study, we aim to introduce a computer-assisted image-computing platform that is both accurate and efficient in quantification of isolated and heterogeneous candidate biomarkers in glioblastoma.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 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".