An improved algorithm using a Health Canada‐approved DNA‐image cytometry system for non‐invasive screening of high‐grade oral lesions
Bibliographic record
Abstract
Abstract Background DNA‐image cytometry (DNA‐ICM) is able to detect gross alterations of cellular DNA‐content representing aneuploidy, a biomarker of malignancy. A Health Canada‐approved DNA‐ICM system, ClearCyte ® in combination with a cytopathologist's review, has demonstrated high sensitivity (89%) and specificity (97%) in identifying high‐grade oral lesions. The study objective was to create an improved automated algorithm (iClearcyte) and test its robustness in differentiating high grade from benign reactive oral lesions without a cytopathologist's input. Methods A set of 214 oral brushing samples of oral cancer (n = 92), severe dysplasia (n = 20), reactive lesions (n = 52), and normal samples (n = 50) were spun down onto slides and stained using Feulgen‐Thionin reaction. Following ClearCyte ® scan, nuclear features were calculated, and nuclei categorized into “diploid,” “hyperdiploid,” “tetraploid,” and “aneuploid” DNA ploidy groups by the ClearCyte ® software. The samples were randomized into training and test sets (70:30) based on patient's age, sex, tobacco use, and lesion site risk. The training set was used to create a new algorithm which was then validated using the remaining samples in the test set, where sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated. Results The proposed iClearCyte algorithm (>1 “aneuploid” cell or ≥ 1.7% combined “hyperdiploid” and “tetraploid” nuclei frequency) identified high‐grade samples with sensitivity, specificity, PPV, and NPV of 100.0%, 86.7%, 89.7%, and 100.0%, respectively, in the test set. Conclusion The iClearCyte test has potential to serve as a robust non‐invasive automated oral cancer screening tool promoting early oral cancer detection and decreasing the number of unnecessary invasive biopsies.
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 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".