Increase of sensitivity of sputum cytology using high‐resolution image cytometry: Field study results
Bibliographic record
Abstract
Lung cancer remains the leading cause of cancer deaths in the developed world. There is no widely accepted method to screen for this cancer. The most commonly used method remains conventional sputum cytology, but this method is hampered by low sensitivity. We tested the hypothesis that sensitivity of sputum cytology for early lung cancer can be greatly improved by using image analysis of sputum cells, at a modest reduction of specificity. The study was double-blinded and used sputum samples from subjects with well-characterized clinical diagnoses. There were 177 cancers, 98 dysplasias, and 558 normals. The study samples were separated into two independent sets: training set and test set. Sputum samples were collected prospectively from subjects with a high probability of having lung cancer. Seven institutions from five countries participated in the study. All subjects had complete clinical diagnoses which included, as a minimum, negative chest x-rays for all negative cancers, while all cancers had confirmed tissue pathology. Samples were prepared according to the Saccomanno method. For conventional cytology, slides were stained using Papanicolaou stain. For image analysis, slides were stained using a DNA-specific (Feulgen-Thionin) stain. An automated, high-resolution image cytometer was used for measurements. At 90% specificity, sensitivity of 60% can be achieved for adenocarcinoma, compared to only 14% sensitivity of conventional cytology (at 99% specificity). Similarly, 45% sensitivity at 90% specificity can be reached for stages 0 and I lung cancer, compared to only 14% (at 99% specificity) using conventional cytology.Cytometry combined with conventional cytology shows an increase in sensitivity to early-stage cancer and to adenocarcinomas compared to conventional cytology alone. While the results are encouraging, the sensitivity to detect early lung cancer should be further improved to 70-80% at 90-95% specificity before this test can be considered for screening of high-risk individuals for lung cancer. Cytometry (Clin. Cytometry) 50:168-176, 2002.
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 | 0.005 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| 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".