Color Fluorescence Ratio for Detection of Bronchial Dysplasia and Carcinoma <i>In situ</i>
Bibliographic record
Abstract
BACKGROUND: Autofluorescence bronchoscopy is more sensitive than conventional bronchoscopy for detecting early airway mucosal lesions. Decreased specificity can lead to excessive biopsy and increased procedural time. Onco-LIFE, a device that combines fluorescence and reflectance imaging, allows numeric representation by expressing red-to-green ratio (R/G ratio) within the region of interest. The aim of the study was to determine if color fluorescence ratio (R/G ratio) added to autofluorescence bronchoscopy could provide an objective means to guide biopsy. METHODS: Subjects at risk for lung cancer were recruited at two centers: VU University Medical Centre (Amsterdam) and BC Cancer Agency (Canada). R/G ratio for each site appearing normal or abnormal was measured before biopsy. R/G ratios were correlated with pathology, and a receiver operating characteristic curve of R/G ratio for high-grade and moderate dysplasia was done. Following analysis of the training data set obtained from two centers, a prospective validation study was done. RESULTS: Three thousand three hundred sixty-two adequate biopsies from 738 subjects with their corresponding R/G ratios were analyzed. R/G ratio 0.54 conferred 85% sensitivity and 80% specificity for the detection of high-grade and moderate dysplasia, area under the curve was 0.90, and 95% confidence interval was 0.88 to 0.92. In another 70 different sites that were assessed, kappa measurements of agreement of R/G ratios with visual scores and pathology were 0.66 (P < 0.0001) and 0.61 (P < 0.0001), respectively. R/G ratio combined with visual score improved specificity to 88% (95% confidence interval, 0.73-0.96) for high-grade and moderate dysplasia. CONCLUSION: Color fluorescence ratio can objectively guide the bronchoscopist in selecting sites for biopsy with good pathologic correlation.
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 | 0.002 | 0.005 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 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".