Preliminary Experimental Results from Multi-Center Clinical Trials for Detection of Cervical Precancerous Lesions Using the Cerviscan(TM) System: A Novel Full-Field Evoked Tissue Fluorescence Based Imaging Instrument
Bibliographic record
Abstract
Cervical cancer is an important cause of death in women worldwide. Women are currently screened for cervical cancer using Pap smear-an imperfect technology with poor sensitivity and specificity. Furthermore, 5-10% of the Pap smear studies result in uncertain findings called ASCUS, These patients are subjected to repeat Pap smears to determine women who need further examination by colposcopy. LifeSpex, Inc., is developing the Cerviscan(TM) system-a novel, full-field multi-spectral tissue fluorescence imaging system that is designed to detect cervical precancerous lesions (i.e. SIL) in real-time, We report preliminary results from a multi-center trial for evaluating the performance of Cerviscan(TM) system. A study population of 67 subjects, in three clinical sites in the US and Canada, each underwent three procedures: (a) repeat liquid-based Pap smear, (b) Cerviscan exam, and (c) colposcopy directed biopsy exam (gold standard). Fifty-two patients for whom data from all three exams were available (i.e. 78% of the patients enrolled) are included in this preliminary analysis. A multivariate classification algorithm has been trained using data from 228 regions (82 SIL, 146 NonSIL) in 42 women. Results are reported on an independent test set of 70 regions (25 SIL, 45 NonSIL) in 10 women. The Cerviscan(TM) system correctly identified 21/25 SIL and 42/45 NonSIL regions, giving a sensitivity of 84% and specificity of 93.3%. The Cerviscan(TM) system correctly resolved 5/7 'ASCUS+LoSIL' calls made by repeat liquid-based cytology. The Cerviscan(TM) system detects precancerous lesions with higher accuracy than repeat liquid-based Pap smear and locates lesion in real-time.
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 | 0.021 | 0.010 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".