Using computer aided optical polyp diagnosis (CADx) and expert review to evaluate colorectal polyps diagnosed as "normal mucosa" in pathology
Bibliographic record
Abstract
Aims Histopathology assessment is currently considered the gold standard for typing of diminutive colorectal polyps; however, polyps are frequently diagnosed as normal mucosa in pathology. We were therefore interested in re-evaluating pathology-based diagnosis of “mucosal polyps” using expert endoscopists and Computer Assisted Diagnosis (CADx) evaluation. Methods We extracted video sequences showing polyps diagnosed as "normal mucosa" and conducted a video-based review with two expert endoscopists (DKR, HP) to obtain optical diagnosis for each polyp. Both experts were blinded to the fact that these polyps had been diagnosed as “normal mucosa” in pathology until after all optical diagnoses were obtained. Experts evaluated the polyp initially under white light, then under Blue Light Imaging, then with CADx diagnosis shown, and were asked to diagnose each polyp before and after seeing CADx results. Results 449 polyps were resected and sent for histologic analysis, of which, 44 polyps (in 36 patients) were diagnosed as normal mucosa by pathology. Expert-based diagnoses of polyps diagnosed as "normal mucosa" were 43-45% adenoma, 40-43% hyperplastic, and 9-11% sessile serrated lesion. There was unanimous expert and CADx adenoma diagnosis for 15 polyps, and unanimous SSL diagnosis for 2 polyps between the experts. Amongst these lesions, 11/17 patients had changes in originally assigned surveillance intervals when incorporating the updated diagnoses. Review of post resection specimen evaluation or polypectomy video sequences showed that at least 90% of polyp resections were adequate. Errors in pathologic processing, sectioning, and evaluating of specimens are therefore likely the cause of misdiagnosis. Conclusions Occurrence of polyps evaluated as normal mucosa is frequent and has potential implications for patient care. This warrants further evaluation of the phenomenon in prospective clinical studies. Endoscopists should consider routinely using CADx and photo or video documentation for arbitration of polyps diagnosed as normal mucosa in pathology. Publication History Article published online: 15 April 2024 © 2024. European Society of Gastrointestinal Endoscopy. All rights reserved. Georg Thieme Verlag KG Rüdigerstraße 14, 70469 Stuttgart, Germany
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 | 0.008 | 0.017 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.005 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.005 | 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".