Real-Time Detection of Colorectal Adenomas Based on an Enhanced YOLOv5 Network
Bibliographic record
Abstract
Colorectal cancer remains one of the leading causes of morbidity and mortality worldwide, posing a serious threat to human health.Colonoscopy is considered the gold standard for colorectal cancer diagnosis, and adenoma detection rate (ADR) is a critical quality indicator of colonoscopic procedures.However, accurate detection is challenging due to the complex intestinal structure under colonoscopy, the presence of interfering elements such as foam, residue, and feces, and the diverse sizes and subtle features of adenomatous polyps.Moreover, most existing AI-based detection models are computationally intensive and too slow for real-time application.To address these challenges, this study proposes a real-time colorectal adenoma detection method based on an improved single-stage object detection network, YOLOv5.To mitigate issues like false negatives and false positives in intermediate video frames caused by motion blur or camera defocus, the original algorithm is enhanced by integrating motion information and a sequential bounding-box matching post-processing module.This improves recall in video-based detection by correcting missed detections in intermediate frames.Performance validation on the public ImageNet VID dataset shows a 5.93% increase in mAP, while experiments on colonoscopy video datasets demonstrate a 20.47% improvement in recall rate.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 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".