Deep Learning-Based Analysis of Ultrasound Colon Videos for Enhanced Medical Imaging of Motor Patterns and Content Flow
Bibliographic record
Abstract
High-resolution manometry has been the gold standard for examining human colon motility, but this method has significant drawbacks, including high costs, lengthy procedures, and patient discomfort. This has led us to explore ultrasonography as a potential alternative. We discovered that conventional machine-learning techniques for segmenting gut walls have been hindered by tracking errors. The present study introduces an innovative approach for monitoring and segmenting colonic walls in ultrasound videos by combining advanced computer vision techniques with U-Net models. The approach involved training a deep-learning U-Net model specifically for intestinal wall segmentation by manually preparing the dataset. Once trained, the model segments and analyzes colonic walls in real-time ultrasound videos, generating spatiotemporal contraction maps and content flow analyses. The method was validated using patient and volunteer data, achieving high Intersection over Union (IoU) scores. The U-Net model demonstrated superior performance to traditional machine learning techniques in tracking colonic walls, even in low-resolution videos. This work showcases how deep learning models can enhance the accuracy and reliability of colonic motility studies using ultrasound, paving the way for more efficient and patientfriendly diagnostic methods.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 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 | 0.001 |
| Open science | 0.000 | 0.000 |
| 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".