Artificial intelligence-assisted approach to assessing bowel wall thickness in pediatric inflammatory bowel disease using intestinal ultrasound images
Bibliographic record
Abstract
BACKGROUND AND AIM: Intestinal ultrasound (IUS) potentially spares patients from repeated endoscopies under sedation and eliminates the need for alternative imaging modalities like magnetic resonance enterography and computed tomography enterography scans. However, interpreting IUS images is challenging for physicians due to the time-intensive process of identifying markers indicative of inflammatory bowel disease (IBD). This study aims for fully automating the analysis of pediatric IBD to distinguish between abnormal and normal cases. METHODS: We used data set of 260 pediatric patients, consisting of 4565 IUS images with 1478 abnormal and 3087 normal cases. Meticulous annotation of the region between the lumen/mucosa and the muscularis/serosa interfaces in a subset of 612 images were performed. An artificial intelligence (AI) algorithm was trained to delineate the region between these interfaces. The boundaries of these regions were extracted, and the average bowel wall thickness (BWT) was calculated and analyzed using cutoff values ranging between 1.5 and 3 mm. RESULTS: This study showed promising segmentation performance in accurately identifying the lumen/mucosa and muscularis/serosa interfaces. In a separate test set of 3953 images, the classification performance at the 2mm BWT cutoff showed the highest sensitivity of 90.29% and a specificity of 93.70%. The AI method showed strong agreement, with an interclass correlation of 0.942 (95% CI: 0.938-0.946), compared to manual clinical measurements. CONCLUSIONS: This study demonstrates an AI approach to automate the analysis of pediatric IBD IUS images, providing a reliable tool for early detection, precise characterization, and monitoring of the disease.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 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".