Deployment of an Artificial Intelligence Histology Tool to Aid Qualitative Assessment of Histopathology Using the Nancy Histopathology Index in Ulcerative Colitis
Bibliographic record
Abstract
BACKGROUND: Ulcerative colitis (UC) is a chronic inflammatory bowel disease characterized by increased stool frequency, rectal bleeding, and urgency. To streamline the quantitative assessment of histopathology using the Nancy Index in UC patients, we developed a novel artificial intelligence (AI) tool based on deep learning and tested it in a proof-of-concept trial. In this study, we report the performance of a modified version of the AI tool. METHODS: Nine sites from 6 countries were included. Patients were aged ≥18 years and had UC. Slides were prepared with hematoxylin and eosin staining. A total of 791 images were divided into 2 groups: 630 for training the tool and 161 for testing vs expert histopathologist assessment. The refined AI histology tool utilized a 4-neural network structure to characterize images into a series of cell and tissue type combinations and locations, and then 1 classifier module assigned a Nancy Index score. RESULTS: In comparison with the proof-of-concept tool, each feature demonstrated an improvement in accuracy. Confusion matrix analysis demonstrated an 80% correlation between predicted and true labels for Nancy scores of 0 or 4; a 96% correlation for a true score of 0 being predicted as 0 or 1; and a 100% correlation for a true score of 2 being predicted as 2 or 3. The Nancy metric (which evaluated Nancy Index prediction) was 74.9% compared with 72.3% for the proof-of-concept model. CONCLUSIONS: We have developed a modified AI histology tool in UC that correlates highly with histopathologists' assessments and suggests promising potential for its clinical application.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".