Deep learning system for true- and pseudo-invasion in colorectal polyps
Bibliographic record
Abstract
Over 15 million colonoscopies were performed yearly in North America, during which biopsies were taken for pathological examination to identify abnormalities. Distinguishing between true- and pseudo-invasion in colon polyps is critical in treatment planning. Surgical resection of the colon is often the treatment option for true invasion, whereas observation is recommended for pseudo-invasion. The task of identifying true- vs pseudo-invasion, however, could be highly challenging. There is no specialized software tool for this task, and no well-annotated dataset is available. In our work, we obtained (only) 150 whole-slide images (WSIs) from the London Health Science Centre. We built three deep neural networks representing different magnifications in WSIs, mimicking the workflow of pathologists. We also built an online tool for pathologists to annotate WSIs to train our deep neural networks. Results showed that our novel system classifies tissue types with 95.3% accuracy and differentiates true- and pseudo-invasions with 83.9% accuracy. The system's efficiency is comparable to an expert pathologist. Our system can also be easily adjusted to serve as a confirmatory or screening tool. Our system (available at http://ai4path.ca ) will lead to better, faster patient care and reduced healthcare costs.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.002 |
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".