Data · dataset · 2026
COLLECT: Counterfactual Oral Lesion Library for Explainable Concept Testing
Listed in Borealis
This dataset contains clinical intra‑oral images collected by certified oral pathologists during routine dental examinations, using digital cameras under standard clinic lighting.
Description
Each image was verified by histopathology or expert assessment. Ethical approval was obtained from the McGill University IRB # [A07-M40-21B, 24-11-096].
The dataset includes four lesion types: (Aphthous Ulcer, Geographic Tongue, Hairy Tongue, and Oral Squamous Cell Carcinoma) selected from a larger study on interpretable AI for oral lesion classification. For each category, 10 high‑quality baseline images (40 total) were selected and validated by oral health experts. Each image was transformed using a structured counterfactual framework applying progressive size, color, and opacity modifications, producing five versions per image (original image and 4 counterfactuals) with a total of 600 images.
Read the rest (1 more)
Lesion size was either gradually increased or decreased to simulate growth or reduction; color was adjusted to mimic clinically similar lesion appearances; and opacity was reduced in steps to represent partial or complete lesion fading. These controlled variations simulate clinically meaningful changes and support research on AI model robustness, interpretability, and diagnostic reliability in oral imaging.
Links
Where it is published
- Dataverse dataset page borealisdata.ca/dataset.xhtml?persistentId=doi%3A10.5683%2FSP3%2FKXYCNY ↗
landing page · from borealisdata ca
- DOI doi.org/10.5683/sp3/kxycny ↗
DOI / persistent id · from borealisdata ca
Catalogue records · 1
- Dataverse API borealisdata.ca/api/datasets/:persistentId/?persistentId=doi%3A10.5683%2FSP3%2… ↗
metadata API · from borealisdata ca
Topics
- Stated by source
- Medicine, Health and Life Sciences
- From keywords
- Computer Science & AI · Life Sciences · Medicine & Health
- Inferred from text
- Clinical sciences 73% · Image 75% · Imaging 75%
Provenance · 1 source records, 13 field assertions
| Source | Key | Last seen | Raw |
|---|---|---|---|
| Borealis | doi:10.5683/SP3/KXYCNY | 10 d ago | JSON v1 |
| Field | Assertion | Extractor | Evidence |
|---|---|---|---|
| concepts[field].anzsrc:group:3202 | enrichment · borealisdata ca | taxonomy-embedding@1.1.0 | title+keywords+description (73%) |
| concepts[field].dataverse_subject:medicine-health-and-life-sciences | source · borealisdata ca | connector:borealisdata_ca@1.0.0 | /subjects |
| concepts[field].local:field:computer-science-ai | mapping · borealisdata ca | connector:borealisdata_ca@1.0.0 | /subjects |
| concepts[field].local:field:life-sciences | mapping · borealisdata ca | connector:borealisdata_ca@1.0.0 | /subjects |
| concepts[field].local:field:medicine-health | mapping · borealisdata ca | connector:borealisdata_ca@1.0.0 | /subjects |
| concepts[modality].local:modality:image | enrichment · borealisdata ca | keyword-concept-rules@1.0.0 | title+description (75%) |
| concepts[modality].local:modality:imaging | enrichment · borealisdata ca | keyword-concept-rules@1.0.0 | title+description (75%) |
| created_date | source · borealisdata ca | connector:borealisdata_ca@1.0.0 | |
| description | source · borealisdata ca | connector:borealisdata_ca@1.0.0 | /description |
| publication_date | source · borealisdata ca | connector:borealisdata_ca@1.0.0 | |
| title | source · borealisdata ca | connector:borealisdata_ca@1.0.0 | /name |
| updated_date | source · borealisdata ca | connector:borealisdata_ca@1.0.0 | |
| version_label | source · borealisdata ca | connector:borealisdata_ca@1.0.0 |