Data · dataset · 2025
Photorealistic Synthesis of Oral Lichen Planus Lesions: Code and Example Dataset
Listed in Teesside University Research Data Repository
This dataset accompanies the manuscript "Photorealistic Synthesis of Oral Lichen Planus and Lichenoid Lesions Enhances Deep-Learning Segmentation in Intra-Oral Photographs" submitted to Computerized Medical Imaging and Graphics.
Description
Research Context: Medical image analysis for oral potentially malignant disorders (OPMDs) is hindered by limited annotated datasets. This work addresses data scarcity by combining CycleGAN with a Realistic Enhancement Algorithm (REA) to synthesize photorealistic oral lichen planus/lichenoid lesion (OLP/OLL) images on healthy buccal mucosa photographs.
What This Dataset Contains: 1. codes.zip — Source code for the CycleGAN+REA synthesis pipeline: buccal mucosa segmentation, CycleGAN lesion generation, REA histogram matching, Laplacian pyramid blending, QC screening, and segmentation inference scripts. 2. models.zip — Pretrained weights: CycleGAN generator, TensorFlow-based buccal mucosa segmentation, OLP lesion segmentation (QC), and three Experiment 1 architectures (MANet+MiT-B2, FPN+MiT-B0, PSPNet+EfficientNet-B0). 3. data.zip — De-identified example images: healthy buccal mucosa inputs and real lesion images with ground-truth masks.
Read the rest (2 more)
Key Findings:
- REA combines masked histogram matching with Laplacian pyramid blending to reduce CycleGAN artifacts (color drift, boundary discontinuities)
- 520 dental professionals achieved only 58.22% discrimination accuracy (chance=50%), indicating high realism
- Synthetic augmentation improved segmentation by up to +2.08 mIoU points How to Use: 1. Unzip codes.zip, data.zip, and models.zip 2. Install dependencies from requirements_simplified.txt 3. Run realistic_lesion_pipeline.py for synthesis 4. Run oral_lesion_segmentation.py for segmentation inference Data Restrictions: Due to ethics restrictions, the full clinical dataset cannot be released. This repository provides minimal examples to demonstrate pipeline functionality. Associated Publication: Theppitak S, Wongsapai M, Jaidee E, Sakdapreecha C, Ittichaicharoen J, Pongsiriwet S, Warin K, Suebnukarn S, Wuttisarnwattana P. "Photorealistic Synthesis of Oral Lichen Planus and Lichenoid Lesions Enhances Deep-Learning Segmentation in Intra-Oral Photographs", Computerized Medical Imaging and Graphics. [Under Review]
Links
Where it is published
- DOI doi.org/10.17632/fgjd95tcr8.1 ↗
DOI / persistent id · from researchdata tees ac uk
Catalogue records · 1
- OAI-PMH record data.mendeley.com/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai%3Adata… ↗
metadata API · from researchdata tees ac uk
Topics
- From keywords
- Computer Science & AI · Deep learning · Earth & Environmental Science · Engineering · Humanities · Life Sciences · Medicine & Health · Social Science
Provenance · 1 source records, 15 field assertions
| Source | Key | Last seen | Raw |
|---|---|---|---|
| Teesside University Research Data Repository | oai:data.mendeley.com/fgjd95tcr8.1 | 11 d ago | JSON v1 |
| Field | Assertion | Extractor | Evidence |
|---|---|---|---|
| access_level | source · researchdata tees ac uk | connector:researchdata_tees_ac_uk@1.0.0 | |
| concepts[field].anzsrc:field:461103 | mapping · researchdata tees ac uk | vocabulary-mapper@1.0.0 | keywords['Deep Learning'] |
| concepts[field].local:field:computer-science-ai | mapping · researchdata tees ac uk | connector:researchdata_tees_ac_uk@1.0.0 | |
| concepts[field].local:field:earth-environmental | mapping · researchdata tees ac uk | connector:researchdata_tees_ac_uk@1.0.0 | |
| concepts[field].local:field:engineering | mapping · researchdata tees ac uk | connector:researchdata_tees_ac_uk@1.0.0 | |
| concepts[field].local:field:humanities | mapping · researchdata tees ac uk | connector:researchdata_tees_ac_uk@1.0.0 | |
| concepts[field].local:field:life-sciences | mapping · researchdata tees ac uk | connector:researchdata_tees_ac_uk@1.0.0 | |
| concepts[field].local:field:medicine-health | mapping · researchdata tees ac uk | connector:researchdata_tees_ac_uk@1.0.0 | |
| concepts[field].local:field:social-science | mapping · researchdata tees ac uk | connector:researchdata_tees_ac_uk@1.0.0 | |
| concepts[modality].local:modality:image | enrichment · researchdata tees ac uk | keyword-concept-rules@1.0.0 | title+description (75%) |
| concepts[modality].local:modality:imaging | enrichment · researchdata tees ac uk | keyword-concept-rules@1.0.0 | title+description (75%) |
| description | source · researchdata tees ac uk | connector:researchdata_tees_ac_uk@1.0.0 | /metadata/dc/description |
| license | source · researchdata tees ac uk | connector:researchdata_tees_ac_uk@1.0.0 | /metadata/dc/rights |
| publication_date | source · researchdata tees ac uk | connector:researchdata_tees_ac_uk@1.0.0 | |
| title | source · researchdata tees ac uk | connector:researchdata_tees_ac_uk@1.0.0 | /metadata/dc/title |