Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.12277 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915495928659968 |
|---|---|
| author | Yousefzadeh, Mehdi Esfahanian, Parsa Rashidifar, Sara Gavalan, Hossein Salahshoor Tabatabaee, Negar Sadat Rafiee Gorgin, Saeid Rahmati, Dara Daneshpazhooh, Maryam |
| author_facet | Yousefzadeh, Mehdi Esfahanian, Parsa Rashidifar, Sara Gavalan, Hossein Salahshoor Tabatabaee, Negar Sadat Rafiee Gorgin, Saeid Rahmati, Dara Daneshpazhooh, Maryam |
| contents | Introduction. Dermoscopy aids melanoma triage, yet image-only AI often ignores patient metadata (age, sex, site) and the physical scale needed for geometric analysis. We present GraphDerm, a population-graph framework that fuses imaging, millimeter-scale calibration, and metadata for multiclass dermoscopic classification, to the best of our knowledge the first ISIC-scale application of GNNs to dermoscopy. Methods. We curate ISIC 2018/2019, synthesize ruler-embedded images with exact masks, and train U-Nets (SE-ResNet-18) for lesion and ruler segmentation. Pixels-per-millimeter are regressed from the ruler-mask two-point correlation via a lightweight 1D-CNN. From lesion masks we compute real-scale descriptors (area, perimeter, radius of gyration). Node features use EfficientNet-B3; edges encode metadata/geometry similarity (fully weighted or thresholded). A spectral GNN performs semi-supervised node classification; an image-only ANN is the baseline. Results. Ruler and lesion segmentation reach Dice 0.904 and 0.908; scale regression attains MAE 1.5 px (RMSE 6.6). The graph attains AUC 0.9812, with a thresholded variant using about 25% of edges preserving AUC 0.9788 (vs. 0.9440 for the image-only baseline); per-class AUCs typically fall in the 0.97-0.99 range. Conclusion. Unifying calibrated scale, lesion geometry, and metadata in a population graph yields substantial gains over image-only pipelines on ISIC-2019. Sparser graphs retain near-optimal accuracy, suggesting efficient deployment. Scale-aware, graph-based AI is a promising direction for dermoscopic decision support; future work will refine learned edge semantics and evaluate on broader curated benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_12277 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GraphDerm: Fusing Imaging, Physical Scale, and Metadata in a Population-Graph Classifier for Dermoscopic Lesions Yousefzadeh, Mehdi Esfahanian, Parsa Rashidifar, Sara Gavalan, Hossein Salahshoor Tabatabaee, Negar Sadat Rafiee Gorgin, Saeid Rahmati, Dara Daneshpazhooh, Maryam Computer Vision and Pattern Recognition Artificial Intelligence Introduction. Dermoscopy aids melanoma triage, yet image-only AI often ignores patient metadata (age, sex, site) and the physical scale needed for geometric analysis. We present GraphDerm, a population-graph framework that fuses imaging, millimeter-scale calibration, and metadata for multiclass dermoscopic classification, to the best of our knowledge the first ISIC-scale application of GNNs to dermoscopy. Methods. We curate ISIC 2018/2019, synthesize ruler-embedded images with exact masks, and train U-Nets (SE-ResNet-18) for lesion and ruler segmentation. Pixels-per-millimeter are regressed from the ruler-mask two-point correlation via a lightweight 1D-CNN. From lesion masks we compute real-scale descriptors (area, perimeter, radius of gyration). Node features use EfficientNet-B3; edges encode metadata/geometry similarity (fully weighted or thresholded). A spectral GNN performs semi-supervised node classification; an image-only ANN is the baseline. Results. Ruler and lesion segmentation reach Dice 0.904 and 0.908; scale regression attains MAE 1.5 px (RMSE 6.6). The graph attains AUC 0.9812, with a thresholded variant using about 25% of edges preserving AUC 0.9788 (vs. 0.9440 for the image-only baseline); per-class AUCs typically fall in the 0.97-0.99 range. Conclusion. Unifying calibrated scale, lesion geometry, and metadata in a population graph yields substantial gains over image-only pipelines on ISIC-2019. Sparser graphs retain near-optimal accuracy, suggesting efficient deployment. Scale-aware, graph-based AI is a promising direction for dermoscopic decision support; future work will refine learned edge semantics and evaluate on broader curated benchmarks. |
| title | GraphDerm: Fusing Imaging, Physical Scale, and Metadata in a Population-Graph Classifier for Dermoscopic Lesions |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2509.12277 |