Model
Pretrained resnet34 model from Pytorch retrained for skin cancer malignacy detection
Base Model
Resnet is the base model used created by He, Zhang, Ren, & Sun (2016)
Pretrained resnet34 was obtained from Pytorch (Pytorch Contributors, 2023)
Dataset
Trained on SLICE-3D ISIC 2024 Challenge Dataset (International Skin Imaging Collaboration, 2024)
Metrics
The metrics used to measure the performance of the model is the partial area under the ROC curve (pAUC) for binary classification of malignant cases, focusing on a true positive rate (TPR) above 80%.
Performance on Validation Set
| Model name | pAUC Performance |
|---|
| Fold 0 | 0.120 |
| Fold 1 | 0.192 |
| Fold 2 | 0.194 |
| Fold 3 | 0.193 |
| Fold 4 | 0.195 |
Contributors
- Albert Widjaja
- Andrew Ngadiman
Sources and References
- He, K., Zhang, X., Ren, S., & Sun, J. Deep Residual Learning for Image Recognition. IEEE Conference on Computer Vision and Pattern Recognition. https://doi.org/10.1109/CVPR.2016.090 (2016).
- International Skin Imaging Collaboration. SLICE-3D 2024 Challenge Dataset. International Skin Imaging Collaboration https://doi.org/10.34970/2024-slice-3d (2024). Creative Commons Attribution-Non Commercial 4.0 International License. The dataset was generated by the International Skin Imaging Collaboration (ISIC) and images are from the following sources: Hospital Clínic de Barcelona, Memorial Sloan Kettering Cancer Center, Hospital of Basel, FNQH Cairns, The University of Queensland, Melanoma Institute Australia, Monash University and Alfred Health, University of Athens Medical School, and Medical University of Vienna.
- PyTorch Contributors. ResNet-34 Model. PyTorch. https://pytorch.org/vision/main/models/generated/torchvision.models.resnet34.html (2023).
