Topological Feature Fusion for Dermoscopic Skin Cancer Detection
Tastan, F.; Chakraborty, S.; Lee, S.; Coskunuzer, B.
Show abstract
Skin cancer is a common and potentially fatal disease where early detection can save lives, especially for melanoma. Current deep learning systems classify skin lesions well, but they mainly rely on appearance cues and may miss deeper structural patterns in lesions. We present TopoCon MP, a method that extracts multiparameter topological signatures from dermoscopic images to capture multiscale lesion structure, and fuses these signatures with Vision Transformers using a supervised contrastive objective. Across three public datasets, TopoCon MP consistently improves performance over strong pretrained CNN and ViT baselines, including in cross dataset transfer. Ablations show that multiparameter topology and contrastive fusion each contribute to the gains. The resulting topological channels also provide an interpretable view of lesion organization, aligning with clinically meaningful structures. Overall, TopoCon MP demonstrates that multipersistence based topology can serve as a complementary modality for robust skin cancer detection.
Matching journals
The top 9 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- A Framework for Falsifiable Explanations of Machine Learning Models with an Application in Computational Pathology 96%
- Clinical Validation of Saliency Maps for Understanding Deep Neural Networks in Ophthalmology 93%
- Spatial Transcriptomics Expression Prediction from Histopathology Based on Cross-Modal Mask Reconstruction and Contrastive Learning 93%
Similar papers in this journal
- Generative AI Enables Medical Image Segmentation in Ultra Low-Data Regimes 94%
- ROSIE: AI generation of multiplex immunofluorescence staining from histopathology images 93%
- Segmenting functional tissue units across human organs using community-driven development of generalizable machine learning algorithms 92%
Similar papers in this journal
Similar papers in this journal
- A framework for network-based epidemiological modeling of tuberculosis dynamics using synthetic datasets 85%
- Generation of virtual populations for quantitative systems pharmacology through advanced sampling methods 85%
- QWENDY: Gene Regulatory Network Inference Enhanced by Large Language Model and Transformer 85%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.