# Learning Superpixel Ensemble and Hierarchy Graphs for Melanoma Detection

arXiv: https://arxiv.org/abs/2604.03710 · HTML: https://mlsanity.com/paper/2604.03710/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 62 references that are in the map.
- First posted on arXiv 4 Apr 2026.

## Builds on (most cited first, 15 of 15)

- [Big Transfer (BiT): General Visual Representation Learning](https://mlsanity.com/paper/1912.11370/) (2019)
- [How to learn a graph from smooth signals](https://mlsanity.com/paper/1601.02513/) (2016)
- [Graph Learning: A Survey](https://mlsanity.com/paper/2105.00696/) (2021)
- [Graph Learning based Recommender Systems: A Review](https://mlsanity.com/paper/2105.06339/) (2021)
- [ISIC 2017 - Skin Lesion Analysis Towards Melanoma Detection](https://mlsanity.com/paper/1703.00523/) (2017)
- [Robust Graph Learning from Noisy Data](https://mlsanity.com/paper/1812.06673/) (2018)
- [A Mutual Bootstrapping Model for Automated Skin Lesion Segmentation and Classification](https://mlsanity.com/paper/1903.03313/) (2019)
- [Image Classification of Melanoma, Nevus and Seborrheic Keratosis by Deep Neural Network Ensemble](https://mlsanity.com/paper/1703.03108/) (2017)
- [Interpretable Medical Image Visual Question Answering via Multi-Modal Relationship Graph Learning](https://mlsanity.com/paper/2302.09636/) (2023)
- [A Comprehensive Survey on Spectral Clustering with Graph Structure Learning](https://mlsanity.com/paper/2501.13597/) (2025)
- [Graph Frequency Analysis of Brain Signals](https://mlsanity.com/paper/1512.00037/) (2015)
- [Graph-Based Intercategory and Intermodality Network for Multilabel Classification and Melanoma Diagnosis of Skin Lesions in Dermoscopy and Clinical Images](https://mlsanity.com/paper/2104.00201/) (2021)
- [Learning Sparse Graphs via Majorization-Minimization for Smooth Node Signals](https://mlsanity.com/paper/2202.02815/) (2022)
- [How to Identify Good Superpixels for Deforestation Detection on Tropical Rainforests](https://mlsanity.com/paper/2409.04330/) (2024)
- [From Pixels to Graphs: Deep Graph-Level Anomaly Detection on Dermoscopic Images](https://mlsanity.com/paper/2508.11826/) (2025)

## Abstract (arXiv)

Graph signal processing (GSP) is becoming a major tool in biomedical signal and image analysis. In most GSP techniques, graph structures and edge weights have been typically set via statistical and computational methods. More recently, graph structure learning methods offered more reliable and flexible data representations. In this work, we introduce a graph learning approach for melanoma detection in dermoscopic images based on two graph-theoretic representations: superpixel ensemble graphs (SEG) and superpixel hierarchy graphs (SHG). For these two types of graphs, superpixel maps of a skin lesion image are respectively generated at multiple levels without and with parentchild constraints among superpixels at adjacent levels, where each level corresponds to a subgraph with a different number of nodes (20, 40, 60, 80, or 100 nodes). Two edge weight assignment techniques are explored: handcrafted Gaussian weights and learned weights based on optimization methods. The graph nodal signals are assigned based on texture, geometric, and color superpixel features. In addition, the effect of graph edge thresholding is investigated by applying different thresholds (25%, 50%, and 75%) to prune the weakest edges and analyze the impact of pruning on the melanoma detection performance. Experimental evaluation of the proposed method is performed with different classifiers trained and tested on the publicly available ISIC2017 dataset. Data augmentation is applied to alleviate class imbalance by adding more melanoma images from the ISIC archive. The results show that learned superpixel ensemble graphs with textural nodal signals give the highest performance reaching an accuracy of 99.00% and an AUC of 99.59%.