Summary of Xai For Skin Cancer Detection with Prototypes and Non-expert Supervision, by Miguel Correia et al.
XAI for Skin Cancer Detection with Prototypes and Non-Expert Supervision
by Miguel Correia, Alceu Bissoto, Carlos Santiago, Catarina Barata
First submitted to arxiv on: 2 Feb 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed prototypical-part model for melanoma diagnosis in dermoscopy images is designed to be both interpretable and reliable. The model relies on two information pathways: binary masks generated by a segmentation network and user-refined prototypes. This approach aims to ensure that the learned prototypes correspond to relevant skin lesion areas, excluding confounding factors. Experimental results show superior performance and generalization compared to non-interpretable models. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A team of researchers has developed a new way to detect melanoma using images taken with dermoscopy. They created a special kind of model that can explain its thinking, making it more trustworthy for doctors. To do this, they used two different types of information: one from a computer program and the other from people who looked at the images. This helps make sure the model is focusing on the right parts of the skin lesion. The results show that this new approach works better than previous methods. |
Keywords
* Artificial intelligence * Generalization
