Summary of Aligning Human Knowledge with Visual Concepts Towards Explainable Medical Image Classification, by Yunhe Gao et al.
Aligning Human Knowledge with Visual Concepts Towards Explainable Medical Image Classification
by Yunhe Gao, Difei Gu, Mu Zhou, Dimitris Metaxas
First submitted to arxiv on: 8 Jun 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: 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 paper presents a novel framework, Explicd, for developing explainable models that mimic human expert decision-making in medical diagnosis. The framework fuses domain knowledge from large language models (LLMs) or human experts to establish diagnostic criteria across various concept axes. This is achieved by injecting these criteria into the embedding space as knowledge anchors using a pretrained vision-language model, allowing the learning of corresponding visual concepts within medical images. The final diagnostic outcome is determined based on similarity scores between encoded visual concepts and textual criteria embeddings. Experimental results demonstrate the framework’s inherent explainability and improved classification performance compared to traditional black-box models. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper creates a new way for computers to understand why they’re making certain decisions in medical diagnosis, just like human experts do. This is important because current AI models are often “black boxes” that don’t reveal how they arrive at their conclusions. The new framework, called Explicd, uses a combination of human input and artificial intelligence to develop diagnostic criteria for different diseases. It then uses these criteria to identify patterns in medical images, allowing doctors to better understand why the computer is making certain diagnoses. |
Keywords
» Artificial intelligence » Classification » Embedding space » Language model
