Summary of Transparent and Clinically Interpretable Ai For Lung Cancer Detection in Chest X-rays, by Amy Rafferty and Rishi Ramaesh and Ajitha Rajan
Transparent and Clinically Interpretable AI for Lung Cancer Detection in Chest X-Rays
by Amy Rafferty, Rishi Ramaesh, Ajitha Rajan
First submitted to arxiv on: 28 Mar 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Computer Vision and Pattern Recognition (cs.CV)
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 ante-hoc approach to Explainable Artificial Intelligence (XAI) addresses the issue of trust in complex deep learning models by introducing clinical concepts into the classification pipeline. The concept bottleneck model yields improved lung cancer detection performance (F1 > 0.9) and generates more reliable explanations compared to baseline models. This approach outperforms post-hoc XAI techniques LIME, SHAP, and CXR-LLaVA on a large public dataset of chest X-rays and medical reports. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper is about making deep learning models more understandable so people can trust them. Right now, these models are like black boxes that don’t explain how they make decisions. The authors came up with a new way to do this by adding clinical information into the model while it’s making decisions. This helps doctors understand why the model is saying something is or isn’t lung cancer. The new approach works better than other ways of doing XAI and can even help detect lung cancer more accurately. |
Keywords
* Artificial intelligence * Classification * Deep learning
