Summary of Evaluating Explainable Ai Methods in Deep Learning Models For Early Detection Of Cerebral Palsy, by Kimji N. Pellano et al.
Evaluating Explainable AI Methods in Deep Learning Models for Early Detection of Cerebral Palsy
by Kimji N. Pellano, Inga Strümke, Daniel Groos, Lars Adde, Espen Alexander F. Ihlen
First submitted to arxiv on: 14 Aug 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 paper explores the application of Explainable AI (XAI) methods in predicting Cerebral Palsy (CP) by analyzing skeletal data extracted from video recordings of infant movements. A deep learning method is used to predict CP, and XAI evaluation metrics such as faithfulness and stability are employed to quantify the reliability of Class Activation Mapping (CAM) and Gradient-weighted Class Activation Mapping (Grad-CAM). The study utilizes a unique dataset of infant movements with perturbations to evaluate the robustness of the models. The findings indicate that both CAM and Grad-CAM effectively identify key body points influencing CP predictions, and that Grad-CAM outperforms CAM in terms of stability. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper uses special AI techniques called Explainable AI (XAI) to predict if an infant might have Cerebral Palsy (CP). They use videos of infants moving and extract data from the video. Then they use a deep learning model to try to predict if the baby has CP. The researchers want to know if this method is reliable, so they tested it with some fake video data to see how well it works. They found that the AI can identify important body parts that might be related to CP and that one type of XAI is better than another at predicting stability. |
Keywords
» Artificial intelligence » Deep learning
