Summary of Deep Learning-based Classification Of Hyperkinetic Movement Disorders in Children, by Nandika Ramamurthy et al.
Deep Learning-Based Classification of Hyperkinetic Movement Disorders in Children
by Nandika Ramamurthy, Dr Daniel Lumsden, Dr Rachel Sparks
First submitted to arxiv on: 19 Nov 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Image and Video Processing (eess.IV)
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 neural network model that can differentiate between dystonia and chorea in children by analyzing video recordings of their motor tasks. The model combines Graph Convolutional Networks (GCNs) and Long Short-Term Memory (LSTM) networks to capture spatial and temporal relationships in the videos. Attention mechanisms are also incorporated to improve model interpretability. The model is trained and validated on a dataset of 50 videos collected from Guy’s and St Thomas’ NHS Foundation Trust, achieving an accuracy of 85%, sensitivity of 81%, and specificity of 88% at 15 frames per second. The attention maps highlight the model’s ability to correctly identify involuntary movement patterns. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper creates a special computer program that can help doctors diagnose children with abnormal movements like dystonia or chorea. This is important because it’s hard to tell these conditions apart just by looking at the child move, and it takes a long time to get an accurate diagnosis. The program uses special algorithms to analyze videos of kids doing different movements, which helps it figure out what kind of movement they are making. The program is pretty good at getting the right answer most of the time. |
Keywords
» Artificial intelligence » Attention » Lstm » Neural network
