Summary of Automatic Tongue Delineation From Mri Images with a Convolutional Neural Network Approach, by Karyna Isaieva (iadi) et al.
Automatic Tongue Delineation from MRI Images with a Convolutional Neural Network Approach
by Karyna Isaieva, Yves Laprie, Nicolas Turpault, Alexis Houssard, Jacques Felblinger, Pierre-André Vuissoz
First submitted to arxiv on: 6 Dec 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
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 A novel approach for extracting tongue contours from real-time magnetic resonance images is proposed, overcoming the challenges posed by artifacts such as blurring or ghostly contours. This is achieved through a U-Net auto-encoder convolutional neural network (CNN) model that demonstrates strong intra- and inter-subject validation. The model takes in real-time MRI images with manually annotated 1-pixel wide contour inputs, generating predicted probability maps that are post-processed to produce accurate tongue contours. The results outperform previously published automatic tongue segmentation methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper finds a way to automatically detect the shape of the tongue from magnetic resonance images taken in real time. This is tricky because some parts of the image can get distorted, making it hard to see what’s really there. To solve this problem, scientists used a special kind of artificial intelligence called a convolutional neural network (CNN). They tested their method using many different MRI images and saw that it worked very well. The results are even better than what other researchers have been able to achieve. |
Keywords
» Artificial intelligence » Cnn » Encoder » Neural network » Probability
