Summary of Automated Detection Of Motion Artifacts in Brain Mr Images Using Deep Learning and Explainable Artificial Intelligence, by Marina Manso Jimeno et al.
Automated detection of motion artifacts in brain MR images using deep learning and explainable artificial intelligence
by Marina Manso Jimeno, Keerthi Sravan Ravi, Maggie Fung, John Thomas Vaughan Jr., Sairam Geethanath
First submitted to arxiv on: 13 Feb 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 A deep learning model for detecting rigid motion in MRI images is introduced, leveraging a 2D CNN for three-class classification and achieving average precision and recall metrics of 85% and 80% on retrospective datasets. The model’s classifications showed a strong inverse correlation with an image quality metric indicative of motion, indicating its potential to automate part of the time-consuming QA process. This research is part of ArtifactID, a tool aimed at inline automatic detection of various MRI artifacts, which can augment expertise on-site and be particularly relevant in low-resource settings where local MR knowledge is scarce. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A new way to check if brain scans are good or not is developed. It uses special computer programs called deep learning models that look at the pictures for things like movement. This helps make sure the pictures are correct and can save time and expertise for people who do this job. The model works really well, getting most of the answers right on test images. This technology could be especially helpful in places where it’s hard to find experts to check the scans. |
Keywords
* Artificial intelligence * Classification * Cnn * Deep learning * Precision * Recall
