Summary of Robust Deep Labeling Of Radiological Emphysema Subtypes Using Squeeze and Excitation Convolutional Neural Networks: the Mesa Lung and Spiromics Studies, by Artur Wysoczanski et al.
Robust deep labeling of radiological emphysema subtypes using squeeze and excitation convolutional neural networks: The MESA Lung and SPIROMICS Studies
by Artur Wysoczanski, Nabil Ettehadi, Soroush Arabshahi, Yifei Sun, Karen Hinkley Stukovsky, Karol E. Watson, MeiLan K. Han, Erin D Michos, Alejandro P. Comellas, Eric A. Hoffman, Andrew F. Laine, R. Graham Barr, Elsa D. Angelini
First submitted to arxiv on: 1 Mar 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 The paper presents a new approach to categorizing pulmonary emphysema into distinct subtypes using unsupervised learning and spatially-informed lung texture patterns (sLTPs) extracted from computed tomography (CT) images. The authors develop a 3-D squeeze-and-excitation convolutional neural network (CNN) for supervised classification of sLTPs and CT Emphysema Subtypes (CTES). The model achieves accurate and reproducible results on lung CT scans across two independent cohorts, regardless of scanner manufacturer or model. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Pulmonary emphysema is a serious condition where the lungs lose tissue. Doctors usually group this condition into three types based on how it looks under a microscope or on a special scan called a CT image. Researchers have found 10 patterns in CT scans that can help identify different types of emphysema, and these patterns are connected to six main groups. But existing methods for identifying these patterns take too long and are sensitive to changes in the way CT scans are taken. This paper presents a new way to use artificial intelligence to quickly and accurately identify the 10 patterns and their related subtypes, using data from two different groups of people. |
Keywords
* Artificial intelligence * Classification * Cnn * Neural network * Supervised * Unsupervised
