Summary of Deep Learning Based Detection Of Collateral Circulation in Coronary Angiographies, by Cosmin-andrei Hatfaludi et al.
Deep learning based detection of collateral circulation in coronary angiographies
by Cosmin-Andrei Hatfaludi, Daniel Bunescu, Costin Florian Ciusdel, Alex Serban, Karl Bose, Marc Oppel, Stephanie Schroder, Christopher Seehase, Harald F. Langer, Jeanette Erdmann, Henry Nording, Lucian Mihai Itu
First submitted to arxiv on: 8 Jan 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
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 deep learning-based method is proposed for detecting coronary collateral circulation (CCC) in angiographic images, which is crucial for personalized medicine in coronary artery disease. The approach relies on a convolutional backbone to extract spatial features from each frame of an image sequence, followed by temporal processing using another convolutional layer. To address the scarcity of data, pretraining the backbone on coronary artery segmentation and few-shot learning are experimented with, showing consistent improvements. Subgroup analyses based on Rentrop grading, collateral flow, and collateral grading provide valuable insights into model performance. The proposed method demonstrates promising results in detecting CCC and can be extended to perform landmark-based CCC detection and quantification. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A new way is developed to use computer vision to detect something important for heart disease treatment. This helps doctors personalize treatment plans for patients with coronary artery disease, which is a big problem worldwide. The method uses deep learning techniques to look at special X-ray images of the heart and identify patterns that indicate the formation of extra blood vessels around blocked arteries. To make this work better, the researchers tried two new approaches: training the model on a related task (segmenting coronary arteries) and using small amounts of data to fine-tune the model. The results show that this method is effective and can be used for further analysis and treatment planning. |
Keywords
» Artificial intelligence » Deep learning » Few shot » Pretraining
