Summary of Segmentation Of Planning Target Volume in Ct Series For Total Marrow Irradiation Using U-net, by Ricardo Coimbra Brioso et al.
Segmentation of Planning Target Volume in CT Series for Total Marrow Irradiation Using U-Net
by Ricardo Coimbra Brioso, Damiano Dei, Ciro Franzese, Nicola Lambri, Daniele Loiacono, Pietro Mancosu, Marta Scorsetti
First submitted to arxiv on: 5 Apr 2023
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 deep learning-based auto-contouring method for segmenting Planning Target Volume (PTV) in Total Marrow and Lymph node Irradiation (TMLI) treatment. The approach uses the U-Net architecture and is trained on a dataset of 100 patients treated with TMLI at the Humanitas Research Hospital between 2011 and 2021. The model achieves an average Dice score of 0.816 for PTV segmentation, despite challenges in lymph node areas. This preliminary work has the potential to save radiation oncologists time, allowing for the treatment of more patients and improving clinical practice efficiency. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper is about making it easier for doctors to plan cancer treatments using special machines called linear accelerators. They use CT scans to see where the tumor is and what areas need protection from too much radiation. Right now, doctors have to manually draw lines around these areas, which takes a lot of time. The researchers developed a computer program that can do this job faster and better than humans. They tested it on 100 patient cases and found that it was very accurate. This could help more patients get treated and make the process more efficient. |
Keywords
* Artificial intelligence * Deep learning
