Summary of Exploring Federated Deep Learning For Standardising Naming Conventions in Radiotherapy Data, by Ali Haidar et al.
Exploring Federated Deep Learning for Standardising Naming Conventions in Radiotherapy Data
by Ali Haidar, Daniel Al Mouiee, Farhannah Aly, David Thwaites, Lois Holloway
First submitted to arxiv on: 14 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Medical Physics (physics.med-ph)
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 In this paper, researchers propose a new approach to standardizing structure volume names in radiotherapy (RT) patient records. The current method is time-consuming and resource-intensive, making it difficult to analyze data across multiple institutions. The proposed method uses machine learning-based methods to standardize nomenclature, with a focus on decentralized real-time data and federated learning (FL). A multimodal deep artificial neural network is used to extract features from RT patient records, including tabular, visual, and volumetric attributes. The models are trained across various scenarios, including multiple data centers, input modalities, and aggregation strategies. The results show that fusing multiple modalities improves the performance of the models, with comparable accuracy reported compared to centralized settings. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps us understand how to make sure that medical records from different places have the same names for structures like tumors. This is important because it makes it easier to share and compare data between hospitals. The authors use a special kind of computer learning called federated learning to help with this task. They show that using information from different types of images, tables, and measurements helps make better predictions. This is useful for doctors who need to analyze lots of medical records to make good decisions about patient care. |
Keywords
* Artificial intelligence * Federated learning * Machine learning * Neural network
