Λεπτομέρειες βιβλιογραφικής εγγραφής
| Τίτλος: |
Patent Application Titled "Computer-Implemented Method For Providing An Encrypted Dataset Providing A Global Trained Function, Computer-Implemented Method For Recovering Personal Information, Computer System And Computer Program" Published Onli. |
| Πηγή: |
Medical Imaging Week; 4/15/2024, p8667-8667, 1p |
| Θεματικοί όροι: |
Patent applications, Computer software, Computer systems, Artificial neural networks, Convolutional neural networks |
| Εταιρία/Οντότητα: |
Siemens Healthineers AG |
| Περίληψη: |
The patent application titled "Computer-Implemented Method For Providing An Encrypted Dataset Providing A Global Trained Function, Computer-Implemented Method For Recovering Personal Information, Computer System And Computer Program" discusses the challenges of training machine learning functions using sensitive personal data, specifically in the field of medical image processing. The document proposes a method that combines federated learning and homomorphic encryption to protect personal information while allowing the use of diverse training data. This method involves encrypting local training datasets and transmitting them to an aggregating system, where a global encrypted dataset is calculated. The approach aims to minimize computational overhead and provide robust protection of personal information. The patent application provides detailed claims and technical information about the method, including the use of reidentification information to protect identifying information in the datasets. [Extracted from the article] |
|
Copyright of Medical Imaging Week is the property of NewsRx and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| Βάση Δεδομένων: |
Biomedical Index |