Data generation, algorithm training, disease information detection methods, and systems and programs
CN116645316BActive Publication Date: 2026-08-28SIEMENS HEALTHINEERS AG
Patent Information
- Application Number
- CN202310152629.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Priority Date
- 2022-02-23
- Filing Date
- 2023-02-21
- Publication Date
- 2026-08-28
- Estimated Expiration
- 2043-02-21
AI Technical Summary
Technical Problem
然而，在检测脑部疾病信息的可训练架构中，难以整合先前的知识
Benefits of technology
[0072]在本发明的上下文中，“基于”这一表述特别地可以理解为“尤其使用”。特别地，根据第一特征基于第二特征计算(或生成、确定等)的措辞并不排除第一特征基于第三特征计算(或生成、确定等)的可能性。
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN116645316B_ABST
Abstract
A method for generating training data (1) for training a deep learning algorithm (6), comprising: receiving (RT1) medical imaging data (2) of an examination region of a patient, the examination region of the patient comprising a first portion and a second portion of a symmetric organ; dividing (MD1) the medical imaging data (2) along a symmetry plane or a symmetry axis into a first data set (3a) and a second data set (3b), wherein the first data set (3a) comprises the medical imaging data (2) of the first portion of the organ and the second data set (3b) comprises the medical imaging data (2) of the second portion of the organ; mirroring (MD1) the second data set (3b) along the symmetry plane or the symmetry axis; generating (GT1) the training data (1) by superimposing the first data set (3a) and the mirrored second data set (3b*); providing (PT1) the training data (1).
Need to check novelty before this filing date? Find Prior Art
Citation Information
Patent Citations
Deep Learning Based Bone Removal in Computed Tomography Angiography
US20180116620A1
Method and data processing system for providing a stroke information
WO2021063709A1