View source for 18470171. BUILDING A MACHINE-LEARNING MODEL TO PREDICT SEMANTIC CONTEXT INFORMATION FOR CONTRAST-ENHANCED MEDICAL IMAGING MEASUREMENTS simplified abstract (Siemens Healthcare GmbH)

=BUILDING A MACHINE-LEARNING MODEL TO PREDICT SEMANTIC CONTEXT INFORMATION FOR CONTRAST-ENHANCED MEDICAL IMAGING MEASUREMENTS=


==Organization Name==

[[:Category:Siemens Healthcare GmbH|Siemens Healthcare GmbH]]


[[Category:Siemens Healthcare GmbH]]

==Inventor(s)==

[[:Category:Martin Kraus of Fuerth (DE)|Martin Kraus of Fuerth (DE)]][[Category:Martin Kraus of Fuerth (DE)]]

[[:Category:Manasi Datar of Erfurt (DE)|Manasi Datar of Erfurt (DE)]][[Category:Manasi Datar of Erfurt (DE)]]

[[:Category:Dominik Neumann of Erlangen (DE)|Dominik Neumann of Erlangen (DE)]][[Category:Dominik Neumann of Erlangen (DE)]]

==BUILDING A MACHINE-LEARNING MODEL TO PREDICT SEMANTIC CONTEXT INFORMATION FOR CONTRAST-ENHANCED MEDICAL IMAGING MEASUREMENTS - A simplified explanation of the abstract==


This abstract first appeared for US patent application 18470171 titled 'BUILDING A MACHINE-LEARNING MODEL TO PREDICT SEMANTIC CONTEXT INFORMATION FOR CONTRAST-ENHANCED MEDICAL IMAGING MEASUREMENTS

==Simplified Explanation==

The abstract describes a method where a machine-learning model is pre-trained in an unsupervised manner using data from contrast-enhanced medical imaging to predict time-related information. This pre-trained model is then used to build another machine-learning model to predict semantic context information for images from the same imaging measurement.

* Machine-learning model pre-trained in an unsupervised manner to predict time-related information from contrast-enhanced medical imaging data.
* Use of pre-trained model to build another model for predicting semantic context information for images from the same imaging measurement.

== Potential Applications ==
This technology could be applied in the field of medical imaging analysis, specifically in improving the interpretation and understanding of contrast-enhanced images.

== Problems Solved ==
This technology helps in predicting both time-related and semantic context information from medical imaging data, which can aid in diagnosis and treatment planning.

== Benefits ==
The technology can potentially improve the accuracy and efficiency of analyzing contrast-enhanced medical images, leading to better patient outcomes.

== Potential Commercial Applications ==
* Enhancing medical imaging software for improved analysis and interpretation of contrast-enhanced images.

== Possible Prior Art ==
There may be existing methods or systems that utilize machine learning for medical imaging analysis, but specific prior art related to pre-training models in an unsupervised manner for predicting time-related and semantic context information from contrast-enhanced images may not be readily available.

=== Unanswered Questions ===

=== How does this technology compare to existing methods for medical imaging analysis? ===
This article does not provide a direct comparison to existing methods or technologies in the field of medical imaging analysis.

=== What are the limitations or challenges of implementing this technology in real-world medical settings? ===
The article does not address potential limitations or challenges that may arise when implementing this technology in actual medical practice.


==Original Abstract Submitted==

In a computer-implemented method, a machine-learning model is pre-trained in an unsupervised manner to predict time-related information based on data obtained from a contrast-enhanced medical imaging measurement. This pre-trained machine-learning model is then used to build another machine-learning model to predict semantic context information for images determined from the contrast-enhanced medical imaging measurement.



[[Category:G16H30/40]]
[[Category:G06T7/00]]
[[Category:G06T7/11]]