Siemens Healthineers has developed a method for medical image fusion using deep machine learning. By aligning anatomy from different scan data sets with a deep neural network, a deformation field is determined to generate a fused medical image. This innovative approach allows for various applications with different training data. GlobalData’s report on Siemens Healthineers gives a 360-degree view of the company including its patenting strategy. Buy the report here.

Smarter leaders trust GlobalData

Report-cover

Data Insights Siemens Healthineers AG - Company Profile

Buy the Report

Data Insights

The gold standard of business intelligence.

Find out more

According to GlobalData’s company profile on Siemens Healthineers, was a key innovation area identified from patents. Siemens Healthineers's grant share as of February 2024 was 62%. Grant share is based on the ratio of number of grants to total number of patents.

Medical image fusion using deep machine-learning for deformation field

Source: United States Patent and Trademark Office (USPTO). Credit: Siemens Healthineers AG

A recently granted patent (Publication Number: US11925434B2) discloses a method and system for medical image fusion using a medical imaging system. The method involves acquiring two sets of scan data representing a patient with deformed anatomy, determining a deformation field aligning the anatomy of the two sets of scan data using a machine-learnt deep neural network, and generating a medical image from the scan data and the deformation field. The acquisition of scan data can be done with the same modality of scanner at different times or with different modalities of scanners. Additionally, the method includes dividing the first set of scan data into patches to determine the deformation field based on intensities and displacements for the patches relative to the second set of scan data.

The system for medical image fusion comprises at least one medical imaging system, an image processor, and a display. The imaging system acquires data representing a patient with tissue displacement, which is then registered using a deep-learnt neural network to output displacements. The image processor divides the data into patches and registers based on an output feature vector from the neural network, considering intensities and displacement vectors for the patches relative to the second data. This innovative method and system offer a sophisticated approach to medical image fusion, enabling accurate alignment of anatomical structures from different scan data sets, ultimately leading to the generation of comprehensive medical images for diagnostic and treatment purposes.

To know more about GlobalData’s detailed insights on Siemens Healthineers, buy the report here.

Data Insights

From

The gold standard of business intelligence.

Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.

GlobalData

GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.

GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.