Device and method for constructing and displaying high quality images from imaging data by transforming a data structure utilizing machine learning techniques
| DWPI Title: Method of using computer to construct image from raw imaging data or encoded imaging data by transforming main data structure, involves processing reorganized data using convolutional neural network to construct image by computer |
| Abstract: Constructing a computer image from raw imaging data or encoded imaging data by transforming a first data structure in which the raw imaging data or the encoded imaging data is stored into a second data structure storing reorganized imaging data. The raw imaging data or the encoded imaging data is received, stored in the first data structure. The computer reorganizes the raw imaging data or the encoded imaging data into the reorganized data and stores the reorganized data in the second data structure, which is a multi-dimensional array having subarrays containing local information needed by a convolutional neural network for processing the reorganized data. Other portions of the multi-dimensional array store other portions of the raw imaging data or the encoded imaging data. The computer also processes the reorganized data using the convolutional neural network to construct the image, whereby a constructed image is formed. |
| Use: Method of using computer to construct image from raw imaging data or encoded imaging data by transforming main data structure. |
| Advantage: The data structure conversion and data processing techniques reduce errors and improve the quality of the image. The combination of a unique projection method for a non-local dataset onto a space facilitates machine learning on the reconstruction of the imaging data into volumetric data. The problems of artifacts are greatly reduced or eliminated. |
| Novelty: The method (600) involves receiving (602) the raw imaging data or the encoded imaging data stored in the first data structure at the computer from an imaging machine. The raw imaging data or the encoded imaging data is recognized (604) into the reorganized data, and the reorganized data is stored in the second data structure by the computer. The second data structure comprises a multi-dimensional array with subarrays. The subarrays contain local information needed by a convolutional neural network for processing the reorganized data by the convolutional neural network. The other portions of the multi-dimensional array store other portions of the raw imaging data or the encoded imaging data. The reorganized data is processed (606) using the convolutional neural network to construct the image by a constructed image is formed by the computer. |
| Filed: 1/17/2019 |
| Application Number: US16250910A |
| Tech ID: SD 14632.0 |
| This invention was made with Government support under Contract No. DE-NA0003525 awarded by the United States Department of Energy/National Nuclear Security Administration. The Government has certain rights in the invention. |
| Data from Derwent World Patents Index, provided by Clarivate All rights reserved. Republication or redistribution of Clarivate content, including by framing or similar means, is prohibited without the prior written consent of Clarivate. Clarivate and its logo, as well as all other trademarks used herein are trademarks of their respective owners and used under license. |