Device and method for constructing and displaying high quality images from imaging data by transforming a data structure utilizing machine learning techniques
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.
1. A method of using a computer to construct an 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 method comprising:
receiving, at the computer from an imaging machine, the raw imaging data or the encoded imaging data stored in the first data structure;
reorganizing, by the computer, the raw imaging data or the encoded imaging data into the reorganized data and storing the reorganized data in the second data structure, wherein the second data structure comprises a multi-dimensional array having subarrays, wherein the subarrays contain only local information needed by a convolutional neural network for processing the reorganized data by the convolutional neural network, and wherein other portions of the multi-dimensional array store other portions of the raw imaging data or the encoded imaging data;
processing, by the computer, the reorganized data using the convolutional neural network to construct the image, whereby a constructed image is formed.
2. The method of claim 1 further comprising:
displaying the constructed image on a display device.
3. The method of claim 1 further comprising:
storing the constructed image on a non-transitory computer readable storage medium.
4. The method of claim 1 further comprising:
performing, by the computer, at least one of displaying the constructed image on a display device and storing the constructed image on a non-transitory computer readable storage medium.
5. The method of claim 1 wherein the raw imaging data or the encoded imaging data consists of the raw imaging data, wherein the raw imaging data is from a computed tomography X-ray machine, and wherein the method further comprises:
encoding, by the computer, a sinogram in order to encode the raw imaging data via a direct mapping of shadow onto a line, whereby encoded data is formed prior to reorganizing; and
wherein reorganizing is performed on the encoded data.
6. The method of claim 5 wherein reorganizing organizes the sinogram into the subarrays.
7. The method of claim 1 wherein the imaging machine comprises one of a computed tomography X-ray machine, a positron emission tomography machine, an X-ray machine, an ultrasound machine, a computerized tomography scanner, a magnetic resonance imaging machine, a synthetic aperture radar machine, an acoustic tomography machine, and a cryogenic electron tomography machine.
8. The method of claim 1 wherein the image comprises one of a two-dimensional image, a three-dimensional image, a solid volume, a function plot, and a numerical representation of data.
9. The method of claim 1 wherein the method is performed on one of a graphical processor unit, a central processor unit, and neural hardware.
10. A computer comprising:
a processor; and
a non-transitory computer readable storage medium storing program code which, when executed by the processor, performs a computer-implemented method of using the computer to construct an 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 program code comprising:
program code for receiving, at the computer from an imaging machine, the raw imaging data or the encoded imaging data stored in the first data structure;
program code for reorganizing, by the computer, the raw imaging data or the encoded imaging data into the reorganized data and storing the reorganized data in the second data structure, wherein the second data structure comprises a multi-dimensional array having subarrays, wherein the subarrays contain only local information needed by a convolutional neural network for processing the reorganized data by the convolutional neural network, and wherein other portions of the multi-dimensional array store other portions of the raw imaging data or the encoded imaging data;
program code for processing, by the computer, the reorganized data using the convolutional neural network to construct the image, whereby a constructed image is formed.
11. The computer of claim 10 wherein the program code further comprises:
program code for displaying the constructed image on a display device.
12. The computer of claim 10 wherein the program code further comprises:
program code for storing the constructed image on the non-transitory computer readable storage medium.
13. The computer of claim 10 wherein the program code further comprises:
program code for performing, by the computer, at least one of displaying the constructed image on a display device and storing the constructed image on a non-transitory computer readable storage medium.
14. The computer of claim 10 wherein the raw imaging data or the encoded imaging data consists of the raw imaging data, wherein the raw imaging data is from a computed tomography X-ray machine, and wherein the program code further comprises:
program code for encoding, by the computer, a sinogram in order to encode the raw imaging data via a direct mapping of shadow onto a line, whereby encoded data is formed prior to reorganizing; and
wherein the program code for reorganizing is executed using the encoded data.
15. The computer of claim 14 wherein the program code for reorganizing comprises program code for organizing the sinogram into the subarrays.
16. The computer of claim 10 wherein the imaging machine comprises one of a computed tomography X-ray machine, a positron emission tomography machine, an X-ray machine, an ultrasound machine, a computerized tomography scanner, a magnetic resonance imaging machine, a synthetic aperture radar machine, an acoustic tomography machine, and a cryogenic electron tomography machine.
17. The computer of claim 10 wherein the image comprises one of a two-dimensional image, a three-dimensional image, a solid volume, a function plot, and a numerical representation of data.
18. The computer of claim 10 wherein the computer comprises one of a graphical processor unit, a central processor unit, and neural hardware.
19. A non-transitory computer readable storage medium storing program code which, when executed by a processor, performs a computer-implemented method of using the computer to construct an 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 program code comprising:
program code for receiving, at the computer from an imaging machine, the raw imaging data or the encoded imaging data stored in the first data structure;
program code for reorganizing, by the computer, the raw imaging data or the encoded imaging data into the reorganized data and storing the reorganized data in the second data structure, wherein the second data structure comprises a multi-dimensional array having subarrays, wherein the subarrays contain only local information needed by a convolutional neural network for processing the reorganized data by the convolutional neural network, and wherein other portions of the multi-dimensional array store other portions of the raw imaging data or the encoded imaging data;
program code for processing, by the computer, the reorganized data using the convolutional neural network to construct the image, whereby a constructed image is formed.
20. The non-transitory computer readable storage medium of claim 19 wherein the raw imaging data or the encoded imaging data consists of the raw imaging data, wherein the raw imaging data is from a computed tomography X-ray machine, and wherein the program code further comprises:
program code for encoding, by the computer, a sinogram in order to encode the raw imaging data via a direct mapping of shadow onto a line, whereby encoded data is formed prior to reorganizing; and
wherein the program code for reorganizing is executed using the encoded data.