Tomographic image analysis using artificial intelligence (AI) engines

1. A method for a computer system to perform tomographic data analysis using an artificial intelligence (AI) engine, wherein the method comprises:

obtaining first three-dimensional (3D) feature volume data generated based on two-dimensional (2D) projection data that is associated with a target object and acquired using an imaging system;

processing the first 3D feature volume data using the AI engine that includes multiple first processing layers, an interposing forward-projection module and multiple second processing layers by performing the following:

generating second 3D feature volume data by processing the first 3D feature volume data using the multiple first processing layers that are associated with first weight data and operate in a 3D volume space;

transforming the second 3D volume data into 2D feature data using the forward-projection module; and

generating analysis output data by processing the 2D feature data using the multiple second processing layers that are associated with second weight data and operate in a 2D projection space.

2. The method of claim 1 , wherein generating the second 3D feature volume data comprises:

generating second 3D feature volume data by processing the first 3D feature volume data using the multiple first processing layers that are trained to perform decoding on the first 3D feature volume data.

3. The method of claim 1 , wherein generating the analysis output data comprises:

generating the analysis output data by processing the 2D feature data using the multiple second processing layers that are trained to perform at least one of the following: automatic segmentation, object or feature detection, image artifact suppression, image enhancement and de-truncation.

4. The method of claim 3 , wherein processing the 2D projection data using the AI engine comprises:

generating the analysis output data by processing both the 2D feature data and the 2D projection data using the multiple second processing layers.

5. The method of claim 1 , wherein the method further comprises:

obtaining training data that includes (a) training 3D feature volume data and (b) training analysis output data; and

training the multiple first processing layers and the multiple second processing layers, with the forward-projection module interposed in between, to transform (a) the training 3D feature volume data and (b) the training analysis output data and to learn the respective first weight data and second weight data.

6. The method of claim 1 , wherein obtaining the first 3D feature volume data comprises:

obtaining the first 3D feature volume data for processing by the AI engine, being a second AI engine, from a first AI engine that is trained to perform tomographic image reconstruction to transform the 2D projection data to the first 3D feature volume data.

7. The method of claim 6 , wherein the method further comprises:

obtaining training data that includes (a) training 2D projection data and (b) training analysis output data; and

training the first AI engine and the second AI engine together to perform integrated tomographic image reconstruction and analysis to transform (a) the training 2D projection data to (b) the training analysis output data.

8. A non-transitory computer-readable storage medium that includes a set of instructions which, in response to execution by a processor of a computer system, cause the processor to perform a method of tomographic data analysis using an artificial intelligence (AI) engine, wherein the method comprises:

obtaining first three-dimensional (3D) feature volume data generated based on two-dimensional (2D) projection data that is associated with a target object and acquired using an imaging system;

processing the first 3D feature volume data using the AI engine that includes multiple first processing layers, an interposing forward-projection module and multiple second processing layers by performing the following:

generating second 3D feature volume data by processing the first 3D feature volume data using the multiple first processing layers that are associated with first weight data and operate in a 3D volume space;

transforming the second 3D volume data into 2D feature data using the forward-projection module; and

generating analysis output data by processing the 2D feature data using the multiple second processing layers that are associated with second weight data and operate in a 2D projection space.

9. The non-transitory computer-readable storage medium of claim 8 , wherein generating the second 3D feature volume data comprises:

generating second 3D feature volume data by processing the first 3D feature volume data using the multiple first processing layers that are trained to perform decoding on the first 3D feature volume data.

10. The non-transitory computer-readable storage medium of claim 8 , wherein generating the analysis output data comprises:

generating the analysis output data by processing the 2D feature data using the multiple second processing layers that are trained to perform at least one of the following: automatic segmentation, object or feature detection, image artifact suppression, image enhancement and de-truncation.

11. The non-transitory computer-readable storage medium of claim 10 , wherein processing the 2D projection data using the AI engine comprises:

generating the analysis output data by processing both the 2D feature data and the 2D projection data using the multiple second processing layers.

12. The non-transitory computer-readable storage medium of claim 8 , wherein the method further comprises:

obtaining training data that includes (a) training 3D feature volume data and (b) training analysis output data; and

training the multiple first processing layers and the multiple second processing layers, with the forward-projection module interposed in between, to transform (a) the training 3D feature volume data and (b) the training analysis output data.

13. The non-transitory computer-readable storage medium of claim 8 , wherein obtaining the first 3D feature volume data comprises:

obtaining the first 3D feature volume data for processing by the AI engine, being a second AI engine, from a first AI engine that is trained to perform tomographic image reconstruction to transform the 2D projection data to the first 3D feature volume data and to learn the respective first weight data and second weight data.

14. The non-transitory computer-readable storage medium of claim 13 , wherein the method further comprises:

obtaining training data that includes (a) training 2D projection data and (b) training analysis output data; and

training the first AI engine and the second AI engine together to perform integrated tomographic image reconstruction and analysis to transform (a) the training 2D projection data to (b) the training analysis output data.

15. A computer system configured to perform tomographic data analysis using an artificial intelligence (AI) engine, wherein the computer system comprises: a processor and a non-transitory computer-readable medium having stored thereon instructions that, when executed by the processor, cause the processor to:

obtain first three-dimensional (3D) feature volume data generated based on two-dimensional (2D) projection data that is associated with a target object and acquired using an imaging system;

process the first 3D feature volume data using the AI engine that includes multiple first processing layers, an interposing forward-projection module and multiple second processing layers by performing the following:

generate second 3D feature volume data by processing the first 3D feature volume data using the multiple first processing layers that are associated with first weight data and operate in a 3D volume space;

transform the second 3D volume data into 2D feature data using the forward-projection module; and

generate analysis output data by processing the 2D feature data using the multiple second processing layers that are associated with second weight data and operate in a 2D projection space.

16. The computer system of claim 15 , wherein the instructions for generating the second 3D feature volume data cause the processor to:

generate second 3D feature volume data by processing the first 3D feature volume data using the multiple first processing layers that are trained to perform decoding on the first 3D feature volume data.

17. The computer system of claim 15 , wherein the instructions for generating the analysis output data cause the processor to:

generate the analysis output data by processing the 2D feature data using the multiple second processing layers that are trained to perform at least one of the following: automatic segmentation, object or feature detection, image artifact suppression, image enhancement and de-truncation.

18. The computer system of claim 17 , wherein the instructions for processing the 2D projection data using the AI engine cause the processor to:

generate the analysis output data by processing both the 2D feature data and the 2D projection data using the multiple second processing layers.

19. The computer system of claim 15 , wherein the instructions further cause the processor to:

obtain training data that includes (a) training 3D feature volume data and (b) training analysis output data; and

train the multiple first processing layers and the multiple second processing layers, with the forward-projection module interposed in between, to transform (a) the training 3D feature volume data and (b) the training analysis output data and to learn the respective first weight data and second weight data.

20. The computer system of claim 15 , wherein the instructions for obtaining the first 3D feature volume data cause the processor to:

obtain the first 3D feature volume data for processing by the AI engine, being a second AI engine, from a first AI engine that is trained to perform tomographic image reconstruction to transform the 2D projection data to the first 3D feature volume data.

21. The computer system of claim 15 , wherein the instructions further cause the processor to:

obtain training data that includes (a) training 2D projection data and (b) training analysis output data; and

train the first AI engine and the second AI engine together to perform integrated tomographic image reconstruction and analysis to transform (a) the training 2D projection data to (b) the training analysis output data.