System and method for synchronized navigation and annotation of correlated, heterogeneous sets of medical images

1 . A computer system for synchronized navigation and annotation of correlated, heterogeneous sets of medical images, the system comprising:

one or more computer processors;

one or more computer-readable storage media;

program instructions stored on the computer-readable storage media for execution by at least one of the one or more processors, the program instructions comprising:

program instructions to:

correlate, based on a first metadata and a second metadata, a first set of sequential tomographic medical (STM) images of a subject with a second set of STM images of the subject to generate a plurality of correlated image pairs,

wherein the first set of STM images each comprise the first metadata, depict a first anatomical plane, and are captured via a first medical imaging technique (MIT),

wherein the second set of STM images each comprise the second metadata, depict the first anatomical plane, and are captured via a second MIT;

superimpose each of the plurality of correlated image pairs to generate a plurality of fusion images each corresponding to one of the correlated image pairs;

selectively and sequentially render, via a display, one or more of the plurality of correlated image pairs, the fusion images, and a third tomographic medical (TTM) image of the subject when an input signal is received from an I/O device, the TTM image depicts a second anatomical plane and is captured via a third MIT; and

selectively render, via the display, a visual representation of one or more of a pixel of interest and a region of interest for one or more of the plurality of correlated image pairs, the fusion images, and the TTM image when input is received from the I/O device, one or more of the pixel of interest and the region of interest is associated with a medical condition.

2 . The system of claim 1 , wherein one of the first MIT, the second MIT, and the third MIT comprises one of an X-ray, a computed tomography (CT) scan, a magnetic resonance imaging (MRI) scan, a positron emission tomography (PET) scan, and a maximum intensity projection (MIP) scan.

3 . The system of claim 2 , wherein the first MIT comprises the CT scan.

4 . The system of claim 2 , wherein the second MIT comprises the PET scan.

5 . The system of claim 2 , wherein the third MIT comprises the MIP scan.

6 . The system of claim 2 , wherein program instructions to selectively render one or more of each correlated image pair, the fusion image, and the TTM image further comprise program instructions to:

sequentially render one or more of each of the plurality of correlated image pairs and each fusion image when the input signal is received from the I/O device.

7 . The system of claim 6 , wherein

program instructions to selectively render the visual representation of the pixel of interest further comprise program instructions to:

identify, using a machine learning algorithm, a pixel of one the first STM images or one of the second STM images that is associated with the medical condition, the pixel comprises a pixel location;

render, via the display a graphical annotation at the pixel location; and

the machine learning algorithm is trained with predetermined medical images that each depict a presence of the medical condition or absence of the medical condition within an anatomical region of the predetermined medical images, wherein the presence of the medical condition is dictated by a pixel value within the anatomical region that is greater than or less than a predetermined value.

8 . The system of claim 7 , wherein program instructions to selectively render the visual representation of the region of interest further comprise program instructions to:

render, via the display, a second graphical annotation that encompasses the pixel location.

9 . A computer-implemented method for synchronized navigation and annotation of correlated, heterogeneous sets of medical images, the method comprising:

correlating, based on first metadata and second metadata, a first set of sequential tomographic medical (STM) images of a subject with a second set of STM images of the subject to generate a plurality of correlated image pairs, wherein the first set of STM images comprises the first metadata, and wherein the second set of STM images comprises the second metadata;

superimposing each of the plurality of correlated image pairs to generate a plurality of fusion images each corresponding to one of the plurality of correlated image pairs;

selectively and sequentially rendering, via a display, one or more of each of the plurality of correlated image pairs, each fusion image, and a third tomographic medical (TTM) image of the subject when an input signal is received from an I/O device;

selectively rendering, via the display, a visual representation of one or more of a pixel of interest and a region of interest for one or more of the plurality of correlated image pairs, the fusion image, and the TTM image when input is received from the I/O device;

wherein:

the first set of STM images each depict a first anatomical plane and are captured via a first medical imaging technique (MIT);

the second set of STM images each depict the first anatomical plane and are captured via a second MIT;

the TTM image depicts a second anatomical plane and is captured via a third MIT; and

one or more of the pixel of interest and the region of interest is associated with a medical condition.

10 . The computer-implemented method of claim 9 , wherein one of the first MIT, the second MIT, and the third MIT comprises one of an X-ray, a computed tomography (CT) scan, a magnetic resonance imaging (MRI) scan, a positron emission tomography (PET) scan, and a maximum intensity projection (MIP) scan.

11 . The computer-implemented method of claim 10 , wherein the first MIT comprises the CT scan.

12 . The computer-implemented method of claim 11 , wherein the second MIT comprises the PET scan.

13 . The computer-implemented method of claim 12 , wherein the third MIT comprises the MIP scan.

14 . The computer-implemented method of claim 13 , wherein the step of selectively rendering one or more of each of the plurality of correlated image pairs, the fusion image, and the TTM image further comprises:

sequentially rendering one or more of each of the plurality of correlated image pairs and the fusion image when the input signal is received from the I/O device.

15 . The computer-implemented method of claim 14 , wherein the step of selectively rendering the visual representation of the pixel of interest further comprises:

identifying, using a machine learning algorithm, a pixel of one the first STM images or one of the second STM images that is associated with the medical condition, the pixel comprising a pixel location;

rendering, via the display, a graphical annotation at the pixel location; and

the machine learning algorithm is trained with predetermined medical images that each depict a presence of the medical condition or absence of the medical condition within an anatomical region of the predetermined medical images, wherein the presence of the medical condition is dictated by a pixel value within the anatomical region that is greater than or less than a predetermined value.

16 . The computer-implemented method of claim 15 , wherein the step of selectively rendering the visual representation of the region of interest further comprises:

rendering, via the display, a second graphical annotation that encompasses the pixel location.

17 . A computer program product, the computer program product comprising a computer readable storage medium having program code embodied therewith, the program code executable by a processor to:

correlate, based on a first metadata and a second metadata, a first set of sequential tomographic medical (STM) images of a subject with a second set of STM images of the subject and thereby generate a plurality of correlated image pairs,

superimpose each of the plurality of correlated image pairs to generate a plurality of fusion images each corresponding to one of the plurality of correlated image pairs;

selectively and sequentially render, via a display, one or more of the plurality of correlated image pairs, the fusion images, and a third tomographic medical (TTM) image of the subject when an input signal is received from an I/O device, the TTM image depicts a second anatomical plane and is captured via a third MIT;

selectively render, via the display, a visual representation of one or more of a pixel of interest and a region of interest for one or more of the plurality of correlated image pairs, the fusion images, and the TTM image when input is received from the I/O device;

wherein:

the first set of STM images each comprise the first metadata, depict a first anatomical plane and are captured via a first medical imaging technique (MIT);

the second set of STM images each comprise the second metadata, depict the first anatomical plane and are captured via a second MIT; and

one or more of the pixel of interest and the region of interest is associated with a medical condition.

18 . The computer program product of claim 17 , wherein one of the first MIT, the second MIT, and the third MIT comprises one of an X-ray, a computed tomography (CT) scan, a magnetic resonance imaging (MRI) scan, a positron emission tomography (PET) scan, and a maximum intensity projection (MIP) scan.

19 . The computer program product of claim 18 , wherein

the program code to selectively render the visual representation of the pixel of interest further comprises computer code executable by the processor to:

identify, using a machine learning algorithm, a pixel of one the first STM images or one of the second STM images that is associated with the medical condition, the pixel comprising a pixel location;

render, via the display, a graphical annotation at the pixel location; and

the machine learning algorithm is trained with predetermined medical images that each depict a presence of the medical condition or absence of the medical condition within an anatomical region of the predetermined medical images, wherein the presence of the medical condition is dictated.

20 . The computer program product of claim 19 , wherein the program code to selectively render the visual representation of the region of interest further comprises program code executable by the processor to:

render, via the display, a second graphical annotation that encompasses the pixel location.