Computer-assisted tumor response assessment and evaluation of the vascular tumor burden

1. A computer system for determining an objective tumor response to an anti-cancer therapy using cross-sectional images, the computer system comprising:

one or more processors; and

one or more computer readable hardware storage devices, wherein the one or more computer readable hardware storage devices comprise computer executable instructions that when executed by at least one of the one or more processors cause the computer system to perform at least the following:

receive a cross-sectional image generated at one or more of an x-ray computed tomography scanner, a computed tomography perfusion imaging system, a positron emission tomography system, a single-photon emission computed tomography system, or a magnetic resonance imaging scanner, wherein the cross-sectional image comprises a cross-sectional slice of digital medical image data;

identify a set of pixels within the cross-sectional image, the set of pixels corresponding to a target lesion;

analyze the set of pixels with an image processing module, wherein for the set of pixels, the image processing module performs the following:

identify a lower threshold of pixel intensities within a total range of pixel intensities;

identify an upper threshold of pixel intensities within the total range of pixel intensities; and

define a subset of pixels from the set of pixels that correspond to vascularized tumor, wherein the subset of pixels comprises pixels having pixel intensities greater than or equal to the lower threshold and lower than or equal to the upper threshold;

derive a vascular tumor burden for the set of pixels;

receive one or more additional cross-sectional images, wherein the one or more additional cross-sectional images comprise one or more cross-sectional slices of the digital medical image data:

identify an additional set of pixels within each of the one or more additional cross-sectional images corresponding to the target lesion;

analyze the additional set of pixels with the image processing module, wherein for the additional set of pixels, the image processing module performs the following:

identify the lower threshold of pixel intensities within the total range of pixel intensities;

identify the upper threshold of pixel intensities within the total range of pixel intensities; and

define an additional subset of pixels from the additional set of pixels within each of the one or more additional cross-sectional images that correspond to vascularized tumor, wherein the additional subset of pixels comprises pixels having pixel intensities greater than or equal to the lower threshold and lower than or equal to the upper threshold;

derive a vascular tumor burden, wherein deriving the vascular tumor burden comprises determining a volume of the subset of pixels and the additional subsets of pixels; and

determine the objective tumor response for the target lesion, wherein the objective tumor response is based on the vascular tumor burden.

2. The computer system as in claim 1 , wherein determining the objective tumor response for the set of pixels is based on the vascular tumor burden and one or more tumor response criteria.

3. The computer system as claim 2 , wherein the one or more tumor response criteria comprise one or more of: Response Evaluation Criteria in Solid Tumors (RECIST) 1.0, RECIST 1.1, modified RECIST, World Health Organization (WHO) Criteria, 10% Tumor Diameter Shrinkage Criteria, Choi Criteria, Modified Choi Criteria, Morphology Attenuation Size and Structure (MASS) Criteria, Immune-related Response Criteria, Cheson Criteria, lymphoma response criteria, Revised Response Criteria for Malignant Lymphoma, Positron Emission Tomography Response Criteria in Solid Tumors (PERCIST), Metabolic Response Criteria, European Organization for Research and Treatment of Cancer (EORTC), International uniform response criteria for multiple myeloma, Current Response Criteria for High-Grade Gliomas, MacDonald Criteria, Response Assessment of Neuro-Oncology (RANO) Criteria, Vascular Tumor Burden (VTB) Criteria, and computed tomography texture analysis criteria.

4. The computer system as in claim 1 , wherein the computer-executable instructions further comprise computer-executable instructions that when executed by the one or more processors configure the computer system to

receive an image type for the cross-sectional image; and

receive a determination of injected radiocontrast in the cross-sectional image from metadata tags associated with the cross-sectional image or from a user selection.

5. The computer system as in claim 4 , wherein the lower and the upper thresholds of pixel intensities change based on the determination of injected radiocontrast in the cross-sectional image.

6. The computer system as in claim 1 , also including computer-executable instructions that when executed by the one or more processors configure the computer system to perform the following:

restrict the total range of pixel intensities to a restricted range of pixel intensities, wherein the restricted range of pixel intensities corresponds to a second subset of pixels representative of necrotic tumor; and

derive a necrotic tumor burden, wherein deriving the necrotic tumor burden comprises determining an area of pixels corresponding to the second subset of pixels.

7. The computer system as in claim 6 , wherein the computer-executable instructions further comprise computer-executable instructions that when executed by the one or more processors configure the computer system to automatically calculate or derive one or more of the vascular tumor burden, the necrotic tumor burden, or a total tumor burden.

8. The computer system as in claim 1 , wherein the computer-executable instructions further comprise computer-executable instructions that when executed by the one or more processors configure the computer system to receive one or more inputs, wherein the one or more inputs comprise:

a determination of injected radiocontrast in any of the one or more cross-sectional images;

data related to a response of one or more non-target lesions;

a presence of one or more new metastases;

a label for the set of pixels, wherein the label one or more of:

a lesion type of the set of pixels, wherein lesion type can be a primary tumor, metastasis or lymph node; and

an anatomical location of the set of pixels

a label for the one or more non-target lesions, wherein the label comprises one or more of: a lesion type of the one or more non-target lesions or an anatomical location of the one or more non-target lesions.

9. The computer system as in claim 1 , wherein the one or more lesion metrics comprise one or more of:

a longest dimension length;

a short axis dimension length;

a longest dimension length of vascularized tumor;

an area of the set of pixels;

a volume of the set of pixels;

a mean value of pixel intensities within the total range of pixel intensities;

a mean value of pixel intensities within the subset of pixels;

a median value of the pixel intensities within the total range of pixel intensities;

a maximum value of the pixel intensities within the total range of pixel intensities;

a histogram parameter, wherein the histogram parameter comprises a quantitative distribution of pixel intensities in the set of pixels; and

a texture parameter, wherein the texture parameter comprises a geographic distribution of pixel intensities in the set of pixels.

10. The computer system as in claim 1 , wherein analyzing the set of pixels with an image processing module comprises:

analyzing the cross-sectional image, the cross-sectional image being captured at a first point in time;

analyzing an analogous cross-sectional image, the analogous cross-sectional image being captured at a second point in time, wherein the cross-sectional image and the second cross-sectional image comprise digital medical image data of the set of pixels and wherein the second point in time is chronologically after the first point in time; and

evaluating the second cross-sectional image with respect to the first cross-sectional image.

11. A method, implemented at a computer system that includes one or more processors, for determining an objective tumor response to an anti-cancer therapy using cross-sectional images, the method comprising the computer system performing the following:

receiving a cross-sectional image generated at one or more of an x-ray computed tomography scanner, a computed tomography perfusion imaging system, a positron emission tomography system, a single-photon emission computed tomography system, or a magnetic resonance imaging scanner, wherein the cross-sectional image comprises a cross-sectional slice of digital medical image data;

identifying a set of pixels within the cross-sectional image, the set of pixels corresponding to a target lesion;

analyzing the set of pixels with an image processing module, wherein for the set of pixels, the image processing module performs the following:

identify a lower threshold of pixel intensities within a total range of pixel intensities;

identify an upper threshold of pixel intensities within the total range of pixel intensities;

define a subset of pixels from the set of pixels that correspond to vascularized tumor, wherein the subset of pixels comprises pixels having pixel intensities greater than or equal to the lower threshold and lower than or equal to the upper threshold; and

deriving a vascular tumor burden for the set of pixels;

determining the objective tumor response for the target lesion, wherein the objective tumor response is based on the vascular tumor burden; and

displaying a customizable summary image comprising an illustration of the target lesion at the first point in time and at least one or more of:

a numeric value of the vascular tumor burden;

a graphical output of the pixel intensities;

a second illustration, wherein the second illustration comprises an illustration of the vascular tumor burden;

a third illustration, wherein the third illustration comprises an illustration of the target lesion at the second point in time;

a fourth illustration, wherein the fourth illustration comprises an illustration of the vascular tumor burden at the second point in time;

a fifth illustration, wherein the fifth illustration comprises an illustration of the necrotic tumor burden at the first point in time;

a sixth illustration, wherein the sixth illustration comprises an illustration of the necrotic tumor burden at the second point in time;

a seventh illustration, wherein the seventh illustration comprises an illustration of a total tumor burden at the first point in time;

an eighth illustration, wherein the eighth illustration comprises an illustration of the total tumor burden at the second point in time;

a ninth illustration, wherein the ninth illustration comprises an illustration of a CT histogram at the first point in time;

a tenth illustration, wherein the tenth illustration comprises an illustration of a texture analysis at the first point in time;

a first graphical display illustrating one or more changes in vascularized tumor between the first point in time and the second point in time;

a second graphical display illustrating one or more changes in necrotic tumor between the first point in time and the second point in time;

a numeric value representing at least one of a percent change, an average change, or an absolute change in the one or more lesion metrics;

a first indication of objective response, wherein the first indication comprises an indication that the set of pixels is responding or not responding to anti-cancer therapy;

a second indication of objective response, wherein the second indication of objective response comprises an indication that the one or more non-target lesions is responding or not responding to anti-cancer therapy;

a first readable text, wherein the first readable text comprises the one or more lesion metrics;

a second readable text, wherein the second readable text comprises the presence or absence of new metastases;

a third readable text, wherein the third readable text comprises the vascular tumor burden for the set of pixels;

a fourth readable text, wherein the fourth readable text comprises the necrotic tumor burden for the set of pixels; and

a fifth readable text, wherein the fifth readable text comprises the objective tumor response for the one or more target lesions as determined by the one or more tumor response criteria.

12. The method as in claim 11 , further comprising:

receiving two or more additional cross-sectional images, wherein the two or more additional cross-sectional images comprise two or more cross-sectional slices of the digital medical image data;

identifying an additional set of pixels within each of the two or more additional cross-sectional images corresponding to the target lesion;

analyzing the additional sets of pixels with an image processing module, wherein for the additional sets of pixels, the image processing module performs the following:

identify the lower threshold of pixel intensities within a total range of pixel intensities;

identify the upper threshold of pixel intensities within the total range of pixel intensities; and

define an additional subset of pixels from the additional set of pixels within each of the two or more additional cross-sectional images that correspond to vascularized tumor, wherein the additional subset of pixels comprises pixels having pixel intensities greater than or equal to the lower threshold and lower than or equal to the upper threshold; and

deriving a vascular tumor burden, wherein deriving the vascular tumor burden comprises determining a volume of the subset of pixels and the additional subsets of pixels.

13. The method as in claim 11 , further comprising:

receiving an additional cross-sectional image, wherein the additional cross-sectional image comprises an additional set of pixels corresponding to the target lesion at a second point in time;

analyzing the additional set of pixels with an image processing module, wherein for the additional set of pixels, the image processing module performs the following:

identify the lower threshold of pixel intensities within a total range of pixel intensities;

identify the upper threshold of pixel intensities within the total range of pixel intensities; and

define an additional subset of pixels from the additional set of pixels that correspond to vascularized tumor, wherein the additional subset of pixels comprises pixels having pixel intensities greater than or equal to the lower threshold and lower than or equal to the upper threshold;

deriving a vascular tumor burden, wherein deriving the vascular tumor burden comprises determining an area pixels corresponding to the additional subset of pixels; and

calculating a change in one or more of vascular tumor burden or the one or more additional lesion metrics.

14. The method as in claim 13 , further comprising:

restricting the total range of pixel intensities to a restricted range of pixel intensities, wherein the restricted range of pixel intensities corresponds to a second subset of pixels representative of necrotic tumor; and

deriving a necrotic tumor burden, wherein deriving the necrotic tumor burden comprises determining a number of pixels corresponding to the second subset of pixels.

15. The method as in claim 11 , wherein calculating the overall tumor burden comprises calculating one or more of a sum, average, and percent change of the area or a volume of pixels corresponding to the subsets of pixels for each of the plurality of target lesions.

16. The method as in claim 11 , further comprising receiving one or more inputs, wherein the one or more inputs comprise:

a determination of injected radiocontrast in the cross-sectional image;

data related to a response of one or more non-target lesions;

a presence of one or more new metastases;

a pixel label for the set of pixels, the pixel label including one or more of an anatomical location of the set of pixels or a lesion type of the set of pixels, the lesion type being a primary tumor, a metastasis or a lymph node; and

a label for the one or more non-target lesions, wherein the label comprises one or more of a lesion type of the one or more non-target lesions or an anatomical location of the one or more non-target lesions.

17. A method, implemented at a computer system that includes one or more processors, for determining an amount of vascularized tumor using cross-sectional images, the method comprising:

receiving one or more cross-sectional images generated at one or more of an x-ray computed tomography scanner, a computed tomography perfusion imaging system, a positron emission tomography system, a single-photon emission computed tomography system, or a magnetic resonance imaging scanner, wherein the one or more cross-sectional images comprise digital medical image data captured at a first point in time;

identifying a set of pixels within the one or more cross-sectional images, the set of pixels corresponding to a target lesion;

analyzing the set of pixels with an image processing module, wherein for the set of pixels, the image processing module performs the following:

identify a total range of pixel intensities within the set of pixels;

identify a lower threshold of pixel intensities within the total range of pixel intensities;

identify an upper threshold of pixel intensities within the total range of pixel intensities;

define a subset of pixels from the set of pixels that correspond to vascularized tumor, wherein the subset of pixels comprises pixels having pixel intensities greater than or equal to the lower threshold and lower than or equal to the upper threshold; and

determine one or more lesion metrics based on the set of pixels; and

deriving a vascular tumor burden for the set of pixels, wherein the vascular tumor burden corresponds to the amount of vascularized tumor,

wherein analyzing the set of pixels with the image processing module comprises:

analyzing the set of pixels for the one or more cross-sectional images captured at the first point in time;

analyzing an analogous cross-sectional image, the analogous cross-sectional image being captured at a second point in time, the second point in time being chronologically after the first point in time; and

evaluating the analogous cross-sectional image with respect to the one or more cross-sectional images.

18. The method as in claim 17 , wherein the derived vascular tumor burden is used to evaluate a primary tumor or metastasis prior to beginning therapy.

19. A computer system for determining an objective tumor response to an anti-cancer therapy using cross-sectional images, the computer system comprising:

one or more processors; and

one or more computer readable hardware storage devices, wherein the one or more computer readable hardware storage devices comprise computer executable instructions that when executed by at least one of the one or more processors cause the computer system to perform at least the following:

receive a cross-sectional image generated at one or more of an x-ray computed tomography scanner, a computed tomography perfusion imaging system, a positron emission tomography system, a single-photon emission computed tomography system, or a magnetic resonance imaging scanner, wherein the cross-sectional image comprises a cross-sectional slice of digital medical image data;

identify a set of pixels within the cross-sectional image, the set of pixels corresponding to a target lesion;

analyze the set of pixels with an image processing module, wherein for the set of pixels, the image processing module performs the following:

identify a lower threshold of pixel intensities within a total range of pixel intensities;

identify an upper threshold of pixel intensities within the total range of pixel intensities; and

define a subset of pixels from the set of pixels that correspond to vascularized tumor, wherein the subset of pixels comprises pixels having pixel intensities greater than or equal to the lower threshold and lower than or equal to the upper threshold;

derive a vascular tumor burden for the set of pixels;

restrict the total range of pixel intensities to a restricted range of pixel intensities, wherein the restricted range of pixel intensities corresponds to a second subset of pixels representative of necrotic tumor; and

derive a necrotic tumor burden, wherein deriving the necrotic tumor burden comprises determining an area of pixels corresponding to the second subset of pixels; and

determine the objective tumor response for the target lesion, wherein the objective tumor response is based on the vascular tumor burden.