Automated determination of muscle mass from images

1. A computer implemented method comprising:

receiving an image file of a patient, the image file comprising data of a 3D image;

performing a thresholding process to the image file to generate a contrasted image;

segmenting pixels of the contrasted image into bone and not bone;

distinguishing muscle from organ for the pixels segmented as not bone by:

determining a location of a rib cage of the patient using the pixels segmented as bone by:

locating a spinal cord of the patient by:

searching a region where the spinal cord should be based on the pixels segmented as bone; and

matching pixels that are segmented as bone to the region where the spinal cord should be based on bone features;

locating rib bones of the patient by:

identifying a first rib bone based on shape of the bone and spacing from a spine; and

identifying successive rib bones based on a distance and angle formed relative to each previously identified rib; and

generating vectors originating from the spinal cord to rib bones of the patient; and

removing pixels segmented as not bone that are located within the location of the rib cage;

calculating a volume of muscle based on remaining pixels segmented as not bone;

calculating a total muscle mass based on the volume of muscle; and

providing the total muscle mass of the patient.

2. The method of claim 1 , wherein removing pixels segmented as not bone that are located within the location of the rib cage comprises creating an ellipse about the rib cage using the generated vectors and removing pixels within the ellipse that are segmented as not bone.

3. The method of claim 1 , wherein searching a region where the spinal cord should be is further based on a patient's height; and

matching pixels that are segmented as bone to the region where the spinal cord should be is further based on the patient's height.

4. The method of claim 1 , wherein matching pixels that are segmented as bone to the region where the spinal cord should be based on bone features comprises using location, size, and dimensions of pixels segmented as bone in relation to:

an overall image size; and

predefined ranges of bone locations, sizes, and angles.

5. The method of claim 1 , wherein performing the thresholding process to the image file to generate the contrasted image comprises:

creating a histogram of intensity values for a plurality of image slices found within the image file comprising the 3D image;

calculating maximum and minimum pixel intensity values relative to a threshold value for each of the plurality of image slices; and

adjusting each of the plurality of image slices to a gray scale based on the maximum and minimum pixel intensity values for the plurality of image slices.

6. The method of claim 1 , further comprising calculating a volume of bone using the segmented pixels of the contrasted image identified as bone.

7. The method of claim 6 , further comprising calculating total bone mass of the patient using the volume of bone; and

providing the total bone mass of the patient.

8. The method of claim 1 , further comprising:

receiving a measurement of creatinine levels of the patient; and

calculating a glomerular filtration rate of the patient based on the total muscle mass of the patient and the measurement of creatinine levels of the patient.

9. The method of claim 8 , wherein calculating the glomerular filtration rate of the patient is further based on a patient's weight, age, race, and gender.

10. One or more computer readable storage media having program instructions stored thereon that, when executed by a processing system, direct a system to:

perform a thresholding process to an image file of a patient to generate a contrasted image;

segment pixels of the contrasted image into bone and not bone;

distinguish muscle from organ for the pixels segmented as not bone by:

determining a location of a rib cage of the patient using the pixels segmented as bone by:

locating a spinal cord of the patient by:

searching a region where the spinal cord should be based on the pixels segmented as bone; and

matching pixels that are segmented as bone to the region where the spinal cord should be based on bone features;

locating rib bones of the patient by:

identifying a first rib bone based on shape of the bone and spacing from a spine; and

identifying successive rib bones based on a distance and angle formed relative to each previously identified rib; and

generating vectors originating from the spinal cord to rib bones of the patient; and

removing pixels segmented as not bone that are located within the location of the rib cage;

calculate a volume of muscle based on remaining pixels segmented as not bone;

calculate a total muscle mass based on the volume of muscle; and

provide the total muscle mass of the patient.

11. The media of claim 10 , wherein the instructions to perform the thresholding process to the image file to generate the contrasted image direct the system to:

create a histogram of intensity values for a plurality of image slices found within the image file comprising a 3D image;

calculate maximum and minimum pixel intensity values relative to a threshold value for each of the plurality of image slices; and

adjust each of the plurality of image slices to a gray scale based on the maximum and minimum pixel intensity values for the plurality of image slices.

12. The media of claim 10 , further comprising instructions that direct the system to calculate a volume of bone using the segmented pixels of the contrasted image identified as bone.

13. The media of claim 12 , further comprising instructions that direct the system to:

calculate total bone mass of the patient using the volume of bone; and

providing the total bone mass of the patient.

14. The media of claim 10 , further comprising instructions that direct the system to:

receive a measurement of creatinine levels of the patient; and

calculate a glomerular filtration rate of the patient based on the total muscle mass of the patient and the measurement of creatinine levels of the patient.

15. The media of claim 14 , wherein the instructions to calculate the glomerular filtration rate of the patient is further based on the patient's weight, age, race, and gender.

16. A system comprising:

a processor directed to:

receive an image file of a patient, the image file comprising computed tomography images;

perform a thresholding process to the image file to generate a contrasted image;

segment pixels of the contrasted image into bone and not bone;

distinguish muscle from organ for the pixels segmented as not bone by:

determining a location of a rib cage of the patient using the pixels segmented as bone by:

locating a spinal cord of the patient by:

 searching a region where the spinal cord should be based on the pixels segmented as bone; and

 matching pixels that are segmented as bone to the region where the spinal cord should be based on bone features;

locating rib bones of the patient by:

 identifying a first rib bone based on shape of the bone and spacing from a spine; and

 identifying successive rib bones based on a distance and angle formed relative to each previously identified rib; and

generating vectors originating from the spinal cord to rib bones of the patient; and

removing pixels segmented as not bone that are located within the location of the rib cage;

calculate a volume of muscle based on remaining pixels segmented as not bone;

calculate a total muscle mass based on the volume of muscle;

provide the total muscle mass of the patient;

receive a measurement of creatinine levels of the patient;

calculate a glomerular filtration rate of the patient based on at least the total muscle mass of the patient and the measurement of creatinine levels of the patient; and

provide the glomerular filtration rate.

17. The system of claim 16 , wherein the glomerular filtration rate of the patient is further based on a patient's weight, age, race, and gender.