System and method for thresholding for residual cancer cell detection
Embodiments related to methods of use of an image analysis system for identifying residual cancer cells after surgery are disclosed. In some embodiments, a patient-specific threshold used to detect abnormal cells in a surgical site can be determined. A medical imaging device can be configured to produce a set of images of an anatomy of a patient. An image analysis system, comprising one or more processors, can be configured to receive the set of images, and analyze the set of images to determine a patient-specific threshold to use to detect abnormal tissue of the patient.
1. A system for determining a patient-specific threshold used to detect abnormal cells, the system comprising:
a medical imaging device configured to produce a set of fluorescence images of an anatomy of a patient; and
an image analysis system comprising one or more processors configured to:
receive the set of fluorescence images; and
analyze the set of fluorescence images to determine a patient-specific threshold to use to detect abnormal tissue of the patient,
wherein the image analysis system is configured to:
analyze the set of fluorescence images by calculating, using a pixel comparator, one or more representative intensity values for each fluorescence image in the set of fluorescence images that represents one or more pixel intensity values of the associated fluorescence image to generate a set of representative intensity values,
select a subset of the set of representative intensity values corresponding to the set of fluorescence images based on a predetermined criterion that is used to filter out one or more of the representative intensity values in the set of representative intensity values;
average the selected subset of representative intensity values to calculate an averaged intensity value; and
calculate the patient-specific threshold based on the averaged intensity value and an adjustment factor associated with the pixel comparator.
2. The system of claim 1 , wherein the fluorescence images are surgical site fluorescence images of a surgical site of the patient.
3. The system of claim 2 , wherein:
the medical imaging device is configured to produce a new surgical site fluorescence image;
the image analysis system is further configured to identify one or more groups of abnormal cells in the new surgical site fluorescence image based on the calculated patient- specific threshold; and
the system comprises a display configured to indicate one or more locations of at least one of the one or more groups of identified abnormal cells.
4. The system of claim 1 , wherein the pixel comparator is selected from the group consisting of:
a maximums comparator that calculates the one or more representative intensity values for each fluorescence image in the set of fluorescence images by calculating a maximum pixel intensity value of each fluorescence image;
a minimums comparator that calculates the one or more representative intensity values for each fluorescence image in the set of fluorescence images by calculating a minimum pixel intensity value of each fluorescence image;
a means comparator that calculates the one or more representative intensity values for each fluorescence image in the set of fluorescence images by calculating a mean of pixel intensity values of each fluorescence image;
a twenty-fifth percentile comparator that calculates the one or more representative intensity values for each fluorescence image in the set of fluorescence images by calculating a 25 % percentile of pixel intensity values of each fluorescence image; and
a medians comparator that calculates the one or more representative intensity values for each fluorescence image in the set of fluorescence images by calculating a median pixel intensity value for each fluorescence image.
5. The system of claim 1 , wherein the image analysis system is configured to select the pixel comparator from a plurality of pixel comparators, comprising:
running the plurality of pixel comparators on a training set of images to calculate a set of results values for each of the pixel comparators in the plurality of pixel comparators;
analyzing the set of results values for each pixel comparator in the plurality of pixel comparators; and
selecting the pixel comparator from the plurality of pixel comparators based on the analysis.
6. The system of claim 1 , wherein each fluorescence image in the set of fluorescence images is an image of healthy tissue.
7. The system of claim 1 , wherein the adjustment factor is a multiplier.
8. The system of claim 7 , wherein the multiplier ranges from 1 to 25.
9. A computer-implemented method for determining a patient-specific threshold used to detect abnormal cells, the method comprising:
receiving a set of fluorescence images of an anatomy of a patient; and
analyzing the set of fluorescence images to determine a patient-specific threshold to use to detect abnormal tissue of the patient,
wherein analyzing the set of fluorescence images comprises:
calculating, using a pixel comparator, one or more representative intensity values for each fluorescence image in the set of fluorescence images that represents one or more pixel intensity values of the associated fluorescence image to generate a set of representative intensity values,
selecting a subset of the set of representative intensity values corresponding to the set of fluorescence images based on a predetermined criterion that is used to filter out one or more of the representative intensity values in the set of representative intensity values;
averaging the selected subset of representative intensity values to calculate an averaged intensity value; and
calculating the patient-specific threshold based on the averaged intensity value and an adjustment factor associated with the pixel comparator.
10. The method of claim 9 , wherein the fluorescence images are surgical site fluorescence images of a surgical site of the patient.
11. The method of claim 10 , further comprising:
receiving a new surgical site fluorescence image;
identifying one or more groups of abnormal cells in the new surgical site fluorescence image based on the calculated patient-specific threshold; and
indicating, via a display, one or more locations of at least one of the one or more groups of identified abnormal cells.
12. The method of claim 9 , wherein the pixel comparator is selected from the group consisting of:
a maximums comparator that calculates the one or more representative intensity values for each fluorescence image in the set of fluorescence images by calculating a maximum pixel intensity value of each fluorescence image;
a minimums comparator that calculates the one or more representative intensity values for each fluorescence image in the set of fluorescence images by calculating a minimum pixel intensity value of each fluorescence image;
a means comparator that calculates the one or more representative intensity values for each fluorescence image in the set of fluorescence images by calculating a mean of pixel intensity values of each fluorescence image;
a twenty-fifth percentile comparator that calculates the one or more representative intensity values for each fluorescence image in the set of fluorescence images by calculating a 25 % percentile of pixel intensity values of each fluorescence image; and
a medians comparator that calculates the one or more representative intensity values for each fluorescence image in the set of fluorescence images by calculating a median pixel intensity value for each fluorescence image.
13. The method of claim 9 , further comprising selecting the pixel comparator from a plurality of pixel comparators, comprising:
running the plurality of pixel comparators on a training set of images to calculate a set of results values for each of the pixel comparators in the plurality of pixel comparators;
analyzing the set of results values for each pixel comparator in the plurality of pixel comparators; and
selecting the pixel comparator from the plurality of pixel comparators based on the analysis.
14. The method of claim 9 , wherein each fluorescence image in the set of fluorescence images is an image of healthy tissue.
15. The method of claim 9 , wherein the adjustment factor is a multiplier.
16. The method of claim 15 , wherein the multiplier ranges from 1 to 25.
17. At least one non-transitory computer-readable storage medium comprising computer-executable instructions that, when executed by at least one processor of an image analysis system configured to collect one or more fluorescence images, perform a method to calculate a threshold used to detect abnormal cells, the method comprising:
receiving a set of fluorescence images of an anatomy of a patient; and
analyzing the set of fluorescence images to determine a patient-specific threshold to use to detect abnormal tissue of the patient,
wherein analyzing the set of fluorescence images comprises:
calculating, using a pixel comparator, one or more representative intensity values for each fluorescence image in the set of fluorescence images that represents one or more pixel intensity values of the associated fluorescence image to generate a set of representative intensity values,
selecting a subset of the set of representative intensity values corresponding to the set of fluorescence images based on a predetermined criterion that is used to filter out one or more of the representative intensity values in the set of representative intensity values;
averaging the selected subset of representative intensity values to calculate an averaged intensity value; and
calculating the patient-specific threshold based on the averaged intensity value and an adjustment factor associated with the pixel comparator.
18. The at least one non-transitory computer-readable storage medium of claim 17 , wherein the fluorescence images are surgical site fluorescence images of a surgical site of the patient.
19. The at least one non-transitory computer-readable storage medium of claim 18 , the method further comprising:
receiving a new surgical site fluorescence image;
identifying one or more groups of abnormal cells in the new surgical site fluorescence image based on the calculated patient-specific threshold; and
indicating, via a display, one or more locations of at least one of the one or more groups of identified abnormal cells.
20. The at least one non-transitory computer-readable storage medium of claim 15 , wherein the pixel comparator is selected from the group consisting of:
a maximums comparator that calculates the one or more representative intensity values for each fluorescence image in the set of fluorescence images by calculating a maximum pixel intensity value of each fluorescence image;
a minimums comparator that calculates the one or more representative intensity values for each fluorescence image in the set of fluorescence images by calculating a minimum pixel intensity value of each fluorescence image;
a means comparator that calculates the one or more representative intensity values for each fluorescence image in the set of fluorescence images by calculating a mean of pixel intensity values of each fluorescence image;
a twenty-fifth percentile comparator that calculates the one or more representative intensity values for each fluorescence image in the set of fluorescence images by calculating a 25 % percentile of pixel intensity values of each fluorescence image; and
a medians comparator that calculates the one or more representative intensity values for each fluorescence image in the set of fluorescence images by calculating a median pixel intensity value for each fluorescence image.
21. The at least one non-transitory computer-readable storage medium of claim 17 , the method further comprising selecting the pixel comparator from a plurality of pixel comparators, comprising:
running the plurality of pixel comparators on a training set of images to calculate a set of results values for each of the pixel comparators in the plurality of pixel comparators;
analyzing the set of results values for each pixel comparator in the plurality of pixel comparators; and
selecting the pixel comparator from the plurality of pixel comparators based on the analysis.
22. The at least one non-transitory computer-readable storage medium of claim 17 , wherein each fluorescence image in the set of fluorescence images is an image of healthy tissue.
23. The at least one non-transitory computer-readable storage medium of claim 17 , wherein the adjustment factor is a multiplier.
24. The at least one non-transitory computer-readable storage medium of claim 23 , wherein the multiplier ranges from 1 to 25.