Tracking surgical items with prediction of duplicate imaging of items
A computer-implemented method for tracking surgical textiles includes receiving a first image comprising a first textile-depicting image region, receiving a second image comprising a second textile-depicting image region, measuring a likelihood that the first and second image regions depict at least a portion of the same textile, and incrementing an index counter if the measure of likelihood does not meet a predetermined threshold. The measure of likelihood may be based on at least one classification feature at least partially based on aspects or other features of the first and second images.
1 . A computer-implemented method for managing surgical textiles, the method comprising:
receiving, at one or more processors, a first image of a first surgical textile;
identifying, with the one or more processors, a first fluid pattern on the first surgical textile depicted within the first image;
quantifying, with the one or more processors, a first fluid component of the first fluid pattern depicted in the first image;
receiving, at one or more processors, a second image of the first surgical textile or a second surgical textile;
identifying, with the one or more processors, a second fluid pattern depicted in the second image;
quantifying, with the one or more processors, a second fluid component of the second fluid pattern depicted in the second image;
determining, with the one or more processors, a similarity measure between first fluid pattern and the second fluid pattern with an algorithm that calculates the similarity measure based on the first fluid component and the second fluid component;
determining, with the one or more processors, whether the second image is of the first surgical textile or the second surgical textile by comparing the similarity measure to a predetermined threshold;
incrementing, with the one or more processors, an index counter if the similarity measure is below the predetermined threshold; and
displaying, on a display, the index counter.
2 . The method of claim 1 , further comprising triggering a prompt, on the display, to request user confirmation that the second image is not of the first surgical textile if the similarity measure is above the predetermined threshold.
3 . The method of claim 2 , further comprising decrementing the index counter if the user confirmation indicates that the second image is of the first surgical textile.
4 . The method of claim 1 , further comprising triggering an alarm if the similarity measure is above the predetermined threshold.
5 . The method of claim 1 , further comprising:
quantifying a first area of the first fluid pattern depicted in the first image;
quantifying a second area of the second fluid pattern depicted in the second image; and
comparing the first area and the second area to determine the similarity measure between the first fluid pattern and the second fluid pattern.
6 . The method of claim 5 , further comprising:
determining a first area ratio between the first area and a total area of the first surgical textile depicted in the first image; and
determining a second area ratio between the second area and a total area of the first surgical textile or the second surgical textile depicted in the second image; and
comparing the first area ratio and the second area ratio to determine the similarity measure between the first fluid pattern and the second fluid pattern.
7 . The method of claim 5 , wherein the first area and the second area are based on a number of pixels having a color component value above a predetermined color threshold.
8 . The method of claim 1 , wherein the first fluid component and the second fluid component are one of hemoglobin and red blood cells.
9 . The method of claim 1 , further comprising:
storing, in a database, the first image and the second image; and
comparing, with the one or more processors, subsequent images of surgical textiles against all images stored in the database.
10 . The method of claim 9 , wherein the subsequent images of surgical textiles are obtained in a different surgical procedure or session.
11 . The method of claim 9 , further comprising aggregating a risk score including a incorporating the similar measure among some or all of the first image, the second image, and the subsequent images of surgical textiles, wherein the aggregate risk score is indicative of a level of uncertainty of an overall textile count based on potential duplicate images.
12 . The method of claim 1 , wherein the algorithm further calculates the similarity measure by applying image transformation permutations and selecting one of the image transformation permutations that results in the highest similarity measure.
13 . The method of claim 12 , wherein the step of applying the image transformation permutations further comprises at least one of flipping the first or second images, rotating the first or second images, and deskewing the first or second images.
14 . The method of claim 12 , further comprising receiving, on an interface, user inputs in which a user manually adjusts one or both of the first image and the second image to facilitate manual comparison of the first and second images.
15 . The method of claim 1 , further comprising displaying, on a display, a notification of potential duplicity if the similarity measure is above the predetermined threshold.
16 . A computer-implemented method for managing surgical textiles, the method comprising:
receiving, at one or more processors, a first image of a first surgical textile;
identifying, with the one or more processors, a first fluid pattern on the first surgical textile depicted within the first image;
receiving, at one or more processors, a second image of the first surgical textile or a second surgical textile;
identifying, with the one or more processors, a second fluid pattern depicted in the second image;
quantifying, with the one or more processors, a first fluid component of the first fluid pattern depicted in the first image;
quantifying, with the one or more processors, a second fluid component of the second fluid pattern depicted in the second image;
determining, with the one or more processors, a similarity measure between first fluid pattern and the second fluid pattern with an algorithm that calculated the similarity measure based on the first fluid component and the second fluid component;
determining, with the one or more processors, whether the second image is of the first surgical textile or the second surgical textile by comparing the similarity measure to a predetermined threshold; and
displaying, on a display, a notification of potential duplicity if the similarity measure is above the predetermined threshold.
17 . The method of claim 16 , further comprising displaying, on the display, the first image and the second image with the notification of potential duplicity.
18 . The method of claim 17 , wherein the step of displaying the notification of potential duplicity further comprises visually indicating potential groups of duplicates including the first image, the second image, and any subsequent images of surgical textiles.
19 . The method of claim 16 , further comprising displaying, on the display, in chronological order the first image, the second image, and any subsequent images of surgical textiles.