Method and apparatus for prescription medication verification

• US 8,861,816 B2
• Filed: 12/05/2011
• Issued: 10/14/2014
• Est. Priority Date: 12/05/2011
• Status: Active Grant

• Current Assignee: Illinois Tool Works Inc.
• Original Assignee: Illinois Tool Works Inc.
• Inventors: Lang, David A., Yanez, David A., Tarr, Nelson D., Burt, Chris S.
• Primary Examiner(s): Mehta, Bhavesh
• Assistant Examiner(s): Harandi, Siamak
• Application Number:
  US13/310,971
• Publication Number:
  US 20130142406A1
• Time in Patent Office: 1,044 Days
• Field of Search: None
• US Class Current: 382/128
• CPC Class Codes: A61J 2205/40 by shape or form, e.g. by using shape recognition
• CPC Class Codes: G06F 18/256 of results relating to different input data, e.g. multimodal recognition
• CPC Class Codes: G06V 10/811 the classifiers operating on different input data, e.g. multi-modal recognition
• CPC Class Codes: G06V 20/66 Trinkets, e.g. shirt buttons or jewellery items recognising microscopic objects G06V20/69
• CPC Class Codes: G16H 20/10 relating to drugs or medications, e.g. for ensuring correct administration to patients

Abstract

A method of processing graphical image data representing optically scanned medication-related units may include receiving image data generated responsive to disposal of the units on a tray disposed a distance from an image acquisition component, the image data including data indicative of visually observable features of the units disposed on the tray. The method further includes comparing at least two features among the visually observable features from the image data to reference data indicative of corresponding features of reference units. The reference data is selected for comparison based on an identification of the reference data as corresponding to a prescription being processed. The reference data includes data indicative of features of the reference units extracted from images captured using hardware corresponding to hardware used to generate the image data. The method further includes generating a likelihood rating for each of the at least two features based on the comparing.

Claims

1. A method of processing graphical image data representing optically scanned medication-related units comprising:

receiving image data generated responsive to disposal of the units on a tray disposed a distance from an image acquisition component, the image data including data indicative of visually observable features of the units disposed on the tray;

comparing, via processing circuitry, at least two features among the visually observable features from the image data to reference data indicative of corresponding features of reference units, the reference data being selected for comparison based on an identification of the reference data as corresponding to a prescription being processed, the reference data including data indicative of features of the reference units extracted from images captured using hardware corresponding to hardware used to generate the image data such that the images are captured using substantially the same camera disposed the same distance from reference units in the reference data as the units on the tray; and

generating a likelihood rating for each of the at least two features based on the comparing,

wherein generating the likelihood rating comprises generating a score indicative of a degree of matching between features of the image data and corresponding features of the reference data, the score being comparable to at least two thresholds to determine at least three classifications of likelihood ratings for the corresponding features based on comparing the score to the at least two thresholds, and wherein the at least three classifications comprising at least one classification for which an automated response is provided and at least one classification for which operator intervention is solicited, and

wherein generating the likelihood rating comprises generating the likelihood rating in association with a counting operation in which the units are counted, and wherein both the counting operation and generating the likelihood rating are accomplished prior to the units being removed from the tray.

2. The method of claim 1, wherein receiving the image data comprises receiving the image data prior to filling a prescription bottle associated with the prescription.

3. The method of claim 2, further comprising providing an indication to an operator to authorize disposal of the units from the tray and into the prescription bottle based on the likelihood rating indicating that the image data corresponds to units that match the reference units.

4. The method of claim 1, further comprising providing an indication to an operator to direct operator action in response to the likelihood rating being a value relative to a threshold indicating that the image data does not correspond to units that match the reference units.

5. The method of claim 1, wherein generating the likelihood rating comprises generating a composite likelihood rating based on independently determined likelihood ratings for each of a plurality of features.

6. The method of claim 5, wherein the plurality of features include at least color, size, shape and surface markings.

7. The method of claim 1, wherein the reference data is stored locally at a device performing the comparing or remotely at a device other than the device performing the comparing.

8. A machine-vision based prescription verification device for medication-related units comprising:

a tray disposed on a base unit to receive the units;

an image acquisition component disposed a distance from the tray, the image acquisition component configured to generate image data responsive to disposal of the units on the tray, the image data including data indicative of visually observable features of the units disposed on the tray;

an image processor comprising processing circuitry configured to;

compare at least two features among the visually observable features from the image data to reference data indicative of corresponding features of reference units, the reference data being selected for comparison based on an identification of the reference data as corresponding to a prescription being processed, the reference data including data indicative of features of the reference units extracted from images captured using hardware corresponding to hardware used to generate the image data such that the images are captured using substantially the same camera disposed the same distance from reference units in the reference data as the units on the tray; and

generate a likelihood rating for each of the at least two features based on the comparison,

wherein generating the likelihood rating comprises generating a score indicative of a degree of matching between features of the image data and corresponding features of the reference data, the score being comparable to at least two thresholds to determine at least three classifications of likelihood ratings for the corresponding features based on comparing the score to the at least two thresholds, and wherein the at least three classifications comprising at least one classification for which an automated response is provided and at least one classification for which operator intervention is solicited, and

wherein the processing circuitry being configured to generate the likelihood rating comprises the processing circuitry being configured to generate the likelihood rating in association with a counting operation in which the units are counted, and wherein both the counting operation and generating the likelihood rating are accomplished prior to the units being removed from the tray.

9. The device of claim 8, wherein the processing circuitry being configured to receive the image data comprises the processing circuitry being configured to receive the image data prior to filling a prescription bottle associated with the prescription.

10. The device of claim 9, wherein the processing circuitry is further configured to provide an indication to an operator to authorize disposal of the units from the tray and into the prescription bottle based on the likelihood rating indicating that the image data corresponds to units that match the reference units.

11. The device of claim 8, wherein the processing circuitry is further configured to provide an indication to an operator to direct operator action in response to the likelihood rating being a value relative to a threshold indicating that the image data does not correspond to units that match the reference units.

12. The device of claim 8, wherein the processing circuitry being configured to generate the likelihood rating comprises the processing circuitry being configured to generate a composite likelihood rating based on independently determined likelihood ratings for each of a plurality of features.

13. The device of claim 12, wherein the plurality of features include at least color, size, shape and surface markings.

14. The device of claim 8, wherein the reference data is stored locally at a device performing the comparing or remotely at a device other than the device performing the comparing.

15. A computer program product for processing graphical image data representing optically scanned medication-related units, the computer program product comprising at least one non-transitory computer-readable storage medium having computer-executable program code instructions stored therein, the computer-executable program code instructions comprising program code instructions for:

receiving image data generated responsive to disposal of the units on a tray disposed a distance from an image acquisition component, the image data including data indicative of visually observable features of the units disposed on the tray;

comparing, via processing circuitry, at least two features among the visually observable features from the image data to reference data indicative of corresponding features of reference units, the reference data being selected for comparison based on an identification of the reference data as corresponding to a prescription being processed, the reference data including data indicative of features of the reference units extracted from images captured using hardware corresponding to hardware used to generate the image data such that the images are captured using substantially the same camera disposed the same distance from reference units in the reference data as the units on the tray; and

generating a likelihood rating for each of the at least two features based on the comparing,

wherein generating the likelihood rating comprises generating a score indicative of a degree of matching between features of the image data and corresponding features of the reference data, the score being comparable to at least two thresholds to determine at least three classifications of likelihood ratings for the corresponding features based on comparing the score to the at least two thresholds, and wherein the at least three classifications comprising at least one classification for which an automated response is provided and at least one classification for which operator intervention is solicited, and

wherein the processing circuitry being configured to generate the likelihood rating comprises the processing circuitry being configured to generate the likelihood rating in association with a counting operation in which the units are counted, and wherein both the counting operation and generating the likelihood rating are accomplished prior to the units being removed from the tray.

16. The computer program product of claim 15, further comprising computer program code for storing the annotated image in a memory to enable future retrieval of the annotated image.