Medical data processing apparatus and method

• US 9,779,505 B2
• Filed: 09/30/2014
• Issued: 10/03/2017
• Est. Priority Date: 09/30/2014
• Status: Active Grant

• Current Assignee: Toshiba Medical Systems Corporation (Canon Inc.)
• Original Assignee: Toshiba Medical Systems Corporation (Canon Inc.)
• Inventors: Koktava, Rachel Louise, Norman, Paul
• Primary Examiner(s): TSAI, TSUNG YIN
• Application Number:
  US14/501,486
• Publication Number:
  US 20160092748A1
• Time in Patent Office: 1,099 Days
• Field of Search: None
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06V 10/75 Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
• CPC Class Codes: G06V 2201/03 Recognition of patterns in medical or anatomical images
• CPC Class Codes: G16H 30/20 for handling medical images, e.g. DICOM, HL7 or PACS

Abstract

A medical image processing apparatus comprises a structure identification unit configured to automatically identify at least one anatomical structure of a medical image data set, and a metadata unit configured to validate or populate metadata associated with the medical image data set based on the identified at least one anatomical structure.

Claims

1. A medical image data processing apparatus configured to process a medical image data set and metadata associated with the medical image data set, the apparatus comprising:

processing circuitry configured to

automatically identify at least one anatomical structure of the medical image data set, wherein the medical image data set includes volumetric or two-dimensional image data obtained from a scanner and the automatic identifying of the at least one anatomical structure includes processing the volumetric or two-dimensional image data to identify the at least one anatomical structure; and

receive the metadata associated with the medical image data set, identify at least one anatomical structure or region from the metadata, and validate the metadata associated with the medical image data set based on the identified at least one anatomical structure by comparing the at least one anatomical structure identified from the metadata with the at least one anatomical structure identified by processing the volumetric or two-dimensional image data,

wherein the processing circuitry is further configured to at least one of generate an error code, raise an exception, and provide a warning signal when it is determined from the comparing that the anatomical structure or region identified from the metadata is not consistent with the anatomical structure identified by processing the volumetric or two-dimensional image data.

2. The apparatus according to claim 1, wherein at least one anatomical structure or region is identifiable from the metadata, and the processing circuitry is further configured to determine whether the at least one identified anatomical structure of the medical image data set is consistent with the at least one anatomical structure or region identified from the metadata of the medical image data set.

3. The apparatus according to claim 2, wherein the processing circuitry is further configured to determine whether the at least one identified anatomical structure of the medical image data set is consistent with the at least one anatomical structure or region identified from the metadata of the medical image data set by

determining whether the at least one identified anatomical structure of the medical image data set and the at least one anatomical structure or region identified from the metadata are expected to be present in substantially a same region of a human or animal body.

4. The apparatus according to claim 2, wherein the processing circuitry is further configured to determine whether the at least one identified anatomical structure of the medical image data set is consistent with the at least one anatomical structure or region identified from the metadata with reference to anatomical ontology data.

5. The apparatus according to claim 1, wherein the processing circuitry is further configured to determine at least one property of a human or animal subject of the medical image data set from the at least one identified anatomical structure, and determine whether the determined at least one property is consistent with at least one property represented by the metadata.

6. The apparatus according to claim 5, wherein the determined at least one property comprises at least one of age, sex, and presence of a medical condition.

7. The apparatus according to claim 1, wherein the processing circuitry is further configured to determine at least one property of the medical image data set, or of a scan used to produce the medical image data set, from the at least one identified anatomical structure, and the processing circuitry is further configured to determine whether the determined at least one property is consistent with at least one property represented by the metadata.

8. The apparatus according to claim 7, wherein the at least one property of the medical image data set, or of the scan used to produce the medical image data set, comprises orientation of a human or animal body that is the subject of the medical image data set, zoom or magnification level, or size of a scan area or volume.

9. The apparatus according to claim 1, wherein the processing circuitry is further configured to obtain a registration of the medical image data set and a further data set that includes or is associated with at least one anatomical identifier.

10. The apparatus according to claim 9, wherein the at least one anatomical identifier comprises at least one anatomical landmark.

11. The apparatus according to claim 10, wherein the processing circuitry is further configured to identify at least one anatomical landmark in the medical image data set, and register the identified at least one anatomical landmark of the medical image data set and the at least one anatomical landmark of the further data set.

12. The apparatus according to claim 9, wherein the further data set comprises a virtual anatomy data set.

13. The apparatus according to claim 9, wherein the processing circuitry is further configured to determine from the registration a region of the further data set that corresponds to an area or volume represented by the medical image data set, and

to perform the automatic identifying of at least one anatomical structure by determining, from the at least one anatomical identifier of the further data set, at least one anatomical structure that falls within the determined region of the further data set.

14. The apparatus according to claim 13, wherein the area or volume of the medical image data set comprises an area or volume bounded by an outer boundary of the medical image data set.

15. The apparatus according to claim 13, wherein the anatomical identifiers comprise or are associated with bounding boxes or other position data, each representing a position of a respective anatomical structure or region, and

the processing circuitry is configured to determine from the anatomical identifiers of the further data set at least one anatomical structure that falls within the determined region of the further data set by determining whether at least one of the bounding boxes or other position data falls within or overlaps the determined region of the further data set.

16. The apparatus according to claim 1, wherein the processing circuitry is further configured to determine whether or not the metadata is consistent with the identified at least one anatomical structure or with at least one property determined from the identified at least one anatomical structure.

17. The apparatus according to claim 16, wherein the processing circuitry is further configured to generate the error code or raise the exception when it is determined that the metadata is not consistent with the identified at least one anatomical structure or with at least one property determined from the identified at least one anatomical structure.

18. The apparatus according to claim 16, wherein the processing circuitry is further configured to provide the warning signal when it is determined that the metadata is not consistent with the identified at least one anatomical structure or with at least one property determined from the identified at least one anatomical structure.

19. The apparatus according to claim 1, wherein the processing circuitry is further configured to populate the metadata associated with the medical image data set by entering or overwriting data in respect of at least one metadata item.

20. The apparatus according to claim 19, wherein the data comprises an anatomical identifier, or at least one property of a human or animal subject or of the medical image data set determined from the identified at least one anatomical structure.

21. The apparatus according to claim 1, wherein the metadata comprises at least one DICOM data element.

22. The apparatus according to claim 21, wherein the at least one DICOM data element comprises at least one of Body Part Examined (0008, 0015), Anatomic Structure (0008, 2208), and Anatomic Region Sequence (0008, 2218).

23. The apparatus according to claim 1, which comprises or forms part of a Picture Archiving and Communication System (PACS) or Report System.

24. A medical image data processing method to process a medical image data set and metadata associated with the medical image data set, comprising:

automatically identifying at least one anatomical structure of the medical image data set, wherein the medical image data set includes volumetric or two-dimensional image data obtained from a scanner and the automatic identifying of the at least one anatomical structure includes processing the volumetric or two-dimensional image data to identify the at least one anatomical structure; and

receiving the metadata associated with the medical image data set;

identifying at least one anatomical structure or region from the metadata; and

validating the metadata associated with the medical image data set based on the identified at least one anatomical structure by comparing the at least one anatomical structure identified from the metadata with the at least one anatomical structure identified by processing the volumetric or two-dimensional image data,

wherein the method further includes at least one of generating an error code, raising an exception, and providing a warning signal when it is determined from the comparing that the anatomical structure or region identified from the metadata is not consistent with the anatomical structure identified by processing the volumetric or two-dimensional image data.

25. A non-transitory computer-readable storage medium storing a computer program comprising computer-readable instructions that are executable to perform a method to process a medical image data set and metadata associated with the medical image data set, comprising:

automatically identifying at least one anatomical structure of the medical image data set, wherein the medical image data set includes volumetric or two-dimensional image data obtained from a scanner and the automatic identifying of the at least one anatomical structure includes processing the volumetric or two-dimensional image data to identify the at least one anatomical structure; and

receiving the metadata associated with the medical image data set;

identifying at least one anatomical structure or region from the metadata; and

validating the metadata associated with the medical image data set based on the identified at least one anatomical structure by comparing the at least one anatomical structure identified from the metadata with the at least one anatomical structure identified by processing the volumetric or two-dimensional image data,

wherein the method further includes at least one of generating an error code, raising an exception, and providing a warning signal when it is determined from the comparing that the anatomical structure or region identified from the metadata is not consistent with the anatomical structure identified by processing the volumetric or two-dimensional image data.