Search

US-12620094-B2 - Image processing apparatus, image processing method, and image processing program

US12620094B2US 12620094 B2US12620094 B2US 12620094B2US-12620094-B2

Abstract

A processor is configured to extract a tubular tissue region from a medical image including a tubular tissue, extract a lesion region in a periphery of the tubular tissue region from the medical image, and correct an extraction result of the tubular tissue region, as necessary, based on positional information of the lesion region.

Inventors

  • Aya Ogasawara

Assignees

  • FUJIFILM CORPORATION

Dates

Publication Date
20260505
Application Date
20231130
Priority Date
20210625

Claims (17)

  1. 1 . An image processing apparatus comprising: at least one processor, wherein the processor is configured to: extract a tubular tissue region from a medical image including a tubular tissue; extract a lesion region in a periphery of the tubular tissue region from the medical image; and correct an extraction result of the tubular tissue region, as necessary, based on positional information of the lesion region.
  2. 2 . The image processing apparatus according to claim 1 , wherein the processor is configured to: specify separated parts in the tubular tissue region; determine whether or not to connect the separated parts of the tubular tissue region based on the positional information of the lesion region; and correct the extraction result of the tubular tissue region such that the separated parts in the tubular tissue region are connected, in a case in which it is determined that the separated parts are to be connected.
  3. 3 . The image processing apparatus according to claim 2 , wherein the processor is configured to determine whether or not the lesion region is present in the separated parts based on the positional information of the lesion region, and determine to connect the separated parts in a case in which it is determined that the lesion region is absent in the separated parts.
  4. 4 . The image processing apparatus according to claim 1 , wherein the processor is configured to function as a trained model that outputs the medical image in which the extraction result of the tubular tissue region is corrected, as necessary, in a case in which the medical image, the tubular tissue region, and the positional information of the lesion region are input.
  5. 5 . The image processing apparatus according to claim 1 , wherein the processor is configured to display the medical image such that whether the tubular tissue region has been corrected or not is distinguishable.
  6. 6 . The image processing apparatus according to claim 2 , wherein the processor is configured to display the medical image such that whether the tubular tissue region has been corrected or not is distinguishable.
  7. 7 . The image processing apparatus according to claim 3 , wherein the processor is configured to display the medical image such that whether the tubular tissue region has been corrected or not is distinguishable.
  8. 8 . The image processing apparatus according to claim 4 , wherein the processor is configured to display the medical image such that whether the tubular tissue region has been corrected or not is distinguishable.
  9. 9 . The image processing apparatus according to claim 5 , wherein the processor is configured to display the medical image such that a corrected part in the tubular tissue region is distinguishable in a case in which the extraction result of the tubular tissue region has been corrected.
  10. 10 . The image processing apparatus according to claim 6 , wherein the processor is configured to display the medical image such that a corrected part in the tubular tissue region is distinguishable in a case in which the extraction result of the tubular tissue region has been corrected.
  11. 11 . The image processing apparatus according to claim 7 , wherein the processor is configured to display the medical image such that a corrected part in the tubular tissue region is distinguishable in a case in which the extraction result of the tubular tissue region has been corrected.
  12. 12 . The image processing apparatus according to claim 8 , wherein the processor is configured to display the medical image such that a corrected part in the tubular tissue region is distinguishable in a case in which the extraction result of the tubular tissue region has been corrected.
  13. 13 . The image processing apparatus according to claim 5 , wherein the processor is configured to correct a route of the tubular tissue region in response to an instruction to correct the route of the tubular tissue region for the medical image.
  14. 14 . The image processing apparatus according to claim 9 , wherein the processor is configured to correct a route of the tubular tissue region in response to an instruction to correct the route of the tubular tissue region for the medical image.
  15. 15 . The image processing apparatus according to claim 1 , wherein the tubular tissue is a main pancreatic duct, and the lesion region is a lesion region in a pancreas.
  16. 16 . An image processing method comprising: extracting a tubular tissue region from a medical image including a tubular tissue; extracting a lesion region in a periphery of the tubular tissue region from the medical image; and correcting an extraction result of the tubular tissue region, as necessary, based on positional information of the lesion region.
  17. 17 . A non-transitory computer-readable storage medium that stores an image processing program causing a computer to execute: a procedure of extracting a tubular tissue region from a medical image including a tubular tissue; a procedure of extracting a lesion region in a periphery of the tubular tissue region from the medical image; and a procedure of correcting an extraction result of the tubular tissue region, as necessary, based on positional information of the lesion region.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS This application is a continuation of International Application No. PCT/JP2022/018958, filed on Apr. 26, 2022, which claims priority from Japanese Patent Application No. 2021-105654, filed on Jun. 25, 2021. The entire disclosure of each of the above applications is incorporated herein by reference. BACKGROUND Technical Field The present disclosure relates to an image processing apparatus, an image processing method, and an image processing program. Related Art In recent years, tubular tissues such as a large intestine, a small intestine, a bronchus, and blood vessels of a patient have been extracted from a three-dimensional image captured by a computed tomography (CT) apparatus, a magnetic resonance imaging (MRI) apparatus, or the like, and three-dimensional images of the extracted tubular tissues have been used for image diagnosis. However, in a case in which fat, plaque, or the like adheres to the tubular tissue and the tubular tissue is blocked, the tubular tissue may be separated and extracted from the three-dimensional image. Therefore, a method of specifying separated parts of the tubular tissue extracted from the three-dimensional image, specifying routes of the separated tubular tissue, and interpolating and displaying the specified route in a case of displaying the three-dimensional image has been proposed (for example, refer to JP2014-064824A and JP2014-054359A). However, in the method disclosed in JP2014-064824A and JP2014-054359A, since the tubular tissue in which the separated parts are interpolated is displayed, even in a case in which the tubular tissue is actually separated due to the presence of a lesion, the tubular tissue is interpolated and displayed. Therefore, in the method disclosed in JP2014-064824A and JP2014-054359A, there is a problem that it is difficult to discern whether the extracted tubular tissue is actually separated. SUMMARY OF THE INVENTION The present disclosure has been made in view of the above circumstances, and an object of the present disclosure is to improve the extraction accuracy of the tubular tissue in consideration of whether or not the tubular tissue is actually separated. The present disclosure relates to an image processing apparatus comprising at least one processor, in which the processor is configured to:extract a tubular tissue region from a medical image including a tubular tissue;extract a lesion region in a periphery of the tubular tissue region from the medical image; andcorrect an extraction result of the tubular tissue region, as necessary, based on positional information of the lesion region. It should be noted that, in the image processing apparatus according to the present disclosure, the processor may be configured to: specify separated parts in the tubular tissue region; determine whether or not to connect the separated parts of the tubular tissue region based on the positional information of the lesion region; and correct the extraction result of the tubular tissue region such that the separated parts in the tubular tissue region are connected, in a case in which it is determined that the separated parts are to be connected. In addition, in the image processing apparatus according to the present disclosure, the processor may be configured to determine whether or not the lesion region is present in the separated parts based on the positional information of the lesion region, and determine to connect the separated parts in a case in which it is determined that the lesion region is absent in the separated parts. In addition, in the image processing apparatus according to the present disclosure, the processor may be configured to function as a trained model that outputs the medical image in which the extraction result of the tubular tissue region is corrected, as necessary, in a case in which the medical image, the tubular tissue region, and the positional information of the lesion region are input. In addition, in the image processing apparatus according to the present disclosure, the processor may be configured to display the medical image such that whether the tubular tissue region has been corrected or not is distinguishable. In addition, in the image processing apparatus according to the present disclosure, the processor may be configured to display the medical image such that a corrected part in the tubular tissue region is distinguishable in a case in which the extraction result of the tubular tissue region has been corrected. In addition, in the image processing apparatus according to the present disclosure, the processor may be configured to correct a route of the tubular tissue region in response to an instruction to correct the route of the tubular tissue region for the medical image. In addition, in the image processing apparatus according to the present disclosure, the tubular tissue may be a main pancreatic duct, and the lesion region may be a lesion region in a pancreas. The present disclos