Image processing device, method of operating the image processing device, and program

Abstract

To provide an image processing device, a method for operating the image processing device, and a program, in which a plurality of images acquired at different times can be preferably compared.SOLUTION: An image processing device (16): receives (30) a plurality of first images generated by imaging a subject and to each of which a plurality of various first imaging conditions are applied; designates (32) a first area of interest in the plurality of first images; acquires (36) measurement information related to a second image having a second area of interest corresponding to the first area of interest in the plurality of second images generated by imaging the subject prior to the imaging of the first image; specifies (38) the first image contained in a range of measurement information from the plurality of first images; and measures (40) the first area of interest specified in the first image.SELECTED DRAWING: Figure 4

Description

Technical Field

[0001] The present invention relates to an image processing apparatus, an operation method for an image processing apparatus, and a program.

Background Art

[0002] Generally, when follow-up observation is performed on the progression and healing status of a lesion existing in a patient's body, after a certain period of time has elapsed since an image of the lesion was acquired, an image of the lesion is acquired again, and comparative interpretation is performed on the two images acquired at different timings. ru2 Comparative interpretation is performed on the two images acquired at different timings.

[0003] Patent Document 1 describes an image processing method in which corresponding regions of interest are obtained from two or more images to be compared of the same subject, and the same image processing is performed on both regions of interest. corresponding regions of interest are obtained from two or more images to be compared of the same subject, and the same image processing is performed on both regions of interest.

[0004] The image processing method described in this document enables accurate comparative interpretation of regions of interest in a plurality of images to be compared, and improves the interpretation performance of regions of interest that are in a correspondence relationship with each other. enables accurate comparative interpretation of regions of interest in a plurality of images to be compared, and improves the interpretation performance of regions of interest that are in a correspondence relationship with each other.

Prior Art Document

Patent Document

[0005]

Patent Document 1

Summary of the Invention

Problem to be Solved by the Invention

[0006] For example, when performing comparative interpretation of tumors, comparison of tumor sizes is the most important. To accurately compare the sizes of two tumors to be compared, it is necessary to apply the same conditions as or conditions close to those of the image used in the past examination to measure the tumor in the current examination. However, it takes time and effort to determine the conditions for the image used in the current examination according to the conditions of the image used in the past examination.

[0007] The method described in Patent Document 1 does not solve the above-mentioned problem because, when the conditions of the images used in past examinations and the images used in the current examination are not the same, it is difficult to compare and interpret the images used in past examinations and the images used in the current examination.

[0008] This invention has been made in view of these circumstances, and aims to provide an image processing device, a method for operating the image processing device, and a program that enable favorable comparison of multiple images acquired at different times. [Means for solving the problem]

[0009] An image processing apparatus according to a first aspect of the present disclosure comprises one or more processors and one or more memories that store instructions to be executed by the one or more processors, wherein the one or more processors receive a plurality of first images which are generated by photographing a subject and to which each of a plurality of different first image conditions is applied, specify a first region of interest in the plurality of first images, acquire measurement information for a plurality of second images which are generated by photographing a subject before the first images are taken and which have a second region of interest corresponding to the first region of interest, identify a first image which is included in the range of the measurement information from the plurality of first images, and measure the first region of interest in the identified first image.

[0010] According to the image processing apparatus of the first aspect of this disclosure, based on measurement information of a second image having a second region of interest corresponding to a first region of interest specified in a first image, the first image included in the range of the measurement information is identified, and the first region of interest in the identified first image is measured. This enables an accurate comparison between the measurement result of the first region of interest in the first image and the measurement result of the second region of interest in the second image.

[0011] In the image processing apparatus according to the second embodiment, one or more processors may identify a first image having the first image conditions that maximize the similarity index representing the similarity with the second image conditions of the second image, as a first image included in the range of measurement information.

[0012] According to this embodiment, even if there is no first image having the same first image conditions as the second image conditions, it is possible to identify a first image that enables an accurate comparison of measurement results with those of the second image.

[0013] The image processing apparatus according to the third embodiment is an image processing apparatus according to the second embodiment in which one or more processors may derive a similar index using at least one of the reconstruction conditions, the slice thickness representing the thickness of the tomography in the tomographic image, the spatial resolution, and the imaging protocol.

[0014] According to this embodiment, a first image having first image conditions close to second image conditions can be identified based on at least one of the reconstruction conditions, slice thickness, spatial resolution, and imaging protocol.

[0015] The image processing apparatus according to the fourth embodiment is an image processing apparatus according to any one embodiment of the first to third embodiments, in which one or more processors may apply, as measurement information, at least one of the second image in which the measurement of the second region of interest is performed and the measurement results of the second region of interest.

[0016] According to this embodiment, based on at least one of the second image and the measurement results of the second region of interest, the first image for which an accurate comparison with the measurement results of the second region of interest is achieved can be identified.

[0017] In the image processing apparatus according to the fifth embodiment, in an image processing apparatus according to any one embodiment of the first to fourth embodiments, one or more processors may estimate the error in the measurement result of the first region of interest with respect to the measurement result of the second region of interest, based on the first image condition and the second image condition.

[0018] According to this aspect, in the measurement of the first region of interest in the first image having the first imaging condition close to the second imaging condition, an error in the measurement result caused by the difference between the first imaging condition and the second imaging condition can be grasped.

[0019] The image processing apparatus according to the sixth aspect is the image processing apparatus according to the fifth aspect, wherein the one or more processors may output an alert when the estimated error exceeds a prescribed range.

[0020] According to this aspect, re-measurement of the first region of interest in the first image and reconsideration of re-specifying the first image can be considered.

[0021] The image processing apparatus according to the seventh aspect is the image processing apparatus according to the fifth aspect or the sixth aspect, wherein the one or more processors may cause a display device to display an error range defined in accordance with the tendency of the estimated error.

[0022] According to this aspect, the user can grasp the error range of the measurement of the first region of interest in the first image.

[0023] The image processing apparatus according to the eighth aspect is the image processing apparatus according to any one of the first aspect to the seventh aspect, wherein the one or more processors may set the first display condition applied to the measurement of the first region of interest in the first image in accordance with the second display condition applied to the measurement of the second region of interest in the second image.

[0024] According to this aspect, when measuring the first region of interest, the first region of interest and the second region of interest to be compared can be displayed by applying the same display mode.

[0025] The image processing apparatus according to the ninth aspect is the image processing apparatus according to the eighth aspect, wherein the one or more processors may set at least any one of brightness, window level, and window width as the first display condition.

[0026] According to this aspect, the first region of interest and the second region of interest in which at least one of brightness, window level and window width has been adjusted can be displayed.

[0027] An image processing apparatus according to a tenth aspect is the image processing apparatus according to any one of the first to ninth aspects, wherein when one or more processors acquire an input for selecting a first region of interest in a first image, the one or more processors may cause a display device to display at least one of the first region of interest and a measurement result of the first region of interest.

[0028] In this aspect, an input for selecting the first region of interest in the first image in accordance with a user operation may be acquired.

[0029] An image processing apparatus according to an eleventh aspect is the image processing apparatus according to any one of the first to ninth aspects, wherein when one or more processors acquire an input for selecting a first region of interest in a first image, the one or more processors may cause a display device to display at least one of the first region of interest and a measurement result of the first region of interest, and cause the display device to display measurement information.

[0030] According to this aspect, it can contribute to improving user convenience.

[0031] In this aspect, an input for selecting the first region of interest in the first image in accordance with a user operation may be acquired.

[0032] An image processing apparatus according to a twelfth aspect is the image processing apparatus according to the eleventh aspect, wherein one or more processors may apply different display modes to at least one of the first region of interest and a measurement result of the first region of interest, and the measurement information.

[0033] According to this aspect, information belonging to the first image and information belonging to the second image can be easily distinguished.

[0034] In this aspect, an input for selecting the first region of interest in the first image in accordance with a user operation may be acquired.

[0035] In the image processing apparatus according to the 13th embodiment, in the image processing apparatus according to the 11th embodiment, when one or more processors acquire an input for selecting a first region of interest in the first image, they may cause at least one of the measurement results of the second image and the second region of interest to be displayed on the display device as measurement information.

[0036] In this embodiment, an input may be obtained to select a first region of interest in the first image in response to user operation.

[0037] The image processing apparatus according to the 14th embodiment is an image processing apparatus according to any one embodiment from the 1st to the 13th embodiment, in which one or more processors receive a plurality of first medical images generated by photographing a subject as a plurality of first images, specify the anatomical structure of the subject in the plurality of first medical images as a first region of interest, and acquire measurement information obtained by measuring the anatomical structure of the subject, which is the second region of interest corresponding to the first region of interest, for a plurality of second medical images generated by photographing the subject as measurement information.

[0038] According to this embodiment, it is possible to accurately compare the measurement results of the first region of interest in the first medical image with the measurement results of the second region of interest in the second medical image.

[0039] The image processing apparatus according to the 15th embodiment is an image processing apparatus according to the 14th embodiment in which one or more processors may cause the measurement results of anatomical structures to be displayed on a display device as measurement results of the first region of interest in the first image.

[0040] According to this embodiment, accurate comparisons can be made between the measurement results of the first and second regions of interest to which the anatomical structures are applied.

[0041] A method for operating an image processing apparatus according to a 16th aspect of the present disclosure is a method for operating an image processing apparatus comprising one or more processors and one or more memories storing programs to be executed by the one or more processors, wherein the one or more processors receive a plurality of first images which are generated by photographing a subject and to which each of a plurality of different first image conditions is applied, specify a first region of interest in the plurality of first images, acquire measurement information for a plurality of second images which are generated by photographing a subject before the first images are taken and which have a second region of interest corresponding to the first region of interest, identify a first image which is included in the range of the measurement information from the plurality of first images, and measure the first region of interest in the identified first image.

[0042] According to the operating method of the image processing apparatus according to the 16th aspect of this disclosure, it is possible to obtain the same effects and advantages as the image processing apparatus according to the first aspect of this disclosure.

[0043] In the operating method of the image processing device according to the 16th embodiment, the same matters as those specified in the 2nd to 15th embodiments can be appropriately combined. In that case, the components responsible for the processing or functions specified in the image processing device can be understood as components of the operating method of the image processing device that are responsible for the corresponding processing or functions.

[0044] A program according to the 17th aspect of this disclosure is a program that enables a computer to have the following functions: a function to receive a plurality of first images which are generated by photographing a subject and to which a plurality of different first image conditions are applied; a function to specify a first region of interest in the plurality of first images; a function to acquire measurement information for a plurality of second images which are generated by photographing a subject before the first image is taken and which have a second region of interest corresponding to the first region of interest; a function to identify a first image which is included in the range of measurement information from the plurality of first images; and a function to measure the first region of interest in the identified first image.

[0045] According to the program relating to the 17th aspect of this disclosure, it is possible to obtain the same effects as those of the image processing apparatus relating to the first aspect of this disclosure.

[0046] In the program relating to the 17th aspect, the same matters as those specified in the 2nd to 15th aspects can be appropriately combined. In that case, the components responsible for the processing and functions specified in the image processing device can be understood as components of the program responsible for the corresponding processing and functions. [Effects of the Invention]

[0047] According to the present invention, based on measurement information of a second image having a second region of interest corresponding to a first region of interest specified in the first image, the first image included in the range of the measurement information is identified, and the first region of interest in the identified first image is measured. This enables accurate comparison between the measurement result of the first region of interest in the first image and the measurement result of the second region of interest in the second image. [Brief explanation of the drawing]

[0048] [Figure 1] Figure 1 is an overall diagram of the medical image processing system. [Figure 2] Figure 2 is a schematic diagram of an image processing method according to an embodiment. [Figure 3] Figure 3 is a schematic diagram showing the procedure of the image processing method according to the first embodiment. [Figure 4] Figure 4 is a functional block diagram showing the electrical configuration of the image processing apparatus according to the first embodiment. [Figure 5] Figure 5 is a schematic block diagram showing an example of the hardware configuration of the image processing device according to the first embodiment. [Figure 6] Figure 6 is a table showing the priority order assigned to image conditions. [Figure 7] Figure 7 is a table showing the points assigned to the image conditions. [Figure 8] Figure 8 is a schematic diagram showing an example of a user interface configuration. [Figure 9]Figure 9 is a schematic diagram showing the procedure of the image processing method according to the second embodiment. [Figure 10] Figure 10 is a functional block diagram showing the electrical configuration of the image processing apparatus according to the second embodiment. [Figure 11] Figure 11 is a schematic block diagram showing an example of the hardware configuration of the image processing device according to the second embodiment. [Figure 12] Figure 12 is a schematic diagram showing the procedure of the image processing method according to the third embodiment. [Figure 13] Figure 13 is a functional block diagram showing the electrical configuration of the image processing apparatus according to the third embodiment. [Figure 14] Figure 14 is a schematic block diagram showing an example of the hardware configuration of an image processing system according to the third embodiment. [Modes for carrying out the invention]

[0049] Preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings. In this specification, identical components are denoted by the same reference numerals, and redundant descriptions are omitted where appropriate.

[0050] [Example configuration of a medical image processing system] Figure 1 is an overall diagram of the medical image processing system. The medical image processing system 10 shown in the figure captures images of the subject being examined and performs image processing on the captured images to support medical image diagnosis. It is a system that automatically performs image processing on medical images. The subject being examined may also be referred to as a test subject or similar.

[0051] The medical image processing system 10 shown in Figure 1 comprises a medical imaging device 12, a medical image database 14, an image processing device 16, a user terminal 20, and a cloud server 26. The medical imaging device 12, the medical image database 14, the image processing device 16, and the user terminal 20 are installed within a medical institution such as a hospital and are connected to each other via a hospital network 22 to enable data transmission and reception. The hospital network 22 can be a LAN (Local Area Network). The hospital network 22 may be wired or wireless.

[0052] The hospital network 22 is connected to the internet 24 via a router (not shown). The hospital network 22 and the cloud server 26 are each connected to the internet 24 so as to be able to send and receive data from each other.

[0053] Medical imaging equipment 12 is an imaging device that photographs the area of ​​a subject to be examined and generates a medical image. Examples of medical imaging equipment 12 include X-ray imaging devices, CT scanners, MRI scanners, PET scanners, ultrasound scanners, and CR scanners using a flat X-ray detector.

[0054] Note that CT is an abbreviation for Computed Tomography. MRI is an abbreviation for Magnetic Resonance Imaging. PET is an abbreviation for Positron Emission Tomography. CR is an abbreviation for Computed Radiography.

[0055] The medical image database 14 is a database for managing medical images taken using medical imaging equipment 12. The medical image database 14 can be implemented using a computer equipped with a large-capacity storage device. The computer incorporates software that provides the functionality of a database management system.

[0056] The medical image database 14 may be configured as part of an image archiving and communication system that stores and manages medical images. The image archiving and communication system is referred to as PACS, an abbreviation for Picture Archiving and Communication Systems.

[0057] The format of medical images can be the DICOM standard. Medical images may have DICOM tag information defined in the DICOM standard attached to them. In this specification, the term "image" may include not only the image itself, such as a photograph, but also the image data, which is the signal representing the image. DICOM is an abbreviation for Digital imaging and communications in medicine.

[0058] The image processing device 16 performs prescribed image processing on medical images generated by photographing a subject using the medical imaging equipment 12 and on medical images stored in the medical image database 14. The image processing device 16 is a computer. The computer may be a personal computer, a workstation, or a tablet terminal. The computer may also be a virtual machine.

[0059] The user terminal 20 is a terminal device used by users such as doctors, and for example, a well-known image viewer for image interpretation may be used. The user terminal 20 may be a personal computer, workstation, or tablet terminal.

[0060] The user terminal 20 includes an input device 20A and a display device 20B. The display device 20B displays medical images captured by the medical imaging equipment 12 and the results of image processing. The display device 20B also displays the results of image processing performed by the image processing device 16 and the cloud server 26. The user can input instructions to the medical image processing system 10 using the input device 20A.

[0061] The cloud server 26 can be, for example, a server computer, a personal computer, or a workstation. The cloud server 26 performs image processing on the medical images of the person being examined, including at least one of lesion extraction and disease name determination processing. The cloud server 26 can be accessed from the hospital networks 22 of multiple hospitals via the internet 24.

[0062] [Overview of the image processing method according to the embodiment] Figure 2 is a schematic diagram of the image processing method according to the embodiment. The image processing method according to the embodiment is performed in the image processing device 16 shown in Figure 1. When performing measurement of a lesion in the current image, the image processing method according to the embodiment acquires measurement information from the previous examination of the lesion specified in the current image, and based on the acquired measurement information, identifies a current image from a group of current images including multiple current images that has the same or similar image conditions as the past image used for the previous measurement.

[0063] Specifically, a group of current images CIG, including multiple current image CIs as shown in Figure 2, is acquired. The figure illustrates current image CI1, current image CI2, and current image CI3 as examples of multiple current image CIs. The group of current images CIG may be acquired from the medical imaging equipment 12 shown in Figure 1, or from the medical image database 14. Note that the image processing method described in this embodiment is just one example of how the image processing device operates.

[0064] Figure 2 illustrates a CT image, which is a two-dimensional slice image representing an axial cross-section, reconstructed from three-dimensional volume data, as an example of a medical image. The medical images shown in Figure 3 and other figures are also examples of two-dimensional slice images.

[0065] Figure 2 also illustrates the reconstruction conditions and slice thickness for multiple current image CIs. The reconstruction condition for current image CI1 is mediastinal, and the slice thickness for current image CI1 is 5 millimeters. The reconstruction condition for current image CI2 is lung field, and the slice thickness for current image CI2 is 5 millimeters. The reconstruction condition for current image CI3 is lung field, and the slice thickness for current image CI3 is 1 millimeter.

[0066] Next, for a specified lesion in any current image CI, the past image PI used for lesion measurement during the previous examination is obtained. The past image PI is obtained from the medical image database 14 shown in Figure 1. The reconstruction conditions for the past image PI shown in Figure 2 are lung field conditions, and the slice thickness of the past image PI is 1 millimeter.

[0067] Next, we identify the current image CI, which has the same image conditions as the past image PI, or has image conditions similar to those of the past image PI. In the example shown in Figure 2, current image CI3, which has the same image conditions as the past image PI, is identified.

[0068] The current image CI1 differs from the past image PI in reconstruction conditions and slice thickness. The current image CI1 has inconsistent image conditions and is a current image CI with image conditions that deviate from those of the past image PI.

[0069] The current image CI2 has the same reconstruction conditions as the past image PI, but the slice thickness is different. The current image CI has some matching image conditions, making it a current image CI with image conditions that are relatively close to those of the past image PI.

[0070] For example, when the reconstruction condition is set to mediastinal, the edges tend to be blurred and unclear, and the lesion tends to be measured as smaller. On the other hand, when the reconstruction condition is set to lung field, the edges are sharp and clear, and the lesion tends to be measured as larger.

[0071] Furthermore, when the slice thickness is 5 millimeters, the partial volume effect tends to cause the lesion to appear smaller in measurement compared to when the slice thickness is 1 millimeter. Consequently, if the measurement of the lesion is not performed using the current image CI, which is subject to the same or similar image conditions as the past image PI used for comparison, it becomes difficult to accurately compare the current lesion with the past lesion. The image processing method according to this embodiment solves the above problems and enables a favorable comparison between the measurement results of the lesion in the current image CI and the measurement results of the lesion in the past image.

[0072] [Procedure for the image processing method according to the first embodiment] Figure 3 is a schematic diagram showing the procedure of the image processing method according to the first embodiment. In the current image group receiving step S10, the image processing device 16 shown in Figure 1 receives a current image group CIG which includes multiple current image CIs with different image conditions. Figure 3 illustrates multiple current image CIs as current image CIs 11, 12, 13, and 14, which are generated by performing a series of single scans on the same patient using a CT scanner, which is a medical imaging device 12.

[0073] The image processing device 16 may receive multiple current image CIs from a medical imaging device 12 such as a CT scanner shown in Figure 3, or it may receive multiple current image CIs from a medical image database 14.

[0074] The current image CI11 shown in Figure 3 is an axial image with mediastinal reconstruction conditions and a slice thickness of 5 mm. The current image CI12 is an axial image with lung field reconstruction conditions and a slice thickness of 5 mm. The current image CI13 is an axial image with lung field reconstruction conditions and a slice thickness of 1 mm. The current image CI14 is a coronal image with mediastinal reconstruction conditions and a slice thickness of 3 mm.

[0075] In the lesion designation step S12, the image processing device 16 designates a lesion RI for any of the multiple current image CIs received in the current image group receiving step S10. For example, any current image CI can be displayed on the display device 20B of the user terminal 20, and the user can operate the input device 20A of the user terminal 20 to designate a lesion RI for any current image CI displayed on the display device 20B.

[0076] In the measurement information acquisition step S14, the image processing device 16 acquires measurement information obtained by measuring the lesion area RI in past image PI for a specified lesion area RI in any current image CI. That is, the image processing device 16 extracts medical images from the medical images stored in the medical image database 14 in which the patient information and examination information match, and from the extracted medical images, it searches for past measurement results or past images used for past measurements as past measurement information for the lesion area RI specified in any current image CI. Patient information includes patient identification information such as the patient's name. Examination information includes examination identification information such as the examination ID and information on the modality used for the examination. Note that ID is an abbreviation for Identification.

[0077] Figure 3 shows examples of past measurement information, specifically past image PI11 and the measurement result PR of past image PI11. Past measurement information may be past image PI11, the measurement result PR of past image PI11, or the measurement result PR of both past image PI11 and past image PI11.

[0078] In the current image identification step S16, the current image CI is identified that has the same image conditions as the past image PI11 acquired as past measurement information, or has image conditions similar to the past image PI11 acquired as past measurement information. That is, the image processing device 16 identifies a current image CI from among current image CI11, current image CI12, current image CI13, and current image CI14 that falls within the range of past measurement information.

[0079] The reconstruction conditions for the past image PI11 are lung field conditions, and the slice thickness is 1 millimeter. The reconstruction conditions for the current image CI13 are lung field conditions, and the slice thickness is 1 millimeter. The image conditions for the current image CI13 match those of the past image PI11. Therefore, in the current image identification step S16, the current image CI13, which has image conditions that match those of the past image PI11 used in past measurements, is identified and automatically selected.

[0080] Figure 3 illustrates reconstruction conditions and slice thickness as image conditions. Image conditions may also include pixel spacing and acquisition protocols. In other words, image conditions can be at least one of reconstruction conditions, slice thickness, pixel spacing, and acquisition protocols. Note that the slice thickness described in the embodiment is an example of a slice thickness representing the thickness of a tomography in a tomographic image, and the pixel spacing described in the embodiment is an example of spatial resolution.

[0081] In the current image measurement process S18, the image processing device 16 performs lesion RI measurement on the current image CI13 identified in the current image identification process S16. The image processing device 16 may also display the lesion RI measurement results on the display device 20B of the user terminal 20. Examples of lesion RI measurement targets include the major axis, minor axis, volume, average CT value, and average signal value of the lesion RI.

[0082] The present image CI described in the embodiment is an example of the first image and is an example of the first medical image. The past image PI described in the embodiment is an example of the second image generated by photographing the subject before the first image is taken and is an example of the second image having a second region of interest corresponding to the first region of interest. Furthermore, the past image PI described in the embodiment is an example of the second medical image.

[0083] Furthermore, the lesion region RI specified in any current image CI described in the embodiment is an example of the first region of interest. The lesion region in the past image PI described in the embodiment is an example of the second region of interest. The image conditions of the current image described in the embodiment are an example of the first image conditions. The past measurement information described in the embodiment is an example of measurement information.

[0084] [Example of electrical configuration of the image processing apparatus according to the first embodiment] Figure 4 is a functional block diagram showing the electrical configuration of the image processing apparatus according to the first embodiment. The image processing apparatus 16 shown in the figure includes a current image group receiving unit 30. The current image group receiving unit 30 executes the current image group receiving process S10 shown in Figure 3 and receives a current image group CIG containing multiple current images.

[0085] The image processing device 16 includes a lesion designation unit 32 and an input information acquisition unit 34. The lesion designation unit 32 executes a lesion designation step S12 and designates a lesion RI using any current image CI included in a plurality of current image CIs. Examples of lesions include tumors, masses, and ulcers. The lesion designation unit 32 may also designate anatomical structures such as bones, nerves, and blood vessels as regions of interest.

[0086] The input information acquisition unit 34 acquires input information for the image processing device 16. For example, the input information acquisition unit 34 may acquire user designation information for lesion area RI for any current image CI. The lesion designation unit 32 may designate a lesion area RI for any current image CI based on the user designation information for lesion area RI for any current image CI acquired via the input information acquisition unit 34.

[0087] The image processing device 16 includes a measurement information acquisition unit 36. The measurement information acquisition unit 36 ​​executes a measurement information acquisition step S14, searches the medical image database 14, and acquires past measurement information of the lesion RI specified for the current image CI from the medical image database 14. The past measurement information may be a past image PI in which the lesion RI was measured, or a past measurement result PR of the lesion RI.

[0088] The image processing device 16 includes a current image identification unit 38. The current image identification unit 38 performs the current image identification process S16 Execute Then, the measurement information acquisition unit 36 ​​identifies the image conditions of past image PI corresponding to past measurement information acquired, and identifies a current image CI that has the same image conditions as the identified past image PI, or has image conditions similar to the identified past image PI. The current image identification unit 38 identifies a current image CI that has image conditions satisfying the above from among a plurality of current image CIs acquired in the current image group receiving step S10.

[0089] The image processing device 16 includes a measurement unit 40 and a measurement condition setting unit 42. The measurement unit 40 applies the measurement conditions set using the measurement condition setting unit 42 to measure the lesion area RI of the current image CI identified by the current image identification unit 38. The measurement of the lesion area RI in the current image CI may be performed by extracting pixels included in the lesion area RI, or it may be performed based on pixels in a region specified by the user. The measurement conditions include measurement parameters for the lesion area RI, such as the major axis, minor axis, and area.

[0090] The image processing device 16 includes a measurement result output unit 44. The measurement result output unit 44 outputs the measurement results of the lesion RI of the current image CI measured using the measurement unit 40. An example of outputting the measurement results is displaying the measurement results on the display device 20B shown in Figure 1. Another example of outputting the measurement results is printing the measurement results using a printing device.

[0091] [Example of hardware configuration of the image processing device according to the first embodiment] Figure 5 is a schematic block diagram showing an example of the hardware configuration of an image processing device according to the first embodiment. The image processing device 16 includes one or more processors 52 and one or more memories 62. The image processing device 16 also includes a communication interface 56 and an input / output interface 58.

[0092] The processor 52 executes various programs stored in the memory 62 of the computer-readable medium 54 to realize various functions of the image processing device 16. The processor 52 includes a CPU (Central Processing Unit). The processor 52 may also include a GPU (Graphics Processing Unit). The processor 52 is connected to the computer-readable medium 54, the communication interface 56, and the input / output interface 58 via the bus 60.

[0093] The computer-readable medium 54 includes a memory 62 which is the main memory and a storage 64 which is the auxiliary memory. The computer-readable medium 54 may include semiconductor memory, hard disk drives, solid-state drives, etc. The computer-readable medium 54 may include any combination of multiple devices.

[0094] Furthermore, hard disk drives can be referred to as HDDs, which are abbreviations for Hard Disk Drives. Solid state drives can be referred to as SSDs, which are abbreviations for Solid State Drives.

[0095] The memory 62 of the computer-readable medium 54 stores the current image group receiving program 70, the lesion area designation program 72, the measurement information acquisition program 74, the current image identification program 76, and the measurement program 78.

[0096] The current image group receiving program 70 is applied to the current image group receiving unit 30 shown in Figure 4, and realizes the current image group receiving function. The lesion area designation program 72 is applied to the lesion area designation unit 32, and realizes the lesion area designation function. The measurement information acquisition program 74 is applied to the measurement information acquisition unit 36, and realizes the measurement information acquisition function. The current image identification program 76 is applied to the current image identification unit 38, and realizes the current image identification function. The measurement program 78 is applied to the measurement unit 40, and realizes the measurement function.

[0097] The various programs stored in the computer-readable medium 54 contain one or more instructions. The computer-readable medium 54 stores various data and various parameters, etc. The term "program" is synonymous with the term "software."

[0098] The hardware structure of processor 52 consists of various types of processors, as shown below. These types of processors include CPUs (Central Processing Units), which are general-purpose processors that execute software (programs) and act as various functional units; GPUs (Graphics Processing Units), which are processors specialized for image processing; PLDs (Programmable Logic Devices), such as FPGAs (Field Programmable Gate Arrays), which are processors whose circuit configuration can be changed after manufacturing; and dedicated electrical circuits, such as ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing.

[0099] A single processing unit may be composed of one of these various processors, or it may be composed of two or more processors of the same or different types (for example, multiple FPGAs, a combination of CPU and FPGA, or a combination of CPU and GPU). Alternatively, multiple functional units may be composed of a single processor. Examples of composing multiple functional units with a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, as is typical of computers such as client or server computers, and this processor acts as multiple functional units. Secondly, a configuration using a processor that realizes the functions of the entire system, including multiple functional units, on a single IC (Integrated Circuit) chip, as is typical of SoCs (System On Chip). Thus, various functional units are configured as hardware structures using one or more of the above-mentioned various processors.

[0100] Furthermore, the hardware structure of these various processors is, more specifically, an electrical circuit composed of circuit elements such as semiconductor devices.

[0101] Memory 62 stores instructions for the processor 52 to execute. Memory 62 includes RAM (Random Access Memory) and ROM (Read Only Memory), which are not shown. The processor 52 uses RAM as a working area and executes software using various programs and parameters, including image processing programs such as the current image group receiving program 70 stored in ROM, and also uses parameters stored in ROM to execute various processes of the image processing device 16.

[0102] The user terminal 20 shown in Figure 1 may implement various functions of the image processing device 16. That is, the user terminal 20 may be equipped with various processing units such as the current image group receiving unit 30 shown in Figure 4, and may execute various processes such as the current image group receiving process S10 shown in Figure 3. In addition, the cloud server 26 shown in Figure 1 may implement various functions of the image processing device 16.

[0103] [Specific examples of current images used for measuring lesions] Figure 6 is a table showing the priority given to image conditions. The figure illustrates reconstruction conditions, slice thickness, pixel spacing, and imaging protocol as examples of image conditions. The imaging protocol may include a distinction between contrast-enhanced and non-contrast imaging. The imaging protocol may also include dose.

[0104] In the current image identification process S16 shown in Figure 3, the number of matching image conditions is calculated for all current image CIs included in the current image group CIG. The current image CI with the highest number of matching conditions is identified as the current image CI with the closest image conditions. If there are multiple current image CIs with the same number of matching conditions, the current image CI that matches the image condition with the highest priority is identified as the current image CI with the closest image conditions.

[0105] Figure 7 is a table showing the points assigned to image conditions. Points may be defined for each image condition. In the current image identification step S16, the sum of points for matching image conditions is calculated for all current image CIs included in the current image group CIG. The current image CI with the largest number of points is identified as the current image CI with the closest image conditions. If there are multiple current image CIs with the same sum of points, the current image CI that matches the image condition with the highest priority is identified as the current image CI with the closest image conditions.

[0106] The sum of points described in the embodiment is an example of a similarity index representing the similarity with the second image condition. The image condition of the past image PI described in the embodiment is an example of the second image condition.

[0107] [Example of user interface configuration] Figure 8 is a schematic diagram showing an example of the user interface configuration. When a user clicks on the lesion RI of the current image CI displayed on the display device 20B shown in Figure 2, the screen may transition from the screen displaying the current image CI to a screen where past image PI and the measurement results from past image PI are displayed as pop-ups, and the measurement results from the current image CI are displayed as pop-ups for the current image CI.

[0108] Furthermore, as shown in Figure 8, the screen after the transition may display an enlarged view of the lesion RI, and text information representing the measurement results may be superimposed in a location near the lesion RI but not overlapping with it. In addition, the lesion RI in the past image PI and the lesion RI in the current image CI may be distinguished using color. Also, the measurement results in the past image PI and the measurement results in the current image CI may be distinguished using color.

[0109] The lesion area RI and measurement results of the past image PI may be colored the same. The lesion area RI and measurement results of the current image CI may be colored the same. The past image PI may have text information representing the past image PI and text information representing the examination date superimposed on it. The current image CI may have text information representing the current image CI and text information representing the examination date superimposed on it. In other words, the past image PI and related information and the current image CI and related information may be displayed in different ways and can be visually distinguished.

[0110] [Effects of the First Embodiment] The image processing method and image processing apparatus according to the first embodiment can obtain the following effects.

[0111] [1] When measuring the lesion RI in a specified lesion in the current image CI, past measurement information of the lesion RI to be measured is acquired, the current image CI within the range of past measurement information is identified, and the lesion RI in the identified current image CI is measured. This allows for an accurate comparison between the lesion RI in the current image CI and the lesion RI in past image PI.

[0112] [2] Current image CIs within the range of past measurement information include current image CIs with the same image conditions as past image PIs used for past measurements, and current image CIs with similar image conditions to past image PIs used for past measurements. This allows for the identification of current image CIs in which lesion RI measurements are performed, even if no current image CIs with the same image conditions as past image PIs used for past measurements exist.

[0113] [3] Image conditions similar to those of past image PI are determined based on similarity in reconstruction conditions, slice thickness, pixel spacing, and acquisition protocol. This allows for the identification of current image CI suitable for measuring lesion RI.

[0114] [4] The similarity of image conditions is determined based on a predetermined priority order. This ensures an accurate determination of the similarity of image conditions.

[0115] [Procedure for the image processing method according to the second embodiment] Figure 9 is a schematic diagram showing the procedure of the image processing method according to the second embodiment. The image processing method according to the second embodiment includes a current image group receiving step S11 instead of the current image group receiving step S10 shown in Figure 3. In addition, the image processing method according to the second embodiment adds an estimated error derivation step S20 and an estimated error output step S22 compared to the image processing method according to the first embodiment.

[0116] The current image group receiving step S11 shown in Figure 9 receives the current image group CIG, which includes current image CI21, current image CI22, and current image CI24. The lesion area designation step S12 is similar to the lesion area designation step S12 shown in Figure 3, in which a lesion area RI is designated for any current image CI included in the current image group CIG.

[0117] In the measurement information acquisition step S14, past measurement information of the specified lesion RI is acquired, similar to the measurement information acquisition step S14 shown in Figure 3. Figure 9 shows an example in which past image PI21 and past measurement results are acquired as past measurement information.

[0118] In the current image identification process S16, there is no current image CI that has the same image conditions as past image PI21, so the image conditions are close to those of past image PI21. Picture The current image CI22, which possesses the desired image conditions, is identified.

[0119] Here, although the reconstruction conditions for the past image PI21 and the current image CI22 are the same, the slice thickness is different. The measurement results of the lesion RI in the current image CI22, which has different image conditions from the past image PI21, will have an error compared to the measurement results of the lesion RI in the past image PI21. Self-deal ru.

[0120] In the estimation error derivation step S20, the estimated error between the measurement result of the lesion RI in the past image PI21 and the measurement result of the lesion RI in the current image CI22 is derived. In the estimation error derivation step S20, an estimation error database is used in which the estimated error for each combination of image conditions is stored.

[0121] The estimated error database stores the measurement error from measurements performed on the same lesion RI under different image conditions, associating it with the combination of image conditions. The estimated error database may be generated for each type of lesion. The estimated error database is illustrated in Figure 10 using the code 82.

[0122] In the estimated error output process S22, the estimated error derived in the estimated error derivation process S20 is output. Figure 9 illustrates the display of character information on a display device as an example of the output of the estimated error. The figure shows an example where the estimated error range is between -3 millimeters and +1 millimeter.

[0123] In the example shown in Figure 9, the slice thickness of the past image PI21 is 1 millimeter, while the slice thickness of the current image CI22 is 5 millimeters. Therefore, the current image CI22 tends to be measured as smaller than the past image PI21. To address this, the estimation error range is adjusted so that the negative numerical range is larger than the positive numerical range.

[0124] An alert output step may be performed in which an alert is issued if the estimation error exceeds a specified range. The alert output format may include sound, voice, and text information display. Multiple output formats may be combined, such as a combination of voice and text information. Note that the display device described in the embodiment is just one example of a display device.

[0125] [Example of electrical configuration of the image processing apparatus according to the second embodiment] Figure 10 is a functional block diagram showing the electrical configuration of the image processing apparatus according to the second embodiment. The image processing apparatus 16A shown in the figure has an estimated error derivation unit 80 and an estimated error output unit 84 added to the image processing apparatus 16 shown in Figure 4. An alert output unit 86 may also be added to the image processing apparatus 16A.

[0126] The estimation error derivation unit 80 executes the estimation error derivation process S20 shown in Figure 9, and refers to the estimation error database 82 to derive the estimation error of the measurement of the lesion RI in the current image CI, to which different image conditions from the past image PI are applied. The estimation error database 82 may be provided in the image processing device 16A or may be an external device of the image processing device 16A.

[0127] The estimated error output unit 84 executes the estimated error output process S22 and outputs the estimated error derived in the estimated error derivation unit 80. The estimated error output unit 84 may also display the estimated error on a display device.

[0128] The alert output unit 86 outputs an alert when the estimated error derived by the estimated error derivation unit 80 exceeds a specified range. The system may also include an alert output condition setting unit for setting alert output conditions for the alert output unit 86.

[0129] [Example of hardware configuration of the image processing device according to the second embodiment] Figure 11 is a schematic block diagram showing an example of the hardware configuration of an image processing device according to the second embodiment. The image processing device 16A shown in the figure includes a computer-readable medium 54A instead of the computer-readable medium 54 of the image processing device 16 shown in Figure 5. The computer-readable medium 54A includes a memory 62A instead of the memory 62 shown in Figure 5.

[0130] Memory 62A stores various programs, such as the current image group receiving program 70, which is stored in memory 62 as shown in Figure 5, and also stores the estimated error derivation program 90. Memory 62A may also store an alert output program 92.

[0131] The estimated error derivation program 90 is applied to the estimated error derivation unit 80 shown in Figure 9 to realize the estimated error derivation function. The alert output program 92 is applied to the alert output unit 86 to realize the alert output function.

[0132] [Effects of the second embodiment] The image processing method and image processing apparatus according to the second embodiment can obtain the following effects.

[0133] [1] If the past image PI and image conditions are not identical, but a current image CI with similar image conditions is identified, the estimated error for the measurement result of the current image CI is derived and output. This enables an accurate comparison of the measurement results of the current image CI and the past image PI.

[0134] [2] The estimation error is derived using an estimation error database in which the difference in measurement results obtained by applying different image conditions to the lesion area is stored and associated with the combination of image conditions. This ensures the derivation of a highly reliable estimation error.

[0135] [3] If the estimation error exceeds a specified range, an alert is issued to that effect. This allows the user to understand when it is difficult to accurately compare the measurement results of the current image CI with those of past image PI.

[0136] [Procedure for the image processing method according to the third embodiment] Figure 12 is a schematic diagram showing the procedure of the image processing method according to the third embodiment. The image processing method according to the third embodiment has a display condition adjustment step S17 added to the image processing method according to the first embodiment.

[0137] The display condition adjustment step S17 is performed after the current image identification step S16, and the display conditions of the current image CI13 identified in the current image identification step S16 are adjusted to match the display conditions of the past image PI11.

[0138] In the display condition adjustment step S17, the display conditions of the current image CI13 are adjusted using the display conditions of the past image PI obtained when acquiring past measurement information in the measurement information acquisition step S14.

[0139] In the example shown in Figure 12, the brightness of the past image PI11 is darker than the current image CI13 identified in the current image identification step S16, and the current image CI13A is displayed with its brightness adjusted to match that of the past image PI11.

[0140] In the current image measurement process S18, the RI of the lesion is measured using the current image CI13A, whose brightness has been adjusted to match the past image PI11. As display conditions to be adjusted, at least one of the following may be applied: a window level that represents the reference for the CT value to be displayed on the image, and a window width that represents the range of the CT value to be displayed on the image.

[0141] Note that the display conditions for the current image CI13 described in the embodiment are an example of the first display conditions. The display conditions for the past image PI11 described in the embodiment are an example of the second display conditions.

[0142] [Example of electrical configuration of the image processing apparatus according to the third embodiment] Figure 13 is a functional block diagram showing the electrical configuration of the image processing apparatus according to the third embodiment. . same The image processing device 16B shown in the figure has a display adjustment unit 39 added to the image processing device 16 shown in Figure 4.

[0143] The display adjustment unit 39 obtains the display conditions for the past image PI11 shown in Figure 12 from the medical image database 14. The display adjustment unit 39 adjusts the display conditions for the current image CI13 identified using the current image identification unit 38, and displays the current image CI13A, with the adjusted display conditions for the current image CI13, on the display device 41. The display device 41 shown in Figure 13 may be the display device 20B of the user terminal 20 shown in Figure 1.

[0144] [Example of hardware configuration of the image processing device according to the third embodiment] Figure 14 is a schematic block diagram showing an example of the hardware configuration of an image processing system according to the third embodiment. The image processing device 16B shown in the figure includes a computer-readable medium 54B instead of the computer-readable medium 54 of the image processing device 16 shown in Figure 5. The computer-readable medium 54B includes a memory 62B instead of the memory 62 shown in Figure 5.

[0145] Memory 62B stores various programs, such as the current image group receiving program 70, which is stored in memory 62 as shown in Figure 5, and also stores a display adjustment program 77. The display adjustment program 77 is applied to the display adjustment unit 39 shown in Figure 13 to realize the display adjustment function.

[0146] [Effects of the Third Embodiment] The image processing method and image processing apparatus according to the third embodiment can obtain the following effects.

[0147] [1] The display conditions for the current image CI, which is identified as the target for measuring lesion RI, are adjusted to match the display conditions for the past image PI. This ensures that the current image CI of the target for lesion RI measurement and the past image PI of the lesion are displayed in a similar appearance, satisfying the requirement to use the same current image CI as the past image PI when measuring lesion RI.

[0148] [2] When past measurement information is retrieved from the medical image database 14, the display conditions for past image PIs corresponding to the past measurement information are also retrieved. This allows for the use of highly reliable display conditions for past image PIs.

[0149] The technical scope of the present invention is not limited to the scope described in the embodiments above. The configurations and other elements in each embodiment can be appropriately combined with those in each embodiment without departing from the spirit of the present invention. [Explanation of Symbols]

[0150] 10 Medical Image Processing Systems 12 Medical imaging equipment 14 Medical Image Databases 16 Image Processing Device 16A Image Processing Device 16B Image Processing Device 20 User Terminals 20A Input Device 20B Display device 22 Hospital Network 24 Internet 26 Cloud Servers 30 Current Image Group Receiving Unit 32 Designated lesion area 34 Input Information Acquisition Unit 36 Measurement Information Acquisition Unit 38 Current Image Identification Section 39 Display adjustment section 40 Measurement section 41 Display device 42 Measurement Condition Setting Unit 44 Measurement Result Output Unit 52 processors 54 Computer-readable media 54A Computer-readable media 54B Computer-readable media 56 Communication Interface 58 Input / Output Interfaces 60 bus 62 memory 62A memory 62B memory Wireless 4 Storage 70 Current Image Set Receiving Program 72. Lesion-Specific Program 74. Measurement Information Acquisition Program 76 Current Image Identification Program 77 Display Adjustment Program 78 Measurement Program 80 Estimation error derivation part 82 Estimation Error Database 84. Estimated Error Output Unit 86 Alert Output Section 90. Program for deriving estimated errors 92 Alert Output Program CI Current Image CI1 Current Image CI2 Current Image CI3 Current Image CI11 Current Image CI12 Current Image CI13 Current Image CI13A Current Image CI14 Current Image CI21 Current Image CI22 Current Image CI24 Current Image CIG Current Image Group PI Past Images PI11 Past Images PR measurement results RI lesion S10 to S22: Each step of the image processing method

Claims

1. One or more processors, One or more memories in which instructions to be executed by the one or more processors are stored, Equipped with, The one or more processors described above are: The system receives multiple first images, each of which is generated by photographing a subject and to which multiple different first image conditions are applied. Specify the first region of interest in the plurality of first images, Before capturing the first image, measurement information is acquired for a plurality of second images generated by photographing the subject, the second image having a second region of interest corresponding to the first region of interest. From the plurality of first images, the first image included in the range of the measurement information is identified. An image processing apparatus for measuring the first region of interest in the identified first image.

2. The image processing apparatus according to claim 1, wherein one or more processors identify the first image as the first image included in the range of measurement information, the first image having the first image condition which maximizes the similarity index representing the similarity with the second image condition of the second image.

3. The image processing apparatus according to claim 2, wherein one or more processors derive the similarity index using at least one of reconstruction conditions, slice thickness representing the thickness of a tomography in a tomographic image, spatial resolution, and imaging protocol.

4. The one or more processors described above are: The image processing apparatus according to claim 1, wherein at least one of the second image in which the measurement of the second region of interest is performed and the measurement results of the second region of interest is applied as the measurement information.

5. The image processing apparatus according to claim 1, wherein one or more processors estimate the error in the measurement result of the first region of interest with respect to the measurement result of the second region of interest based on the first image condition and the second image condition.

6. The image processing apparatus according to claim 5, wherein one or more processors cause an alert to be output when the estimated error exceeds a specified range.

7. The image processing apparatus according to claim 5, wherein one or more processors cause the range of the error, defined according to the estimated trend of the error, to be displayed on a display device.

8. The image processing apparatus according to any one of claims 1 to 4, wherein one or more processors set a first display condition applied to the measurement of a first region of interest in a first image, according to a second display condition applied to the measurement of a second region of interest in a second image.

9. The image processing apparatus according to claim 8, wherein one or more processors set at least one of brightness, window level, and window width as the first display condition.

10. The image processing apparatus according to any one of claims 1 to 4, wherein when one or more processors obtain an input for selecting a first region of interest in the first image, the apparatus displays at least one of the first region of interest and the measurement result of the first region of interest on a display device.

11. The image processing apparatus according to any one of claims 1 to 4, wherein when one or more processors obtain an input for selecting a first region of interest in the first image, they cause at least one of the first region of interest and the measurement result of the first region of interest to be displayed on a display device, and the measurement information is displayed on the display device.

12. The image processing apparatus according to claim 11, wherein one or more processors apply different display modes to at least one of the first region of interest and the measurement results of the first region of interest, and to the measurement information.

13. The image processing apparatus according to claim 11, wherein when one or more processors obtain an input for selecting a first region of interest in the first image, the apparatus displays at least one of the measurement results of the second image and the second region of interest on a display device as measurement information.

14. The one or more processors described above are: The system receives multiple first images, which are generated by photographing the subject. As the first region of interest, the anatomical structure of the subject in the plurality of first medical images is specified, The image processing apparatus according to claim 1, wherein, as the measurement information, measurement information is obtained by measuring the anatomical structure of the subject, which is the second region of interest corresponding to the first region of interest, for a plurality of second medical images generated by photographing the subject.

15. The image processing apparatus according to claim 14, wherein the one or more processors cause the measurement results of the anatomical structure to be displayed on a display device as the measurement results of the first region of interest in the first image.

16. A method for operating an image processing device comprising one or more processors and one or more memories in which programs to be executed by the one or more processors are stored, One or more processors, The system receives multiple first images, each of which is generated by photographing a subject and to which multiple different first image conditions are applied. Specify the first region of interest in the plurality of first images, Before capturing the first image, measurement information is acquired for a plurality of second images generated by photographing the subject, the second image having a second region of interest corresponding to the first region of interest. From the plurality of first images, the first image included in the range of the measurement information is identified. A method for operating an image processing device that measures the first region of interest in the identified first image.

17. On the computer, A function that receives multiple first images, each of which is generated by photographing a subject and to which multiple different first image conditions are applied. A function to specify a first region of interest in the plurality of first images. A function to acquire measurement information for a plurality of second images generated by photographing the subject before capturing the first image, the second image having a second region of interest corresponding to the first region of interest. A function to identify the first image included in the range of the measurement information from the plurality of first images, and A program that implements a function for measuring the first region of interest in the identified first image.

Images