Medical image processing device, medical image processing system, medical image processing method and program

Abstract

The goal is to display annotations correctly in BSTS images. [Solution] The medical image processing device 1 includes a processing unit (control unit 11) that performs temporal subtraction processing on multiple medical images that have been subjected to bone attenuation processing, and information indicating that bone attenuation processing has been performed is embedded in the image after the temporal subtraction processing and is input so as to be visible from the image after the temporal subtraction processing.

Description

[Technical Field]

[0001] The present invention relates to a medical image processing apparatus, a medical image processing system, a medical image processing method, and a program. [Background technology]

[0002] Conventionally, TS processing (Temporal Subtraction) has been used to check changes over time, such as the progression of a lesion. TS processing is a process that uses two medical images taken at different times to align the structures shown in the medical images, and then performs subtraction processing after alignment to extract information on only changes over time.

[0003] In TS processing, artifacts often occur despite the registration and warping processes used for registration. This is because the conditions at the time of capture, such as the patient's condition and the imaging environment, are different between the two medical images. For this reason, image processing is performed before and after TS processing to reduce artifacts. For example, Patent Document 1 describes a method for reducing artifacts in medical images by blurring bone edges using a blur mask to generate blurred images and then performing TS processing on the blurred images. Furthermore, Patent Document 2 describes a bone suppression (BS) process that weakens bones to make it easier to examine lung field portions overlapping with ribs, etc., when diagnosing lung fields using chest medical images. By performing BS processing as pre-processing of TS processing, artifact reduction measures can be implemented. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2004-194357 [Patent Document 2] Special Publication No. 2017-510427 Summary of the Invention [Problem to be solved by the invention]

[0005] Incidentally, after BS processing, an annotation indicating that BS processing has been performed is added to the medical image after BS processing (BS image). Here, adding means embedding the annotation in the BS image by replacing the image data. There are two main methods for adding annotations: one is to embed the annotation in the image, and the other is to save the annotation as additional information for the image and overlay it when displayed. However, if the storage destination or display method is a different system, it is often not possible to read the additional information, and so embedding it in the image is often used. Therefore, when TS processing is performed after BS processing, the embedded parts may overlap and disappear in the medical image after BS processing and TS processing (BSTS image) due to TS processing, or may become blurred due to misalignment of the display position. In such cases, the visibility of the annotations may be reduced, and because the medical image that has only undergone TS processing (TS image) and the BSTS image look similar, it may be difficult for doctors to distinguish between the two. There is no problem with diagnosis even if doctors are unaware that medical images have been subjected to alignment or warping processing. However, if doctors are unaware that BS processing has been performed, they will be making a diagnosis without knowing that structures such as bones have been weakened, which could lead to a misdiagnosis.

[0006] Therefore, an object of the present invention is to correctly display annotations in BSTS images. [Means for solving the problem]

[0007] In order to solve the above problems, the medical image processing device of the present invention comprises: a processing unit that performs temporal subtraction processing on a plurality of medical images that have been subjected to bone attenuation processing; Information indicating that the bone weakening processing has been performed is embedded in the image after the temporal subtraction processing, and is input so as to be visible from the image after the temporal subtraction processing.

[0008] In order to solve the above problems, the medical image processing system of the present invention comprises: a first processing unit that performs temporal subtraction processing on a plurality of medical images that have been subjected to bone attenuation processing; a display unit, information indicating that the bone weakening processing has been performed is embedded in the image after the temporal subtraction processing and is input so as to be visible from the image after the temporal subtraction processing; The display unit displays information indicating that the bone weakening treatment has been performed.

[0009] Further, the medical image processing method of the present invention comprises: A medical image processing method using a medical image processing device having a processing unit that performs temporal subtraction processing on a plurality of medical images that have been subjected to bone attenuation processing, The method includes a step of embedding information indicating that the bone weakening processing has been performed in the image after the temporal subtraction processing, and inputting the information so as to be visible from the image after the temporal subtraction processing.

[0010] The program of the present invention also includes: The computer of the medical image processing device, a processing unit that performs temporal subtraction processing on a plurality of medical images that have been subjected to bone attenuation processing; Information indicating that the bone weakening processing has been performed is embedded in the image after the temporal subtraction processing, and is input so as to be visible from the image after the temporal subtraction processing. [Effects of the Invention]

[0011] According to the present invention, annotations can be displayed correctly in BSTS images. [Brief explanation of the drawings]

[0012] [Figure 1] FIG. 1 is a block diagram showing the configuration of a medical image processing system. [Figure 2] 1 is a flowchart showing BSTS processing. [Figure 3] FIG. 1 is an image diagram of TS processing in BSTS processing. [Figure 4] FIG. 1 is an image diagram of TS processing in BSTS processing. [Figure 5] 1 is a flowchart showing BSTS processing. [Figure 6] FIG. 1 is an image diagram of TS processing in BSTS processing. DETAILED DESCRIPTION OF THE INVENTION

[0013] Hereinafter, embodiments of the present invention will be described with reference to the drawings. However, the embodiments described below are subject to various limitations that are technically preferable for implementing the present invention. Therefore, the technical scope of the present invention is not limited to the following embodiments and illustrated examples.

[0014] <Medical image processing system 100> First, the configuration of a medical image processing system 100 will be described with reference to Fig. 1. As shown in Fig. 1, the medical image processing system 100 is configured by connecting a medical image processing device 1, a modality 2, and a terminal device 3 via a communication network NT such as a LAN (Local Area Network).

[0015] The medical image processing device 1 is an information processing device that performs BS processing (bone attenuation processing) on ​​medical images, performs TS processing (temporal subtraction processing) on ​​multiple medical images, and performs TS processing after BS processing on multiple medical images. Specifically, the medical image processing device 1 is an information processing device such as a cloud server or an on-premise server. The modality 2 is a device that captures or manages medical images. Specifically, the modality 2 is various medical imaging devices that capture medical images, such as X-ray devices (DR, CR), ultrasound diagnostic devices (US), computed tomography (CT), and magnetic resonance imaging (MRI), or various medical image management devices that manage medical images, such as a Radiology Information System (RIS) and a Picture Archiving and Communication System (PACS). The terminal device 3 is a terminal device for a user such as a doctor to check medical images transmitted from the medical image processing apparatus 1 and the modality 2. The terminal device 3 includes a display unit (not shown).

[0016] <Medical image processing device 1> Each component of a medical image processing apparatus 1 according to this embodiment will be described with reference to Fig. 1. Fig. 1 is also a block diagram showing the configuration of the medical image processing apparatus 1. As shown in FIG. 1, the medical image processing apparatus 1 includes a control unit 11, an operation unit 12, a communication unit 13, a storage unit 14, a display unit 15, and the like.

[0017] The control unit 11 is composed of a CPU (Central Processing Unit), RAM (Random Access Memory), etc. The CPU of the control unit 11 reads out various programs stored in the storage unit 14, loads them into the RAM, executes various processes in accordance with the loaded programs, and controls the operation of each unit of the medical image processing device 1.

[0018] The control unit 11 functions as a processing unit (first processing unit) that performs temporal subtraction processing on a plurality of medical images that have been subjected to bone attenuation processing. The control unit 11 functions as a second processing unit that performs temporal subtraction processing on a plurality of medical images that have not been subjected to bone attenuation processing. The multiple medical images are multiple medical images of the same region of the same patient.

[0019] The operation unit 12 includes a keyboard equipped with cursor keys, numeric input keys, various function keys, etc., a pointing device such as a mouse, a touch panel laminated on the surface of the display unit 15, etc. The operation unit 12 is configured to be operable by an operator. Further, the operation unit 12 outputs various signals based on operations performed by the operator to the control unit 11.

[0020] The communication unit 13 is capable of transmitting and receiving various signals and various data to and from other devices etc. that are communicatively connected via a communication network.

[0021] The storage unit 14 is composed of a non-volatile semiconductor memory, a hard disk, etc., and stores various programs executed by the control unit 11, parameters necessary for the execution of the programs, various data, etc.

[0022] The display unit 15 is composed of a monitor such as an LCD (Liquid Crystal Display), and displays various screens etc. according to the instructions of the display signals input from the control unit 11.

[0023] <BSTS processing case 1> Next, the BSTS processing in the present embodiment will be described using FIG. 2. The BSTS processing is a process of performing TS processing after BS processing using a plurality of medical images. Hereinafter, the case of performing BSTS processing using two medical images will be used to describe the BSTS processing. The two medical images are two medical images of the chest of the same patient. Note that embedding the annotation described later means replacing the image data.

[0024] First, the control unit 11 acquires two medical images from modality 2 via the communication unit 13 (step S1).

[0025] Next, the control unit 11 performs BS processing on the two medical images to generate a BS image (step S2).

[0026] Next, the control unit 11 embeds an annotation indicating that the BS processing has been performed in the BS image (step S3).

[0027] For example, as shown in FIG. 3, the control unit 11 may embed annotations with different pixel values ​​in two BS images. The BS image 1001 is a BS image in which an annotation 2001 is embedded in the upper left corner of the image. The BS image 1002 is a BS image in which an annotation 2002 is embedded in the upper left corner of the image. Annotation 2001 and annotation 2002 are annotations of different pixel values. Specifically, annotation 2001 is a white "BS" on a black background, and annotation 2002 is a gray "BS" on a black background. In the case of FIG. 3, the annotation is embedded in the same location with the same name ("BS").

[0028] Furthermore, for example, as shown in FIG. 4, the control unit 11 may embed an annotation in only one BS image, and not embed an annotation in the other BS image. The BS image 1004 is a BS image in which an annotation 2004 is embedded in the upper left corner of the image. The BS image 1005 is a BS image in which no annotations are embedded. When three or more medical images are used, the control unit 11 only needs to embed an annotation in one BS image.

[0029] Next, the control unit 11 performs TS processing on the two BS images to generate a BSTS image (step S4). In the TS processing, the TS processing is also performed on the annotation portion in the BS image.

[0030] For example, as shown in FIG. 3, the control unit 11 performs TS processing by taking the difference between two BS images 1001 and 1002, and generates a BSTS image 1003. At this time, the difference is also calculated for the annotations 2001 and 2002 embedded in the two BS images 1001 and 1002, and the difference occurs because the pixel values ​​of the two annotations 2001 and 2002 are different. Therefore, the BSTS image 1003 is a BSTS image in which the annotation 2003 is embedded in the upper left corner of the image as information indicating that BS processing has been performed, and is visible. This allows annotations to be displayed correctly on BSTS images. The control unit 11 may determine whether the annotation that has undergone the difference processing matches a predefined display position, display format, etc., and if they match, maintain the annotation as is, or rewrite the annotation if they differ. For example, since usability is poor if the display format of the embedded information differs for each BSTS image, in such a case, it is advisable to rewrite the area where the annotation is embedded (annotation area) with an annotation indicating BS processing again. Specifically, the control unit 11 determines whether the visibility of the difference result is ensured using machine learning or the like, and if it is determined to be poor, rewrite the annotation using a predefined display format or the like. In the above case, the control unit 11 may remove the annotation portion before performing the TS processing and add a new annotation. In addition to differences in pixel values, the same applies if the annotation drawing position is shifted. If the drawing position is shifted, the difference processing will result in a shifted form, making the characters unreadable. Therefore, the annotation area may be subjected to processing such as that described in steps S14 and S15, which will be described later.

[0031] As shown in FIG. 4, the control unit 11 performs TS processing by taking the difference between two BS images 1004 and 1005 to generate a BSTS image 1006. At this time, the difference is also taken for the annotation 2004 embedded in the BS image 1004, but the difference occurs because the annotation 2004 is embedded in only one of the BS images 1004. Therefore, the BSTS image 1006 becomes a BSTS image in which the annotation 2006 is embedded in the upper left of the image and is visible as information indicating that the BS process has been performed. Thereby, the annotation can be correctly displayed in the BSTS image.

[0032] Next, the control unit 11 embeds an annotation indicating that the TS process has been performed in the BSTS image (step S5). For example, as shown in FIG. 3, the control unit 11 may embed the annotation 3003 in the BSTS image 1003. Also, for example, as shown in FIG. 4, the control unit 11 may embed the annotation 3006 in the BSTS image 1006.

[0033] Next, the control unit 11 causes the display unit 15 or the display unit of the terminal device 3 to display the BSTS image and ends the BSTS process (step S6).

[0034] <BSTS Process Case 2> Next, the BSTS process in the present embodiment will be described using FIG. 5. Hereinafter, the BS process will be described using a case where the BSTS process is performed using two medical images. The two medical images are two medical images obtained by photographing the chest of the same patient.

[0035] First, the control unit 11 acquires two medical images from the modality 2 via the communication unit 13 (step S11).

[0036] Next, the control unit 11 performs a BS process on the two medical images to generate a BS image (step S12).

[0037] Next, the control unit 11 embeds an annotation indicating that the BS process has been performed in the BS image (step S13). For example, as shown in FIG. 6, the control unit 11 may embed the annotations 2007 and 2008 in the two BS images 1007 and 1008. The BS image 1007 is a BS image in which an annotation 2007 is embedded in the upper left corner of the image. The BS image 1008 is a BS image in which an annotation 2008 is embedded in the upper left corner of the image. In the case of FIG. 6, the annotations are embedded in the same location.

[0038] Next, the control unit 11 recognizes an area in the BS image where an annotation is embedded (annotation area) (step S14). Specifically, the control unit 11 may recognize the annotation region by using various analytical models such as machine learning models that are trained to recognize the annotation region from within the image. Furthermore, if it is assumed that the position in the image where the annotation is to be embedded has been determined, the control unit 11 may recognize that position as the annotation area.

[0039] Next, the control unit 11 performs TS processing on the two BS images using a predetermined method to generate a BSTS image (step S15). For example, the control unit 11 may delete the images of the annotation regions recognized in step S4 from the two BS images 1007 and 1008, and then perform TS processing. Also, for example, the control unit 11 may perform TS processing on the annotation area recognized in step S4 without calculating the difference. Note that, as will be described later, for the annotation area, the control unit 11 may preferentially use the annotation of one of the two BS images 1007 and 1008.

[0040] Next, the control unit 11 embeds an annotation in the BSTS image indicating that the BS processing and the TS processing have been performed (step S16). For example, the control unit 11 may embed an annotation 2009 in the annotation region recognized in step S4 as information indicating that the BS process has been performed. Furthermore, for example, the control unit 11 may prioritize the image of the annotation region in any one of the BS images for the annotation region. Specifically, the control unit 11 may prioritize the BS image 1007 and embed the annotation 2007 as the annotation 2009. Additionally, for example, as shown in FIG. 6, the control unit 11 may embed an annotation 3009 indicating TS processing in the two medical images. In this way, the BSTS image 1009 becomes a BSTS image in which the annotation 2009 is embedded in the upper left corner of the image as information indicating that BS processing has been performed, and is visible. This allows annotations to be displayed correctly on BSTS images.

[0041] Next, the control unit 11 causes the display unit 15 or the display unit of the terminal device 3 to display the BSTS image, and ends the BSTS processing (step S17).

[0042] <Other> In the above, the BSTS processing has been described using two medical images, but the present invention is not limited to this example, and three or more medical images may be used.

[0043] Furthermore, the control unit 11 may display an annotation indicating that BS processing or TS processing has been performed in an area other than the area where the subject structure is displayed. In this case, the control unit 11 may automatically adjust the mark, wording, or size depending on the display location and the display range. For example, as shown in FIG. 3, the control unit 11 may place an annotation 2001 in an area other than the subject portion in the BS image 1001.

[0044] Furthermore, annotations indicating that BS processing has been performed or annotations indicating that TS processing has been performed may be displayed in white on a black background as shown in Figures 3, 4, and 6. Note that the background color and text color are not limited to this example.

[0045] Furthermore, in the BSTS processing flow shown in Figures 2 and 5, the BS processing is performed followed by the TS processing, but the control unit 11 may obtain a BS image that has already been subjected to BS processing from the memory unit 14 and perform TS processing thereon.

[0046] Furthermore, information indicating that BS processing has been performed and information indicating that TS processing has been performed may be embedded in a distinguishable manner. For example, in the examples of Figures 3, 4, and 6, the information can be distinguished by changing the character information to "BS" and "TS." The information indicating that BS processing has been performed and the information indicating that TS processing has been performed may be embedded so as not to overlap. For example, in the examples of Figures 3, 4, and 6, the control unit 11 embeds an annotation indicating "BS" in the upper left of the medical image and an annotation indicating "TS" in the upper right of the medical image.

[0047] It is also possible for the control unit 11 to perform TS processing from multiple medical images that have not been subjected to BS processing. In this case, the control unit 11 may embed an annotation indicating "TS" in the upper right corner of the medical image as information indicating that TS processing has been performed, similar to the examples of FIGS. 3, 4, and 6. For example, the annotation indicating "TS" may be embedded as white information on a black background. Also, for example, the annotation indicating that TS processing has been performed may be displayed in an area other than the area in which the subject's structure is displayed. As described above, the control unit 11 may display the annotation indicating "TS" and the annotation indicating "BS" in a distinguishable manner.

[0048] In addition, in the above illustrated examples, the BS annotation is in the upper left of the image, but even if the annotation indicating "BS" in the first and second BS images is in different positions, for example, in the upper left and lower right, the annotation indicating "BS" may be rewritten in one position without appearing in two positions. In such a case, for example, the control unit 11 can identify the positions of the annotation indicating "BS" by machine learning or the like, erase each annotation, and then re-embed only one annotation in a predetermined position.

[0049] This is not limited to cases where the annotation is displayed in multiple locations or is displayed in an unrecognizable state as described above, but may also be re-embedded as described above even when the image is not displayed in a position suitable for the final image. For example, when a previous image (first image) has BS embedded in the top center, and when taking the difference with the latest image (second image), the top center would cover, for example, the neck of the subject, so for visibility reasons, it is desired to change the annotation display position to the top left.

[0050] <Effects> From the above, the medical image processing device 1 includes a processing unit (control unit 11) that performs temporal subtraction processing from multiple medical images that have been subjected to bone attenuation processing, and information indicating that bone attenuation processing has been performed is embedded in the image after the temporal subtraction processing and is input so as to be visible from the image after the temporal subtraction processing. This allows annotations to be displayed correctly on BSTS images.

[0051] In addition, the medical image processing system 100 has a first processing unit (control unit 11) that performs temporal subtraction processing from multiple medical images that have been subjected to bone attenuation processing, and a display unit (display unit of the terminal device 3), and information indicating that bone attenuation processing has been performed is embedded in the image after the temporal subtraction processing and is input so as to be visible from the image after the temporal subtraction processing, and the display unit displays the information indicating that bone attenuation processing has been performed. This allows annotations to be displayed correctly on BSTS images.

[0052] Furthermore, the medical image processing method includes a step (step S5, step S16) of embedding information indicating that bone attenuation processing has been performed in the image after the temporal subtraction processing and inputting the information so as to be visible from the image after the temporal subtraction processing, in a medical image processing device 1 having a processing unit (control unit 11) that performs temporal subtraction processing on multiple medical images that have been subjected to bone attenuation processing. This allows annotations to be displayed correctly on BSTS images.

[0053] The program also causes the computer of the medical image processing device 1 to function as a processing unit (control unit 11) that performs temporal subtraction processing from multiple medical images that have been subjected to bone attenuation processing, and information indicating that bone attenuation processing has been performed is embedded in the image after the temporal subtraction processing and is input so as to be visible from the image after the temporal subtraction processing. This allows annotations to be displayed correctly on BSTS images.

[0054] Although the present invention has been specifically described above based on the embodiments, the present invention is not limited to the above embodiments and can be modified within the scope of the invention.

[0055] Furthermore, in the above description, an example has been disclosed in which a semiconductor memory or a hard disk is used as a computer-readable medium for the program according to the present invention, but the present invention is not limited to this example. Other computer-readable media that can be used include non-volatile memories such as flash memories and portable recording media such as CD-ROMs. Furthermore, a carrier wave is also applied to the present invention as a medium for providing data of the program according to the present invention via a communication line. [Explanation of symbols]

[0056] 100 Medical Image Processing System 1 Medical image processing equipment 11 control unit (processing unit, first processing unit, second processing unit) 12 Control section 13 Communications Department 14 Storage section 15 Display section 2. Modality 3 Terminal Devices

Claims

1. a processing unit that performs temporal subtraction processing on a plurality of medical images that have been subjected to bone attenuation processing; A medical image processing device, wherein information indicating that the bone attenuation processing has been performed is embedded in the image after the temporal subtraction processing and is input so as to be visible from the image after the temporal subtraction processing.

2. 2. The medical image processing apparatus according to claim 1, wherein information indicating that the bone weakening processing has been performed is embedded in the image after the temporal subtraction processing by replacing the image data.

3. The plurality of medical images subjected to bone attenuation processing include a first image embedded with information indicating that a first bone attenuation processing has been performed, and a second image embedded with information indicating that a second bone attenuation processing has been performed, The medical image processing device according to claim 1 , wherein the information indicating that the first bone attenuation processing has been performed and the information indicating that the second bone attenuation processing has been performed are information of different pixel values.

4. 2. The medical image processing device according to claim 1, wherein only one of the first image and the second image, which are the plurality of medical images subjected to bone attenuation processing, is an image in which information indicating that bone attenuation processing has been performed is embedded.

5. The medical image processing apparatus according to claim 1 , wherein information indicating that the bone weakening processing has been performed is embedded after the temporal subtraction processing.

6. The medical image processing apparatus according to claim 1 , wherein the information indicating that the bone weakening processing has been performed is displayed in an area other than an area in which the structure of the subject is displayed.

7. The medical image processing apparatus according to claim 1 , wherein the information indicating that the bone weakening treatment has been performed is displayed in white on a black background.

8. 2. The medical image processing apparatus according to claim 1, wherein information indicating that the temporal subtraction processing has been performed is embedded in the image after the temporal subtraction processing and is input so as to be visible from the image after the temporal subtraction processing.

9. 9. The medical image processing apparatus according to claim 8, wherein the information indicating that the temporal subtraction process has been performed is embedded in white information on a black background.

10. The medical image processing apparatus according to claim 8 , wherein information indicating that the bone weakening processing has been performed and information indicating that the temporal subtraction processing has been performed are embedded in a distinguishable manner.

11. The medical image processing apparatus according to claim 8 , wherein the information indicating that the bone weakening processing has been performed and the information indicating that the temporal subtraction processing has been performed are embedded so as not to overlap.

12. a first processing unit that performs temporal subtraction processing on a plurality of medical images that have been subjected to bone attenuation processing; a display unit, information indicating that the bone weakening processing has been performed is embedded in the image after the temporal subtraction processing and is input so as to be visible from the image after the temporal subtraction processing; The display unit displays information indicating that the bone weakening treatment has been performed.

13. a second processing unit that performs temporal subtraction processing on a plurality of medical images that have not been subjected to bone attenuation processing; 13. The medical image processing system according to claim 12, wherein the display unit distinguishably displays information to be displayed on a time-lapse subtraction processed image that has not undergone the bone attenuation processing and has undergone time-lapse subtraction processing from information indicating that the bone attenuation processing has been performed.

14. 14. The medical image processing system according to claim 13, wherein the information indicating that the bone attenuation processing has been performed is information indicating that the bone attenuation processing has been performed and that the temporal subtraction processing has been performed.

15. the display unit displays information indicating that the bone attenuation processing has not been performed and that the temporal subtraction processing has been performed on the temporal subtraction processed image that has not been performed and that has been subjected to the bone attenuation processing, 14. The medical image processing system according to claim 13, wherein information indicating that the bone attenuation processing has been performed and that the temporal subtraction processing has been performed is displayed on the temporal subtraction processed image that has been subjected to the bone attenuation processing and the temporal subtraction processing.

16. A medical image processing method using a medical image processing device having a processing unit that performs temporal subtraction processing on a plurality of medical images that have been subjected to bone attenuation processing, A medical image processing method comprising the steps of embedding information indicating that the bone weakening processing has been performed in the image after the temporal subtraction processing and inputting the information so as to be visible from the image after the temporal subtraction processing.

17. The computer of the medical image processing device, a processing unit that performs temporal subtraction processing on a plurality of medical images that have been subjected to bone attenuation processing; A program in which information indicating that the bone weakening processing has been performed is embedded in the image after the temporal subtraction processing and is input so as to be visible from the image after the temporal subtraction processing.

Images