JP2013192835A - Medical image display device and medical image display method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a medical image display device and a medical image display method, allowing the erasure of personal information embedded in a medical image in optional arrangement order.SOLUTION: This medical image display device utilizes a fact that personal information is embedded in a fixed position in a medical image over a plurality of medical images. Specifically, the medical image display device including a display part displaying the medical image includes: a personal information extraction part extracting pixels wherein a result obtained by calculating respective pixel values of the same coordinate position between the plurality of medical images satisfies a prescribed condition as the personal information; and a personal information erasure part erasing the personal information from the medical image by changing the pixel values of the pixels extracted as the personal information.

Description

  The present invention relates to a medical image display apparatus and a medical image display method for displaying a medical image acquired from a medical image diagnostic apparatus including an X-ray imaging apparatus, an X-ray CT apparatus, an MRI apparatus, an ultrasonic diagnostic apparatus, and a nuclear medicine diagnostic apparatus. In particular, the present invention relates to a technique for deleting incidental information embedded in a medical image, particularly personal information.

  Medical images acquired from medical image diagnostic devices including X-ray imaging devices, X-ray CT devices, MRI devices, ultrasound diagnostic devices, and nuclear medicine diagnostic devices are accompanied by character information such as personal information and examination information of the subject. Embedded as information. Auxiliary information is useful when medical images are used for diagnostic imaging, but when medical images are used for education and academic conference presentations, supplementary information, especially personal information, must be deleted from the viewpoint of protecting the privacy of the subject. Is desirable.

  For example, Patent Document 1 discloses a technique for deleting incidental information embedded in a medical image. In Patent Document 1, symbol information such as punctuation marks, parentheses, and colons is extracted from character information read out from a medical image by an OCR (Optical Character Recognition) program, and personal information is arranged after the symbol information. A technique for extracting and erasing personal information based on the above is disclosed.

Japanese Unexamined Patent Publication No. 2007-44239

  However, in Patent Document 1, it is necessary to register symbol information for extracting personal information in advance, and personal information that follows the registered symbol information is erased. Could not be extracted. That is, only personal information embedded in a predetermined order can be deleted.

  SUMMARY An advantage of some aspects of the invention is that it provides an image display device and a medical image display method capable of erasing personal information embedded in a medical image in an arbitrary arrangement order.

  In order to achieve the above-mentioned object, the present invention uses a fact that personal information is embedded at a predetermined position in a medical image over a plurality of medical images, and extracts and erases personal information in the medical image. A display device and a medical image display method.

  Specifically, in a medical image display device including a display unit that displays a medical image, a pixel that satisfies a predetermined condition as a result of calculating each pixel value at the same coordinate position between a plurality of medical images And a personal information erasure unit for erasing the personal information from the medical image by changing a pixel value of the pixel extracted as the personal information.

  Also, a medical image display method including a display step for displaying a medical image, wherein a pixel satisfying a predetermined condition as a result of calculating each pixel value at the same coordinate position between a plurality of medical images is extracted as personal information. A personal information extracting step; and a personal information deleting step of deleting the personal information from the medical image by changing a pixel value of a pixel extracted as the personal information.

  According to the present invention, it is possible to provide an image display device and a medical image display method capable of erasing personal information embedded in a medical image in an arbitrary arrangement order.

The figure which shows the hardware constitutions of the medical image display apparatus of this invention The figure which shows the structure of the principal part of this invention The figure which shows the flow of a process of this invention The figure which shows the flow of a process of 1st Embodiment The figure which explains supplementarily about the comparison of the pixel value between multiple images The figure explaining supplementary about the change of the pixel value of the pixel which is personal information The figure which shows the flow of a process of 2nd Embodiment The figure which shows the flow of a process of 3rd Embodiment The figure which shows the flow of a process of 4th Embodiment

  DESCRIPTION OF EMBODIMENTS Hereinafter, preferred embodiments of a medical image display apparatus according to the present invention will be described with reference to the accompanying drawings. In the following description and the accompanying drawings, the same reference numerals are given to the constituent elements having the same functional configuration, and redundant description will be omitted.

  FIG. 1 is a diagram showing a hardware configuration of the medical image display apparatus 1. As shown in FIG. A medical image display device 1 includes a CPU (Central Processing Unit) 2, a main memory 3, a storage device 4, a display memory 5, a display device 6, a controller 7 connected to a mouse 8, a keyboard 9, and a network adapter 10 including a system bus 11. Is configured to be capable of transmitting and receiving signals. The medical image display device 1 is connected to a medical image photographing device 13 and a medical image database 14 via a network 12 so as to be able to send and receive signals. Here, “to enable signal transmission / reception” indicates a state in which signals can be transmitted / received to each other or from one to the other, regardless of whether they are electrically or optically wired or wireless.

  The CPU 2 is a device that controls the operation of each component. The CPU 2 loads a program stored in the storage device 4 and data necessary for program execution into the main memory 3 and executes it. The storage device 4 is a device that stores medical images taken by the medical image photographing device 13, and is specifically a hard disk or the like. The storage device 4 may be a device that exchanges data with a portable recording medium such as a flexible disk, an optical (magnetic) disk, a ZIP memory, or a USB memory. The medical image is acquired from the medical image photographing device 13 or the medical image database 14 via a network 12 such as a LAN (Local Area Network). The storage device 4 stores a program executed by the CPU 2 and data necessary for program execution. The main memory 3 stores programs executed by the CPU 2 and the progress of arithmetic processing.

  The display memory 5 temporarily stores display data to be displayed on the display device 6 such as a liquid crystal display or a CRT (Cathode Ray Tube). The mouse 8 and the keyboard 9 are operation devices for an operator to give an operation instruction to the medical image display device 1. The mouse 8 may be another pointing device such as a trackpad or a trackball. The controller 7 detects the state of the mouse 8, acquires the position of the mouse pointer on the display device 6, and outputs the acquired position information and the like to the CPU 2. The network adapter 10 is for connecting the medical image display apparatus 1 to a network 12 such as a LAN, a telephone line, or the Internet.

  The medical image photographing device 13 is a device that acquires a medical image such as a tomographic image of a subject. The medical imaging apparatus 13 is, for example, an MRI apparatus, an X-ray CT apparatus, an ultrasonic diagnostic apparatus, a scintillation camera apparatus, a PET apparatus, a SPECT apparatus, or the like. The medical image database 14 is a database system that stores medical images photographed by the medical image photographing device 13.

[First embodiment]
Extraction processing and deletion processing of personal information from the supplementary information embedded in the medical image in an arbitrary arrangement order are performed by the image reading unit 201, the personal information extraction unit 202, and the personal information deletion unit 203 shown in FIG. Is called. Each of these units 101 to 103 may be configured by dedicated hardware, or may be configured by the CPU 2 executing a processing flow to be described later. When the units 101 to 103 are configured by dedicated hardware, they are connected to the CPU 2 via the system bus 11.

  The image reading unit 101 executes a process of reading a plurality of medical images from the storage device 4, the medical image photographing device 13, or the medical image database 14. Additional information is embedded in each of the plurality of medical images read by the image reading unit 101.

  The incidental information is character information such as personal information and examination information of the subject. Specifically, it includes personal information of the subject such as the subject's name, identification number, sex, date of birth, and examination information such as the examination date, examination time, examination site, examination condition, and image number. In many cases, the incidental information is embedded at a fixed position in the medical image, and is present at the same coordinate position over a plurality of medical images. Further, in order to clearly identify the incidental information, the pixel value of the incidental information is often assigned a value farthest from the pixel value of the background area of the medical image. For example, if a medical image is displayed in monochrome 256 gradations, if the pixel value of the background area is 0, that is, black, the auxiliary information pixel value is assigned 255, that is, white, and if the background area is white, it is included in the auxiliary information. Is assigned black.

  In a plurality of medical images of the same subject, examination information may be displayed differently for each medical image, whereas personal information is displayed in the same display format across a plurality of medical images. That is, the examination time, the image number, and the like may be different numbers for each image, while the name, date of birth, and the like are displayed as the same character across a plurality of medical images.

  The personal information extraction unit 102 executes processing for extracting personal information to be deleted from a plurality of read medical images. For extracting personal information, it is used that personal information is embedded in the same coordinate position in the same shape over a plurality of medical images.

  The personal information erasure unit 103 executes a process of erasing the personal information from the medical image by changing the pixel values of the pixels constituting the extracted personal information. The medical image from which the personal information has been deleted is displayed on the display device 6 via the display memory 5.

  A flow of processing executed by the medical image display apparatus 1 having the above configuration will be described with reference to FIG.

(Step 301)
The image reading unit 101 reads a plurality of medical images selected by the operator by operating the mouse 8 and the keyboard 9 from the storage device 4, or from the medical image photographing device 13 or the medical image database 14 via the network 12. The accompanying information is embedded in each of the read medical images.

(Step 302)
The personal information extraction unit 102 extracts personal information to be erased from medical images based on the calculation result of pixel values at the same coordinate position across a plurality of images. FIG. 4 is a diagram showing a flow of personal information extraction processing according to the present embodiment. Hereinafter, each step of FIG. 4 will be described in detail.

(Step 401)
The personal information extraction unit 102 performs a comparison operation on the pixel values at the same coordinate position over a plurality of read images. That is, as shown in FIG. 5A, after obtaining pixel values at the same coordinate position over a plurality of images, the pixel values at the same coordinate position are compared between the images. In the comparison operation, for example, a graph as shown in FIG. 5B may be created. In the graph of FIG. 5B, the vertical axis represents the pixel value of each image, and the horizontal axis represents the image number. In the pixel of personal information embedded in the medical image, the same pixel value is shown over a plurality of images as indicated by reference numeral 501. On the other hand, in the pixels of the imaging area where the organs of the subject are displayed, the pixel values differ from image to image as indicated by reference numeral 502 due to the difference in the imaging cross-section position, imaging time, or the influence of noise included during imaging. Will be shown.

(Step 402)
The personal information extraction unit 102 determines whether or not the target pixel is personal information based on the result of the pixel value comparison operation between the images. As described above, the pixel of personal information shows the same pixel value across multiple images, whereas the pixel that is not personal information like a shooting region shows a different pixel value for each image. Is not changed, or when the change amount of the pixel value is smaller than a predetermined threshold, it is determined that the target pixel is a pixel constituting personal information.

(Step 303)
The personal information erasure unit 103 erases the personal information extracted in step 302 from the medical image.

  The process of deleting the personal information is executed by changing the pixel value of the personal information to, for example, the pixel value of the background area of the medical image. More specifically, if the pixel value of the background area is 0, that is, black, the pixel value of the personal information is changed to 0. By changing the pixel value of the personal information to the pixel value of the background area, it becomes impossible to distinguish the background area from the personal information, and the personal information is deleted.

  Further, when the personal information does not fit in the background area and overlaps the shooting area, it may be insufficient even if the pixel value of the personal information is changed to the pixel value of the background area. For example, when personal information of white characters overlaps with a photographing area, that is, a gray area, even if the pixel of the personal information is changed to black, the personal information is not erased. Therefore, when changing the pixel value of personal information, the pixel value of a pixel that is adjacent to the pixel of personal information and is not personal information is measured, the average value of the measured pixel values is calculated, and the calculated average value is The pixel value of information may be changed.

  This will be described more specifically with reference to FIG. FIG. 6 (a) shows the letter “A” extracted as personal information, and FIG. 6 (b) is an enlarged view of nine pixels in a region 600 surrounded by a thick line in FIG. 6 (a). When the pixel value to be changed is the pixel 601 that is the center of the region 600, the pixels that are adjacent to the pixel 601 and are not personal information are the three pixels 602a, 602b, and 602c. When the pixel values of the pixels 602a, 602b, and 602c are measured, the average value of the measured values of the three pixels is calculated, and the pixel value of the pixel 601 is changed to the average value of the three pixels, the pixel value of the pixel 601 is changed to the pixels 602a and 602b. , 602c becomes an intermediate color of pixel values. By executing the same process for each pixel constituting the personal information, all the pixels constituting the personal information become an intermediate color of surrounding pixels. When all the pixels around the personal information pixel have the same pixel value, the average value is the pixel value of the surrounding pixels, and thus the pixel of the personal information has the same pixel value as the surrounding pixels. As a result, even if the personal information overlaps the shooting area, the personal information cannot be distinguished from the shooting area, and the personal information is deleted.

  When all the pixels adjacent to the pixel whose pixel value is to be changed are pixels that constitute personal information, the average value may be calculated using the changed pixel value.

(Step 204)
The CPU 2 causes the display device 6 to display the medical image from which the personal information has been deleted in step 303 via the display memory 5.

  When the medical image display apparatus 1 executes the above processing flow, it is possible to delete personal information embedded in the medical image in an arbitrary arrangement order, which can contribute to personal information protection.

[Second Embodiment]
In the first embodiment, in step 302 of FIG. 3, pixels of personal information are extracted based on the result of comparison calculation of pixel values at the same coordinate position between a plurality of images. In contrast, in the present embodiment, an average image is created using a plurality of images, and pixels of personal information are extracted based on the pixel values of the created average image. The processing in step 302 in FIG. Other than this flow is the same as in the first embodiment. Hereinafter, the processing flow of step 302 in the second embodiment will be described with reference to FIG.

(Step 701)
The personal information extraction unit 202 creates an average image using the plurality of images read out in step 301. For example, the following formula is used to create the average image.

ここで、I_ave（x,y）は平均画像の座標位置(x,y)における画素値、iは画像番号、nは画像の総数、I_i（x,y）は画像番号iの画像の座標位置(x,y)における画素値、である。

Here, I _ave (x, y) is the pixel value at the coordinate position (x, y) of the average image, i is the image number, n is the total number of images, and I _i (x, y) is the image number i. The pixel value at the coordinate position (x, y).

(Step 702)
The personal information extraction unit 202 determines whether the target pixel is personal information based on the pixel value of the average image created in step 701. For example, the pixel value at each coordinate position of the average image is compared with a predetermined threshold value, and based on the result, it is determined whether or not the target pixel is a pixel constituting personal information.

  As described above, the pixel value of the supplementary information is often assigned a value farthest from the pixel value of the background region of the medical image. If the pixel value of the background region is 0, that is, black, If the pixel value is 255, that is, white is assigned, and the background area is white, the incidental information is assigned black. On the other hand, since the pixel value of the imaging region differs depending on the part, the pixel value of the average image in the imaging region is a value between 0 and 255, that is, an intermediate color.

  Therefore, if the pixel value of the background area is 0, a comparatively large threshold value, for example, a threshold value of about 250 is used to compare with the pixel value of the average image, and personal information is configured with pixels larger than the threshold value. What is necessary is just to extract as a pixel. Also, if the pixel value of the background area is 255, a comparison is made with the pixel value of the average image using a relatively small threshold value, for example, a threshold value of about 5, and personal information is configured with pixels smaller than the threshold value. What is necessary is just to extract as a pixel.

  Note that different threshold values may be set for the periphery and the center of the image using the fact that the auxiliary information is arranged around the image so as not to overlap the imaging region. For example, when the pixel value of the background region is 0, the threshold value may be set to about 245 in the vicinity, and the threshold value may be increased as it approaches the center. By doing so, erroneous extraction at the center of the image can be reduced.

  When the medical image display apparatus 1 executes the above processing flow, it is possible to delete personal information embedded in the medical image in an arbitrary arrangement order, which can contribute to personal information protection.

  Further, according to the present embodiment, even if there is a positional shift between a plurality of images, if the number of misaligned images is sufficiently small compared to the total number of images, the positional shift to the personal information in the average image Therefore, the personal information in the medical image can be accurately extracted and deleted.

[Third embodiment]
In the first and second embodiments, personal information is extracted in units of pixels. When personal information is extracted in units of pixels, some pixels constituting the character may be erroneously extracted as personal information and displayed in a state where a part of the character is missing. Therefore, in the present embodiment, personal information is not extracted in units of pixels, but a plurality of consecutive pixels constituting a character are grouped into a group, and personal information is extracted in units of groups. That is, in the present embodiment, based on the distance between each extracted pixel, a plurality of pixels are extracted as a pixel group constituting one character, and personal information is extracted in units of characters. Except for the processing flow in step 302, the processing is the same as in the first and second embodiments. Hereinafter, the flow of the process of step 302 in the third embodiment will be described with reference to FIG.

(Step 801)
The personal information extraction unit 202 extracts pixel candidates constituting the personal information from the medical images read out in step 301 as target pixels. The processing in this step may be the processing in step 302 in the first embodiment or the second embodiment, that is, the processing flow shown in FIG. 4 or FIG. 7, or may be extraction processing by threshold processing. Also good.

(Step 802)
The personal information extraction unit 202 calculates the inter-pixel distance of the pixels extracted in step 801.

(Step 803)
The personal information extraction unit 202 groups a plurality of pixels as one pixel group based on the inter-pixel distance calculated in step 802. For example, when the inter-pixel distance is equal to or less than a certain threshold, the same group is collected. More specifically, using a threshold value set so that the pixels can be regarded as the same group if they are adjacent to each other, the pixel groups whose inter-pixel distance is equal to or less than the threshold value are grouped into the same group.

  In addition, when the character size is predetermined, a group of pixels whose distance from a certain pixel is equal to or smaller than the threshold value can be grouped into the same group using a threshold value set according to the character size. good.

(Step 804)
The personal information extraction unit 202 determines whether the pixel group grouped in step 803 is a pixel group constituting personal information. In this step, the same determination as in step 402 of the first embodiment and step 702 of the second embodiment is performed for all the pixels constituting the pixel group, and all the pixels satisfy the condition. The pixel group is determined to be personal information.

  When the medical image display apparatus 1 executes the above processing flow, the personal information embedded in the medical image in an arbitrary arrangement order is deleted in character units.

[Fourth embodiment]
In the third embodiment, personal information is extracted in units of characters. When personal information is extracted in units of characters, only some characters constituting the character string may be erroneously extracted as personal information and displayed in a state where some characters of the character string are missing. Therefore, in this embodiment, personal information is not extracted in units of characters, but a plurality of characters constituting a character string are set as one cluster, and personal information is extracted in units of clusters. That is, this embodiment extracts a plurality of characters as a character group constituting one character string based on the distance between each extracted character, and extracts personal information in character string units. The third embodiment is the same as the third embodiment except for the processing flow in step 302 in FIG. Hereinafter, the flow of the process of step 302 in the fourth embodiment will be described with reference to FIG.

(Step 901)
The personal information extraction unit 202 extracts candidate characters constituting the personal information from the medical images read in step 301 as target characters. The processing in this step is the same as the processing flow from step 801 to step 803 in the third embodiment.

(Step 902)
The personal information extraction unit 202 calculates the inter-character distance of the characters extracted in step 901. The reference point for the distance between characters is, for example, the barycentric coordinate of the pixel group constituting the character, or the center point of the smallest rectangle that covers the character.

(Step 903)
The personal information extraction unit 202 clusters a plurality of characters as one character group based on the distance between characters calculated in step 902. For example, when the distance between characters is less than a certain threshold, they are collected as one cluster. More specifically, using a threshold value set so that characters can be regarded as one character string, a group of characters whose inter-character distance is equal to or less than the threshold value is collected into one cluster.

(Step 904)
The personal information extraction unit 202 determines whether or not the character group clustered in step 903 is a character group constituting personal information. In this step, the same determination as in step 402 of the first embodiment and step 702 of the second embodiment is performed for all characters constituting the character group, and all characters satisfy the condition. The character group is determined to be personal information.

  When the medical image display device 1 executes the above processing flow, the personal information embedded in the medical image in an arbitrary arrangement order is deleted in character string units.

  The medical image display device of the present invention is not limited to the above embodiment. For example, in the third embodiment, the process from step 801 to step 803 is replaced by OCR processing to extract characters from the medical image, and it is determined whether or not the character extracted in step 804 is personal information. You may do it.

  Further, in the fourth embodiment, characters are extracted from a medical image by OCR processing, a character group constituting a character string is extracted based on a distance calculated between the extracted characters, and then the extracted characters are extracted. It may be determined whether the group is personal information.

  1 Medical image display device, 2 CPU, 3 Main memory, 4 Storage device, 5 Display memory, 6 Display device, 7 Controller, 8 Mouse, 9 Keyboard, 10 Network adapter, 11 System bus, 12 Network, 13 Medical imaging device , 14 Medical image database, 201 Image reading unit, 202 Personal information extraction unit, 203 Personal information deletion unit

Claims (7)

A medical image display device including a display unit for displaying a medical image,
A personal information extraction unit that extracts, as personal information, pixels in which the result of calculating each pixel value at the same coordinate position between a plurality of medical images satisfies a predetermined condition;
A medical image display device comprising: a personal information erasing unit that erases the personal information from the medical image by changing a pixel value of a pixel extracted as the personal information. The medical image display device according to claim 1,
The personal information extraction unit compares a pixel value at the same coordinate position between a plurality of medical images, and extracts personal information based on a result of the comparison calculation. The medical image display device according to claim 1,
The medical information display device, wherein the personal information extraction unit calculates an average value of pixel values at the same coordinate position among a plurality of medical images, and extracts personal information based on the average value. The medical image display device according to any one of claims 1 to 3,
The personal information extraction unit calculates a distance between the extracted pixels, and extracts a plurality of pixels as a pixel group constituting one character based on the calculated distance between the pixels,
The medical information display device, wherein the personal information erasing unit erases the pixel group constituting a character from the medical image. The medical image display device according to claim 4,
The personal information extraction unit calculates a distance between the extracted characters, and extracts a plurality of characters as a character group constituting one character string based on the calculated distance between the characters,
The medical information display device, wherein the personal information erasure unit erases the character group constituting the character string from the medical image. The medical image display device according to any one of claims 1 to 5,
The medical information display device, wherein the personal information erasing unit changes a pixel value of a pixel extracted as the personal information to an average value of pixel values of surrounding pixels. A medical image display method comprising a display step of displaying a medical image,
A personal information extraction step for extracting, as personal information, pixels in which the result of calculating each pixel value at the same coordinate position between a plurality of medical images satisfies a predetermined condition;
A medical image display method comprising: a personal information erasing step of erasing the personal information from the medical image by changing a pixel value of a pixel extracted as the personal information.

Images