JP2007299163A - Medical image processor - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To easily collate a character recognition result of patient information included in a medical image inputted from modality as a character image with correct patient information, in a medical facility of having no retrieval system of the patient information. <P>SOLUTION: This medical information processor 2 performs image recognition processing of the character image indicating the patient information included in image data, by converting an inputted medical image signal into the image data of a predetermined form by an image input part 24, when inputting the medical image signal from the modality 1. When reading and inputting the patient information recorded on a consultation ticket of a patient or recorded on a paper medical chart, the character recognition result is collated with the inputted patient information, and when not coincident, the character recognition result is corrected by being substituted with the inputted character information. <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention relates to a medical image processing apparatus that recognizes a character represented by a character image included in a medical image and attaches the recognition result to the medical image.

  A CT (Computed Tomography) apparatus, an MRI (Magnetic Resonance Imaging) apparatus, an ultrasonic diagnostic apparatus, an endoscope apparatus, or the like that outputs a medical image by photographing a patient is output. The medical image includes a character image indicating patient information such as a patient ID and a patient name. Therefore, in the medical image processing apparatus, the character represented by the character image included in the medical image output from the modality is recognized, character information indicating the recognition result is attached to the medical image, and the image display apparatus, the image output apparatus, the image It is sent to the server.

In the medical image processing apparatus, whether the character recognition result is correct is determined by, for example, displaying the medical image and the character recognition result on the screen and visually confirming the user, as described in Patent Document 1, or As described in Patent Document 2, a database is searched using an ID or the like recognized from a character image as a key, and a character recognition result and information retrieved from the database are compared and collated.
JP 2005-100280 A JP 2002-269097 A

  However, as described in Patent Document 1, it takes time to visually confirm the character recognition result. Further, as described in Patent Document 2, in order to perform a search in a database using a patient ID as a key, a search system including a database including patient information is required, and a medical facility in which such a search system is not constructed Then, collation could not be performed and there was no choice but to confirm visually.

  An object of the present invention is to make it possible to easily collate a character recognition result of patient information included as a character image in a medical image input from a modality with correct patient information in a medical facility where a patient information search system is not constructed. That is.

In order to solve the above-mentioned problem, a medical image processing apparatus according to claim 1 is provided.
Character recognition means for extracting the character image from a medical image including a character image indicating patient information, recognizing the character represented by the character image, and outputting the recognition result as character information;
Patient information input means for reading the patient information from a recording medium on which the patient information of the patient to be imaged for the medical image is recorded and inputting character information corresponding to the patient information;
Collation means for collating the character recognition result by the character recognition means and the character information input by the patient information input means;
As a result of collation by the collation means, when the character recognition result and the character information input by the patient information input means do not match, a correction means for correcting the character recognition result;
Patient information supplementary information that accompanies the medical image with the character recognition result determined by the collating means to match the character information input from the patient information input means or the character recognition result corrected by the correction means Means,
It is characterized by having.

The invention according to claim 2 is the invention according to claim 1,
The correction means performs correction by replacing the character recognition result with character information input from the patient information input means.

The invention according to claim 3 is the invention according to claim 1,
Display means;
An input means for a user to perform an operation input,
The correction means displays the character recognition result and the character information input by the patient information input means in association with each other on the display means, accepts correction input of character information from the input means, and receives the character recognition The result is corrected by the character information corrected and input by the input means.

The invention according to claim 4 is the invention according to any one of claims 1 to 3,
The recording medium on which the patient information is recorded is an examination ticket,
The patient information input means is a card reader that reads patient information recorded on the examination ticket.

The invention according to claim 5 is the invention according to any one of claims 1 to 3,
The recording medium on which the patient information is recorded is a paper chart,
The patient information input means is an OCR device that reads patient information recorded on the paper chart.

  According to the first aspect of the present invention, since the character recognition result of the patient information included as the character image in the medical image is collated with the correct patient information read from the recording medium on which the patient information is recorded, the patient information search In a medical facility where a system is not constructed, it is possible to easily collate the character recognition result with the correct patient information, and to save the trouble of visually confirming the character-recognized patient information.

  According to the second aspect of the present invention, when the patient information whose character is recognized is incorrect as a result of collation, the character information whose character is recognized is replaced by the patient information read from the recording medium on which the patient information is recorded. Therefore, the patient information can be easily corrected without the user inputting characters.

  According to the third aspect of the invention, the user can make corrections while confirming the character recognition result and the patient information read from the recording medium on which the patient information is recorded.

  According to the invention described in claim 4, it is possible to collate the character recognition result of the patient information included as a character image in the medical image with the patient information recorded on the examination ticket.

  According to the fifth aspect of the present invention, the character recognition result of the patient information included as a character image in the medical image can be collated with the patient information recorded on the paper chart.

  Hereinafter, an embodiment of a medical image system 100 according to the present invention will be described with reference to FIGS. 1 to 5. However, the present invention is not limited to the illustrated example.

First, the configuration will be described.
FIG. 1 shows a system configuration example of the medical image system 100.
As shown in FIG. 1, a medical image system 100 includes a medical image processing device 2 connected to a modality 1, an image output device 3, an image display device 4, and an image server 5, which are a LAN (Local Area Network), a WAN ( Connected via a communication network N such as a Wide Area Network. The modality 1 is a device not compatible with the DICOM (Digital Image and Communications in Medicine) standard, which is a medical image and communication standard, and the image output device 3, the image display device 4, and the image server 5 conform to the DICOM standard. Device. Note that a plurality of modalities 1 may be provided.

Hereinafter, each device constituting the medical image system 100 will be described.
The modality 1 is an apparatus that images a patient and generates a medical image, such as an X-ray imaging apparatus, an ultrasonic diagnostic apparatus, an endoscopic diagnostic apparatus, or an MRI apparatus. Modality 1 is provided with an input unit such as a keyboard. When a patient inputs patient information such as a patient ID of a patient to be imaged and a patient name from the input unit by the photographer, it corresponds to the input patient information. A character image to be generated is generated, arranged at a predetermined position of the taken medical image, and synthesized. Then, an image signal of a medical image including a character image of patient information is output to the medical image processing apparatus 2. The arrangement position of the character image is set in advance to a position where the overlap with the subject region in the medical image is statistically small, such as the upper left and upper right of the medical image, for example. FIG. 2 shows an example of a medical image including a character image of patient information.

  The medical image processing apparatus 2 converts the medical image signal input from the modality 1 into DICOM format image data, recognizes patient information included as a character image in the image data, and converts the obtained patient information into image data. It is a device that is attached as supplementary information and output to the image output device 3, the image display device 4, the image server 5, and the like. The DICOM format image data has a header portion. In the header portion, incidental information regarding the image data is written.

FIG. 3 shows a functional configuration example of the medical image processing apparatus.
As shown in FIG. 3, the medical image processing apparatus 2 includes a CPU 21, an input unit 22, a display unit 23, an image input unit 24, a card reader 25, an OCR (Optical Character Reader) 26, a RAM 27, a storage unit 28, and a communication unit 29. Etc., and each part is connected by a bus 30.

  The CPU 21 reads out various programs such as system programs and processing programs stored in the storage unit 28 and expands them in the RAM 27, and executes various processes including the patient information collating process shown in FIG. 4 according to the expanded programs. To do.

  The input unit 22 is an input means for a user to perform an operation input, and includes a keyboard having cursor keys, numeric input keys, various function keys, and the like, and a pointing device such as a mouse, and is pressed by the keyboard. The operated key pressing signal and mouse operation signal are output to the CPU 21 as input signals.

  The display unit 23 includes a monitor such as a CRT (Cathode Ray Tube) or an LCD (Liquid Crystal Display), for example, and displays various screens according to instructions of a display signal input from the CPU 21.

  The image input unit 24 includes an I / F for connecting the modality 1 and the medical image processing apparatus 2 and inputting medical image signals such as video signals and digital image signals from the modality 1 to the medical image processing apparatus 2. The medical image signal input via the I / F is converted into DICOM format image data and output to the CPU 21.

  The card reader 25 functions as patient information input means, reads patient information recorded on a medical examination ticket constituted by an IC card, and outputs it to the CPU 21. In the present embodiment, the medical examination ticket is an IC card. However, when the medical examination ticket is composed of another recording medium, a reading device corresponding to the recording medium is provided. For example, in the case of a magnetic card, a card reader capable of reading the magnetic card is provided.

  The OCR 26 functions as a patient information input unit. The OCR 26 optically reads a paper chart, specifies characters described in the paper chart, and outputs character information (character code) of the specified characters to the CPU 21.

  The RAM 27 forms a work area for temporarily storing various programs, input or output data, parameters, and the like that can be executed by the CPU 21 read from the storage unit 28 in various processes that are executed and controlled by the CPU 21. For example, the RAM 27 temporarily stores the patient information read from the image storage area for temporarily storing image data, the character recognition result area for temporarily storing the character recognition result, the card reader 25 or the OCR 26 in the patient information collation process. A patient information area or the like to be stored is formed.

The storage unit 28 includes an HDD (Hard Disc), a semiconductor nonvolatile memory, or the like.
The storage unit 28 stores various programs including a system program executed by the CPU 21 and a patient information collation processing program.

The storage unit 28 has a character pattern image storage unit 281. The character pattern image storage unit 281 stores character information and a character pattern image representing a character of the character information in association with each other.
The functional configuration of the medical image processing apparatus 2 has been described above.

  The image output apparatus 3 is an apparatus that records and outputs an image on a transmissive recording medium (film) based on the image data input from the medical image processing apparatus 2. As the image output device 3, for example, a photothermal silver salt type imager that records a latent image by laser exposure to input image data and visualizes the latent image by thermal phenomenon processing can be applied.

  The image display device 4 is a terminal device such as a PC (Personal Computer) installed for the purpose of displaying image data of medical images distributed from the medical image processing device 2 or the image server 5 and performing diagnostic interpretation. .

  The image server 5 includes an image DB (Data Base), and stores the image data transmitted from the medical image processing apparatus 2 and its accompanying information in the image DB. In response to a request from the image display device 4, the image data is read from the image DB and distributed to the image display device 4.

Next, the operation will be described.
FIG. 4 shows patient information collation processing executed by the CPU 21. The process is a process realized by a software process in cooperation with the CPU 21 and the patient information collation process program stored in the storage unit 28.

  When the medical image signal from the modality 1 is input to the image input unit 24, the input medical image signal is converted into DICOM format image data and temporarily stored in the image storage area of the RAM 27 (step S1). Next, character recognition processing is performed on the image data of the input medical image (step S2: character recognition means).

  In the character recognition process, first, an image region that is predetermined as a region where a character image is located is extracted from the image data, and the image signal value of each pixel of the extracted image region is “0” according to a predetermined threshold value. ”Or“ 1 ”, and a character image is extracted from the binarized image, for example, by extracting the pixel“ 1 ”. Then, matching between the extracted character image and the character pattern image stored in the character pattern image storage unit 281 is performed, and as a result of the matching, characters in the matched character pattern image are recognized as characters represented by the character image. Then, the character information stored in the character pattern image storage unit 281 in association with the characters of the character pattern image is output as the character recognition result. The character recognition result output by the character recognition processing is stored in the character recognition result area of the RAM 27.

  Next, patient information of a patient who is a subject of imaging of the input medical image is input (step S3). For example, a user such as a radiographer or a doctor inserts an examination ticket for a patient to be imaged into the card reader 25. In the card reader 25, patient information recorded as character information on the examination ticket is read, output to the CPU 21, and stored in the patient information area of the RAM 27. Or a user reads the area | region where the patient information of the paper chart was recorded by OCR26. In the OCR 26, the patient information on the paper chart is optically read to identify character information corresponding to the patient information, and the identified character information is output to the CPU 21 and stored in the patient information area of the RAM 27.

  When the patient information is input, the character information stored in the character recognition result area and the character information stored in the patient information area are collated to determine whether or not they match ( Step S4: collating means). As a result of the collation, when it is determined that the two match (step S4; YES), the process proceeds to step S6. As a result of the collation, when it is determined that they do not match (step S4; NO), the character information in the character recognition result area is corrected by being replaced with the character information stored in the patient information area (step S5: correction). Means), the process proceeds to step S6.

  As described above, the correction of the character recognition result in step S5 is performed by the information input from the input unit 22 by the user, in addition to the replacement with the character information stored in the patient information area. Also good. For example, when it is determined in step S4 that they do not match, a correction screen in which the character recognition result and the input patient information are displayed in association with each other is displayed as shown in FIG. The correction input from the unit 22 may be received, and the character information of the character recognition result may be corrected to the character information input from the input unit 22. In this way, the user can make corrections while confirming the character recognition result and the patient information read from the examination ticket or paper chart.

  In step S6, the character information indicating the patient information is attached to the image data by writing the character information of the character recognition result area as the patient information in the header portion of the image data input in step S1 (step S6: Patient information supplementary means) is output to the image output device 3, the image display device 4, or the image server 5 via the communication unit 29 (step S7), and this processing is terminated.

  As described above, according to the medical image processing apparatus 2, when a medical image signal is input from the modality 1, the image input unit 24 converts the input medical image signal into image data of a predetermined format, Character recognition processing of a character image indicating patient information included in the image data is performed. When patient information recorded on a patient's examination ticket or recorded on a paper chart is read and input from the card reader 25 or OCR 26, the character recognition result and the input patient information are collated and matched. If not, correct the character recognition result by replacing it with the input character information. Then, the character recognition result or the corrected character information that matches the input character information is attached to the medical image data, and is output to the image output device 3, the image display device 4, or the image server 5 by the communication unit 29.

  Therefore, a patient information search system has been constructed since the result of character recognition of patient information included as a character image in a medical image input from a modality is collated with correct patient information recorded on a medical examination ticket or paper chart. It is possible to easily collate the character recognition result with correct patient information in a medical facility that does not, and to save time and effort to visually confirm the patient information that has been character-recognized. In addition, if the patient information recognized as a result of collation is not correct as a result of the verification, the character information recognized by the patient information read from the examination ticket or the paper chart is replaced, so that the user can easily input the characters. It is possible to correct patient information.

  In addition, the description content in the said embodiment is a suitable example of the medical image system 100 which concerns on this invention, and is not limited to this.

  For example, the medical image processing apparatus 2 is configured to include both the card reader 25 and the OCR 26, but may be configured to include only one of them.

  In addition, the detailed configuration and detailed operation of each apparatus constituting the medical image system 100 can be changed as appropriate without departing from the spirit of the present invention.

1 is a diagram illustrating an example of the overall configuration of a medical image system 100 according to the present invention. It is a figure which shows an example of the medical image containing the character image of patient information. It is a block diagram which shows the functional structure of the medical image processing apparatus 2 shown in FIG. It is a flowchart which shows the patient information collation process performed by CPU21. It is a figure which shows an example of the correction screen of a character recognition result.

Explanation of symbols

DESCRIPTION OF SYMBOLS 100 Medical image system 1 Modality 2 Medical image processing apparatus 3 Image output apparatus 4 Image display apparatus 5 Image server N Communication network 21 CPU
22 Input unit 23 Display unit 24 Image input unit 25 Card reader 26 OCR
27 RAM
28 Storage Unit 281 Character Pattern Image Storage Unit 29 Communication Unit 30 Bus

Claims (5)

Character recognition means for extracting the character image from a medical image including a character image indicating patient information, recognizing the character represented by the character image, and outputting the recognition result as character information;
Patient information input means for reading the patient information from a recording medium on which the patient information of the patient to be imaged for the medical image is recorded and inputting character information corresponding to the patient information;
Collation means for collating the character recognition result by the character recognition means and the character information input by the patient information input means;
As a result of collation by the collation means, when the character recognition result and the character information input by the patient information input means do not match, a correction means for correcting the character recognition result;
Patient information supplementary information that accompanies the medical image with the character recognition result determined by the collating means to match the character information input from the patient information input means or the character recognition result corrected by the correction means Means,
A medical image processing apparatus comprising:   The medical image processing apparatus according to claim 1, wherein the correction unit performs correction by replacing the character recognition result with character information input from the patient information input unit. Display means;
An input means for a user to perform an operation input,
The correction means displays the character recognition result and the character information input by the patient information input means in association with each other on the display means, accepts correction input of character information from the input means, and receives the character recognition The medical image processing apparatus according to claim 1, wherein the result is corrected by character information corrected and input by the input unit. The recording medium on which the patient information is recorded is an examination ticket,
The medical image processing apparatus according to claim 1, wherein the patient information input unit is a card reader that reads patient information recorded on the examination ticket. The recording medium on which the patient information is recorded is a paper chart,
The medical image processing apparatus according to any one of claims 1 to 3, wherein the patient information input unit is an OCR apparatus that reads patient information recorded on the paper chart.

Images