JP2012194928A - Information providing program, information providing device and information providing method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide easy-to-understand information about the situation of an object to a person to whom the information is provided.SOLUTION: A read image P1 is a target image of image reading and an image of an object. Observation document data Dt is document data of observation for the read image P1. Explanation document data Dv is document data converted from explanation voice data of an explanation for the read image P1. Here, a medical term in the observation document data Dt is converted into a general term. Then, from character strings in the observation document data Dt after conversion, a character string that matches a character string in the explanation document data Dv is extracted. The extracted matching character string is printed in the column of a keyword provided on the read image P1 and output as a read image for patient P2. Thus, the read image for patient P2 attached with the general term is created.

Description

  The present invention relates to an information providing program, an information providing apparatus, and an information providing method.

  In a medical institution, a doctor in a medical department may perform a diagnosis based on a captured image of a subject such as a patient that is interpreted by an interpreting doctor and a finding that is a result of interpreting the captured image by the interpreting doctor. Hereinafter, a captured image that is interpreted by an interpreting doctor is referred to as an interpretation image. In addition, since there are a large number of interpretation images, the interpretation doctor designates an image among the interpretation images that the doctor in the medical department should pay particular attention to. The specified image is called the specified image. For example, the doctor makes a diagnosis with reference to the designated image and the findings, and explains the diagnosis result to the patient and the patient concerned. On the other hand, a technique for outputting an interpretation image together with a character string of findings input by an interpretation doctor is disclosed.

JP 2007-72649 A

  Here, from the viewpoint of informed consent or the like, it is conceivable that a doctor provides a part of a captured image (designated image or the like) to a patient or the like, for example. Then, by providing the findings along with the photographed image, the patient is informed of the test result. However, there is a problem that the recipient may not be able to read information on the state of the subject from the provided captured image. For example, since the findings are created for medical personnel such as doctors and nurses, medical terms may be used. In this case, a recipient who lacks knowledge about medical terms may not understand the findings contained in the provided interpretation image.

  The present invention provides an information providing program, an information providing apparatus, and an information providing method capable of providing easy-to-understand information about the state of a subject to a recipient in order to solve the above-described problems caused by the prior art. Objective.

  In order to solve the above-described problems and achieve the object, according to one aspect of the present invention, an image of a subject, document data indicating findings input to the image, and audio data for the image are audio. The description document data converted by recognition is acquired, and the character string included in the acquired document data is obtained by referring to the conversion master in which the character string is associated with another character string related to the character string. Is converted into the other character string, the converted document data is compared with the explanatory document data, a matching character string is extracted, and the extracted matching character string is output together with the image A providing program, an information providing apparatus, and an information providing method are proposed.

  According to one aspect of the present invention, it is possible to provide easy-to-understand information about the state of a subject to a recipient.

FIG. 1 is an explanatory diagram (part 1) of an example of providing information according to the first embodiment. FIG. 2 is an explanatory diagram (part 2) of the information providing example according to the first embodiment. FIG. 3 is an explanatory diagram (part 3) of an information providing example according to the first embodiment. FIG. 4 is an explanatory diagram (part 4) of an example of providing information according to the first embodiment. FIG. 5 is an explanatory diagram of an example of the information providing system according to the first embodiment. FIG. 6 is a block diagram of a hardware configuration example of the attending medical terminal according to the first embodiment. FIG. 7 is an explanatory diagram showing an example of the contents stored in the conversion master. FIG. 8A is an explanatory diagram (part 1) of an example of the contents stored in the electronic medical record DB. FIG. 8-2 is an explanatory diagram (part 2) of an example of the contents stored in the electronic medical record DB. FIG. 9 is an explanatory diagram showing an example of the contents stored in the finding DB. FIG. 10 is an explanatory diagram illustrating an example of tag information of image data. FIG. 11 is an explanatory diagram showing a display example of the display of the attending medical terminal. FIG. 12 is a block diagram showing a functional configuration of the attending medical terminal. FIG. 13 is a flowchart of an example of an information providing process procedure of the attending medical terminal according to the first embodiment. FIG. 14 is an explanatory diagram (part 1) of an example of providing information according to the second embodiment. FIG. 15 is an explanatory diagram (part 2) of an example of providing information according to the second embodiment. FIG. 16 is an explanatory diagram illustrating an example of explanatory document data according to the second embodiment. FIG. 17 is a flowchart of an example of an information providing process procedure of the attending medical terminal according to the second embodiment.

  Exemplary embodiments of an information providing program, an information providing apparatus, and an information providing method according to the present invention will be described below in detail with reference to the accompanying drawings.

<Embodiment 1>
First, Embodiment 1 of an information providing program, an information providing apparatus, and an information providing method according to the present invention will be described. In the first embodiment, an interpretation image to which a character string explained in plain expression by a doctor is added among the character strings of the findings of the interpretation image is output. Thereby, it is possible to provide easy-to-understand information about the state of the subject to the recipient who is provided with the interpretation image.

(Information provision example)
1 to 4 are explanatory diagrams illustrating examples of providing information according to the first embodiment. 1 to 4, a patient interpretation image P2 provided to a patient is created from the interpretation image P1, the finding document data Dt, and the explanation document data Dv.

  An output example of the patient interpretation image P2 will be described with reference to FIG. In FIG. 1, a description will be given of a process until an interpretation image to which a word explained in a plain expression by a doctor is added among the words in the findings of the interpretation image is output.

  The interpretation image P1 is an image to be interpreted, and is a living body image that is a subject. The subject (living body) may be a person or an animal other than a person. The interpretation image P1 is a CT (Computed Tomography) image of a person's abdomen, but is not limited to this. For example, an MRI (Magnetic Resonance Image) image or an RI (Radioisotope) image may be used. Further, the imaging target region is not limited to the body, and may be, for example, the skin. The interpretation image P1 may be a flat image or a stereoscopic image. The interpretation image P1 is a designated image designated by an interpretation doctor.

  The finding document data Dt is the finding document data for the interpretation image P1. The findings are, for example, diagnosis or opinion by an interpreting doctor on the interpretation image P1. Medical terms are mainly used in the character string of the observation document data Dt. Medical terms include, for example, “colon”, “pathological significance”, “ascites”, “schatten”, and the like.

  The explanation document data Dv is document data converted from the explanation voice data for the interpretation of the interpretation image P1. The explanation for the interpretation image P1 is, for example, an oral explanation from the attending physician to the patient with reference to the interpretation image P1 and the finding document data Dt. Further, for example, the explanation for the interpretation image P1 is an explanation of the patient's condition and symptoms. General terms are mainly used in the character string of the explanatory document data Dv. Common terms are preferred for patients because they are simpler than medical terms. For example, common terms include “large intestine”, “small intestine”, “medicine”, “meal”, and the like.

  Here, an example of a process until the patient interpretation image P2 in FIG. 1 is output will be described. First, medical terms in the finding document data Dt are converted into general terms. For example, the medical term “colon” is converted to the general term “colon” which is synonymous with “colon”. Next, a matching character string that matches the character string of the explanatory document data Dv is extracted from the character string of the converted finding document data Dt. For example, “colon” is extracted as the matching character string.

  Then, the extracted matching character string is attached to the keyword column provided in the interpretation image P1, and is output as a patient interpretation image P2. At this time, the position to which the matching character string is attached may be in the image data including the interpretation image P1, and is not limited to the interpretation image P1. In the example of FIG. 1, the patient interpretation image P2 with the matching character string attached on the interpretation image P1 is output. However, the present invention is not limited to this. For example, the document data of the matching character string and the interpretation image P1. The image data may be output as different data. In this way, the patient interpretation image P2 to which explanations in general terms relating to the interpretation image P1 are added is output.

  Next, an output example of the patient interpretation image P2 including the position information of the part will be described with reference to FIG. In FIG. 2, an interpretation image in which a part name word explained in a plain expression by a doctor, together with position information of the part, is output among the words of the part name in the findings of the interpretation image. The process up to will be described.

  In the interpretation image P1, the name of the part of the subject included in the interpretation image P1 and the position information of the part in the interpretation image P1 are associated. Medical terms are mainly used for the names of the parts. For example, the names of the parts are “colon”, “stomack”, “kidney”, and the like. The position information of the part is, for example, position information based on coordinates with a predetermined position of the interpretation image as an origin. Specifically, for example, in the interpretation image P1, a plane coordinate composed of the X axis and the Y axis is set with the point P0 as the origin, and the position information of X = X1 and Y = Y1 is set in the “colon”. Associated.

  Here, an example of a process until the patient interpretation image P2 in FIG. 2 is output will be described. The process until the matching character string is extracted is the same as the process shown in FIG. When the character string of the medical term corresponding to the matched character string is a part name, the position information of the part corresponding to the name is extracted. The extracted matching character string is attached so as to indicate the position on the interpretation image P1 corresponding to the position information, and is output as the patient interpretation image P2. In this way, the patient interpretation image P2 to which the explanation in general terms relating to the interpretation image P1 and the position information are added is output.

  Next, an output example of the patient interpretation image P2 including findings in medical terms and general terms will be described with reference to FIG. In FIG. 3, among the words of the part names in the findings of the interpretation image, the part name words explained in plain expression by the doctor and the part name words in the findings together with the position information of the parts A process until the added interpretation image is output will be described.

  Here, an example of a process until the patient interpretation image P2 in FIG. 3 is output will be described. The process until the matching character string is extracted is the same as the process shown in FIG. The extracted matching character string and the character string of the finding document data Dt corresponding to the matching character string are output together with the interpretation image P1. In this way, the patient interpretation image P2 to which findings based on medical terms and general terms are added is output, and the recipient can understand the correspondence between the medical terms and the general terms.

  Next, with reference to FIG. 4, an output example of the patient interpretation image P2 including the findings by text will be described. In FIG. 4, a description will be given of a process until an interpretation image to which a character string of a sentence explained in a plain expression by a doctor is added among sentence character strings in the findings of the interpretation image P <b> 1 is output.

  The character string of the observation document data Dt includes a sentence using medical terms. In addition, the character string of the explanatory document data Dv includes a sentence using general terms.

  Here, an example of a process until the patient interpretation image P2 in FIG. 4 is output will be described. First, medical terms in a character string in the finding document data Dt are converted into general terms. For example, the medical term “colon” is converted to the general term “colon” which is synonymous with “colon”. Similarly, the medical term “ascites” is synonymous with “ascites” and the general term “shadow”, and the medical term “pathological significance” is synonymous with “pathological significance”. Each is converted to the term “abnormal”.

  Next, a matching sentence that matches the sentence of the character string of the explanatory document data Dv is extracted from the sentence of the character string of the finding document data Dt after conversion. At that time, specifically, for example, a sentence in which the subject, the predicate, and the modifier match is extracted. For example, “having a shadow in the large intestine but no abnormality” is extracted as a matching sentence.

  When the name of a part is included in the character string of the medical term corresponding to the matching sentence, the position information of the part corresponding to the name is extracted. Then, the extracted matching sentence and position information are output together with the interpretation image P1. In this way, the patient interpretation image P2 to which the explanatory text in general terms relating to the interpretation image P1 is added is output.

(Example of information provision system)
FIG. 5 is an explanatory diagram of an example of the information providing system according to the first embodiment. In FIG. 5, an information providing system 500 includes an attending medical terminal 510, an electronic medical record server 520, an interpretation medical terminal 530, and an interpretation medical system 540, including the Internet, a LAN (Local Area Network), and a WAN (Wide Area Network). Or the like via a network 550.

  The attending physician terminal 510 is a computer operated by the attending physician. The attending medical terminal 510 includes a voice input device 511 and a conversion master 512. The voice input device 511 is a device that inputs voice and transmits the input voice to the primary medical terminal 510 as voice data. Further, when acquiring the voice data from the voice input device 511, the attending medical terminal 510 transmits the voice data to the electronic medical record server 520. The conversion master 512 is a table in which rules used for converting medical terms into general terms are stored. Details of the conversion master 512 will be described later with reference to FIG.

  The electronic medical record server 520 has an electronic medical record DB 521. The electronic medical record DB 521 stores a digitalized medical record for each patient ID. Patient ID is an identification number set for each patient. In the electronic medical record DB 521, the explanation voice data transmitted from the attending medical terminal 510 is converted into explanation document data Dv and stored. Specifically, the electronic medical record server 520 converts the explanatory voice data into the explanatory document data Dv by the voice recognition function, and stores it in the electronic medical chart DB 521. Details of the electronic medical record DB 521 will be described later with reference to FIGS.

  Interpretation medical terminal 530 is a computer operated mainly by an interpreting physician. The interpretation doctor is a doctor who creates a finding on the interpretation image P1 taken in response to a request from the attending physician. The interpretation medical terminal 530 creates the finding document data Dt by inputting a character string from the interpretation doctor, for example.

  The interpretation medical system 540 includes an interpretation medical server 541 and an imaging device 542. The interpretation medical server 541 has an interpretation medical system DB 543. Examples of the imaging device 542 include CT equipment, MRI equipment, RI equipment, and the like. This imaging device 542 is operated by, for example, a radiologist who has received a request from an interpreting doctor.

  The interpretation medical system DB 543 includes an image DB 544 and an observation DB 545. In the image DB 544, image data photographed by the photographing device 542 is stored together with additional information (tag information). The tag information is, for example, the name of the part of the subject included in the image data, the position information of the part, and the like. Details of the tag information will be described later with reference to FIG.

  The finding DB 545 stores the finding document data Dt created by the interpretation medical terminal 530 in association with the order number. The order number is a unique number that is set when an imaging request is created by the attending physician. Details of the finding DB 545 will be described later with reference to FIG.

  In the information providing system 500, when the primary medical terminal 510 receives an output request for the patient interpretation image P2, the primary medical terminal 510 performs the following processing. First, the attending physician's terminal 510 acquires the image data of the interpretation image P1 and the finding document data Dt from the image DB 544 and the finding DB 545.

  Specifically, for example, the attending medical terminal 510 transmits an acquisition request for image data and finding document data Dt together with the order number to the electronic medical record server 520. The electronic medical record server 520 that has received the order number and the acquisition request acquires the image data and the finding document data Dt from the interpretation medical server 541 by outputting the order number and the acquisition request to the interpretation medical server 541. Then, the attending medical terminal 510 acquires image data and finding document data Dt from the electronic medical record server 520.

  Next, the attending medical terminal 510 obtains the explanatory document data Dv from the electronic medical record DB 521. Specifically, for example, the attending medical terminal 510 acquires the explanatory document data Dv from the electronic medical record DB 521 by transmitting an acquisition request for the explanatory document data Dv together with the order number to the electronic medical record server 520. Then, the attending medical terminal 510 refers to the conversion master 512 and converts the medical term in the character string of the acquired finding document data Dt into a general term. For example, in the example shown in FIGS. 1 to 4, the medical term “colon” is converted to the general term “colon”.

  Thereafter, the attending medical terminal 510 compares the finding document data Dt converted into general terms with the explanation document data Dv, and among the character strings of the converted finding document data Dt, the character string of the explanation document data Dv. The matching character string that matches is extracted. At this time, if there is a matching sentence that matches the sentence of the character string of the explanatory document data Dv among the converted text of the finding document data Dt, the attending medical terminal 510 extracts the matching sentence.

  At that time, the attending medical terminal 510 converts medical terms in the character string of the explanatory document data Dv into general terms, and compares the converted explanatory document data Dv with the converted finding document data Dt. It is good to do.

  Then, when the matching character string is the name of the part, the attending medical terminal 510 extracts position information corresponding to the part based on the tag information added to the image data. Specifically, for example, the attending medical terminal 510 determines whether or not there is a word that matches the matching character string in the name of the part stored as the tag information, and if there is a matching word, Position information associated with the matching word is extracted from the image data. The attending medical terminal 510 outputs the extracted matched character string and position information together with the acquired image data. Here, examples of the output destination include a display, a printer, and a memory.

(Hardware configuration example of primary medical doctor terminal 510)
FIG. 6 is a block diagram of a hardware configuration example of the attending medical terminal according to the first embodiment. In FIG. 6, the attending medical terminal 510 includes a CPU (Central Processing Unit) 601, a ROM (Read-Only Memory) 602, a RAM (Random Access Memory) 603, a magnetic disk drive 604, a magnetic disk 605, and an optical disk. A drive 606, an optical disk 607, and an I / F (Interface) 608 are provided. Each component is connected by a bus 600.

  Here, the CPU 601 controls the entire medical doctor terminal 510. The ROM 602 stores programs such as a boot program. The RAM 603 is used as a work area for the CPU 601. The magnetic disk drive 604 controls the reading / writing of the data with respect to the magnetic disk 605 according to control of CPU601. The magnetic disk 605 stores data written under the control of the magnetic disk drive 604.

  The optical disk drive 606 controls the reading / writing of the data with respect to the optical disk 607 according to control of CPU601. The optical disk 607 stores data written under the control of the optical disk drive 606, and causes the computer to read data stored on the optical disk 607.

  An interface (hereinafter abbreviated as “I / F”) 608 is connected to a network 550 such as a LAN (Local Area Network), a WAN (Wide Area Network), and the Internet through a communication line, and the other via the network 550. Connected to other devices. The I / F 608 controls an internal interface with the network 550 and controls input / output of data from an external device. For example, a modem or a LAN adapter can be used as the I / F 608.

  Next, the contents stored in the conversion master 512 will be described. The conversion master 512 is realized by a storage device such as the ROM 602 of the medical doctor terminal 510 shown in FIG. 6, the RAM 603, the magnetic disk 605, and the optical disk 607, for example.

(Storage contents of conversion master 512)
FIG. 7 is an explanatory diagram showing an example of the contents stored in the conversion master. In FIG. 7, the conversion master 512 has fields for a post-conversion character string and a pre-conversion character string. By setting information in each field, conversion characteristic data 513-1 to 513-n are stored as records.

  Here, the converted character string is a character string of general terms. The pre-conversion character string is a synonym for the post-conversion character string and is mainly a medical term. Further, the pre-conversion character string may be a language different from the language in the post-conversion character string as long as it is a synonym for the post-conversion character string. For example, the pre-conversion character string may include an English or German character string, and the post-conversion character string may include a Japanese character string. By referring to the conversion master 512, the attending medical terminal 510 converts the pre-conversion character string from the pre-conversion character string to the post-conversion character string when the character strings of the observation document data Dt and the explanation document data Dv are included. Convert.

  As an example, when the conversion characteristic data 513-1 is taken as an example, a post-conversion character string “shadow”, a pre-conversion character string “covered”, “shadow”, “Schatten”, and “Schatten” are stored. That is, by referring to the conversion master 512, the attending medical terminal 510 converts “covered water”, “shadow”, “Shatten”, and “Schatten” in the character strings of the finding document data Dt and the explanatory document data Dv to “shadow”. Convert to

  Next, the contents stored in the electronic medical record DB will be described with reference to FIGS. 8A and 8B. The electronic medical record DB is realized by a storage device such as a ROM, a RAM, a magnetic disk, and an optical disk of the electronic medical record server 520, for example.

(Storage contents of electronic medical record DB 521)
8A and 8B are explanatory diagrams illustrating an example of the contents stored in the electronic medical record DB. 8A and 8B, the electronic medical record DB 521 includes fields for patient ID, name, sex, age, order number, imaging content, finding pointer, image pointer, and description content. By setting information in each field, electronic medical record characteristic data 522-1 to 522-m is stored as a record.

  Here, the name is the patient's full name. The sex is a type representing the sex of the patient. Age is a numerical value indicating the number of years that have passed since the patient was born. The imaging content is the content of the imaging request by the attending physician, and includes, for example, an imaging location and an imaging method. An imaging | photography location shows the position and site | part which image | photographed the patient, and, specifically, is a head, a chest, an abdomen, etc., for example. The imaging method indicates the type of imaging method, such as CT or MRI. The patient ID, name, age, order number, and imaging content are issued, for example, when the primary medical terminal 510 receives an imaging request from the primary physician, and is received by the electronic medical record server 520 from the primary medical terminal 510.

  The finding pointer indicates an address in the interpretation medical system DB 543 in which the finding document data Dt corresponding to the order number is stored. When receiving an acquisition request for finding document data Dt from the attending medical terminal 510, the electronic medical record server 520 acquires the finding document data Dt from the interpretation medical server 541 with reference to the finding pointer. Then, the electronic medical record server 520 transmits the acquired finding document data Dt to the attending medical terminal 510. The finding pointer is transmitted from the interpretation medical server 541 to the electronic medical record server 520 and stored when the finding document data Dt is stored by the interpretation medical server 541.

  The image pointer indicates an address in the interpretation medical system DB 543 in which image data corresponding to the order number is stored. When receiving an image data acquisition request from the attending medical terminal 510, the electronic medical record server 520 acquires image data from the interpretation medical server 541 with reference to the image pointer. Then, the electronic medical record server 520 transmits the acquired image data to the attending medical terminal 510. The image pointer is transmitted from the interpretation medical server 541 to the electronic medical record server 520 and stored when the image data is stored by the interpretation medical server 541. The explanation content is a character string of the explanation document data Dv.

  As an example, taking electronic medical record characteristic data 522-1 as an example, patient ID “000000001”, name “Tokyo Kyoko”, gender “female”, age “54”, order number “# 000000001”, photographing content “abdomen, CT ”, finding pointer“ s / 2011/2/1 / ct / # 1 ”, image pointer“ g / 2011/2/1 / ct / # 1 ”, explanation“ today, left chest, uterus and ureter A shadow was seen on the left chest from the image taken, but it is harmless, so there is no anomaly. ing.

  Next, the contents stored in the finding DB 545 will be described. The findings DB 545 is realized by a storage device such as a ROM, a RAM, a magnetic disk, and an optical disk of the interpretation medical server 541, for example.

(Contents stored in the finding DB 545)
FIG. 9 is an explanatory diagram showing an example of the contents stored in the finding DB. In FIG. 9, the finding DB 545 includes fields for order numbers and finding contents. By setting information in each field, the observation characteristic data 900-1 to 900-l are stored as records.

  Here, the order number is stored when the findings are written by the interpretation medical terminal 530. The finding content is a character string of finding document data Dt stored for each order number. The findings are stored when the findings DB 545 receives the findings document data Dt from the interpretation medical terminal 530.

  As an example, taking the case characteristic data 900-1 as an example, order number “# 000000001”, findings “1) No abnormality in the kidneys and ureters. 2) There is a small amount of ascites in the left chest. Is not stored. "

  Next, an example of tag information of image data stored in the image DB 544 will be described. The image DB 544 is realized by a storage device such as a ROM, a RAM, a magnetic disk, or an optical disk of the interpretation medical server 541, for example.

(Tag information of image data)
FIG. 10 is an explanatory diagram illustrating an example of tag information of image data. In FIG. 10, the tag information 1000 has items set for each tag, and information corresponding to the items is stored. For example, the tag information 1000 includes information on items such as an order number, a series instance UID, an inspection instance UID, an inspection part, and a name (position).

  The series instance UID is an identification number set for each image data. The inspection instance UID is an identification number for each group grouped from a plurality of image data. The examination region is a region to be imaged, and includes, for example, the head, chest, and abdomen. The name (position) indicates the name of the part included in the image and its position information. For example, when the name (position) is a colon (x43 / y53), it indicates that the position of X = 43 and Y = 53 in the coordinates provided in the image is a colon. The name (position) information is, for example, information that is referred to when the patient interpretation image P2 is output by the attending medical terminal 510. Further, the name (position) information is determined by, for example, analyzing color shading when image data is created.

(Display example of the display of the attending doctor's terminal 510)
FIG. 11 is an explanatory diagram showing a display example of the display of the attending medical terminal. A display example 1100 shown in FIG. 11 is an image displayed on the display (not shown) of the attending medical terminal 510 when the attending medical terminal 510 acquires the finding document data Dt.

  The display example 1100 includes an image button 1101. For example, the attending medical terminal 510 receives an operation on the mouse while the cursor is positioned on the image button 1101, thereby obtaining an order number corresponding to the displayed observation document data Dt and an image data acquisition request from the electronic medical record server. Output to 520. Then, the attending medical terminal 510 outputs the image data acquired from the electronic medical record server 520 to the display.

  Further, the display example 1100 includes photographing information such as reception time, photographing room, examination name, instruction item, photographing direction, film, number of divisions, and observation character string. The attending physician gives an explanation to the patient with reference to, for example, image data, imaging information, and finding character strings. At this time, the attending medical terminal 510 creates explanatory voice data.

(Functional configuration example of primary medical doctor terminal 510)
Next, a functional configuration example of the attending medical doctor terminal 510 will be described. FIG. 12 is a block diagram showing a functional configuration of the attending medical terminal. The attending medical terminal 510 includes an acquisition unit 1201, a conversion unit 1202, a character string extraction unit 1203, an output unit 1204, and a position extraction unit 1205. Specifically, the functions (acquisition unit 1201 to position extraction unit 1205) serving as the control unit are, for example, programs stored in a storage device such as the ROM 602, the RAM 603, the magnetic disk 605, and the optical disk 607 illustrated in FIG. The function is realized by causing the CPU 601 to execute it or by using the I / F 608.

  The acquisition unit 1201 acquires an image of a subject, document data of findings for the image, and explanatory document data Dv converted from audio data for the image. The subject image is, for example, an interpretation image P1. The document data of findings on the image is, for example, the above-described finding document data Dt. The audio data for the image is, for example, the explanation audio data described above. For example, the acquisition unit 1201 acquires the interpretation image P1, the observation document data Dt, and the explanation document data Dv described above with reference to FIGS.

  Specifically, for example, the acquisition unit 1201 transmits each data to a terminal in which an image of a subject, document data of findings for the image, and explanatory document data Dv converted from audio data for the image are registered. Each data is acquired by sending an acquisition request. In the first embodiment, the acquisition unit 1201 transmits an acquisition request to the electronic medical record server 520, whereby the image of the subject, the document data of the findings regarding the image, and the explanatory document data Dv converted from the audio data of the image. And get.

  Further, the acquisition unit 1201 acquires the explanatory document data Dv converted from the voice data by the electronic medical record server 520, but is not limited thereto. For example, the acquisition unit 1201 may acquire the explanatory document data Dv converted from the voice data by the interpretation medical terminal 530 or the interpretation medical server 541. For example, the acquisition unit 1201 may acquire the explanatory document data Dv converted from the audio data by the attending medical terminal 510.

  The conversion unit 1202 refers to the conversion master in which the character string is associated with another character string related to the character string, and converts the character string included in the document data acquired by the acquisition unit 1201 to the other character. Convert to column. The character string is a medical term in the first embodiment. Further, the other character strings related to the character string are general terms that are synonymous with medical terms in the first embodiment. Further, the character string and other character strings related to the character string may be in different languages. The conversion master is a master in which a character string is associated with another character string related to the character string, for example, the conversion master 512 described above. For example, the conversion unit 1202 converts the medical term “colon” into the translated word “colon” as described above with reference to FIGS. Further, for example, as described above with reference to FIG. 4, the conversion unit 1202 converts the medical term “colon” into the translated word “colon”, the medical term “ascites” into the translated word “shadow”, and the medical term “ “Pathological significance” is converted into “abnormality” in the translation.

  The character string extraction unit 1203 extracts a matching character string that matches the character string of the explanatory document data Dv from the character strings of the document data of the findings after conversion by the conversion unit 1202. Specifically, for example, the character string extraction unit 1203 extracts the matching character string by comparing the character string of the finding document data Dt and the character string of the explanatory document data Dv. For example, as described above with reference to FIGS. 1 to 3, the character string extraction unit 1203 extracts “colon” as a matching character string.

  The output unit 1204 outputs the matching character string extracted by the character string extraction unit 1203 together with the image. Specifically, for example, the output unit 1204 outputs the matching character string and the interpretation image P1 to a printer, a storage medium, a display, or the like. That is, the output unit 1204 outputs the patient interpretation image P2. For example, as described above with reference to FIGS. 1 to 4, the output unit 1204 outputs the matching character string together with the interpretation image P1 as the patient interpretation image P2.

  In addition, the patient interpretation image P2 that is output is provided to the patient, but is not limited thereto, and may be provided to, for example, a patient concerned. Further, when the subject of the interpretation image P1 is a pet, the patient interpretation image P2 may be provided to the owner of the subject pet.

  The acquisition unit 1201 also includes image data in which the subject image, the name of the part of the subject included in the image, and the position information of the part in the image are associated with each other, the document data of the findings for the image, and the audio data for the image It is good also as acquiring the description document data Dv converted from (1). The image data is the image and tag information in the first embodiment. For example, the acquisition unit 1201 acquires the interpretation image P1, the observation document data Dt, the description document data Dv, and the position information described above with reference to FIGS.

  The position extraction unit 1205 extracts position information corresponding to the matching character string based on the document data and image data of the findings before conversion by the conversion unit 1202. Specifically, for example, the position extraction unit 1205 extracts position information corresponding to the name of the part included in the character string of the document data of the finding before conversion as position information corresponding to the matching character string. For example, the position extraction unit 1205 extracts X = X1 and Y = Y1 as position information corresponding to one character string described above with reference to FIGS.

  The output unit 1204 outputs the position information corresponding to the matching character string and the matching character string together with the image. Specifically, for example, the output unit 1204 outputs the matching character information so as to display the position of the part on the image. For example, as described above with reference to FIGS. 2 to 4, the output unit 1204 outputs position information and one character string of X = X1, Y = Y1. Further, the output unit 1204 may output the matching character string and the position information together with the image so as to be expressed as a character string.

  Further, the character string extraction unit 1203 extracts a character string of a sentence that matches the character string of the explanatory document data Dv from the character strings of the document data of the findings converted into translated words by the conversion unit 1202. Specifically, for example, the character string extraction unit 1203 extracts a character string in which the subject, the predicate, and the modifier match. For example, as described above with reference to FIG. 4, the character string extraction unit 1203 extracts “the large intestine has a shadow but no abnormality” as a matched character string. Then, the output unit 1204 outputs the character string of the sentence extracted by the character string extraction unit 1203 together with the image acquired by the acquisition unit 1201. For example, as described above with reference to FIG. 4, the output unit 1204 outputs “There is a shadow in the large intestine but there is no abnormality” together with the interpretation image P1.

  In addition, although the attending medical terminal 510 includes each unit (acquisition unit 1201 to position extraction unit 1205), the present invention is not limited to this. For example, the electronic medical record server 520, the interpretation medical terminal 530, or the interpretation medical server 541 may have each unit.

(File information provision processing procedure of the attending physician's terminal 510)
FIG. 13 is a flowchart of an example of an information providing process procedure of the attending medical terminal according to the first embodiment. The information providing process is a process executed by the CPU 601. In the information providing process, the attending medical terminal 510 first determines whether or not an output request for the patient interpretation image P2 has been received from the user (step S1301), and if not received (step S1301: No), waits until it is received. .

  In step S1301, when an output request for the patient interpretation image P2 is received from the user (step S1301: Yes), the acquisition unit 1201 acquires image data of the interpretation image P1 (step S1302). Then, the finding document data Dt is obtained by the obtaining unit 1201 (step S1303). Thereafter, the conversion unit 1202 refers to the conversion master 512 to convert the medical term of the character string of the acquired finding document data Dt into a general term (step S1304).

  Thereafter, the acquisition unit 1201 acquires the description document data Dv (step S1305), and the conversion unit 1202 converts the character string of the description document data Dv into a general term with reference to the conversion master 512 (step S1305). S1306). Then, the character string extraction unit 1203 compares the character string of the finding document data Dt converted in step S1304 with the character string of the explanatory document data Dv converted in step S1306 (step S1307).

  Then, the character string extraction unit 1203 determines whether there is a sentence that matches the character string of the finding document data Dt converted in step S1304 and the character string of the explanatory document data Dv converted in step S1306. (Step S1308). If there is a matching sentence (step S1308: Yes), the character string extraction unit 1203 extracts the matching sentence (step S1309).

  Thereafter, the character string extraction unit 1203 extracts words that match the character string of the finding document data Dt converted in step S1304 and the character string of the explanatory document data Dv converted in step S1306 (step S1310). In that case, when performing step S1310 via step S1309, the character string extraction unit 1203 extracts a matching word from a character string not extracted as a sentence. If it is determined in step S1308 that there is no matching sentence (step S1308: No), the attending medical terminal 510 proceeds to step S1310.

  Thereafter, the position extraction unit 1205 extracts position information for the extracted character string (step S1311). Then, the output unit 1204 outputs the extracted character string and position information to the printer or memory together with the image data, that is, outputs the patient interpretation image P2 (step S1312), and ends the series of processing according to this flowchart. To do.

  According to the medical doctor terminal 510 according to the first embodiment described above, among the general terms converted from the medical terms of the character string of the finding document data Dt, the matching character string that matches the explanatory document data Dv is interpreted. It can be output together with the image P1. That is, it is possible to output the patient interpretation image P2 to which the character string explained in a plain expression by the doctor among the character strings of the finding document data Dt is added. As a result, the recipient who has been provided with the patient interpretation image P2 can easily read the information contained in the patient interpretation image P2 even if he / she lacks knowledge of medical terms.

  Here, when all the findings data are provided to the patient, the amount of information provided to the patient becomes enormous. Usually, the findings input by the interpretation doctor are because various interpretation results are described. When all the explanatory document data is provided to the patient, the amount of information to be provided becomes enormous, and the explanatory document data also reflects questions and answers and voices about other topics. When the explanatory document data is enormous, it is difficult for the patient to determine which part is important.

  On the other hand, in the present embodiment, it is possible to specify a portion common to both by using the converted finding document data and the explanation document data. That is, the common part is a part used for the observation and the explanation voice, and the part that is assumed to be important can be provided to the patient. Therefore, by providing a character string common to both images together with the image, it is possible to help the patient understand the test result.

  Further, according to the attending medical terminal 510, it is possible to output the matching character string and the position information of the part included in the matching character string together with the interpretation image P1. That is, the attending physician terminal 510 can output a patient interpretation image P2 to which a part explained by a doctor in plain expression and position information of the part are added. As a result, the recipient can easily understand the name and position of the part even if he / she lacks knowledge of medical terms.

  In addition, according to the medical doctor terminal 510, the matching character string of the sentence that matches the explanatory document data Dv among the character strings of the sentence using the general terms converted from the medical terms in the finding document data Dt is the interpretation image. Output with P1. That is, the attending physician's terminal 510 can output a patient interpretation image P2 to which a character string of a sentence explained in a plain expression by a doctor is added. Thereby, even if the recipient has little knowledge of medical terms, the recipient can promote understanding of the details of the state of the subject.

  In the first embodiment, if there is a sentence matching character string in the finding document data Dt and the explanatory document data Dv, the attending medical terminal 510 extracts a sentence matching character string and then extracts a sentence matching character string. However, the present invention is not limited to this. For example, when there is a matching character string of text between the finding document data Dt and the explanatory document data Dv, the attending medical doctor terminal 510 may not extract the word matching character string. Further, the attending medical terminal 510 may extract a word matched character string when there is no sentence matched character string between the finding document data Dt and the explanatory document data Dv.

  In the first embodiment, the primary medical terminal 510 uses only the character string of the finding document data Dt as the character string to be compared with the character string of the explanatory document data Dv. However, the present invention is not limited to this. For example, medical terms of the character string of the finding document data Dt and the character string of the examination information when the interpretation image P1 is photographed are converted into translated words, and the explanatory document data Dv among the character strings of the examination information after conversion. A matching character string that matches the character string may be output together with the interpretation image P1. The examination information is information set at the time of photographing the interpretation image P1, and is, for example, the examination name, the examination place, the photographing method, and the like.

<Embodiment 2>
Next, a second embodiment will be described. In the first embodiment, the patient interpretation image P2 to which the character string described in plain expression is added among the character strings of the findings is output. However, in the second embodiment, the added character is added. A patient interpretation image P2 to which the reproduction time of the explanation voice data corresponding to the column is further added is output. In the first embodiment, only the patient interpretation image P2 is provided to the patient and the patient concerned. However, in the second embodiment, the patient interpretation image P2 and the explanation voice data are obtained from the patient and the patient. Provide to interested parties. As a result, a portion corresponding to the patient interpretation image P2 in the explanation voice data can be reproduced without taking the trouble of searching. In addition, description is abbreviate | omitted about the location same as the location demonstrated in Embodiment 1. FIG.

  14 and 15 are explanatory diagrams illustrating an example of providing information according to the second embodiment. 14 and 15, the explanation document data Dv is associated with the reproduction time information of the explanation voice data for each character string.

  In FIG. 14, among the part name words in the findings of the interpretation image P <b> 1, the part name words explained in plain expression by the doctor are added together with the information of the reproduction time of the explanation voice data. A process until the interpretation image P2 is output will be described. In FIG. 14, in the interpretation image P1, the name of the part of the subject included in the interpretation image P1 and the position information of the part in the interpretation image P1 are related. Here, an example of a process until the patient interpretation image P2 in FIG. 14 is output will be described. The process until the matching character string is extracted is the same as the process shown in FIG.

  First, the reproduction time corresponding to the extracted matched character string is extracted. Then, the extracted matched character string, reproduction time, and interpretation image P1 are output as a patient interpretation image P2. In this way, the patient interpretation image P2 to which explanations in general terms relating to the interpretation image P1 are added together with the reproduction time of the explanation audio data is output.

  The patient interpretation image P2 to which the reproduction time information is added is provided from the attending physician to the recipient along with the explanation voice data, for example. As a result, the recipient can easily reproduce the location where the explanation regarding the patient interpretation image P2 in the explanation voice data is performed without searching for the location. Therefore, the recipient can easily deepen the understanding of the synergistic subject state by the explanation voice data and the patient interpretation image P2.

  Further, as shown in FIG. 15, medical terms, general terms, and reproduction times corresponding to the extracted matched character strings may be output together with the interpretation image P1. In this case, the recipient of the patient interpretation image P2 can easily reproduce it without searching for a location where the explanation regarding the patient interpretation image P2 is performed in the explanation voice data. Therefore, the recipient can easily deepen the state of the subject and the correspondence between medical terms and general terms using the explanation voice data and the patient interpretation image P2.

  Here, in Embodiment 2, the electronic medical record DB 521 stores the explanation voice data. Then, when the primary medical terminal 510 receives an output request for the patient interpretation image P2, the primary medical terminal 510 receives the explanation voice data from the electronic medical record server 520, and uses the voice recognition function to explain from the explanation voice data. It is assumed that the document data Dv is converted. At that time, specifically, the attending medical terminal 510 creates explanatory document data Dv to which information on the reproduction time of the explanatory voice data is added. An example of explanatory document data to which reproduction time information is added will be described with reference to FIG.

(Example of explanatory document data Dv)
FIG. 16 is an explanatory diagram illustrating an example of explanatory document data according to the second embodiment. The explanatory document data Dv shown in FIG. 16 includes a character string for each reproduction time.

  For example, in the explanation document data Dv, “Today is the left chest, uterus, and ureter” is stored as a character string corresponding to a reproduction time of 0 minutes 0 seconds to 0 minutes 5 seconds. Similarly, in the explanatory document data Dv, “CT was taken. A shadow on the left chest from the photographed image” is stored as a character string for the playback time of 0 minutes 5 seconds to 0 minutes 10 seconds. Has been.

(Information provision processing procedure of the attending physician's terminal 510)
FIG. 17 is a flowchart of an example of an information providing process procedure of the attending medical terminal according to the second embodiment. The information providing process is a process executed by the CPU 601. In the information providing process, the attending medical terminal 510 first determines whether or not an output request for the patient interpretation image P2 has been received from the user (step S1701). If not received (step S1701: No), it waits until it is received. .

  In step S1701, when an output request for the patient interpretation image P2 is received from the user (step S1701: Yes), the acquisition unit 1201 acquires image data of the interpretation image P1 (step S1702). Then, the obtaining unit 1201 obtains the finding document data Dt (step S1703). Thereafter, the conversion unit 1202 refers to the conversion master 512, and converts the medical term of the character string of the acquired finding document data Dt into a general term (step S1704).

  Thereafter, the explanation voice data is obtained by the obtaining unit 1201 (step S1705). The attending medical terminal 510 converts the acquired explanation voice data into the explanation document data Dv (step S1706). Then, the conversion unit 1202 converts the character string of the explanatory document data Dv into a general term with reference to the conversion master 512 (step S1707). Then, the character string extraction unit 1203 compares the character string of the finding document data Dt converted in step S1704 with the character string of the explanatory document data Dv converted in step S1707 (step S1708).

  Then, the character string extraction unit 1203 determines whether there is a sentence that matches the character string of the finding document data Dt converted in step S1704 and the character string of the explanatory document data Dv converted in step S1707. (Step S1709). If there is a matching sentence (step S1709: YES), the character string extraction unit 1203 extracts the matching sentence (step S1710).

  Thereafter, the character string extraction unit 1203 extracts words that match the character string of the finding document data Dt converted in step S1704 and the character string of the explanatory document data Dv converted in step S1707 (step S1711). In that case, when performing step S1711 via step S1710, the character string extraction unit 1203 extracts a matching word from a character string not extracted as a sentence. If it is determined in step S1709 that there is no matching sentence (step S1709: NO), the attending medical terminal 510 proceeds to step S1711.

  Thereafter, the position extraction unit 1205 extracts position information for the extracted character string (step S1712). Then, the output unit 1204 outputs the extracted character string and position information to the printer and the memory together with the image data, that is, outputs the patient interpretation image P2 (step S1713), and ends the series of processing according to this flowchart. To do.

  According to the medical doctor terminal 510 according to the second embodiment described above, the matching character string and the reproduction time of the explanation voice data can be output as the patient interpretation image P2 together with the interpretation image P1. The patient who is provided with the patient interpretation image P2 and the explanation voice data can easily reproduce the explanation portion related to the matching character string in the explanation voice data without taking time and effort.

  As a result, the recipient can easily read the information included in the patient interpretation image P2 even if he / she has little knowledge of medical terms, and the portion corresponding to the patient interpretation image P2 in the explanation voice data can be read. , It can be played without the hassle of searching. Therefore, according to the attending medical terminal 510, it is possible to shorten the understanding of the state of the subject by the recipient.

  In the second embodiment, the description document data Dv includes a character string at the reproduction time every 5 seconds. However, the present invention is not limited to this. For example, the explanatory document data Dv may include a character string at the reproduction time per second, or may be associated with an individual reproduction time for each word. Specifically, the explanation document data Dv may include “12 minutes 23 seconds” as the reproduction time corresponding to the character string “CT imaging”. Moreover, when one character string exists a plurality of times, a plurality of reproduction times may be associated with each other.

  The information providing method described in the embodiments can be realized by executing a program prepared in advance on a computer such as a personal computer or a workstation. The information providing program is recorded on a computer-readable recording medium such as a hard disk, a flexible disk, a CD-ROM, an MO, and a DVD, and is executed by being read from the recording medium by the computer. The information providing program may be distributed through a network such as the Internet.

  The following additional notes are disclosed with respect to the embodiment described above.

(Supplementary Note 1) An acquisition process for acquiring an image of a subject, document data indicating the findings input to the image, and explanatory document data obtained by converting voice data for the image by voice recognition;
The character string included in the document data acquired by the acquisition process is converted into the other character string with reference to a conversion master in which the character string and another character string related to the character string are associated with each other. Conversion process,
A character string extraction process for comparing the document data after conversion by the conversion process with the explanatory document data and extracting a matching character string;
An output process for outputting the matched character string extracted by the character string extraction process together with the image;
An information providing program for causing a computer to execute.

(Supplementary Note 2) In the acquisition process, together with the image of the subject, acquire the image data in which the name of the part of the subject included in the image and the position information of the part in the image are associated,
In addition to the computer,
A position extraction process for extracting the position information corresponding to the matching character string based on the document data and the image data;
An output process for outputting the position information corresponding to the matched character string and the matched character string together with the image;
The information providing program according to appendix 1, wherein the information providing program is executed.

(Additional remark 3) The said character string extraction process compares the said document data with the other document data converted into the said other character string by the said conversion process, and extracts a text as the said matching character string,
The information providing program according to appendix 1 or 2, wherein the output process outputs the sentence extracted by the character string extraction process together with the image acquired by the acquisition process.

(Supplementary note 4) In any one of Supplementary notes 1 to 3, the output process outputs a command for printing the matched character string extracted by the character string extraction process together with the image to a printer. The information provision program described.

(Additional remark 5) The said output process memorize | stores the character string extracted by the said character string extraction process to a storage medium with the said image. The information provision program as described in any one of additional marks 1-3 characterized by the above-mentioned.

(Additional remark 6) The acquisition part which acquires the image of a to-be-photographed object, the document data which shows the finding content input with respect to the said image, and the explanatory document data by which the audio | voice data with respect to the said image were converted by voice recognition,
The character string included in the document data acquired by the acquisition unit is converted into the other character string with reference to a conversion master in which the character string and another character string related to the character string are associated with each other. A conversion unit;
A character string extraction unit that compares the document data converted by the conversion unit with the explanatory document data and extracts a matching character string;
An output unit that outputs the matching character string extracted by the character string extraction unit together with the image;
An information providing apparatus comprising:

(Additional remark 7) The computer which memorize | stores the conversion master with which the character string and the other character string relevant to this character string were linked | related,
An acquisition process for acquiring an image of a subject, document data indicating the findings input to the image, and explanatory document data obtained by converting voice data for the image by voice recognition;
A conversion process for referring to the conversion master and converting the character string included in the document data acquired by the acquisition process into the other character string;
A character string extraction process for comparing the document data after conversion by the conversion process with the explanatory document data and extracting a matching character string;
An output process for outputting the matched character string extracted by the character string extraction process together with the image;
To provide information.

510 medical doctor terminal 511 voice input device 512 conversion master 520 electronic medical record server 521 electronic medical record DB
530 Interpretation medical terminal 540 Interpretation medical system 541 Interpretation medical server 542 Imaging device 543 Interpretation medical system DB
1201 Acquisition unit 1202 Conversion unit 1203 Character string extraction unit 1204 Output unit 1205 Position extraction unit

Claims (5)

An acquisition process for acquiring an image of a subject, document data indicating the findings input to the image, and explanatory document data obtained by converting voice data for the image by voice recognition;
The character string included in the document data acquired by the acquisition process is converted into the other character string with reference to a conversion master in which the character string and another character string related to the character string are associated with each other. Conversion process,
A character string extraction process for comparing the document data after conversion by the conversion process with the explanatory document data and extracting a matching character string;
An output process for outputting the matched character string extracted by the character string extraction process together with the image;
An information providing program for causing a computer to execute. In the acquisition process, together with the image of the subject, obtains image data in which the name of the part of the subject included in the image and the position information of the part in the image are associated with each other,
In addition to the computer,
A position extraction process for extracting the position information corresponding to the matching character string based on the document data and the image data;
An output process for outputting the position information corresponding to the matched character string and the matched character string together with the image;
The information providing program according to claim 1, wherein: The character string extraction process compares the description document data with other document data converted into the other character string by the conversion process, and extracts a sentence as the matching character string,
The information providing program according to claim 1, wherein the output process outputs the sentence extracted by the character string extraction process together with the image acquired by the acquisition process. An acquisition unit that acquires an image of a subject, document data indicating the content of the findings input to the image, and explanatory document data obtained by converting voice data for the image by voice recognition;
The character string included in the document data acquired by the acquisition unit is converted into the other character string with reference to a conversion master in which the character string and another character string related to the character string are associated with each other. A conversion unit;
A character string extraction unit that compares the document data converted by the conversion unit with the explanatory document data and extracts a matching character string;
An output unit that outputs the matching character string extracted by the character string extraction unit together with the image;
An information providing apparatus comprising: A computer that stores a conversion master in which a character string and another character string related to the character string are associated with each other.
An acquisition process for acquiring an image of a subject, document data indicating the findings input to the image, and explanatory document data obtained by converting voice data for the image by voice recognition;
A conversion process for referring to the conversion master and converting the character string included in the document data acquired by the acquisition process into the other character string;
A character string extraction process for comparing the document data after conversion by the conversion process with the explanatory document data and extracting a matching character string;
An output process for outputting the matched character string extracted by the character string extraction process together with the image;
To provide information.

Images