X-ray imaging apparatus, processing apparatus, and examination method
The X-ray imaging device synchronously collects and analyzes X-ray and audio data to automatically identify and display relevant images, addressing the manual search burden in speech disorder examinations, thereby improving efficiency.
Patent Information
- Application Number
- JP2024024773
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-02-21
- Publication Date
- 2025-09-02
AI Technical Summary
The burden on radiologists is significant due to the need to manually search through a large number of X-ray images during speech examinations, particularly for disorders like dysarthria, as high frame rates result in numerous images, increasing the time required for analysis.
An X-ray imaging device and method that synchronously collects X-ray images and audio information during patient speech, identifies speech deviations, and automatically displays corresponding X-ray images, reducing the need for manual searching.
Automated identification and display of relevant X-ray images based on speech deviations reduce the radiologist's burden, enhancing efficiency in speech disorder examinations.
Smart Images

Figure 2025127840000001_ABST
Abstract
Description
[Technical Field]
[0001] The present invention relates to an X-ray imaging apparatus, a processing apparatus, and an inspection method. [Background technology]
[0002] It is known to test the vocalization of a patient (see, for example, Non-Patent Document 1).
[0003] Non-Patent Document 1 above discloses that a patient's speech is examined in a speech study to test for dysarthria. A dysarthria is a disorder in which the patient has problems with the organs involved in speech production (such as the tongue, soft palate, and pharynx) or the movement of those organs, resulting in poor speech production. In a speech study, a contrast agent is applied to the organs involved in speech production, and the patient's speech is recorded and X-rays are taken with an X-ray imaging device. A radiologist observes the patient's recorded speech and the X-ray images obtained from the X-ray imaging to test the patient's speech ability. [Prior art documents] [Non-patent literature]
[0004] [Non-Patent Document 1] Hajime Watanabe and two others, "Analysis of Articulatory Movements Using an X-Ray Television System in Patients Undergoing Two-Stage Palatoplasty," Journal of the Japanese Cleft Palate Society, July 31, 1997, Vol. 22, No. 3, pp. 108-123 Summary of the Invention [Problem to be solved by the invention]
[0005] In a speech study such as that described in Non-Patent Document 1, a relatively large number of X-ray images are acquired. For example, the X-ray imaging rate when examining an articulation disorder is as high as 30 fps, and 300 to 400 X-ray images may be acquired in one examination. For this reason, when examining an articulation disorder, the radiologist must search for the X-ray image to be confirmed from among a large number of X-ray images. Furthermore, if X-ray imaging is performed multiple times in an examination, the time required to search for the X-ray image to be confirmed increases by the number of times it is taken. Furthermore, similar problems occur when examining a patient's speech for disorders other than articulation disorders. For this reason, it is desirable to reduce the burden on the radiologist when examining a patient's speech.
[0006] The present invention has been made to solve the above-mentioned problems, and one object of the present invention is to provide an X-ray imaging device, processing device, and examination method that can reduce the burden on radiologists when examining a patient's speech. [Means for solving the problem]
[0007] In order to achieve the above object, an X-ray imaging apparatus according to a first aspect of the present invention comprises an X-ray irradiation unit that irradiates a patient with X-rays; an X-ray detection unit that detects the X-rays irradiated by the X-ray irradiation unit; an X-ray image audio information collection unit that collects a plurality of X-ray images based on the detection results of the X-rays irradiated to the patient during a time period in which the patient speaks an examination sentence, and collects audio information of the patient input from an audio information input unit during a time period that at least partially overlaps with the time period in which the plurality of X-ray images are collected; an X-ray image storage unit that stores the plurality of X-ray images collected by the X-ray image audio information collection unit together with time information; an audio information storage unit that stores the audio information collected by the X-ray image audio information collection unit together with time information; a timing identification unit that identifies a timing at which the patient's speech differs from the examination sentence based on the audio information stored in the audio information storage unit; an X-ray image identification unit that identifies a corresponding X-ray image corresponding to the timing from among the plurality of X-ray images stored in the X-ray image storage unit; and a display control unit that displays the corresponding X-ray image on a display unit.
[0008] In order to achieve the above object, a processing device in a second aspect of the present invention includes an X-ray image audio information collection unit that collects multiple X-ray images based on the detection results of X-rays irradiated to the patient during a time period in which the patient speaks an examination sentence, and collects the patient's audio information input from an audio information input unit during a time period that at least partially overlaps with the time period in which the multiple X-ray images are collected; an X-ray image storage unit that stores the multiple X-ray images collected by the X-ray image audio information collection unit together with time information; an audio information storage unit that stores the audio information collected by the X-ray image audio information collection unit together with time information; a timing identification unit that identifies the timing at which the patient's speech differs from the examination sentence based on the audio information stored in the audio information storage unit; an X-ray image identification unit that identifies a corresponding X-ray image corresponding to the timing from among the multiple X-ray images stored in the X-ray image storage unit; and a display control unit that displays the corresponding X-ray image on a display unit.
[0009] In order to achieve the above object, an examination method in a third aspect of the present invention includes the steps of collecting a plurality of X-ray images based on the detection results of X-rays irradiated to the patient during a time period in which the patient speaks an examination sentence, collecting voice information of the patient input from a voice information input unit during a time period that at least partially overlaps with the time period in which the plurality of X-ray images are collected, saving the collected X-ray images together with time information, saving the collected voice information together with the time information, identifying a timing at which the patient's voice differs from the examination sentence based on the saved voice information, identifying a corresponding X-ray image from the saved X-ray images that corresponds to the timing, and displaying the corresponding X-ray image on a display unit. [Effects of the Invention]
[0010] In the X-ray imaging device according to the first aspect, the processing device according to the second aspect, and the examination method according to the third aspect, as described above, multiple X-ray images based on the detection results of X-rays irradiated on the patient are collected during a time span in which the patient speaks an examination sentence, and patient voice information input from a voice information input unit is collected during a time span that at least partially overlaps with the time span in which the multiple X-ray images are collected. The collected multiple X-ray images are saved together with time information, and the collected voice information is saved together with the time information. Based on the saved voice information, a timing at which the patient's voice differs from the examination sentence is identified. A corresponding X-ray image from the saved multiple X-ray images corresponding to the timing is identified, and the corresponding X-ray image is displayed on a display unit. This allows the corresponding X-ray image to be confirmed during the patient's voice examination to be automatically identified and displayed. As a result, the radiologist does not need to manually search for the X-ray image to be confirmed from among multiple X-ray images. This reduces the burden on the radiologist during the patient's voice examination. [Brief explanation of the drawings]
[0011] [Figure 1] 1 is a block diagram showing an X-ray imaging apparatus according to an embodiment. [Figure 2] FIG. 1 is a schematic diagram illustrating controls related to testing a patient's speech in accordance with one embodiment. [Figure 3] FIG. 2 is a schematic diagram for explaining an image displayed on a display unit according to an embodiment. [Figure 4] 1 is a flowchart illustrating a control process for testing a patient's speech according to one embodiment. DETAILED DESCRIPTION OF THE INVENTION
[0012] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, specific embodiments of the present invention will be described with reference to the accompanying drawings.
[0013] (Overall configuration of X-ray imaging device) The configuration of an X-ray imaging apparatus 100 according to an embodiment of the present invention will be described with reference to FIG.
[0014] As shown in FIG. 1, the X-ray imaging device 100 is a device that uses X-rays to image a patient. The X-ray imaging device 100 is configured to be able to acquire X-ray images of a patient by fluoroscopic imaging or serial imaging (imaging using X-rays with higher intensity than fluoroscopic imaging). In this embodiment, the X-ray imaging device 100 images the organs involved in the patient's speech (such as the tongue, soft palate, and pharynx) and acquires X-ray images of the organs involved in the patient's speech in order to examine the patient's speech. The X-ray imaging device 100 is used to examine a patient's speech disorder (speech study).
[0015] The X-ray imaging device 100 includes an X-ray irradiation unit 10, an X-ray detection unit 20, a display unit 30, a microphone 40, and a processing unit 50. The microphone 40 and the processing unit 50 are examples of the "audio information input unit" and the "processing device" in the claims, respectively.
[0016] The X-ray irradiation unit 10 irradiates the patient with X-rays. The X-ray irradiation unit 10 includes an X-ray tube that generates X-rays, and a collimator that adjusts the irradiation direction and irradiation range of the X-rays generated from the X-ray tube.
[0017] The X-ray detection unit 20 detects the X-rays irradiated by the X-ray irradiation unit 10. The X-ray detection unit 20 includes an FPD (Flat Panel Detector) or an II (Image Intensifier). The X-ray detection unit 20 is disposed at a position facing the X-ray irradiation unit 10 with the patient in between.
[0018] An image of the patient is taken by irradiating the patient with X-rays from the X-ray irradiator 10 and detecting the X-rays with the X-ray detector 20. In an examination of the patient's speech, the X-ray irradiator 10 and the X-ray detector 20 are placed in positions facing each other with the patient's organs related to speech sandwiched between them. Then, X-rays are irradiated from the X-ray irradiator 10 to the organs related to speech, and the X-rays are detected by the X-ray detector 20.
[0019] The display unit 30 includes a monitor and displays information related to X-ray imaging. The microphone 40 accepts input of voice information from the patient. The microphone 40 is placed in a position (such as a position near the patient's mouth) where the patient's voice information can be input during a voice test.
[0020] The processing unit 50 is a computer including a control unit 51 and a storage unit 52. The control unit 51 includes processors such as a CPU (Central Processing Unit) and a GPU (Graphics Processing Unit), and controls the operation of each unit of the X-ray imaging apparatus 100. The control unit 51 as hardware has, as software functional blocks, an X-ray image audio information collecting unit 51a, a voice-to-text converting unit 51b, a voice-to-text comparing unit 51c, a timing identifying unit 51d, an X-ray image identifying unit 51e, and a display control unit 51f. The control unit 51 executes a predetermined program to function as the X-ray image audio information collecting unit 51a, the voice-to-text converting unit 51b, the voice-to-text comparing unit 51c, the timing identifying unit 51d, the X-ray image identifying unit 51e, and the display control unit 51f.
[0021] The storage unit 52 includes a volatile storage device such as a RAM (Random Access Memory) and a non-volatile storage device such as a ROM (Read Only Memory), a hard disk drive, and a solid state drive, and stores information related to X-ray imaging. The storage unit 52 has, as storage areas therein, an X-ray image storage unit 52a, an audio information storage unit 52b, and a normality information storage unit 52c.
[0022] (Configuration for testing the patient's voice) The configuration of the X-ray imaging apparatus 100 for examining the patient's speech will be described with reference to FIGS. 2 and 3. FIG.
[0023] In a patient's speech test, the patient speaks a predetermined test sentence. The X-ray irradiation unit 10 irradiates X-rays onto the organs related to the patient's speech, and the X-ray detection unit 20 detects the X-rays irradiated onto the organs related to the patient's speech. The control unit 51 acquires the detection results of the X-rays irradiated onto the patient from the X-ray detection unit 20, and generates an X-ray image 61 based on the acquired detection results. A plurality of X-ray images 61 are generated at a predetermined frame rate. Furthermore, voice information 62 of the patient speaking the test sentence is input to the microphone 40.
[0024] As shown in FIG. 2 , the X-ray image and audio information collecting unit 51a collects multiple X-ray images 61 based on the detection results of X-rays irradiated on the patient during a time span in which the patient utters the examination sentence, and collects audio information 62 of the patient input from the microphone 40 during a time span that at least partially overlaps with the time span in which the multiple X-ray images 61 are collected. Specifically, the X-ray image and audio information collecting unit 51a collects the multiple X-ray images 61 and the patient's audio information 62 in synchronization with the start of X-ray irradiation by the X-ray irradiator 10 on organs related to the patient's vocalization. Furthermore, the X-ray image and audio information collecting unit 51a ends the collection of the multiple X-ray images 61 and the audio information 62 in synchronization with the end of X-ray irradiation by the X-ray irradiator 10 on organs related to the patient's vocalization.
[0025] A plurality of X-ray images 61 collected by the X-ray image and audio information collecting unit 51a are stored in the X-ray image storage unit 52a. The X-ray image storage unit 52a stores the plurality of X-ray images 61 collected by the X-ray image and audio information collecting unit 51a together with time information (time log). For example, the X-ray image storage unit 52a stores the plurality of X-ray images 61 collected by the X-ray image and audio information collecting unit 51a in association with the elapsed time from the start of X-ray irradiation.
[0026] Furthermore, the audio information 62 collected by the X-ray image and audio information collecting unit 51a is stored in the audio information storage unit 52b. The audio information storage unit 52b stores the audio information 62 collected by the X-ray image and audio information collecting unit 51a together with time information. For example, the audio information storage unit 52b stores the audio information 62 collected by the X-ray image and audio information collecting unit 51a in association with the elapsed time from the start of X-ray irradiation.
[0027] The timing identification unit 51d identifies the timing at which the patient's speech differs from the test sentence based on the voice information 62 stored in the voice information storage unit 52b. The patient's speech differing from the test sentence means that the sound uttered by the patient differs from the sound that should be uttered from the test sentence. The normal information storage unit 52c stores normal information corresponding to the test sentence. Specifically, the normal information storage unit 52c stores normal text information 63 representing the test sentence as the normal information. The normal information storage unit 52c is configured to be able to change the normal text information 63 as the normal information depending on the test sentence. For example, the user changes the normal text information 63 as the normal information using an operation unit such as an operation panel provided in the X-ray imaging device 100.
[0028] The timing identification unit 51d identifies the timing based on the normal information and the voice information 62. Specifically, the voice-to-text conversion unit 51b converts the voice information 62 stored in the voice information storage unit 52b into text information using a predetermined voice conversion process, and creates converted text information 64. The voice-to-text comparison unit 51c compares the normal text information 63 with the converted text information 64. If the sound uttered by the patient differs from the sound that should be uttered from the test sentence, there will be a portion in the converted text information 64 where the characters differ from those in the normal text information 63 (a different portion). Therefore, the voice-to-text comparison unit 51c compares the normal text information 63 with the converted text information 64 and extracts the different portion.
[0029] The timing identifying unit 51d identifies the timing based on the comparison result between the normal text information 63 and the converted text information 64. Specifically, the timing identifying unit 51d extracts the timing (time information) of the voice information 62 corresponding to the difference portion, and identifies the extracted timing as the timing at which the patient's utterance differs from the test sentence. When there are multiple difference portions extracted by the voice-text comparing unit 51c, the timing identifying unit 51d identifies the timing for each of the multiple difference portions.
[0030] The X-ray image specifying unit 51e specifies a corresponding X-ray image 65 corresponding to the timing specified by the timing specifying unit 51d from among the multiple X-ray images 61 stored in the X-ray image storage unit 52a. Specifically, the X-ray image specifying unit 51e specifies the X-ray image 61 acquired at the same timing as the timing specified by the timing specifying unit 51d as the corresponding X-ray image 65. If there is one X-ray image 61 (one frame) acquired at the same timing as the timing specified by the timing specifying unit 51d, the X-ray image specifying unit 51e specifies the single X-ray image 61 as the corresponding X-ray image 65. If there are multiple X-ray images 61 (multiple frames) acquired at the same timing as the timing specified by the timing specifying unit 51d, the X-ray image specifying unit 51e specifies the multiple X-ray images 61 as the corresponding X-ray images 65. Furthermore, when there are multiple timings identified by the timing identification unit 51d, the X-ray image identification unit 51e identifies the corresponding X-ray image 65 for each of the multiple timings.
[0031] The display control unit 51f causes the display unit 30 to display the corresponding X-ray image 65 identified by the X-ray image identification unit 51e. At this time, as shown in FIG. 3, the display control unit 51f causes the display unit 30 to display text information 66 of the portion of the test sentence corresponding to the corresponding X-ray image 65 in addition to the corresponding X-ray image 65. In the example shown in FIG. 3, the characters of the normal test sentence are displayed as the text information 66. The characters of the converted text information 64 may also be displayed as the text information 66. Furthermore, the display control unit 51f causes the display unit 30 to highlight the portion of the text information 66 of the test sentence corresponding to the corresponding X-ray image 65 where the patient's speech differs from the test sentence. In the example shown in FIG. 3, the portion of the text information 66 where the patient's speech differs from the test sentence is highlighted by underlining and bolding. The portion of the text information 66 where the patient's speech differs from the test sentence may also be highlighted by italics, a box, a mark, or the like.
[0032] When one image is identified as the corresponding X-ray image 65, the display control unit 51f causes the display unit 30 to display the one image identified as the corresponding X-ray image 65. When multiple images are identified as the corresponding X-ray images 65, the display control unit 51f causes the display unit 30 to display, for example, one representative image from among the multiple images identified as the corresponding X-ray images 65. Furthermore, for example, the display control unit 51f causes the display unit 30 to display all of the multiple images identified as the corresponding X-ray images 65 side by side. Furthermore, for example, the display control unit 51f causes the display unit 30 to display the multiple images identified as the corresponding X-ray images 65 as a moving image that is played back based on a user operation.
[0033] (Control process for testing patient's speech) 4, a control process relating to an examination of a patient's speech by the X-ray imaging apparatus 100 of this embodiment will be described based on a flowchart. Each process in the flowchart is executed by the processing unit 50.
[0034] As shown in FIG. 4, in step 101, a plurality of X-ray images 61 based on the detection results of X-rays irradiated on the patient are collected during a time span in which the patient utters the test sentence, and voice information 62 of the patient input from microphone 40 is collected during a time span that at least partially overlaps with the time span in which the plurality of X-ray images 61 are collected. Then, in step 102, each of the collected plurality of X-ray images 61 and voice information 62 is stored together with time information. Then, in step 103, a timing at which the patient's voice differs from the test sentence is identified based on the stored voice information 62. Then, in step 104, a corresponding X-ray image 65 corresponding to the timing identified in step 104 is identified from the plurality of stored X-ray images 61. Then, in step 105, the corresponding X-ray image 65 is displayed on display unit 30. Then, the control process ends.
[0035] (Effects of this embodiment) In this embodiment, the following effects can be obtained.
[0036] In this embodiment, as described above, multiple X-ray images 61 based on the detection results of X-rays irradiated on the patient are collected during the time span in which the patient speaks the test sentence. Voice information 62 of the patient input from the voice information 62 input unit is collected during a time span that at least partially overlaps with the time span in which the multiple X-ray images are collected. The collected multiple X-ray images 61 are saved together with time information. Based on the saved voice information 62, a timing at which the patient's voice differs from the test sentence is identified. A corresponding X-ray image 65 corresponding to the timing is identified from the saved multiple X-ray images 61, and the corresponding X-ray image 65 is displayed on the display unit 30. This allows the corresponding X-ray image 65, which is the X-ray image 61 to be confirmed during the patient's voice examination, to be automatically identified and displayed. As a result, the radiologist does not need to manually search for the X-ray image 61 to be confirmed from among the multiple X-ray images 61. This reduces the burden on the radiologist during the patient's voice examination.
[0037] Furthermore, as described above, this embodiment further includes the normality information storage unit 52c in which normality information corresponding to the test sentence is stored, and the timing identification unit 51d identifies the timing based on the normality information and the voice information 62. Thus, by using the normality information, it is possible to more easily and accurately identify the timing at which the patient's speech differs from the test sentence, compared to using only the voice information 62.
[0038] In this embodiment, as described above, the normal information is normal text information 63 representing the test sentence. The system further includes a speech-to-text converter 51b that converts the speech information 62 stored in the speech information storage unit 52b into text information and creates converted text information 64, and a speech-to-text comparator 51c that compares the normal text information 63 with the converted text information 64. The timing identifier 51d identifies the timing based on the comparison result between the normal text information 63 and the converted text information 64. This allows for comparison of text information (the normal text information 63 and the converted text information 64), making it easier to obtain accurate comparison results than when speech information is compared without converting the text information into text information. As a result, it is easier and more accurate to identify the timing at which the patient's speech differs from the test sentence. Furthermore, because text information (the normal text information 63) is stored as normal information in the normal information storage unit 52c, the data volume of the normal information can be reduced compared to when speech information 62 is stored as normal information in the normal information storage unit 52c. As a result, it is possible to conserve the storage area of the normal information storage unit 52c used to store the normal information.
[0039] Furthermore, in this embodiment, as described above, the normal information storage unit 52c is configured to be able to change the normal information according to the test sentence. This allows the normal information to be appropriately changed according to the test sentence, even if the test sentence differs depending on the facility (such as a hospital) where the patient's speech test is conducted. Furthermore, even if the test sentence is changed at the facility, the normal information can be appropriately changed according to the changed test sentence. As a result, the timing can be appropriately identified using the normal information.
[0040] Furthermore, in this embodiment, as described above, the display control unit 51f displays, on the display unit 30, not only the corresponding X-ray image 65 but also the text information 66 of the examination sentence that corresponds to the corresponding X-ray image 65. This eliminates the need for the radiologist to search for not only the corresponding X-ray image 65 but also the text information 66 of the examination sentence that corresponds to the corresponding X-ray image 65. As a result, the burden on the radiologist in examining the patient's speech can be further reduced.
[0041] Furthermore, in this embodiment, as described above, the display control unit 51f highlights and displays on the display unit 30 the portions of the text information 66 corresponding to the corresponding X-ray image 65 of the test sentence where the patient's speech differs from the test sentence. This allows the radiologist to easily confirm the portions where the patient's speech differs from the test sentence. As a result, the burden on the radiologist can be more easily reduced.
[0042] Furthermore, in this embodiment, as described above, the X-ray image and audio information collecting unit 51a synchronously collects a plurality of X-ray images 61 and the patient's audio information 62. This allows a plurality of X-ray images 61 and the patient's audio information 62 to be collected synchronously, so that the corresponding X-ray image 65 can be easily and accurately identified.
[0043] [Variations] The embodiments disclosed herein should be considered to be illustrative and not restrictive in all respects. The scope of the present invention is defined by the claims rather than the above description of the embodiments, and further includes all modifications (variations) within the meaning and scope of the claims.
[0044] For example, in the above embodiment, an example was shown in which the X-ray imaging device is used to examine a patient for speech disorders, but the present invention is not limited to this. In the present invention, the X-ray imaging device may be used for an examination other than an examination for a patient for speech disorders, as long as it examines the patient's speech.
[0045] In the above embodiment, an example was shown in which the X-ray imaging device is equipped with a microphone, but the present invention is not limited to this. In the present invention, the X-ray imaging device does not have to be equipped with a microphone. Voice information of the patient may be input to the X-ray imaging device from an external microphone.
[0046] In the above embodiment, an example was shown in which the X-ray imaging device is equipped with a display unit, but the present invention is not limited to this. In the present invention, the X-ray imaging device does not have to be equipped with a display unit. Image information may be output from the X-ray imaging device to an external display unit, and the corresponding X-ray image, etc. may be displayed on the external display unit.
[0047] In the above embodiment, the normal information is normal text information, but the present invention is not limited to this. In the present invention, the normal information may be normal speech information representing a test sentence. In this case, a speech information comparison unit may be provided that compares the normal speech information with speech information stored in the speech information storage unit, and the timing identification unit may identify the timing at which the patient's speech differs from the test sentence based on the comparison result between the normal speech information and the speech information stored in the speech information storage unit.
[0048] Furthermore, in the above embodiment, an example was shown in which the timing at which the patient's utterance differs from the test sentence was identified based on normal information and voice information, but the present invention is not limited to this. In the present invention, the timing at which the patient's utterance differs from the test sentence may be identified from the voice information using AI technology such as a machine learning model. For example, the timing at which the patient's utterance differs from the test sentence may be identified using a machine learning model that has been trained to use voice information as input and output a timing at which the patient's utterance differs from the test sentence. Furthermore, for example, the timing at which the patient's utterance differs from the test sentence may be identified using a machine learning model that has been trained to use converted text information obtained by converting voice information into text information as input and output a timing at which the patient's utterance differs from the test sentence.
[0049] Furthermore, in the above embodiment, an example was shown in which, in addition to the corresponding X-ray image, text information of the portion of the examination sentence corresponding to the corresponding X-ray image was displayed on the display unit, but the present invention is not limited to this. In the present invention, as long as the corresponding X-ray image is displayed on the display unit, it is not necessary to display the text information of the portion of the examination sentence corresponding to the corresponding X-ray image on the display unit. Furthermore, when the text information of the portion of the examination sentence corresponding to the corresponding X-ray image is displayed on the display unit, it is not necessary to highlight the portion of the text information of the portion of the examination sentence corresponding to the corresponding X-ray image where the patient's speech differs from the examination sentence.
[0050] In addition, in the above embodiment, an example is shown in which multiple X-ray images and patient voice information are collected in synchronization, but the present invention is not limited to this. In the present invention, multiple X-ray images and patient voice information do not need to be collected in synchronization. In this case, the X-ray image having time information closest to the timing at which the patient's voice identified by the timing identification unit differs from the test sentence may be identified as the corresponding X-ray image.
[0051] In addition, in the above embodiment, when the user performs a predetermined operation while the corresponding X-ray image is displayed on the display unit, audio information corresponding to the corresponding X-ray image displayed on the display unit may be played back. That is, when the user performs a predetermined operation, a portion of the audio information in which the patient's speech differs from the test sentence may be played back.
[0052] [Aspect] It will be appreciated by those skilled in the art that the exemplary embodiments described above are examples of the following aspects.
[0053] (Item 1) an X-ray irradiation unit that irradiates the patient with X-rays; an X-ray detection unit that detects the X-rays irradiated by the X-ray irradiation unit; an X-ray image and audio information collection unit that collects a plurality of X-ray images based on the detection results of the X-rays irradiated to the patient during a time span in which the patient utters the test sentence, and collects audio information of the patient input from an audio information input unit during a time span that at least partially overlaps with the time span in which the plurality of X-ray images are collected; an X-ray image storage unit that stores the plurality of X-ray images collected by the X-ray image and audio information collection unit together with time information; an audio information storage unit that stores the audio information collected by the X-ray image audio information collection unit together with time information; a timing identification unit that identifies a timing at which the patient's speech differs from the test sentence based on the speech information stored in the speech information storage unit; an X-ray image specifying unit that specifies a corresponding X-ray image corresponding to the timing from among the plurality of X-ray images stored in the X-ray image storage unit; and a display control unit that causes the corresponding X-ray image to be displayed on a display unit.
[0054] (Item 2) a normality information storage unit storing normality information corresponding to the test sentence; Item 2. The X-ray imaging apparatus according to item 1, wherein the timing specifying unit specifies the timing based on the normal information and the audio information.
[0055] (Item 3) the normal information is normal text information representing the test sentence; a voice-to-text conversion unit that converts the voice information stored in the voice information storage unit into text information and creates converted text information; a voice-to-text comparison unit that compares the normal text information with the converted text information, 3. The X-ray imaging apparatus according to item 2, wherein the timing specifying unit specifies the timing based on a result of comparison between the normal text information and the converted text information.
[0056] (Item 4) 4. The X-ray imaging apparatus according to item 2 or 3, wherein the normal information storage unit is configured to be able to change the normal information depending on the test sentence.
[0057] (Item 5) The X-ray imaging device according to any one of items 1 to 4, wherein the display control unit causes the display unit to display, in addition to the corresponding X-ray image, text information of the part of the examination sentence corresponding to the corresponding X-ray image.
[0058] (Item 6) Item 6. The X-ray imaging device according to item 5, wherein the display control unit displays on the display unit text information of the portion of the test sentence corresponding to the corresponding X-ray image, emphasizing the portion of the patient's speech that differs from the test sentence.
[0059] (Item 7) 7. The X-ray imaging apparatus according to any one of items 1 to 6, wherein the X-ray image and audio information collecting unit collects the plurality of X-ray images and the audio information of the patient in synchronization with each other.
[0060] (Item 8) an X-ray image and audio information collection unit that collects a plurality of X-ray images based on the detection results of X-rays irradiated to the patient during a time span in which the patient utters an examination sentence, and collects audio information of the patient input from an audio information input unit during a time span that at least partially overlaps with the time span in which the plurality of X-ray images are collected; an X-ray image storage unit that stores the plurality of X-ray images collected by the X-ray image and audio information collection unit together with time information; an audio information storage unit that stores the audio information collected by the X-ray image audio information collection unit together with time information; a timing identification unit that identifies a timing at which the patient's speech differs from the test sentence based on the speech information stored in the speech information storage unit; an X-ray image specifying unit that specifies a corresponding X-ray image corresponding to the timing from among the plurality of X-ray images stored in the X-ray image storage unit; a display control unit that displays the corresponding X-ray image on a display unit.
[0061] (Item 9) collecting a plurality of X-ray images based on the detection results of X-rays irradiated to the patient during a time span in which the patient utters the test sentence, and collecting voice information of the patient input from a voice information input unit during a time span that at least partially overlaps with the time span in which the plurality of X-ray images are collected; storing the collected X-ray images together with time information; storing the collected audio information together with time information; Identifying, based on the stored speech information, when the patient's speech differs from the test sentence; Identifying a corresponding X-ray image corresponding to the timing from among the plurality of stored X-ray images; and displaying the corresponding X-ray image on a display unit. [Explanation of symbols]
[0062] 10 X-ray irradiation section 20 X-ray detection unit 30 Display section 40 Microphone (voice information input section) 50 Processing unit (processing device) 51a X-ray image and audio information collection unit 51b Speech-to-text conversion unit 51c Audio-to-text comparison section 51d Timing determination unit 51e X-ray image identification section 51f Display control unit 52a X-ray image storage section 52b Audio information storage section 52c Normal information storage section 61 X-ray image 62 Audio Information 63 Normal text information (normal information) 64 Converted Text Information 65 Corresponding X-ray images 66 Text Information 100 X-ray equipment
Claims
1. an X-ray irradiation unit that irradiates the patient with X-rays; an X-ray detection unit that detects the X-rays irradiated by the X-ray irradiation unit; an X-ray image and voice information collecting unit that collects a plurality of X-ray images based on the detection results of the X-rays irradiated to the patient during a time span in which the patient utters the test sentence, and collects voice information of the patient input from a voice information input unit during a time span that at least partially overlaps with the time span in which the plurality of X-ray images are collected; an X-ray image storage unit that stores the plurality of X-ray images collected by the X-ray image and audio information collection unit together with time information; an audio information storage unit that stores the audio information collected by the X-ray image audio information collection unit together with time information; a timing identification unit that identifies a timing at which the patient's speech differs from the test sentence based on the speech information stored in the speech information storage unit; an X-ray image specifying unit that specifies a corresponding X-ray image corresponding to the timing among the plurality of X-ray images stored in the X-ray image storage unit; a display control unit that causes the corresponding X-ray image to be displayed on a display unit.
2. a normality information storage unit storing normality information corresponding to the test sentence; The X-ray imaging apparatus according to claim 1 , wherein the timing specifying unit specifies the timing based on the normality information and the audio information.
3. the normal information is normal text information representing the test sentence; a voice-to-text conversion unit that converts the voice information stored in the voice information storage unit into text information and creates converted text information; a voice-to-text comparison unit that compares the normal text information with the converted text information, The X-ray imaging apparatus according to claim 2 , wherein the timing specifying unit specifies the timing based on a result of comparison between the normal text information and the converted text information.
4. The X-ray imaging apparatus according to claim 2 , wherein the normality information storage unit is configured to be able to change the normality information according to the test sentence.
5. The X-ray imaging apparatus according to claim 1 , wherein the display control unit causes the display unit to display, in addition to the corresponding X-ray image, text information of a portion of the examination sentence that corresponds to the corresponding X-ray image.
6. 6. The X-ray imaging device according to claim 5, wherein the display control unit displays on the display unit text information of a portion of the test sentence corresponding to the corresponding X-ray image, the portion of the test sentence in which the patient's speech differs from the test sentence, in an emphasized manner.
7. The X-ray imaging apparatus according to claim 1 , wherein the X-ray image and audio information collecting unit collects the plurality of X-ray images and the audio information of the patient in synchronization with each other.
8. an X-ray image and audio information collection unit that collects a plurality of X-ray images based on the detection results of X-rays irradiated on the patient during a time span in which the patient utters an examination sentence, and collects audio information of the patient input from an audio information input unit during a time span that at least partially overlaps with the time span in which the plurality of X-ray images are collected; an X-ray image storage unit that stores the plurality of X-ray images collected by the X-ray image and audio information collection unit together with time information; an audio information storage unit that stores the audio information collected by the X-ray image audio information collection unit together with time information; a timing identification unit that identifies a timing at which the patient's speech differs from the test sentence based on the speech information stored in the speech information storage unit; an X-ray image specifying unit that specifies a corresponding X-ray image corresponding to the timing among the plurality of X-ray images stored in the X-ray image storage unit; a display control unit that causes the corresponding X-ray image to be displayed on a display unit.
9. collecting a plurality of X-ray images based on the detection results of X-rays irradiated to the patient during a time span in which the patient utters the test sentence, and collecting voice information of the patient inputted from a voice information input unit during a time span that at least partially overlaps with the time span in which the plurality of X-ray images are collected; storing the acquired X-ray images together with time information; storing the collected audio information together with time information; Identifying, based on the stored speech information, when the patient's speech differs from the test sentence; Identifying a corresponding X-ray image corresponding to the timing from among the plurality of stored X-ray images; and displaying the corresponding X-ray image on a display unit.