Information processing apparatus, information processing method, and program
The information processing device addresses the challenge of accurately associating radiographic images with related information in swallowing contrast examinations by using speech recognition to automatically generate and associate this information with the images, thereby enhancing examination efficiency and safety.
Patent Information
- Application Number
- JP2023156461
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-09-21
- Publication Date
- 2025-04-03
AI Technical Summary
In swallowing contrast examinations, accurately associating radiographic images with related information, such as the type of sample or subject posture, is challenging due to the need for manual placement of lead markers and the potential for prolonged inspection times and exposure for photographers.
An information processing device that acquires a series of radiation images and generates related information through speech recognition, associating the images with the recognized information, including the type of sample, subject posture, and photographing direction, thereby eliminating the need for manual marker placement.
This solution enables easy and accurate association of radiographic images with related information, improving the efficiency and safety of swallowing contrast examinations by reducing inspection time and minimizing exposure for photographers.
Smart Images

Figure 2025047766000001_ABST
Abstract
Description
[Technical field]
[0001] The disclosed technology relates to an information processing device, an information processing method, and a program. [Background technology]
[0002] The following techniques are known as techniques related to image processing using audio. For example, Patent Document 1 describes an endoscope device that includes an imaging unit that images an object and outputs an image signal, an audio acquisition unit that records audio and outputs an audio signal, a character generation unit that receives the audio signal, converts it into a character string, and generates a character signal, and a video creation unit that receives the image signal, the audio signal, and the character signal, and creates a video file. The video creation unit records the character signal as a character code in the video file separately from the image signal.
[0003] Patent Document 2 describes an apparatus for converting content including video, audio, or data into a stream, and recording and reproducing the stream on an information recording medium together with metadata related to the video, audio, or data. The apparatus is provided with a voice recognition means for selecting an externally input voice by voice recognition and converting it into character data, and describes how, by setting a recording control means, the character data or information obtained by adding format information to the character data is inserted into a data portion constituting the video frame, thereby recording metadata or character data marking a scene as metadata related to the content on the information recording medium. [Prior art documents] [Patent documents]
[0004] [Patent Document 1] JP 2014-036682 A [Patent Document 2] JP 2007-082088 A Summary of the Invention [Problem to be solved by the invention]
[0005] A swallowing contrast examination is known as one of the examinations using radiation images. The swallowing contrast examination is an examination for evaluating the process and state of a subject swallowing a sample. In the swallowing contrast examination, a video consisting of a series of radiation images taken by continuously irradiating the subject with radiation is used. In the swallowing contrast examination, the subject swallows a sample while appropriately changing the combination of the subject's posture and the type of sample (i.e., while changing the examination level). In such an examination using radiation images, when there are multiple examination levels, it is necessary to accurately correspond the contents of the examination level to the taken radiation image so that it is possible to know which examination level the taken radiation image corresponds to.
[0006] In conventional swallowing contrast examinations, a lead marker with the type of sample, such as "thickened," "chopped," or "kayu," was engraved on it, and the subject was photographed. However, it was time-consuming to position the marker so that it did not overlap with the subject's area of interest, which led to a long examination time. In addition, the photographer, such as a doctor or radiologist, had to position the marker, which led to exposure to radiation.
[0007] The disclosed technology has been made in consideration of the above points, and has an object to easily and accurately associate related information relating to the capture content of a radiological image with the radiological image. [Means for solving the problem]
[0008] An information processing device according to the disclosed technique includes at least one processor that acquires a series of radiographic images captured by continuously irradiating radiation, acquires associated information related to the captured content of the series of radiographic images, the associated information being information generated by recognizing a voice, and associates the series of radiographic images with the associated information.
[0009] The processor may associate the latest related information acquired before a predetermined timing synchronized with the capture of the series of radiation images with the series of radiation images. The predetermined timing may be a timing of start of irradiation of radiation that is continuously irradiated in the capture of the series of radiation images. The predetermined timing may be determined by receiving a radiation switch signal transmitted by a user input means and indicating the start of irradiation that is continuously irradiated in the capture of the series of radiation images.
[0010] The processor may generate a data file including image group data including the series of radiation images and the related information. The processor may include a notation corresponding to the related information in a file name of the data file including the series of radiation images. The processor may process the image group data including the series of radiation images such that a notation corresponding to the related information is displayed together with the series of radiation images.
[0011] When the processor acquires new related information generated by recognizing voice emitted during the period in which a series of radiological images are captured, the processor may associate the new related information with a radiological image among the series of radiological images that is acquired after the acquisition of the new related information.
[0012] The processor may display a radiographic image associated with the designated related information from among the series of radiographic images. The processor may obtain related information generated by a method other than voice recognition, and replace the related information generated by voice recognition with related information generated by a method other than voice recognition. The processor may issue an alert when the related information associated with the series of radiographic images does not include specific information.
[0013] The related information may be information indicating a type of sample used in an examination using a series of radiation images. The related information may be information indicating a type of posture of a subject in an examination using a series of radiation images. The related information may be information indicating a type of imaging direction of a series of radiation images. The above examination may be a swallowing contrast examination. In a swallowing contrast examination, the burden of supporting the subject is large, so that the disclosed technology can be utilized in the swallowing contrast examination to improve workability. The related information may be generated by recognizing a voice in which a predetermined term is pronounced.
[0014] The information processing method of the disclosed technology involves acquiring a series of radiological images captured by continuously irradiating radiation, and generating information by recognizing voice, whereby at least one processor provided in an information device acquires associated information related to the captured contents of the series of radiological images, and performs a process of matching the series of radiological images with the associated information.
[0015] The program related to the disclosed technology is a program for causing at least one processor provided in an information device to execute a process of acquiring a series of radiological images captured by continuously irradiating radiation, acquiring related information related to the captured contents of the series of radiological images, which is information generated by recognizing voice, and associating the series of radiological images with the related information. Effect of the Invention
[0016] According to the disclosed technique, it is possible to simply and accurately associate related information relating to the captured content of a radiological image with the radiological image. [Brief description of the drawings]
[0017] [Figure 1] FIG. 1 is a diagram illustrating an example of a configuration of a radiation image capturing system according to an embodiment of the disclosed technique. [Diagram 2] 1 is a diagram illustrating an example of a configuration of a radiographic image capturing device according to an embodiment of the disclosed technique. [Diagram 3]FIG. 2 is a diagram illustrating an example of a hardware configuration of an information processing device according to an embodiment of the disclosed technique. [Figure 4] 1 is a functional block diagram illustrating an example of a functional configuration of an information processing device according to an embodiment of the disclosed technology. [Diagram 5] 11 is a diagram illustrating an example of a structure of a data file generated by an association processing unit according to an embodiment of the disclosed technique. [Figure 6] 11 is a flowchart showing an example of a flow of processing performed by a CPU according to an embodiment of the disclosed technology by executing an association program. [Figure 7] 11 is a diagram illustrating an example of an association process performed by an information processing device according to an embodiment of the disclosed technique. [Figure 8] FIG. 11 is a functional block diagram showing an example of a functional configuration of an information processing device according to another embodiment of the disclosed technology. [Figure 9] 13 is a flowchart showing an example of a flow of processing performed by a CPU according to another embodiment of the disclosed technology by executing an association program. [Figure 10] 11 is a diagram illustrating an example of an association process performed by an information processing device according to another embodiment of the disclosed technique. [Figure 11] FIG. 11 is a functional block diagram illustrating an example of a functional configuration of an information processing device according to another embodiment of the disclosed technology. [Figure 12] FIG. 1 is a diagram showing the posture of a subject in a swallowing contrast test. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0018] Hereinafter, an example of an embodiment of the disclosed technology will be described with reference to the drawings. In each drawing, the same or equivalent components and parts are given the same reference numerals, and duplicated descriptions will be omitted.
[0019] [First embodiment] 1 is a diagram showing an example of a configuration of a radiographic imaging system 1 according to an embodiment of the disclosed technique. In the following description, a case where the radiographic imaging system 1 is used for a swallowing radiography test will be described as an example. The radiographic imaging system 1 includes an information processing device 10, a radiographic imaging device 20, a sound collection device 30, and a voice recognition device 40.
[0020] The radiological image capturing device 20 is capable of capturing radiological images using radiation such as X-rays. It is also possible to display a series of radiological images captured by continuously irradiating radiation in a time series, in order to display a moving image. The capturing of a series of radiological images for displaying a moving image is called fluoroscopic imaging. In a swallowing contrast examination, fluoroscopic imaging is performed to observe the process in which a subject swallows a sample. Note that "continuous irradiation of radiation" includes both a case where radiation is continuously irradiated for a certain period of time and a case where pulsed radiation is irradiated multiple times within a certain period of time. The radiological images captured by the radiological image capturing device 20 are immediately transmitted to the information processing device 10.
[0021] 2 is a diagram showing an example of the configuration of the radiographic image capturing device 20. The radiographic image capturing device 20 has an imaging table 21. The imaging table 21 is supported on the floor surface by a stand 22. A radiation generating unit 24 is attached to the imaging table 21 via a support 23. The radiation generating unit 24 is configured to include a radiation source 25 and a collimator 26. A radiation detector 27 is built into the imaging table 21.
[0022] The radiation source 25 has a radiation tube (not shown) and irradiates the subject P with radiation. The collimator 26 limits the irradiation field of the radiation emitted from the radiation tube. The radiation detector 27 has a plurality of pixels that generate signal charges according to the radiation that has passed through the subject P. The radiation detector 27 is called an FPD (Flat Panel Detector).
[0023] The radiation generating unit 24 can be moved back and forth together with the support 23 along the long side direction of the imaging table 21 by a moving mechanism such as a motor (not shown). The radiation detector 27 can be moved back and forth along the long side direction of the imaging table 21 in conjunction with the movement of the radiation generating unit 24. The imaging table 21 and the support 23 can be rotated between a standing state shown in FIG. 2 and a lying state (not shown) by a rotating mechanism such as a motor (not shown). In the lying state, the surface of the imaging table 21 is parallel to the floor surface, and the extension direction of the support 23 is perpendicular to the floor surface. On the other hand, in the standing state, the surface of the imaging table 21 is perpendicular to the floor surface, and the extension direction of the support 23 is parallel to the floor surface. In the standing state, it is possible to perform fluoroscopic imaging on a subject P sitting on a wheelchair 50 as shown in FIG. 2.
[0024] The sound collection device 30 is a microphone that collects surrounding sounds. The sound collection device 30 may be provided in the voice recognition device 40, or may be a neck-hanging microphone or the like that is worn by a radiographer such as a doctor or a radiologist. The voice of a radiographer such as a doctor or a radiologist is collected by the sound collection device 30. The voice recognition device 40 recognizes the voice collected by the sound collection device 30 using a known voice recognition technology. When the collected voice includes a predetermined specific term indicating the content of the examination level in the swallowing contrast examination, the voice recognition device 40 generates identification information of the examination level indicated by the term as related information related to the radiographing of the radiograph.
[0025] The specific term indicating the content of the examination level may include a term indicating the type of sample swallowed by the subject in the swallowing contrast examination, such as "water", "thick", "chopped", and "soy sauce". In this case, the related information includes identification information of the type of sample. The specific term indicating the content of the examination level may also include a term indicating the type of posture taken by the subject in the swallowing contrast examination, such as "90°", "75°", "60°", "45°", "30°", "0°", "supine", and "prone". In this case, the related information includes identification information of the type of posture of the subject. The above angle is the angle of the spine with the horizontal direction as the reference (0°) when the subject swallows in the swallowing contrast examination, as shown in FIG. 12. The specific term indicating the content of the examination level may also include a term indicating the type of imaging direction of the radiographic image taken in the swallowing contrast examination, such as "front imaging" and "side imaging". In this case, the related information includes identification information of the type of imaging direction.
[0026] For example, when the voice collected by the sound collection device 30 includes the term "toromi" indicating the type of sample, which is the content of the test level, the voice recognition device 40 generates identification information corresponding to "toromi" as the related information. In this case, the voice recognition device 40 may generate, for example, text describing "toromi" or a level code consisting of letters, numbers, symbols, or a combination of these corresponding to "toromi" as the related information. Also, when the voice collected by the sound collection device 30 includes the term "yonjugodo" indicating the posture of the subject, which is the content of the test level, the voice recognition device 40 generates identification information corresponding to "45°" as the related information. In this case, the voice recognition device 40 may generate, for example, text describing "45°" or a level code consisting of letters, numbers, symbols, or a combination of these corresponding to "45°" as the related information. The terms indicating the test level, such as "toromi", "kizamimi", "kayu", "yonjugodo", and "kyujudo" exemplified above, are preregistered in the voice recognition device 40. By using preregistered terms as the target of speech recognition, it is possible to improve the accuracy of speech recognition. When a specific term is included in the recognized speech, the speech recognition device 40 instantly generates related information and immediately transmits it to the information processing device 10. That is, the related information is transmitted to the information processing device 10 immediately after the speech containing the specific term is heard. When an utterance containing a specific term is made intermittently multiple times, related information corresponding to each utterance is generated in sequence and transmitted to the information processing device 10 in sequence.
[0027] 3 is a diagram showing an example of a hardware configuration of the information processing device 10. The information processing device 10 includes a CPU (Central Processing Unit) 101, a RAM (Random Access Memory) 102, a non-volatile memory 103, an input device 104 including a keyboard and a mouse, a display 105, and a communication interface 106. These pieces of hardware are connected to a bus 108.
[0028] The display 105 may be a touch panel display. The communication interface 106 is an interface for the information processing device 10 to communicate with the radiation image capturing device 20 and the voice recognition device 40. The communication method may be either wired or wireless. For the wireless communication, a method conforming to existing wireless communication standards such as Wi-Fi (registered trademark) and Bluetooth (registered trademark) can be applied.
[0029] The non-volatile memory 103 is a non-volatile storage medium such as a hard disk or a flash memory. An association program 110 is stored in the non-volatile memory 103. The RAM 102 is a work memory for the CPU 101 to execute processing. The CPU 101 loads the association program 110 stored in the non-volatile memory 103 into the RAM 102, and executes processing in accordance with the association program 110. The CPU 101 is an example of a "processor" in the disclosed technology.
[0030] 4 is a functional block diagram showing an example of a functional configuration of the information processing device 10. The information processing device 10 has an image acquisition unit 11, a related information acquisition unit 12, and an association processing unit 13. When the CPU 101 executes the association program 110, the information processing device 10 functions as the image acquisition unit 11, the related information acquisition unit 12, and the association processing unit 13.
[0031] The image acquisition unit 11 acquires a series of radiological images captured by continuously irradiating radiation in the radiological image capturing device 20. The series of radiological images are fluoroscopic images of the process in which a subject chews and swallows a sample in a swallowing contrast examination.
[0032] The related information acquisition unit 12 acquires related information generated by the voice recognition device 40. The related information is information related to the shooting contents of the series of radiation images acquired by the image acquisition unit 11. Specifically, identification information of the examination level generated based on the speech of a doctor or radiologist when shooting the series of radiation images is acquired as the related information. The related information is acquired immediately after the generation of a voice containing a specific term. When multiple pieces of related information are generated intermittently, these pieces of related information are acquired sequentially by the related information acquisition unit 12.
[0033] The association processing unit 13 associates the series of radiation images acquired by the image acquisition unit 11 with the related information acquired by the related information acquisition unit 12. Specifically, the association processing unit 13 associates the latest related information acquired before a predetermined timing synchronized with the capture of the series of radiation images with the series of radiation images. The association processing unit 13 uses a radiation switch signal input to the information processing device 10 to determine related information to be associated from related information that can be sequentially acquired.
[0034] The radiation switch signal is a signal indicating the start and end of radiation irradiation, and is, for example, a signal output in conjunction with the on / off of a foot switch operated by a doctor or radiologist when irradiating radiation in the radiation image capturing device 20. In the radiation image capturing system 1 according to the present embodiment, a common radiation switch signal is provided to the radiation image capturing device 20 and the information processing device 10. In the following description, the radiation switch signal is assumed to be at a high level during the radiation irradiation period (including a non-irradiation period when pulsed radiation is irradiated multiple times) and at a low level otherwise. The association processing unit 13 associates the latest related information acquired before the timing at which the radiation switch signal transitions to a high level with the series of radiation images. The timing at which the radiation switch signal transitions to a high level is the timing at which irradiation of radiation that is continuously irradiated in capturing the series of radiation images begins. When multiple pieces of related information have been acquired by the timing at which irradiation of radiation begins, the association processing unit 13 associates the latest related information among the multiple pieces of related information acquired up to that point.
[0035] There are various examples of the manner in which a series of radiographic images are associated with the related information. For example, as shown in Fig. 5, the association processing unit 13 may associate the series of radiographic images with the related information by generating a data file 60 including image group data 61 including the series of radiographic images and related information 62.
[0036] The association processor 13 may also associate a series of radiographic images with the related information by including a notation corresponding to the related information in the file name of a data file including the series of radiographic images. The "notation corresponding to the related information" is a letter, a number, a symbol, or a combination thereof that can identify the content of the inspection level indicated by the related information. For example, a character such as "thick" that indicates the content of the inspection level is applied as part of the file name of the data file.
[0037] The association processing unit 13 may also process image group data including a series of radiation images so that notations corresponding to the related information are displayed together with the series of radiation images. In this case, when the series of radiation images is displayed as a video, characters such as "thickness" indicating the content of the inspection level indicated by the related information are displayed together with the video.
[0038] The association processing unit 13 stores a data file in which a series of radiation images and related information are associated with each other in a recording medium. The recording medium in which the data file is stored may be the non-volatile memory 103 included in the information processing device 10, or may be a recording medium included in an external image server (not shown).
[0039] FIG. 6 is a flowchart showing an example of the flow of processing carried out by CPU 101 executing association program 110. As shown in FIG.
[0040] In step S1, the related information acquisition unit 12 acquires related information generated by the voice recognition device 40. When a plurality of pieces of related information are intermittently generated by the voice recognition device 40, the related information acquisition unit 12 acquires these pieces of related information sequentially.
[0041] In step S2, the association processing unit 13 determines whether or not radiation irradiation has started in the radiographic image capturing device 20. When the radiation switch signal transitions from a low level to a high level, the association processing unit 13 determines that radiation irradiation has started.
[0042] In step S3, the association processing unit 13 determines the most recent related information acquired before the start of radiation irradiation as the related information to be associated with the series of radiation images.
[0043] In step S4, the image acquiring unit 11 acquires a series of radiographic images captured by continuously irradiating radiation in the radiographic imaging device 20. The series of radiographic images are fluoroscopic images of the process in which the subject swallows a sample in a swallowing contrast examination. The acquisition of the series of radiographic images by the image acquiring unit 11 continues until the irradiation of radiation (fluoroscopic imaging) in the radiographic imaging device 20 ends.
[0044] In step S5, the association processing unit 13 determines whether or not the irradiation of radiation has ended in the radiographic image capturing device 20. The association processing unit 13 determines that the irradiation of radiation has ended when the radiation switch signal has transitioned from a high level to a low level.
[0045] In step S6, the association processing unit 13 associates the related information determined in step S3 as the object of association with the series of radiographic images acquired in step S4. The association processing unit 13 associates the series of radiographic images with the related information by generating a data file 60 including image group data 61 including the series of radiographic images and related information 62, for example, as shown in Fig. 5.
[0046] In step S7, the association processor 13 stores the data file generated in step S6 on the recording medium.
[0047] 7 is a diagram showing an example of the association process by the information processing device 10. When a radiographer such as a doctor or a radiologist makes an utterance including the term "thickness" indicating the content of the examination level at time t1, the voice recognition device 40 generates identification information of the examination level corresponding to "thickness" (for example, text describing "thickness") as related information. The related information is obtained instantly by the information processing device 10.
[0048] When a doctor or radiologist who is taking a radiological image makes an utterance including the term "notches" indicating the contents of the examination level at time t2, the voice recognition device 40 generates identification information of the examination level corresponding to "notches" (for example, text describing "notches") as related information. The related information is instantly acquired by the information processing device 10.
[0049] At time t3 when the radiation switch signal transitions from low level to high level, radiation irradiation is started in the radiation image capturing device 20. In a swallowing contrast examination, a series of radiation images are captured by continuously irradiating radiation. The series of radiation images constitute each frame when the series of radiation images are displayed as a moving image. A plurality of frames (radiation images) from the first frame to the nth frame are generated in the radiation image capturing device 20 by time t4 when the radiation switch signal transitions to low level. The radiation images generated in the radiation image capturing device 20 are instantly acquired by the information processing device 10.
[0050] The information processing device 10 determines the associated information corresponding to the latest "notch" acquired by time t3 when the radiation switch signal transitions to a high level as the target for association. The information processing device 10 generates a data file 60 including image group data 61 including a series of radiation images (1st frame to nth frame) and associated information 62 corresponding to the "notch", and stores this in a recording medium.
[0051] As described above, the information processing device 10 according to the embodiment of the disclosed technology acquires a series of radiographic images captured by continuously irradiating radiation, acquires related information related to the captured content of the series of radiographic images, which is information generated by recognizing voice, and associates the series of radiographic images with the related information. According to the information processing device 10 according to the present embodiment, the related information generated by recognizing voice is associated with the series of radiographic images, so that the user does not need to perform a special operation for the association. In other words, according to the information processing device 10 according to the present embodiment, it is possible to simply and accurately associate the related information with the radiographic images.
[0052] Furthermore, according to the information processing device 10 of this embodiment, the latest related information acquired before a predetermined timing synchronized with the capture of the series of radiographic images is associated with the series of radiographic images. The predetermined timing is the timing of the start of irradiation of radiation that is continuously irradiated in the capture of the series of radiographic images.
[0053] When associating related information generated in response to the speech of a radiographer, such as a doctor or radiologist, with a series of radiographic images, it is considered that the speech immediately before the start of radiography contains appropriate related information. By associating the latest related information acquired before the start of radiation irradiation with the series of radiographic images, it is possible to associate the appropriate related information with the series of radiographic images.
[0054] The information processing device 10 may have the following additional functions. The information processing device 10 may acquire related information generated by a method other than voice recognition, and replace the related information generated by voice recognition with related information generated by a method other than voice recognition. According to this aspect, for example, when the related information generated by voice recognition contains an error, the erroneous related information can be updated by the related information generated by a method other than voice recognition. The "related information generated by a method other than voice recognition" may be, for example, related information generated by operating an input device such as a keyboard or a function button.
[0055] Furthermore, the information processing device 10 may issue an alert when the related information associated with a series of radiographic images does not include specific information. The "specific information" may be identification information of an examination level that should be included in the videofluoroscopic examination. According to this aspect, it is possible to notify that radiographic images related to an examination level that should be included in the videofluoroscopic examination have not been captured.
[0056] [Second embodiment] FIG. 8 is a functional block diagram showing an example of a functional configuration of an information processing device 10A according to a second embodiment of the disclosed technology. In the information processing device 10 according to the first embodiment, one piece of related information is associated with a series of radiation images. In contrast, the information processing device 10A according to the second embodiment associates a plurality of pieces of related information with a series of radiation images. More specifically, when the association processing unit 13 according to the second embodiment acquires new related information generated by recognizing a voice uttered during the imaging period of a series of radiation images, it associates the new related information with a radiation image acquired after acquiring the new related information among the series of radiation images. According to the information processing device 10A according to this embodiment, certain related information is associated with some frames of a video composed of a series of radiation images, and other related information is associated with some other frames.
[0057] In the information processing device 10A according to the second embodiment, the association processing unit 13 associates related information with each radiation image (frame) by using a radiation control pulse input to the information processing device 10. In this embodiment, the radiation image capturing device 20 captures a series of radiation images by irradiating pulsed radiation multiple times within a certain period of time. The radiation control pulse is a pulse signal corresponding to each pulse of the pulsed radiation. That is, one pulse of the radiation control pulse corresponds to one pulse of the pulsed radiation. One radiation image (one frame) is generated by irradiating one pulse of radiation. Therefore, one pulse of the radiation control pulse corresponds to one radiation image (one frame) of the series of radiation images.
[0058] FIG. 9 is a flowchart showing an example of the flow of processing carried out by the CPU 101 according to the second embodiment by executing the association program 110. As shown in FIG.
[0059] In step S11, the related information acquisition unit 12 acquires related information generated by the voice recognition device 40. When a plurality of pieces of related information are intermittently generated by the voice recognition device 40, the related information acquisition unit 12 acquires these pieces of related information sequentially.
[0060] In step S12, the association processing unit 13 determines whether or not radiation irradiation has started in the radiographic image capturing device 20. When the radiation switch signal transitions from a low level to a high level, the association processing unit 13 determines that radiation irradiation has started.
[0061] In step S13, the association processing unit 13 determines the most recent related information acquired before the start of radiation irradiation as the related information to be associated with the series of radiation images.
[0062] In step S14, the image acquiring unit 11 acquires a series of radiographic images captured by continuously irradiating radiation in the radiographic imaging device 20. The series of radiographic images are fluoroscopic images of the process in which the subject swallows a sample in a swallowing contrast examination. The acquisition of the series of radiographic images by the image acquiring unit 11 continues until the irradiation of radiation (fluoroscopic imaging) in the radiographic imaging device 20 ends.
[0063] In step S15, the association processing unit 13 associates the related information determined as the object of association in step S13 with the radiation images (frames) acquired so far.
[0064] In step S16, the association processing unit 13 judges whether or not new related information has been acquired by the related information acquisition unit 12 after the start of radiation. The new related information is related information generated by the voice recognition device 40 by recognizing a voice uttered during the period of capturing a series of radiation images. If it is judged that new related information has been acquired, the process proceeds to step S17, and if it is judged that new related information has not been acquired, the process proceeds to step S18.
[0065] In step S17, the association processing unit 13 associates the new related information acquired in step S16 with the radiological image (frame) acquired after acquiring the new related information.
[0066] In step S18, the association processing unit 13 determines whether or not radiation irradiation has ended in the radiographic image capturing device 20. When the radiation switch signal transitions from high level to low level, the association processing unit 13 determines that radiation irradiation has ended. If it is determined in step S18 that radiation irradiation has not ended, the process returns to step S16. As a result, every time new related information is acquired during the capturing period of a series of radiographic images, the latest related information is associated with the radiographic image (frame) acquired after the acquisition of the latest related information. If it is determined in step S18 that radiation irradiation has ended, the process proceeds to step S19.
[0067] In step S19, the association processing unit 13 generates a data file in which the most recently acquired related information is associated with each radiation image (each frame), and stores this in the recording medium.
[0068] 10 is a diagram showing an example of association processing by the information processing device 10A according to the second embodiment. When a doctor or radiologist performing a swallowing contrast examination utters a word including the term "thickness" indicating the content of the examination level at time t11, the voice recognition device 40 generates identification information of the examination level corresponding to "thickness" (for example, text describing "thickness") as related information. The related information is instantly acquired by the information processing device 10A.
[0069] When a doctor or radiologist makes an utterance including the term "kizami" indicating the contents of the examination level at time t12, the voice recognition device 40 generates identification information of the examination level corresponding to "kizami" (for example, text describing "kizami") as related information. The related information is instantly acquired by the information processing device 10A.
[0070] At time t13 when the radiation switch signal transitions from low level to high level, radiation irradiation is started in the radiation image capturing device 20. In a swallowing contrast examination, a series of radiation images are captured by continuously irradiating radiation. The series of radiation images constitute each frame when the series of radiation images are displayed as a moving image. A plurality of radiation images from the first frame to the nth frame are generated in the radiation image capturing device 20 by time t15 when the radiation switch signal transitions from high level to low level. During this period, pulsed radiation is irradiated multiple times in accordance with the radiation control pulse. One radiation image (one frame) is generated by irradiating one pulse of radiation. That is, each frame is generated in synchronization with the radiation control pulse.
[0071] When a doctor or radiologist makes an utterance including the term "Kayu" indicating the content of the examination level at time t14 during the period of capturing a series of radiation images, the voice recognition device 40 generates identification information of the examination level corresponding to "Kayu" (for example, text describing "Kayu") as new related information. The new related information is instantly acquired by the information processing device 10A.
[0072] The information processing device 10A determines the inspection level identification information corresponding to “Notch”, which is the latest related information acquired up to time t13 when the radiation switch signal transitions to a high level, as related information corresponding to each of the radiation images (first frame and second frame) acquired up to time t14 when new related information is acquired, and associates them with each other.
[0073] The information processing device 10A determines the examination level identification information corresponding to "itch", which is new related information acquired at time t14 during the radiation shooting period, as the related information corresponding to each of the radiation images acquired after time t14 (from the third frame to the nth frame), and associates them with each other.
[0074] The information processing device 10A generates a data file 60A including image group data 61A including a portion of the series of radiation images (first and second frames) and a data block 63A including related information 62A corresponding to "nibble", and a data block 63B including image group data 61B including another portion of the series of radiation images (third to nth frames) and related information 62B corresponding to "kayu", and stores this on a recording medium.
[0075] As described above, when the information processing device 10A according to the second embodiment of the disclosed technology acquires new related information generated by recognizing voice uttered during the period in which a series of radiological images are captured, the information processing device 10A associates the new related information with a radiological image among the series of radiological images that is acquired after the acquisition of the new related information.
[0076] In a swallowing contrast examination, a series of radiographic images may be captured while sequentially changing the examination level. In this case, it is necessary to be able to grasp which frame of a video consisting of a series of radiographic images corresponds to which examination level. According to the information processing device 10A according to the present embodiment, when new related information generated by recognizing a voice uttered during the period of capturing a series of radiographic images is acquired, the radiographic images acquired after the acquisition of the new related information are associated with the new related information among the series of radiographic images, so that the user does not need to perform a special operation for associating each frame with the related information.
[0077] [Third embodiment] 11 is a functional block diagram showing an example of a functional configuration of an information processing device 10B according to a third embodiment of the disclosed technology. Like the information processing device 10A according to the second embodiment described above, the information processing device 10B has a function of associating different related information with each frame of a video composed of a series of radiation images. The information processing device 10B according to the third embodiment further includes a playback control unit 14. The playback control unit 14 displays a radiation image associated with designated related information from among the series of radiation images.
[0078] It is assumed that a data file in which certain related information is associated with some frames of a moving image constituted by a series of radiation images and other related information is associated with some other frames is generated by the association processing unit 13, and this data file is stored in the recording medium 70. The recording medium 70 may be a non-volatile memory 103 included in the information processing device 10B.
[0079] The user operates the input device 104 to give an instruction to play the data file stored in the recording medium 70 together with the designation of related information to the information processing device 10B. The user can designate a portion (frame) to be played back from a moving image composed of a series of radiation images by designating the related information. For example, when trying to play back a portion (frame) associated with identification information corresponding to "notches" as related information, the user designates "notches" and issues an instruction to play the data file. In response to the above-mentioned playback instruction, the playback control unit 14 reads out the data file from the recording medium 70 and plays back image group data included in the data file that is associated with related information corresponding to "notches". A part of the radiation images associated with related information corresponding to "notches" from the series of radiation images is displayed as a moving image on the display 105.
[0080] As described above, according to the information processing device 10B relating to the third embodiment of the disclosed technology, when playing back a video consisting of a series of radiological images taken while sequentially changing the inspection level, it becomes possible to easily play back a portion (frame) corresponding to a desired inspection level.
[0081] In the above-described embodiments, the disclosed technology is applied to a radiological image acquired in a videofluoroscopic examination, but the disclosed technology is not limited to this. The disclosed technology can be applied to any radiological image acquired in an examination or diagnosis other than a videofluoroscopic examination.
[0082] In addition, in each of the above embodiments, the radiographic imaging system 1, 1A includes the voice recognition device 40, but the information processing device 10, 10A, 10B may have at least a part of the functions of the voice recognition device 40. For example, the voice recognition device 40 may transmit a voice recognition result to the information processing device 10, and the information processing device 10 may generate related information based on the recognized voice. Also, the information processing device 10, 10A, 10B may recognize voice and generate related information based on the recognized voice.
[0083] The hardware for executing the processes in each functional unit of the information processing devices 10, 10A, and 10B may be various processors as shown below. The processor may be a CPU that executes software (programs) and functions as various processing units. The processor may also be a programmable logic device (PLD) that can change the circuit configuration, such as an FPGA. The processor may also have a circuit configuration designed specifically for executing specific processes, such as an application specific integrated circuit (ASIC).
[0084] Each of the functional units of the information processing devices 10, 10A, and 10B may be configured with one of the various processors described above, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs or a combination of a CPU and an FPGA). Also, multiple functional units may be configured with one processor.
[0085] In the above embodiment, the association program 110 is pre-stored (installed) in the non-volatile memory 103, but the present invention is not limited to this. The association program 110 may be provided in a form recorded on a recording medium such as a CD-ROM (Compact Disc Read Only Memory), a DVD-ROM (Digital Versatile Disc Read Only Memory), or a USB (Universal Serial Bus) memory. The association program 110 may be downloaded from an external device via a network.
[0086] The following supplementary notes are further disclosed regarding the above first to third embodiments. (Appendix 1) An information processing device having at least one processor, The processor, A series of radiographic images are obtained by successively irradiating the radiation; acquiring related information related to the imaging content of the series of radiation images, the related information being generated by recognizing a voice; Correlating the series of radiation images with the related information Information processing device.
[0087] (Appendix 2) The processor, The latest related information acquired before a predetermined timing synchronized with the capturing of the series of radiation images is associated with the series of radiation images. The information processing device according to claim 1.
[0088] (Appendix 3) The predetermined timing is the timing of starting irradiation of radiation that is continuously irradiated in capturing the series of radiation images. 3. An information processing device according to claim 2.
[0089] (Appendix 4) The predetermined timing is determined by receipt of a radiation switch signal, transmitted by a user input means, indicating the start of successive exposures in capturing the series of radiation images. 4. The information processing device according to claim 3.
[0090] (Appendix 5) The processor generates a data file including video data including the series of radiographic images and the associated information. 5. An information processing device according to any one of claims 1 to 4.
[0091] (Appendix 6) The processor includes a notation corresponding to the associated information in a filename of a data file including the series of radiological images. 6. An information processing device according to any one of claims 1 to 5.
[0092] (Appendix 7) The processor processes video data including the series of radiographic images so that notations corresponding to the related information are displayed together with the series of radiographic images. 7. An information processing device according to any one of claims 1 to 6.
[0093] (Appendix 8) When the processor acquires new related information generated by recognizing a voice uttered during an imaging period of the series of radiation images, the processor associates the new related information with a radiation image acquired after acquisition of the new related information among the series of radiation images. 8. An information processing device according to any one of claims 1 to 7.
[0094] (Appendix 9) The processor displays a radiographic image associated with designated related information from among the series of radiographic images. 9. An information processing device according to any one of claims 1 to 8.
[0095] (Appendix 10) The processor, Acquire relevant information generated by a method other than voice recognition; To replace related information generated by speech recognition with related information generated by a method other than speech recognition 10. An information processing device according to any one of claims 1 to 9.
[0096] (Appendix 11) The processor issues an alert if the associated information associated with the series of radiological images does not include specific information. 11. An information processing device according to any one of claims 1 to 10.
[0097] (Appendix 12) The related information is information indicating a type of a sample used in an examination using the series of radiation images. 12. An information processing device according to any one of claims 1 to 11.
[0098] (Appendix 13) The related information is information indicating a type of posture of the subject in the examination using the series of radiation images. 13. An information processing device according to any one of claims 1 to 12.
[0099] (Appendix 14) The test is a swallowing contrast test. 14. The information processing device according to claim 12 or 13.
[0100] (Appendix 15) The related information is information indicating a type of imaging direction of the series of radiation images. 2. An information processing device according to claim 1.
[0101] (Appendix 16) The related information is generated by recognizing a voice that pronounces a predetermined term. 16. An information processing device according to claim 1 .
[0102] (Appendix 17) A series of radiographic images are obtained by successively irradiating the radiation; acquiring related information related to the imaging content of the series of radiation images, the related information being generated by recognizing a voice; Correlating the series of radiation images with the related information An information processing method in which processing is executed by at least one processor provided in an information device.
[0103] (Appendix 18) A series of radiographic images are obtained by successively irradiating the radiation; acquiring related information related to the imaging content of the series of radiation images, the related information being generated by recognizing a voice; Correlating the series of radiation images with the related information A program for causing at least one processor in an information device to execute a process. [Explanation of symbols]
[0104] 1 Radiography system 10, 10A, 10B Information processing device 11 Image acquisition section 12 Related Information Acquisition Department 13 Correspondence Processing Unit 14 Playback control section 20 Radiation imaging device 21 Photo stand 22 Stand 23 Pillar 24 Radiation Generation Unit 25 Radiation source 26 Collimator 27 Radiation Detector 30 Sound recording device 40 Voice recognition device 50 Wheelchair 60, 60A, 60B Data File 61, 61A, 61B Image Group Data Related information for 62, 62A, 62B 63A, 63B Data Blocks 70 Recording media 101 CPU 102 RAM 103 Non-volatile memory 104 Input Devices 105 Display 106 Communication Interface 108 Bus 110 Matching Program
Claims
1. An information processing device including at least one processor, The processor, A series of radiographic images are obtained by successively irradiating the radiation; acquiring related information related to the imaging content of the series of radiation images, the related information being generated by recognizing a voice; Correlating the series of radiation images with the related information Information processing device.
2. The processor, The latest related information acquired before a predetermined timing synchronized with the capturing of the series of radiation images is associated with the series of radiation images. The information processing device according to claim 1 .
3. The predetermined timing is the timing of starting irradiation of radiation that is continuously irradiated in capturing the series of radiation images. The information processing device according to claim 2 .
4. The predetermined timing is determined by receipt of a radiation switch signal, transmitted by a user input means, indicating the start of successive exposures in capturing the series of radiation images. The information processing device according to claim 3 .
5. The processor generates a data file including image collection data including the series of radiographic images and the associated information. The information processing device according to claim 1 .
6. The processor includes a notation corresponding to the associated information in a filename of a data file including the series of radiological images. The information processing device according to claim 1 .
7. The processor processes image group data including the series of radiographic images so that notations corresponding to the related information are displayed together with the series of radiographic images. The information processing device according to claim 1 .
8. When the processor acquires new related information generated by recognizing a voice uttered during an imaging period of the series of radiation images, the processor associates the new related information with a radiation image acquired after the acquisition of the new related information among the series of radiation images. The information processing device according to claim 1 .
9. The processor displays a radiographic image associated with designated related information from among the series of radiographic images. The information processing device according to claim 1 .
10. The processor, Acquire relevant information generated by a method other than voice recognition; To replace related information generated by speech recognition with related information generated by a method other than speech recognition The information processing device according to claim 1 .
11. The processor issues an alert if the associated information associated with the series of radiological images does not include specific information. The information processing device according to claim 1 .
12. The related information is information indicating a type of a sample used in an examination using the series of radiation images. The information processing device according to claim 1 .
13. The related information is information indicating a type of posture of the subject in the examination using the series of radiation images. The information processing device according to claim 1 .
14. The test is a swallowing contrast test. The information processing device according to claim 12 or 13.
15. The related information is information indicating a type of imaging direction of the series of radiation images. The information processing device according to claim 1 .
16. The related information is generated by recognizing a voice that pronounces a predetermined term. The information processing device according to claim 1 .
17. A series of radiographic images are obtained by successively irradiating the radiation; acquiring related information related to the imaging content of the series of radiation images, the related information being generated by recognizing a voice; Correlating the series of radiation images with the related information An information processing method in which processing is executed by at least one processor included in an information device.
18. A series of radiographic images are obtained by successively irradiating the radiation; acquiring related information related to the imaging content of the series of radiation images, the related information being generated by recognizing a voice; Correlating the series of radiation images with the related information A program for causing at least one processor included in an information device to execute a process.
Citation Information
Patent Citations
Contents and meta data recording and reproducing device and contents processing device and program
JP2007082088A
Training device for endoscope
JP2014036682A