JPH11188027A - Medical diagnosis device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To improve an operation by having an input procedure that lists up words and phrases, 'which?', 'where?', 'how long or how mach?', 'what?', those are operational commands, and controlling a device with the word that recognizes a reception of voice and the word that performs the voice. SOLUTION: At a radiography device, when operator moves, for example, a table 2, he inputs voice, 'command', 'table', 'ahead', '50 mm', 'move slowly', 'perform' with a voice input device 5 following a voice input procedure displayed on a confirmation monitor 29. The input word is converted to voice signal pattern. After a noise rejection, voice signal pattern 79 is calculated a similarity comparing to the voice signal pattern 78 that is previously registered and called at any time. When the pattern almost agrees with, the word is determined of its classification, displayed on the confirmation monitor 29, output to a command conversion part 7 and it makes the table 2 move as he desired.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention
The present invention relates to a medical diagnostic apparatus which enables operation by voice without touching the operation means of a medical diagnostic apparatus such as an X-ray CT apparatus, a magnetic resonance imaging apparatus, and an ultrasonic diagnostic apparatus. The present invention relates to a medical diagnostic device that recognizes and operates with naturally handled words.

[0002]

2. Description of the Related Art In medical diagnostic apparatuses, recently, a treatment method called IVR (interventional radiology) under X-ray fluoroscopy has been actively performed. In this treatment, since the surgeon keeps his hands clean, he cannot touch the operating device, and employs a method of requesting a third party to perform an operation. However, since the operation of the operator is not well communicated and the operation takes time, improvement has been desired.
Therefore, a method for improving this is disclosed in Japanese Patent Application Laid-Open No. 8-229028.
Is disclosed. In this method, words corresponding to the device to be operated and the content of the operation, that is, operation commands, are determined in advance, these are registered as own voices, and the voices are stored in the specific speaker-compatible voice recognition device. When the device is activated and a voice input operation is enabled, the operator inputs an operation command toward the microphone of the voice input device. The voice recognition device recognizes the input operation command, decodes the command with the control device, and supports the support table, the patient table,
The operation setting of a device such as a monitor is performed, and a control command is sent to each device to operate each device.

[0003] According to this method, an operator can operate the apparatus without using a hand.

[0004]

However, in an IVR system, there are many devices to be operated, such as device operation and image operation. To operate all these devices, the number of words that can be handled by voice is limited. And it becomes difficult for the surgeon to memorize all of the words. In addition, if the words to be operated are limited, if the words are forgotten, the operation may not be able to be continued. In an emergency, a problem remains. On the other hand, it is conceivable to monitor words that can be input by voice, but since the surgeon does not know which device to operate next, it is necessary to display all of the words that can be input on the monitor. However, it takes time and effort for the surgeon to search for the word to be commanded from many words, and this reduces the effect of using voice.

An object of the present invention is to provide a medical diagnostic apparatus which operates by voice without having to store all of the words to be operated and which can be operated even when the registered words are forgotten. Is to do.

[0006]

SUMMARY OF THE INVENTION The object of the present invention is to provide a control means for operating each part of the apparatus in response to various commands from an operation means, a sound input apparatus for converting a sound into an electric signal and outputting the signal, and a predetermined object. A voice storage device in which the control means control words are registered, and an output signal of the voice input device and voice data stored in the voice storage device are compared. A voice recognition device for determining which of the above is applicable, and a command conversion transmission device for converting the words determined by the voice recognition device into corresponding control commands, setting the operation of each section of the device, and inputting this to the control means And a medical diagnostic apparatus for operating each part of the apparatus by an output signal of the command conversion transmission device, wherein the voice input device includes input means for inputting words for controlling the control means,
A procedure for inputting words for controlling the control means is determined, and at the beginning of the procedure, a word for accepting a voice to be inputted and a speech input at the end of the procedure for adding a word for executing an operation by the voice inputted so far. This is achieved by inputting words for controlling the control means to the voice recognition device in accordance with the procedure of the voice input procedure means.

Specifically, the voice input procedure means inputs a command to be operated from now on in the form of one sentence, and includes "what", "how", "how much or how much", An input procedure for arranging the words "what do you want to do?", And words for recognizing reception of a voice at the beginning of the input procedure and words for executing the voice of the input procedure means at the end of the input procedure It is.

In this manner, the procedure for inputting the words for controlling the control means is determined, and at the beginning of this procedure, the words to be accepted for the speech to be inputted and the operation at the end of the procedure are executed by the inputted speech. By providing the voice input procedure means to which words are added, it is not necessary to store all the words stored in the voice storage device,
Even if these stored words are forgotten, voice can be input according to the voice input procedure. This eliminates the need to memorize all the words to be operated,
In addition, the operation can be performed even when the registered words are forgotten, and the reliability and safety of the voice operation can be improved.

In order to enable the operation even if the voice input procedure is forgotten, the voice input procedure is displayed on a confirmation monitor means for displaying the voice input procedure on a monitor. If you enter it,
Furthermore, reliability and safety are improved.

[0010]

Embodiments of the present invention will be described below with reference to the drawings. FIG. 2 is a view showing one embodiment (example) of the present invention, and exemplifies a case where the voice operating means according to the present invention is used in a circulatory organ X-ray inspection apparatus. In FIG.
1 is a patient, 2 is a table which moves in the direction before and after placing the patient, left and right, up and down, etc., 3 is a console for operating the table and the like, 4 is a foot switch for controlling X-rays, 21 is an imaging intensifier ( Hereinafter, referred to as II) 2
2 and a support mechanism for supporting the X-ray tube 23; I. 2
A support mechanism for supporting the X-ray tube 5 and the X-ray tube 26 and a monitor 28 for observing an X-ray image are installed in an examination room.
I. I. The reference numerals 22 and 25 can be moved up and down in order to widen the field of view of the part being photographed or enlarge the image. During inspection, this I.D. I. Up and down movement may be performed.

The combination of the photographing system supported by the support mechanism 21 and the photographing system supported by the support mechanism 24 facilitates positioning from multiple directions, and allows a target blood vessel to be selected from a group of complicatedly moving blood vessels. An X-ray fluoroscopic image can be obtained. The fluoroscopy is performed by operating the foot switch 4.

The operator 41 performs a catheter operation (not shown) while always observing the X-ray fluoroscopic image. In the X-ray fluoroscopic image, the operator 41 operates the foot switch 4 to output an irradiation signal, and as shown in FIG. 3, receiving the irradiation signal, X-rays are irradiated from the X-ray tube, and the patient's body is illuminated. X penetrated
Line I. I. The received signal is converted into a digital signal by an A / D converter 55 and sent to an image processing unit 56. The sent image signal is subjected to image processing such as conversion of contrast and gamma characteristics, and sent to a display gradation processing unit 57 for performing gradation processing. After the gradation processing, the digital image signal is converted to an analog signal by the D / A converter 58 and displayed on the monitor 28.

When the positioning is completed, a contrast medium is injected into the blood vessel through the catheter, and imaging is performed, for example, a cine camera 45 is used for film imaging.

The circulatory organ X-ray examination apparatus includes a support mechanism for two imaging systems, a patient table, I. There are many devices, such as image display, that the surgeon wants to operate as he or she wants. A system for performing this operation through the operator's own voice will be described with reference to FIG.

This system comprises a voice input unit 5, a voice analysis unit 6 (a voice storage device and a voice recognition device) comprising a microphone (voice input means) 5a for inputting voice and a voice input procedure means 5b, a command conversion unit 7, The system operation control unit 8 and the confirmation monitor 29 are configured.

The words of the command to be operated are inputted from the microphone 5a and processed by the voice input procedure means 5b shown in FIG. 1 in accordance with the following procedure. (1) First, a word (phrase) for permitting operation by voice input, for example, "command" is input (step 3).
0). (2) Next, "what" (step 31), (3)
Input the words necessary for the operation in the order of "how" (step 32), (4) "how much or how much" (step 33), (5) "what" (step 34), Finally, a configuration is provided in which voice input means 5b for inputting, for example, "execute" (step 35) so that it can be recognized as one sentence is provided.

In the above voice input procedure, words to be voice input are displayed on the confirmation monitor 29 in order to avoid having to memorize them, and words required for operation are input from the microphone 5a in accordance with the voice input procedure. Manipulate.

Next, the operation of the circulatory organ X-ray inspection apparatus shown in FIG. 2 operated by voice using the voice input procedure means 5b will be described. The IVR procedure performs examination and treatment on a target site while performing angiography on the heart, head, abdomen, and the like. For example, for a patient 1 having a heart disease, Insert a catheter, X
Monitor the progress of the catheter by fluoroscopy.
Proceed inside the blood vessel toward the heart while confirming with. At this time, the operation is performed while the table 2 on which the patient is lying is operated back and forth, left and right, up and down, and the like. Since the operator cannot operate the table by hand because of the operation of the catheter, the operator displays the voice input microphone 5a in advance on the confirmation monitor 29 when the operator operates the table, for example. In accordance with a given voice input procedure, "command", "table", "forward", "50 mm", "moving slowly", and "execute" are input based on the voice input procedure means 5b.

The input words are processed in the following steps in the voice analysis unit shown in FIG. (1) The input word is converted into an audio signal pattern and noise is removed (step 70). (2) A previously registered audio signal pattern 78 is called at any time (step 71), and (3) a similarity is calculated while comparing with the input audio signal pattern 79 (step 72).
(4) It is determined whether or not the degree of similarity with the previously registered voice pattern 78 is equal to or greater than a specified value (whether or not the pattern is the same as the input voice signal pattern) (step 7).
3), (5) If the input audio signal pattern is the same pattern, determine the pattern (step 74), (6)
Recognize what the words of the voice pattern are (step 75), (7) From the recognized words, determine which classification of the input procedure means the words fall into (step 76). (8) Store it in the classification box of the voice analysis unit (step 77) and display it on the confirmation monitor 29 at the same time.

To which classification of the input procedure means 5b the word recognized according to the above-described procedure is applicable is determined from the speech signal pattern 78 registered in advance, which is classified according to the classification. Becomes possible. As described above, by inputting the first word “command”, the subsequent words are recognized as words controlled by voice, not private words, and the subsequent words are sent to the voice analysis unit 6 word by word. Only the analyzed words are displayed on the confirmation monitor 29.

The operator inputs the last "execute" while checking the display, and the voice analysis unit 6 confirms that all the classification boxes in the voice analysis unit 6 have been filled, and inputs the analyzed words. Output to the command converter 7. The command conversion unit 7 converts the analyzed words and signals into a command signal in accordance with a predetermined matrix, and sets the operation of the operation target device (in this case, a table). Is output to the system operation control means 8 to operate each unit (table in this case). Then, the operation result is displayed on the screen of the confirmation monitor 29.

In the above example, the case of a table has been described, but the object to be operated is not limited to the table.
I. There are many objects to be operated, such as two support mechanisms for the X-ray tube and the X-ray tube, and the re-display of the captured image. More than 50 words are required for the operation of only one target device.

It is difficult for the operator to memorize all such words, and if these words are forgotten, no operation can be performed, leading to a factor that lowers safety.

Therefore, by analyzing the words necessary for the operation by the voice input means 5b and the voice analysis unit 6, the operator does not need to memorize anything, and can decide only the first and last words. If this is the case, the device can be operated in the normal natural language of the surgeon, so that safety is improved.

Also, in order to limit the words that can be input by voice as much as possible, for example, "table" means words commonly used such as "sleeper" and "table" as the same object. Thus, the matrix of the voice analysis unit 6 is formed. By doing so, the operator does not need to worry about the words of the voice input.

[0026]

As described above, according to the present invention,
The voice input procedure is performed by the voice input procedure
(Step 31), "How" (Step 32), "How much or how much" (Step 33), "What to do" (Step 34), and the procedure for inputting voice are determined, and First, a word for validating voice input, for example, "command" (step 30), and a word for recognizing and executing the last voice input word, for example, "execute" (step 35), and the words that can be input are: By providing a voice analysis unit that can handle commonly used words as the same target, the surgeon can operate with the words that are handled naturally every day. This eliminates the need for input, and allows many devices to be operated alone. Accordingly, in an emergency such as at night, the operation can be safely performed by one person, and the operation can be performed by one person. Therefore, it is not necessary to arrange staff members, and the operability of the medical diagnostic apparatus is improved.

[Brief description of the drawings]

FIG. 1 is a diagram showing processing steps of a voice input procedure means according to the present invention.

FIG. 2 is an overall configuration diagram in which the present invention is applied to a circulatory organ X-ray inspection apparatus.

FIG. 3 is a display control block diagram of the circulatory organ X-ray inspection apparatus.

FIG. 4 is a diagram showing processing steps of a voice analysis unit.

[Explanation of symbols]

 Reference Signs List 1 patient 2 table 3 console 5 voice input device 5a microphone 5b voice input procedure means 6 voice analysis unit (voice storage device and voice recognition device) 7 command conversion unit 29 confirmation monitor

Claims (1)

[Claims] A control means for operating each part of the apparatus in response to various commands from an operation means; a voice input device for converting a voice into an electric signal and outputting the signal; and a predetermined word for controlling the control means. A voice storage device to be registered is compared with an output signal of the voice input device and voice data stored in the voice storage device to determine which of the words for controlling the control means corresponds to. A speech recognition device, a command conversion transmission device that converts words determined by the speech recognition device into corresponding control commands, sets the operation of each section of the device, and inputs the operation settings to the control means; In a medical diagnostic apparatus that operates each section of the apparatus with an output signal, the voice input device determines input means for inputting the control means control words and a procedure for inputting the control means control words. At the beginning of this procedure, a word for accepting a voice to be input is provided, and at the end of the procedure, a speech input procedure means for adding a word for performing an operation by the voice input so far, A medical diagnostic apparatus characterized in that an input is made to the speech recognition apparatus according to a procedure of a speech input procedure means.