JPH04321096A - Work station for operation room - Google Patents

Abstract

PURPOSE:To enable a doctor in operation to drive in non-contact a work station set up in an operation room. CONSTITUTION:The work station is constituted of a microphone for inputting doctor's voice, a means for identifying the input voice and the contents of a display instruction and a means for selecting diagnostic information to be displayed on a screen in accordance with the identified results and displaying the selected information on the screen. Since the work station set up in the operation room can be handled in non-contact, the work station can be prevented from being soiled even at the time of operating a patient suffered from an infective desease or the like and the generation of unnecessary infection can be prevented.

Description

[Detailed description of the invention]

0001

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a workstation that can be installed in an operating room, and more particularly to a workstation for operating rooms that allows input of operating commands without contact.

0002

[Prior Art] Conventional operating room workstations are
It is a contact type system that uses a keyboard, and doctors in the operating room can directly touch the keyboard to display the necessary diagnostic information on a multi-window screen. here,
The multi-window format is used because there are cases where, for example, an electroencephalogram measurement waveform and a three-dimensional head CT image are displayed simultaneously on one screen for diagnosis. In addition to waveforms and images, the diagnostic information also includes text such as reports.

0003

[Problems to be Solved by the Invention] A contact type method using a keyboard is not preferable during surgery for infectious diseases because pathogenic bacteria may adhere to the keyboard. for example,
If another surgeon uses this keyboard, there may be a risk of infection.

[0004] An object of the present invention is to provide a workstation for an operating room that uses a non-contact operation input format to improve safety such as prevention of infectious diseases and improve operability.

[0005]

[Means for achieving the object] The present invention provides a microphone for inputting voice from an operator, identifying the input voice,
The present invention comprises means for identifying the contents of a display command, and means for selecting diagnostic information to be displayed on the screen based on the identification result and displaying the same on the screen (Claim 1).

The present invention further provides a means for inputting reference speech from an operator, performing waveform analysis, extracting features, and storing the extracted features, a microphone for inputting display command speech from the operator, means for analyzing the waveform of input speech and extracting features; means for identifying display commands by comparing the extracted features with the stored extracted features; and selecting diagnostic information to be displayed on the screen based on the identification results. and means for displaying the information on the screen (Claim 2).

[0007]

According to the present invention, the operation input format is voice, and the voice is identified to select and display diagnostic information according to the content of the display command (Claim 1).

[0008]Furthermore, the present invention allows the operator to input a reference voice in advance and store its characteristics, and identifies the actually input display command voice by comparing it with these characteristics (Claim 2). .

[0009]

Embodiment FIGS. 2 and 3 show flowcharts of reference voice input processing. In FIG. 2, a doctor, who is an operator, calls a reference voice and captures it into the workstation through a microphone (step 101). This reference sound is a sound that means various commands used for display commands, such as "electroencephalogram waveform", "MR image", "head C
These are sounds such as "T3-dimensional image", "electrocardiogram", and "brain diagnosis report". Instead of these word sounds, "electroencephalography"
It is also possible to enter voice input into words such as ``brain'', ``wave'', and ``meter'', or break it down further into words such as ``brain'', ``wave'', and ``meter''. Note that there is also a voice format in which key terms are set in advance and are called out. For example, instead of "electroencephalograph waveform", you may use "electroencephalograph" or "electroencephalogram".
There are things like that. Next, in step 102, the input audio waveform is analyzed. This analysis process is digital processing. The analysis processing includes peak detection processing, spectrum analysis processing using Fourier transform processing, histogram processing, and the like.

[0010] In step 103, from the analysis processing results,
Voice features are extracted, and in step 104, these extracted features are registered as data. Extracted features include peak distribution, spectral distribution, intensity distribution by histogram processing, and the like. In addition to these, there may be parameters indicating various characteristics.

[0011] In step 105, the number of voices is checked, and steps 101 to 10 are performed until the number of voices reaches the specified value N.
Repeat step 4.

FIG. 3 is an embodiment diagram in which the processing flow of FIG. 2 is clearly displayed by adding waveforms. First, the doctor makes a reference voice call and causes the workstation to automatically receive the electrical signal of the voice through the microphone (step 201). Next, in step 202, waveform analysis processing is performed. This analysis process provided an example of peak detection. There are two types of peaks: upper peaks and lower peaks. The upper peak is the maximum value, and the lower peak is the minimum value. In step 203, the peak value obtained in the analysis process is extracted as a feature amount, and in step 204, this is registered in the memory. As for the registration method, the term "electroencephalograph" and the peak value of the voice "electroencephalograph" are stored in correspondence.

FIG. 1 is a flowchart of the voice identification process of the present invention. As a prerequisite for this processing, it is necessary that the reference speech is inputted in the processing according to FIGS. 2 and 3, and that its extracted features are stored in the memory.

In FIG. 1, in step 301, the doctor who has input the reference voice inputs the voice for display commands into the workstation through the microphone. In step 302, waveform analysis of the audio electrical waveform is performed, and in step 30
In step 3, the features are extracted. In step 304, FIG.
, the memory created in FIG. 2 is searched to see if a feature matching the feature extracted in step 303 is registered. If there is a matching feature, words for display commands associated with the feature are extracted (step 305). Extracting words from "characteristics" is a kind of translation,
In the figure, it is "translated into instructions." In step 306, the function of the command is executed and diagnostic information corresponding to the command is displayed on the screen.

FIG. 4 is a processing flow specifically showing the processing of FIG. The doctor calls the two words "electroencephalogram" and "head CT 3D image" into the microphone and imports them into the workstation (step 4).
01). In step 402, these two voices are subjected to waveform analysis processing one after another, and in step 403, their peak values are extracted as feature quantities. In step 404, FIG.
In Figure 3, the registered memory is searched and the presence or absence of matching features is automatically checked. As a result, since matching features have already been registered, they match the extracted features of "electroencephalograph" and "head CT three-dimensional image," respectively. Step 4
In step 05, this is translated into an instruction, and in step 406,
The diagnostic information corresponding to this command is read and displayed.

An example of this display is shown in FIG. FIG. 5 is an example of a display screen of a workstation with a multi-window function, and shows the side of the screen 501 on which the electroencephalograph measurement waveform is displayed on the left side and the head CT three-dimensional image is displayed on the right side.

FIG. 6 is a diagram of an embodiment of a surgical workstation that implements the processes of FIGS. 1-5. This workstation consists of an input device 1, an output device 2, and various measuring instruments 3.
, an image processing device 4, and a data transfer bus 5.

[0018] The input device is a voice terminal for operation (such as a microphone), which replaces a keyboard. The output device 2 consists of a display means such as a CRT or a printer, and the figure shows an example of a CRT. The measuring device 3 refers to various measuring machines, and includes various measuring means such as an electroencephalograph, an electrocardiograph, an X-ray CT device, and an MRI device.

The image processing device 4 includes a central processing unit (CPU).
) 40, a main storage device 41, a high-speed arithmetic unit 42, and an external storage device 43, which are commonly connected to each other via a data transfer bus 5. The central processing unit 40 and main memory 41 are the main parts of the computer, and perform various processes as shown in FIGS. 1 to 4 according to programs. The high-speed arithmetic unit 42 performs dedicated processing instead of the processing by the CPU 40, and is used for image processing and the like. It can also be used for waveform analysis and feature extraction in FIGS. 1 to 4.

Now, in FIG. 6, the doctor's voice input is as follows:
This is performed via the terminal 1, and the reference voice is registered in a part of the main storage device 41. Furthermore, the diagnostic information can be input directly online (for example, online electroencephalograms from the electroencephalogram of the measuring device 3) or registered offline in the external storage device 43. In the example of FIG. 5, during surgery, the electroencephalogram (example shown on the left) is obtained directly from the patient online, and the head CT three-dimensional image is the online data stored in the external storage device 43. This is what is displayed.

The CPU 40 performs the processes shown in FIGS. 2 and 3 based on such voice input, and registers the extracted features of the reference voice in the main storage device 41. Furthermore, the CPU 40 inputs the actual display command voice, performs the processing shown in FIGS. 1 and 4, finds a command that matches the input display command voice, processes this, and displays the command on the screen in a multi-window format. Thus, in the case of the display example shown in FIG. 5, the waveform of the electroencephalogram of the patient undergoing surgery can be determined by comparing it with the examined CT image, and diagnostic ability can be improved. At this time, since the display instructions can be given by voice, the workstation will not be contaminated even when performing surgery on a patient with an infectious disease, and as a result, the risk of infection to other doctors etc. will be reduced.

Although the above has been an example of operation for displaying images during surgery, the workstation of this embodiment can also be used in cases where there is a request to perform simulations or the like before surgery to increase the success of the surgery. In these cases, the diagnostic information
It may be stored offline in an external storage device.

[0023]

[Effects of the Invention] The present invention has the following effects. (1) Since the workstation can be controlled without contact using the doctor's voice, infections can be prevented. (2) The voice control improves the operability of the workstation. (3) By installing the workstation in the operating room, it is possible to easily refer to diagnostic plans such as pre-operative simulations.

[Brief explanation of drawings]

FIG. 1 is a flowchart of display command voice processing of the present invention.

FIG. 2 is a flowchart of reference voice registration processing of the present invention.

FIG. 3 is a detailed flowchart of the reference voice registration process of the present invention.

FIG. 4 is a detailed flowchart of display command voice processing of the present invention.

FIG. 5 shows an example of a multi-window display according to the present invention.

FIG. 6 is an embodiment diagram of a workstation of the present invention.

[Explanation of symbols]

1 Input device (voice terminal for operation) 2 Output device 3 Measuring instruments 4 Image processing device

Claims (2)

[Claims] Claim 1: In an operating room workstation that displays a plurality of pieces of diagnostic information in a multi-window format on a screen and that can be installed in an operating room, a microphone that inputs audio from an operator and the input audio are identified, A workstation for an operating room, comprising means for identifying display command contents, and means for selecting diagnostic information to be displayed on a screen based on the identification result and displaying the same on the screen. [Claim 2] An operating room workstation that displays multiple pieces of diagnostic information in a multi-window format on a screen and that can be installed in an operating room, inputs a reference voice from an operator, performs waveform analysis, and extracts features. , a means for storing the extracted feature, a microphone for inputting a display command voice from an operator, a means for performing waveform analysis of the input voice and extracting the feature, and a means for storing the extracted feature and the stored extracted feature. 1. A workstation for an operating room, comprising: means for identifying a display command by comparing the results; and means for selecting diagnostic information to be displayed on a screen based on the identification result and displaying the same on the screen.