JP2003280681A - Apparatus and method for medical image processing, program, and recording medium - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To improve the operability of a medical image processor. <P>SOLUTION: As for the medical image processor 1, a control part 11 recognizes a user's aural signal inputted to a speech input part 19 by a speech recognition part in such a case and converts the signal into text data when the speech is inputted by a microphone. Then the control part 11 performs a process corresponding to the input text data by reference to a speech process correspondence file 151 storing processes to be carried out when various input buttons displayed on input pictures displayed at a display part 13 are pressed and text data while making them correspond to each other for every input screen so that they correspond to each other, and displays the processing result at the display part 13 and also the result is outputted from a speech output part 21. <P>COPYRIGHT: (C)2004,JPO

Description

Detailed Description of the Invention

[0001]

TECHNICAL FIELD The present invention relates to a medical image processing apparatus, a medical image processing method, a program, and a recording medium.

[0002]

2. Description of the Related Art In recent years, CT (Computed
Tomography) equipment and MRI (Magnetic Resonance Imag)
ing) devices such as medical image capturing devices and CR (Compute
d Radiography) device and FPD (Flat Panel Detector)
CRT by performing various image processing on medical images input as digital images by input devices such as various medical image reading devices such as DR (Digital Radiography) devices
A medical image processing device for displaying on a monitor such as the above or outputting to a film output device has been developed. By observing an image that is easily visualized by such a medical image processing apparatus, a doctor can make an accurate diagnosis.

In radiography used for diagnosis, there are a wide variety of regions to be imaged from the head to the extremities, and the areas the doctor pays attention to are different, so the image processing conditions for obtaining the optimum image for diagnosis are , It will be different for each imaging region. Similarly, the processing conditions vary depending on the shooting direction. Therefore, before performing image processing, in order to perform image processing under optimal processing conditions together with patient information, a radiologist or the like inputs in advance imaging conditions such as an imaging region and imaging direction of a subject. There is a need.

In many hospitals, hospital information systems (HI
S) and a radiology information system (RIS) are also provided, and it is possible to directly obtain patient information and radiographic region information from order information for radiography. In order to perform this, even in a hospital equipped with the above-mentioned HIS or RIS, an engineer or the like may input an imaging condition or the like.

After inputting the patient information and imaging conditions, the radiologist or the like inputs an instruction to the medical image processing apparatus such as starting reading of the image, acquires the medical image, and performs appropriate image processing. The applied image is displayed on a monitor such as a CRT. Then, the user confirms the positioning, etc., and if necessary, inputs an instruction to re-photograph or change the image processing condition.

[0006]

Conventionally, such information as photographing conditions and instructions is input by touching various instruction buttons displayed on the display screen, and the response result or processing of the input instruction or the like is performed. The result confirmed what was displayed on that screen.

However, since the method of inputting an instruction and the method of confirming an instruction in the conventional medical image processing apparatus are configured based on a manual input operation, the operation is complicated and time-consuming, and it is possible to reduce operation errors to the utmost limit. It was difficult. In particular, in general, there are several tens to several hundreds of regions to be imaged, and when an emergency patient or the like is imaged, a manual input operation is troublesome and an input error is likely to occur.

An object of the present invention is to improve the operability of a medical image processing apparatus.

[0009]

In order to solve the above-mentioned problems, the invention according to claim 1 uses a medical image processing apparatus for performing image processing on radiation medical image data on the basis of an input imaging condition, and outputs a sound. A voice input means for inputting; a voice recognizing means for recognizing the voice signal input by the voice input means; and a process executing means for executing a process corresponding to the voice signal recognized by the voice recognizing means. It is characterized by that.

According to a fifth aspect of the present invention, there is provided a medical image processing method in a medical image processing apparatus for performing image processing on radiation medical image data on the basis of input imaging conditions.
It is characterized by including a step of inputting a voice, a step of recognizing the input voice signal, and a step of executing a process corresponding to the recognized voice signal.

According to a sixth aspect of the present invention, there is provided a function of causing a computer for controlling a medical image processing apparatus for performing image processing on radiological image data to input a voice based on the input imaging condition, and the input. It is a program for realizing a function of recognizing the recognized voice signal and a function of executing a process corresponding to the recognized voice signal.

According to a seventh aspect of the present invention, there is provided a recording medium which stores a computer-executable program for controlling a medical image processing apparatus for performing image processing on radiation medical image data based on an input imaging condition. A computer-executable program code for inputting a voice, a computer-executable program code for recognizing the input voice signal, and executing a process corresponding to the recognized voice signal And a program including the program code executable by the computer.

According to the inventions of claim 1, claim 5, claim 6, and claim 7, in the medical image processing apparatus,
It is possible to recognize a voice signal input from the voice input unit and execute a process corresponding to the recognized voice. Therefore, a complicated input operation in the medical image processing apparatus can be performed easily and quickly.

According to a second aspect of the invention, in the first aspect of the invention, a voice synthesizing means for synthesizing voice text data for notifying the processing result based on the result of the processing executed by the processing executing means. And voice output means for converting the voice text data synthesized by the voice synthesizing means into a voice signal and outputting the voice signal.

According to the second aspect of the invention, the result of the processing executed by the instruction by voice input is notified by voice. Therefore, the omission of confirmation, which often occurs when confirming the processing result on the screen as in the prior art, is significantly reduced, and input errors can be reduced.

The invention according to claim 3 is the invention according to claim 1 or 2, further comprising an error detecting means for detecting whether or not there is an error in the voice signal recognized by the voice recognizing means. The synthesizing means synthesizes voice text data for warning the error based on the error detected by the error detecting means.

According to the invention described in claim 3, it is detected whether or not there is an error in the voice input, and if there is an error, a warning is given. Therefore, input errors can be further reduced.

The invention according to claim 4 is characterized in that, in the invention according to any one of claims 1 to 3, the voice synthesis means synthesizes voice text data for voice guidance for instructing an input method. There is.

According to the fourth aspect of the invention, voice guidance for instructing the input method is output. Therefore, the input can be performed smoothly.

[0020]

BEST MODE FOR CARRYING OUT THE INVENTION Embodiments of the present invention will be described below with reference to the drawings. The control unit 11 in the present embodiment has a function as a process execution unit and an error detection unit described in claims of the present invention, and the microphone of the voice input unit 19 has a function as a voice input unit. Having, voice input unit 1
The voice recognition unit 9 has a function as a voice recognition means. Further, the voice synthesizing unit 20 has a function as a voice synthesizing unit, and the voice output unit 21 has a function as a voice outputting unit.

First, the structure will be described. FIG. 1 is a diagram conceptually showing the overall configuration of the present embodiment. As shown in FIG. 1, the medical image processing apparatus 1 is connected via a cable 2 to a medical image reading apparatus 3 that reads radiation medical image information. Note that one or more medical image reading devices 3 can be connected to the medical image processing device 1.

The medical image processing apparatus 1 controls the operation of the medical image reading apparatus 3 when a radiological technologist or the like gives an instruction to take an image, acquires the taken radiological image information, and displays it on a display screen. .

The medical image reading device 3 is a medical image reading device provided with an X-ray irradiator, and is irradiated with X-rays from the X-ray irradiator in accordance with an instruction input from the controller 1 connected via the cable 2. Then, the radiation image information of the subject such as a human body by the X-rays emitted from the X-ray irradiator was once accumulated on the sheet-shaped stimulable phosphor plate formed by stacking the stimulable phosphor on the support. An object is scanned with a laser beam to sequentially accumulate stimulated emission of radiation image information, and the stimulated emission light is sequentially read photoelectrically to obtain an image signal. The medical image reading device 3 outputs the image signal thus obtained,
It is transmitted to the controller 1 via the cable 2 as medical image data. After reading the image signal, the medical image reading device 3 irradiates the stimulable phosphor plate with erasing light to release the radiation energy remaining on the plate, and prepares for the next imaging.

FIG. 2 is a block diagram showing the functional configuration of the medical image processing apparatus 1. Hereinafter, the internal configuration of the medical image processing apparatus 1 will be described in detail with reference to FIG.

As shown in FIG. 2, the medical image processing apparatus 1 is
Control unit 11, input unit 12, display unit 13, RAM 14, storage unit 15 having recording medium 15a, I / F 16, image analysis unit 17, image processing unit 18, voice input unit 19, voice synthesis unit 20, voice output unit. 21 and each unit is connected by a bus.

The control unit 11 includes a CPU (Central Processi).
ng Unit) and the like, which reads the system program and various control programs stored in the storage unit 15 and expands them in the RAM 14, and centrally controls the operation of each unit according to the expanded program. Further, the control unit 11 controls the RA
Various processes including a voice input process described later are executed according to the program expanded in M14, and the processing result is temporarily stored in the RAM 14 and displayed on the display unit 13. Then, the processing result stored in the RAM 14 is
It is stored in a predetermined storage destination of the storage unit 15 or the recording medium 15a.

The input unit 12 outputs position information input by touching a transparent sheet panel covering the display screen of the display unit 13 with a finger or a dedicated stylus pen to the control unit 11 as an input signal. Composed. Alternatively, the input unit 12 is a character / alphanumeric input key,
A keyboard having cursor keys and various function keys, a mouse as a pointing device, and the like are provided, and the control unit 11 receives a key press signal of a key pressed by the keyboard and a mouse operation signal as input signals. You may make it output.

The display unit 13 is an LCD (Liquid Crystal D).
isplay), a CRT (Cathode Ray Tube), etc., and displays an image on the display screen in accordance with an instruction of a display signal input from the control unit 11.

The RAM (Random Access Memory) 14 is
In various processes controlled to be executed by the control unit 11, a temporary storage area for a system program read from the storage unit 15 and executable by the medical image processing apparatus 1, various processing programs, input or output data, parameters, and the like. Becomes

The storage unit 15 is composed of an HD (Hard Disc), a non-volatile semiconductor memory, or the like, a system program corresponding to the medical image processing apparatus 1, various processing programs executable on the system program, and these. The data processed by the program is stored. The program is stored in the form of a computer-readable program code, and the control unit 11 sequentially executes operations according to the program code.

The recording medium 15a is composed of a magnetic or optical recording medium, or a non-volatile memory such as a semiconductor, and stores the program data and the medical image reading apparatus 3.
Stores various data including image data received from. The recording medium 15a is fixedly provided in the storage unit 15 or detachably mounted. In the present embodiment, the recording medium 15a is configured to include a sound processing correspondence file 151, a guidance sound file 152, a warning sound file 153, and a confirmation notification sound file 154.

The I / F 16 is an interface for the medical image processing apparatus 1 to connect to the medical image reading apparatus 3 via the cable 2. The I / F 16 acquires medical image data from the medical image reading apparatus 3 and outputs it from the control unit 11. In response to the instruction, the medical image data is output to the image analysis unit 17, the image processing unit 18, the display unit 13, the storage unit 15, and the like.

The image analysis unit 17 analyzes the medical image data input from the medical image reading device 3, determines the anatomical image region of the human body part of the image data, and determines the anatomical image region within the anatomical image region. The gradation processing conditions are determined from the statistical properties of the image data. Further, the contour of the human body part in the image data is anatomically recognized.

The image processing unit 18 is input from the medical image reading apparatus 3 or stored in the storage unit 15 according to an instruction from the control unit 11 based on the input image capturing condition or the set image processing condition. Image processing such as rotation processing and gradation processing is performed on the existing medical image data. In addition, a compression process of compressing in a predetermined encoding format, a decompression process of decoding and decompressing the compressed image data, and the like are executed.

The voice input unit 19 is composed of a microphone, a voice recognition unit, etc. (none of which are shown). Voice input unit 1
Reference numeral 9 denotes a user's voice signal input from a microphone after the voice input button of the input unit 12 is pressed down, voice-recognized by the voice recognition unit and converted into text data, and the converted text data is input to the control unit 11 as voice input information. Output. When the voice cancel button is pressed, voice input is stopped.

The voice synthesizing unit 20 stores warning voice data corresponding to the voice content obtained from the voice recognition result of the voice input unit 19 or the content input from the input unit 12 in the recording medium 15a. Warning sound file 15
Refer to 3 and synthesize. Further, the confirmation notification voice data corresponding to the result of the voice recognition or the processing performed based on the input content is synthesized with reference to the confirmation notification voice file 154. Also, the guidance voice data is synthesized with reference to the guidance voice file 152.

The voice output section 21 is composed of a speaker, a D / A converter, an amplifier, etc. (none of which are shown), and when a voice output instruction signal from the CPU 11 is inputted, text data of voice to be outputted. Is converted into a digital audio signal, the digital audio signal is converted into an analog signal by a D / A converter, and the analog audio signal is amplified to a predetermined volume by an amplifier and output as a sound from a speaker.

Next, the operation will be described. First, the voice input process executed by the medical image processing apparatus 1 will be described with reference to the flowchart of FIG.

When the predetermined key of the input unit 12 is operated and the display of the input screen such as the photographing condition input screen is instructed, the control unit 11 causes the display unit 13 to display the input screen (step S1). When the voice input button is pressed on the input screen (step S2; YES), the control unit 11 recognizes the voice input from the microphone of the voice input unit 19 thereafter as the input instruction signal so that the voice input mode is selected. (Step S3), the guidance voice data of the input method on the input screen is read from the guidance voice file 152 and synthesized by the voice synthesis unit 20, and the voice output unit 2
Output from 1 (step S4).

When voice is input from the microphone after switching to the voice input mode (step S5), the control unit 11
Causes the voice input unit 19 to cause the voice recognition unit to perform voice recognition of the input voice signal of the user and convert it into text data (step S6). Then, the control unit 11 stores, for each input screen displayed on the display unit 13, the process executed when various input buttons displayed on the input screen are pressed and the text data in association with each other. It is determined whether or not there is a process corresponding to the input text data by referring to the voice processing correspondence file 151 (step S).
7).

When it is determined that there is no processing corresponding to the input text data (step S7; NO), the control unit 1
1, the voice synthesizing unit 20 synthesizes the warning voice data corresponding to the input voice content with reference to the warning voice file 153, and outputs the synthesized voice data from the voice output unit 21 (step S8). In addition, the control unit 11 causes the voice synthesis unit 20 to synthesize the guidance voice data corresponding to the input voice content with reference to the guidance voice file 152, and outputs the guidance voice data from the voice output unit 21 (step S9).

When the control section 11 determines in step S7 that there is processing corresponding to the input text data (step S7; YES), it executes the processing corresponding to the input text data (step S10). Then, the control unit 11 displays the processing result on the display unit 13 and refers to the confirmation notification voice file 154,
The confirmation notification voice data is synthesized by the voice synthesizing unit 20 and output from the voice output unit 21 (step S11).

It is also possible to input from the input unit 12 after switching to the voice input mode. At this time, the input result is notified by voice.

Next, the above-mentioned voice input processing will be described by taking the photographing condition input screen as an example. FIG. 4 shows a shooting condition input screen 1
It is a figure which shows an example of 31. In the upper center of the imaging condition input screen 131 shown in FIG. 4, the imaging I of the patient to be imaged is taken.
D and name are displayed. On the upper right side of the screen, "Voice input" button to switch to voice input mode, "Voice cancel" button to cancel voice input mode, "Confirm" button to register the input shooting conditions, Input shooting A “delete” button for deleting the condition, a “cancel” button for canceling the input of the shooting condition, and the like are displayed. A "previous page" button for shifting the screen to the previous page and a "next page" button for shifting the screen to the next page are displayed on the lower right side of the screen.

The area 131a is a selected condition display area for displaying the selected photographing condition. A site region 131b is displayed below the selected condition display region 131a, and a selection region 131c is displayed further below. When a part (for example, abdomen) in the part region 131b is selected, the head of the abdominal option is jumped and displayed at the head of the option region 131c.

When this photographing condition input screen 131 is displayed (step S1 in FIG. 3) and the "voice input" button is pressed (step S2 in FIG. 3), the control unit 11 switches to the voice input mode (Fig. 3 step S3), and the voice guidance "Please input the shooting conditions" is output (step S4 in FIG. 3). When "cranial bone PA" is input from the microphone (step S5), steps S6 to S10
Is executed, and “Skull P is displayed in the selected condition display area 131a.
“→ A” is displayed and a confirmation notification voice “skull PA” is output from the voice output unit 21 (step S11 in FIG. 3). When the voice input "skull reese" is input from the microphone (step S5 in Fig. 3), the control unit 11 executes the steps "S6" and "S7", and then gives an error "Incorrect input. Please input again." The warning and the input guidance are output (steps S8 and S9 in FIG. 3).

As described above, when the photographing conditions are inputted by voice input, it is not necessary to display and select the choices of more than 100 kinds of the photographing parts by switching the screens one by one, and the input can be performed quickly.

As described above, according to the medical image processing apparatus 1, when the voice input button is pressed on the input screen, the control unit 11 changes the voice input from the microphone of the voice input unit 19 thereafter. The voice input mode is switched so that the input instruction signal is recognized. When voice is input from the microphone after switching to the voice input mode, the control unit 11 causes the voice recognition unit to perform voice recognition of the user's voice signal input to the voice input unit 19 and converts it into text data. Output. Then, the control unit 11 stores, for each input screen displayed on the display unit 13, the process executed when various input buttons displayed on the input screen are pressed and the text data in association with each other. File with audio processing 151
Referring to, the processing corresponding to the input text data is executed, the processing result is displayed on the display unit 13, and the confirmation notification voice data is synthesized by the voice synthesis unit 20.
The audio output unit 21 outputs the audio.

Therefore, since the input operation is performed by voice,
The complicated input operation can be performed easily and quickly. Also, since the result of the input instruction is notified by voice, the user can immediately notice an input error, and the confirmation omission that often occurs when confirming the processing result on the screen is greatly reduced. Typing errors can be reduced. As a result, the operability of the medical image processing apparatus is improved.

The description in the above embodiment is a preferred example of the medical image processing apparatus 1 according to the present invention, and the present invention is not limited to this. For example, although the present embodiment exemplifies a system in which the medical image processing apparatus 1 and the medical image reading apparatus 3 are connected by a cable, the present invention is not limited to this, and may be connected by a network such as a LAN or the Internet. Good. Further, a reservation device for inputting reservation information such as patient information and imaging conditions, a server, a printer, and the like are connected to the network so that data can be transmitted and received to and from the medical image processing apparatus 1 for image reading. The system may be configured. The present invention
It may be applied to a reservation device.

Further, in the present embodiment, the medical image reading device 3 is provided with an X-ray irradiating unit, and the medical image processing device 1 controls the radiography and the reading of the medical image, but it is not limited to this. . For example, the medical image processing apparatus 1 has a function as a medical image reading apparatus, and is a stimulable fluorescent substance including a sheet-shaped support and a stimulable fluorescent substance that are used for X-ray photography by an unconnected X-ray irradiation unit. A cassette containing a body sheet can be attached, and the stimulable phosphor sheet stored in the attached cassette is taken out and scanned with excitation light to sequentially accumulate and store the radiation image information. Then, the stimulated emission light may be photoelectrically sequentially read to obtain an image signal and image processing may be performed.

Further, it goes without saying that the present invention can be applied not only to the medical image processing apparatus but also to the input in the medical image photographing apparatus and the medical image reading apparatus.

In addition, the detailed configuration and the detailed operation of the medical image processing apparatus 1 can be appropriately changed without departing from the spirit of the present invention.

[0054]

According to the inventions of claim 1, claim 5, claim 6, and claim 7, the medical image processing apparatus recognizes the audio signal input from the audio input means,
Processing corresponding to the recognized voice can be executed.
Therefore, a complicated input operation in the medical image processing apparatus can be performed easily and quickly.

According to the second aspect of the invention, the result of the processing executed by the instruction by the voice input is notified by voice. Therefore, the omission of confirmation, which often occurs when confirming the processing result on the screen as in the prior art, is significantly reduced, and input errors can be reduced.

According to the third aspect of the invention, it is detected whether or not there is an error in the voice input, and if there is an error, a warning is given. Therefore, input errors can be further reduced.

According to the fourth aspect of the invention, voice guidance for instructing the input method is output. Therefore, the input can be performed smoothly.

[Brief description of drawings]

FIG. 1 is a diagram conceptually showing the overall structure of the present embodiment.

FIG. 2 is a block diagram showing a functional configuration of the medical image processing apparatus 1 of FIG.

FIG. 3 is a flowchart showing a voice input process executed by a control unit 11 in FIG.

4 is a diagram showing an example of a shooting condition input screen 131 displayed by the display unit 13 of FIG.

[Explanation of symbols]

1 Medical image processing device 2 cables 3 Medical image reader 11 Control unit 12 Input section 13 Display 14 RAM 15 memory 15a recording medium 16 I / F 17 Image analysis section 18 Image processing unit 19 Voice input section 20 Speech synthesizer 21 Audio output section

─────────────────────────────────────────────────── ─── Continuation of front page (51) Int.Cl. ⁷ Identification code FI theme code (reference) G10L 15/28 G10L 3/00 571K ER 561A

Claims (7)

[Claims] 1. A medical image processing apparatus for performing image processing on radiation medical image data on the basis of input imaging conditions, a voice input unit for inputting voice, and a voice signal input by the voice input unit. A medical image processing apparatus, comprising: a voice recognition unit that performs the processing; and a process execution unit that executes a process corresponding to the voice signal recognized by the voice recognition unit. 2. A voice synthesizing unit for synthesizing voice text data for notifying a processing result based on a result of the process executed by the process executing unit, and voice text data synthesized by the voice synthesizing unit. The medical image processing apparatus according to claim 1, further comprising: a sound output unit that converts the sound signal and outputs the sound signal. 3. An error detecting means for detecting whether or not there is an error in the voice signal recognized by said voice recognizing means, wherein said voice synthesizing means is based on the error detected by said error detecting means. 3. The medical image processing apparatus according to claim 1, wherein voice text data for warning an error is synthesized. 4. The medical image processing apparatus according to claim 1, wherein the voice synthesizing unit synthesizes voice text data for voice guidance instructing an input method. 5. A medical image processing method in a medical image processing apparatus for performing image processing on radiation medical image data based on input imaging conditions, the step of inputting voice, and recognizing the input voice signal. A medical image processing method comprising: a step; and a step of performing a process corresponding to the recognized voice signal. 6. A function of causing a computer for controlling a medical image processing apparatus for performing image processing on radiological image data to input a voice on the basis of an input imaging condition, and recognizing the input voice signal. And a function for executing processing corresponding to the recognized voice signal. 7. A voice is input to a recording medium that stores a computer-executable program for controlling a medical image processing apparatus that performs image processing on radiological image data based on input imaging conditions. A computer-executable program code, a computer-executable program code for recognizing the input voice signal, and a computer for executing a process corresponding to the recognized voice signal. A recording medium characterized by storing a program including a program code.