JP2003150714A - Diagnostic imaging support system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a medical diagnostic imaging support system by which a client can obtain the result of CAD calculation from a serber in real time. SOLUTION: The system is provided with a client 2 which transmits medical image data obtained from a medical diagnostic imaging equipment 21, a server 1 which receives the transmitted medical image data, detects an abnormal shadow in the received medical image data and puts a mark to the detected place, and a network 5 for connecting the server 1 and the client 2 so as to transmit and receive data to each other. Information of specifying the address of the abnormal shadow on the medical image and the size of the mark is generated by the server 1, and the generated information is transmitted from the server 1 to the network 5. The transmitted information is received from the network 5 to the client 2, and the information is reproduced to the mark. Then, the reproduced mark and the medical image data obtained from the medical diagnostic imaging equipment 21 are superposed and displayed on a shadow reading device 22.

Description

Description: BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a computer-aided detection of a lesion (abnormal shadow) having a predetermined feature amount in a medical image (Computer Aided Detection: CA).
D) The present invention relates to an image diagnosis support system in which another medical image diagnosis device and the like are connected to a network to an image diagnosis support device that performs an operation. 2. Description of the Related Art A conventional image diagnosis support apparatus analyzes a shadow of an image captured by a CT apparatus or an MRI apparatus by a computer, narrows down a lesion candidate from the shadow, and presents it to a doctor. Diagnosis support for asking for judgment is provided. There have been various reports on medical images of lung fields as examples of narrowing focus candidates from shadows. As one of the methods, as a method of distinguishing elongated blood vessel shadows and cancer shadows close to a circle from medical images of lung fields, for example, a "Quite filter" (November 1999, 9th Annual Meeting of the Computer-Aided Diagnostic Imaging Society of Japan) Papers on page 21). Medical images of the lung field include shadows such as cancer,
Since blood vessels, cross-sections of blood vessels, and cross-sections of bronchi are mixed, the shadows that are considered to be cancer candidates are extracted from these images, and a display image with the shadow portions marked is presented to the doctor. ing. In recent years, an image diagnosis support system for connecting the above-mentioned image diagnosis support apparatus to a plurality of medical image diagnosis apparatuses such as a CT apparatus and an MRI apparatus via a network has been increasing.
In such an image diagnosis support system, for example, a facility (server) such as a local base hospital having an image diagnosis support device and a regional hospital (client) that is remote from the facility and has no image diagnosis support device are provided. There is a current state of network connection. [0004] Medical image data such as CT images obtained by a client is transmitted from the client to a server via a network. The transmitted medical image of the client is CAD-calculated by the image diagnosis support device of the server. CA
The medical image subjected to the D operation is marked as a result of extraction of the abnormal shadow part. The marked medical image is transmitted from the server to the client via the network. In this way, the client can diagnose the CAD-calculated image similarly to the server. [0005] However, according to the above-mentioned prior art, even if transmission of a medical image from a client to a server is processing data, it is unavoidable.
Since the transmission of the medical image as a result of the CAD operation from the server to the client is performed at least twice even if the data transfer of the huge medical image is normally completed, the network transfer is performed during the data transfer time. Is occupied (busy state). Therefore, when the number of clients is further increased, there is a problem that some clients may not be able to receive the result of the CAD operation in real time. An object of the present invention is to provide a medical image / diagnosis support system in which a client can obtain a result of a CAD operation from a server in real time. An object of the present invention is to provide a client for transmitting medical image data obtained from a medical image diagnostic apparatus, receiving the transmitted medical image data, and receiving the received medical image data. In a diagnostic imaging support system comprising: a server for detecting abnormal shadows and marking the detected locations, and a network connecting the client and the server so as to be able to transmit and receive data to and from the medical image of the abnormal shadows. Means for generating information specifying the size of the address and the mark, transmitting the generated information from the server to the network, causing the client to receive the transmitted information from the network, And superimpose and display the associated mark and medical image data obtained from the medical image diagnostic apparatus. And an image diagnosis support system. As described above, according to the present invention, only the information on the address and size of the mark on which the CAD operation has been performed is transmitted as the result without transmitting the resulting medical image data itself. Since transmission can be performed almost instantaneously as compared with the case where the network is connected, it is possible to prevent the network from becoming busy. Therefore, the client can receive the result of the CAD operation from the server in real time. For example, an image matrix size of 512 × 5
If there are 32 CT images of 12,65536 gradations, there will be 16 megabytes of medical image data.
On the other hand, assuming that there are 500 abnormal shadows in the same medical image, let us consider the parameters required for data transfer.
These parameters are the number n of the CT image, the addresses x and y of the abnormal shadow, and the radius is r if the mark surrounding the abnormal shadow is circular. Since two bytes are sufficient for the parameters n, x, y, and r, the amount of data to be transferred is calculated as 2 × 4 × 500 = 4 kilobytes. If the data amounts of the image data and the parameters are compared, they are 16 megabytes and 4 kilobytes, and in this example, the data amount is only 1/4000. First, the configuration of an image diagnosis support system according to the present invention will be described with reference to FIG. FIG. 2 is a diagram showing a configuration example of an image diagnosis support system employing the present invention. The image diagnosis support system is a facility (server)
1 and hospitals (clients) 2, 3, and 4 are connected to each other via a local area network (LAN) in each site via a network 5 so that data can be transmitted and received. The server 1 performs a CAD operation on a medical image, extracts an abnormal shadow in the medical image, and performs a mark so that the extracted abnormal shadow can be recognized. An image processing device 11 which is a computer system for performing calculations, a display device 12 for displaying a medical image on which CAD calculations have been performed, and an ID of a patient for performing CAD calculations
And an external input device 13 for inputting conditions of CAD operation and C
An external storage device 14 such as a magnetic disk for storing the result of the AD operation is provided. In the hospital 2, at least one medical image diagnostic apparatus 21 such as a CT apparatus or an MRI apparatus is arranged, and an image reading apparatus 22 for viewing an image obtained by the medical image diagnostic apparatus 21 is arranged. Similarly, the medical image diagnostic apparatus 31 and the image reading apparatus 32 are arranged in the hospital 3, and the medical image diagnostic apparatus 41 and the image reading apparatus 42 are arranged in the hospital 4, respectively. The image reading device 22 is an image processing device 221 which is a computer system that performs so-called image processing such as filter processing so as to be used for diagnosis, a display device 222 for displaying a medical image subjected to image processing, and an image processing device. It has an external input device 223 for inputting the ID of the patient to be processed and the conditions for image processing. Image interpretation devices 32 and 42
Has the same configuration as that of the image interpretation device 22, and a description thereof will be omitted. Next, the operation of the image diagnosis support system of the present invention will be described with reference to FIGS. 1 and 2. FIG. 3 is a diagram showing the manner in which a CAD operation is performed on a medical image to extract information on the address and size of an abnormal shadow. Is described with reference to FIG. Here, the server and the client each have a computer system. The computer system has input devices such as a keyboard and a mouse, output devices such as a display and a network interface, and storage for storing programs and data. As described above, the devices and the control device (CPU) that controls these devices have been described, so the procedure (software) of each computer system will be described. The medical image diagnostic apparatus 2 in the client 2
1 captures a diagnostic image of a subject. Here, the subject ID0000000001 and the Taro Hitachi
Consider an example in which 32 slice images of the chest of i Taro) are continuously taken. (Step 211) Image attribute information such as the subject ID of the photographed slice image, the photographing date and time (eg, January 01, 2002), the subject name, and the slice number of each photographed image are Image data is created by adding the data to a series of slice image data.
(Step 212) The medical image diagnostic apparatus 21 stores the created image data in a storage device of the computer system of the client 2. (Step 213) The medical image diagnostic apparatus 21 transmits the image data stored in the previous step to the LAN in the client. (Step 214) The image reading apparatus 22 receives the image data transmitted to the LAN in the client in the previous step. (Step 221) The image interpretation device 22 stores the received image data in a storage device in the image processing device 221. (Step 222) The image reading apparatus 22 transmits the image data stored in the previous step to the network 5. (Step 2
23) In the previous step, the server 1
Receiving the image data transmitted to. (Step 10
1) The server 1 stores the received image data in the external storage device 14. (Step 102) The server 1 sends the stored image data to the CA
D Check if the data can be calculated. (Step 103) If the checked result indicates that the CAD operation can be performed, the server 1 executes the CAD operation. (Step 10
4) The server 1 determines whether or not an abnormal shadow has been detected in the CAD calculation. As a result of the determination, "detected" proceeds to step 106, and proceeds to "not detected" step 107. (Step 105) When the server 1 detects an abnormal shadow,
As shown in (1), the coordinates (X, Y) of the abnormal shadow and the radius R of the circle surrounding the abnormal shadow are obtained and stored in the external storage device 14.
In FIG. 3, as a specific example, the coordinates of the center of the abnormal shadow (such as the position of the center of gravity) are X = 380, Y = 200, and the radius R surrounding the abnormal shadow is R = 10. This calculation and storage is performed until the abnormal shadow disappears, that is, until the image is not detected. (Step 106) When the abnormal shadow is not detected or not detected at all, the server 1 adds the image attribute information to the CAD calculation result and stores it in the external storage device 14 (step 106). 107). The server 1 has a CA to which image attribute information is added.
The D operation result is read from the storage device, and CA operation as shown in FIG.
D Create a result information file. (Step 108) The server 1 checks the CA created in the previous step.
The D result information file is transmitted to the network 5. (Step 109) The image reading apparatus 22 receives the CAD result information file transmitted to the network 5 in the previous step.
(Step 224) The image interpretation device 22 stores the received CAD result information file in the storage device. (Step 225) The image interpretation device 22 analyzes the saved CAD result information file. That is, the image data obtained by the medical image diagnostic apparatus 21 of the client 2 is associated with the data in the CAD result information file. (Step 226). If the associations match, the image interpretation device 22 creates image data in which a mark, that is, a circle is superimposed on the abnormal shadow in the image data. (Step 227). The image reading device 22 displays the image data on which the mark is superimposed on the display device 222 (step 22).
8). The network may be any network that can transfer data, such as a telephone line or a broadband line.
Further, although the above-mentioned mark is circular, the shape of the mark may be any shape. In the above embodiment, only the information on the address and size of the CAD-calculated mark is transmitted as a result without transmitting the medical image data itself as the CAD-calculated result. In the case of transmitting information on the order of kilobytes as compared with the case of transmitting medical image data, the transmission can be performed almost instantaneously, so that the network can be prevented from becoming busy. Therefore, the client can receive the result of the CAD operation in real time and can immediately perform image interpretation. The present invention has an effect of providing a medical image diagnosis support system in which a client can obtain a result of a CAD operation from a server in real time.

BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a functional block diagram illustrating an image diagnosis support system according to an embodiment of the present invention. FIG. 2 is a diagram showing a configuration example of an image diagnosis support system employing the present invention. FIG. 3 is a diagram showing a mode of calculating coordinate data from a CAD-calculated medical image. FIG. 4 is a view showing a mode of creating a data file from the coordinate data calculated in FIG. 3; [Description of Signs] 1 ... server, 2 ... client, 5 ... network, 2
DESCRIPTION OF SYMBOLS 1 ... Medical image diagnostic device, 22 ... Interview device

   ────────────────────────────────────────────────── ─── Continuation of front page    F-term (reference) 4C093 AA22 AA26 CA26 FA06 FA35                       FF17 FG13 FH03 FH06 FH09                 4C096 AB29 AD14 AD15 AD16 DC20                       DD13 DD18 DE03 DE06 DE09                 5B057 AA09 CA02 CA08 CA12 CA16                       CB02 CB08 CB12 CB16 CE08                       DA07 DA08 DA16 DB02 DB05                       DB09 DC04 DC36

Claims (1)

Claims: 1. A client for transmitting medical image data obtained from a medical image diagnostic apparatus, receiving the transmitted medical image data, and detecting an abnormal shadow in the received medical image data. In a diagnostic imaging support system comprising a server for marking the detected portion and a network connecting the client and the server so as to be able to transmit and receive data to and from each other, an address and a mark on the medical image of the abnormal shadow are provided. Means for generating information specifying the size, means for transmitting the generated information from the server to the network, causing the client to receive the transmitted information from the network, and associating a mark from the information;
Means for superimposing and displaying the associated mark and medical image data obtained from the medical image diagnostic apparatus.