Computer-aided diagnosis system for medical use

What is claimed is:

1. A system for automatically analyzing a medical image using a predetermined computer-aided diagnosis algorithm, comprising:

means for inputting a single medical image of a plurality of medical images of different types and attributes data of the medical image, said attribute data denoting the type of the medical image;

means for determining, based on the attribute data, whether or not the predetermined computer-aided diagnosis algorithm can be applied to the medical image by a comparison of the input attribute data with the predetermined computer-aided diagnosis algorithm;

means for analyzing the medical image using the predetermined computer-aided diagnosis algorithm in accordance with a result of a determination of said determining means indicates that the predetermined computer-aided diagnosis algorithm can be applied to the medical image; and

means for displaying an analysis result of said analyzing means.

2. A system according to claim 1, which further comprises:

modalities for providing the medical image, said modalities including at least said input means; and

a network for connecting said modalities with said analyzing means, said determining means, and said display means.

3. A system for automatically analyzing a medical image, comprising:

means for inputting a medical image of a plurality of medical images of different types and attribute data of the medical image, said attribute data denoting the type of the medical image;

means for storing a plurality of computer-aided diagnosis algorithms which correspond respectively to a plurality of types of the medical images;

means for selecting, based on the attribute data, an optimum computer-aided diagnosis algorithm suitable for the medical image input by said inputting means;

means for analyzing the medical image using the optimum computer-aided diagnosis algorithm selected by said selecting means; and

means for displaying an analysis result of said analyzing means.

4. A system according to claim 3, which further comprises:

modalities for providing the medical images, said modalities including at least said input means; and

a network for connecting said modalities with said analyzing means, said determining means, and said display means.

5. A system for automatically analyzing a medical image, comprising:

means for storing a plurality of medical images of different types and attribute data of the medical images, said attribute data denoting the type of the medical image;

means for storing a plurality of computer-aided diagnosis algorithms which correspond respectively to a plurality of types of the medical images;

means for selecting, based on the attribute data, optimum computer-aided diagnosis algorithms suitable for diagnosis of the medical images stored in said image and attribute data storing means;

means for analyzing the medical images using computer-aided diagnosis algorithms which are selected by said selecting means;

means for storing an analysis result of said analyzing means in association with the medical images, as the attribute data of the image; and

means for selectively reading out a desired medical image and a corresponding analysis result and displaying the desired medical image and the corresponding analysis result.

6. A system according to claim 5, which further comprises:

modalities for providing the medical image, said modalities including at least said input means; and

a network for connecting said modalities with said analyzing means, said determining means, and said display means.

7. A system according to claim 5, wherein said reading and displaying means comprises:

means for inputting retrieval data; and

means for reading out an analysis result which is in accordance with the retrieval data.

8. A system for automatically analyzing a medical image, comprising:

means for storing a plurality of medical images and attribute data of the medical images, said attribute data denoting whether or not the medical image has been viewed by an operator;

means for selectively extracting one of first medical images which have been viewed by an operator and second medical images which have not been viewed by an operator based on the attribute data;

means for analyzing one of the first medical images and the second medical images extracted by said extracting means using a computer-aided diagnosis algorithm; and

means for displaying an analysis result of said analyzing means.

9. A system according to claim 8, wherein said storing means further stores the analysis result in association with the medical images.

10. A system according to claim 8, wherein said storing means stores an item of the attribute data denoting whether or not the medical image has been analyzed by said analyzing means.

11. A system according to claim 10, wherein said extracting means extracts medical images which have been viewed but have not been analyzed by said analyzing means.

12. A system for automatically analyzing a medical image using a computer-aided diagnosis algorithm, comprising:

means for storing a plurality of medical images and attribute data of the medical images, the attribute data including an item of data denoting whether or not the medical image has been analyzed using a computer-aided diagnosis algorithm, an item of data denoting whether or not the medical image has been viewed by an operator, and an item of data denoting a type of the medical image;

means for storing a plurality of computer-aided diagnosis algorithms;

means for analyzing medical images which are stored in said storing means, have not been analyzed using a computer-aided diagnosis algorithm, and have been viewed by an operator using an optimum computer-aided diagnosis algorithm selected based on the attribute data;

means for storing an analysis result of said analyzing means in association with the medical images; and

means for selectively reading out a desired medical image and a corresponding analysis result and displaying the desired medical image and the corresponding analysis result.

13. A system according to claim 1, wherein said analyzing means comprises means for determining a position, a type, and a degree of abnormality, and said displaying means comprises means for displaying the position of abnormality and means for displaying a text representing the type and the degree of abnormality.

14. A system according to claim 13, wherein said analyzing means comprises means for hierarchically determining the position, the type, and the degree of abnormality, and said displaying means comprises means for displaying the position of abnormality, and means for stopping display of the position of abnormality as well as for displaying the text representing the type and the degree of the abnormality when a display command is input while the position of abnormality is displayed.

15. A system according to claim 1, wherein said displaying means comprises means for flickering display of the result of said analyzing means.

16. A system according to claim 1, which further comprises means for sounding the analysis result of said analyzing means.

17. A system according to claim 1, wherein said displaying means comprises means for displaying the medical image and means for starting display of the analysis result after a predetermined period of time has elapsed from start of display of the medical image.

18. A system according to claim 1, wherein said displaying means comprises means for displaying the medical image, means for counting the number of times a medical image has been displayed, and means for starting display of the analysis result if the medical image is displayed at predetermined times.

19. A system according to claim 1, which further comprises means for stopping display of the analysis result after a predetermined period of time has elapsed from start of the display of the analysis result.

20. A system according to claim 1, wherein said attribute data denotes an imaging source of the medical image, an object to be diagnosed, and an imaging direction of the medical image.

21. A system according to claim 1, wherein said determining means comprises means for storing reference attribute data which corresponds to the predetermined computer-aided diagnosis algorithm and means for comparing the attribute data of the medical image and the reference attribute data, thereby determining that the medical image is adapted to the predetermined computer-aided diagnosis algorithm when the attribute data of the medical image coincides with the reference attribute data.

22. A system according to claim 3, wherein said analyzing means comprises means for determining a position, a type, and a degree of abnormality, and said displaying means comprises means for displaying the position of abnormality and means for displaying a text representing the type and the degree of abnormality.

23. A system according to claim 22, wherein said analyzing means comprises means for hierarchically determining the position, the type, and the degree of abnormality, and said displaying means comprises means for displaying the position of abnormality, and means for stopping display of the position of abnormality as well as for displaying the text representing the type and the degree of the abnormality when a display command is input while the position of abnormality is displayed.

24. A system according to claim 3, wherein said displaying means comprises means for flickering display of the result of said analyzing means.

25. A system according to claim 3, which further comprises means for sounding the analysis result of said analyzing means.

26. A system according to claim 3, wherein said displaying means comprises means for displaying the medical image and means for starting display of the analysis result after a predetermined period of time has elapsed from start of display of the medical image.

27. A system according to claim 3, wherein said displaying means comprises means for displaying the medical image, means for counting the number of times a medical image has been displayed, and means for starting display of the analysis result if the medical image is displayed at predetermined times.

28. A system according to claim 3, which further comprises means for stopping display of the analysis result after a predetermined period of time has elapsed from start of the display of the analysis result.

29. A system according to claim 3, wherein said attribute data denotes an imaging source of the medical image, an object to be diagnosed, and an imaging direction of the medical image.

30. A system according to claim 3, wherein said determining means comprises means for storing reference attribute data which corresponds to the predetermined computer-aided diagnosis algorithm and means for comparing the attribute data of the medical image and the reference attribute data, thereby determining that the medical image is adapted to the predetermined computer-aided diagnosis algorithm when the attribute data of the medical image coincides with the reference attribute data.

31. A system according to claim 5, wherein said analyzing means comprises means for determining a position, a type, and a degree of abnormality, and said displaying means comprises means for displaying the position of abnormality and means for displaying a text representing the type and the degree of abnormality.

32. A system according to claim 31, wherein said analyzing means comprises means for hierarchically determining the position, the type, and the degree of abnormality, and said displaying means comprise means for displaying the position of abnormality, and means for stopping display of the position of abnormality as well as for displaying the text representing the type and the degree of the abnormality when a display command is input while the position of abnormality is displayed.

33. A system according to claim 5, wherein said displaying means comprises means for flickering display of the result of siad analyzing means.

34. A system according to claim 5, which further comprises means for sounding the analysis result of said analyzing means.

35. A system according to claim 5, wherein said displaying means comprises means for displaying the medical image and means for starting display of the analysis result after a predetermined period of time has elapsed from start of display of the medical image.

36. A system according to claim 5, wherein said displaying means comprises means for displaying the medical image, means for counting the number of times a medical image has been displayed, and means for starting display of the analysis result if the medical image is displayed at predetermined times.

37. A system according to claim 5, which further comprises means for stopping display of the analysis result after a predetermined period of time has elapsed from start of the display of the analysis result.

38. A system according to claim 5, wherein said attribute data denotes an imaging source of the medical image, an object to be diagnosed, and an imaging direction of the medical image.

39. A system according to claim 5, wherein said determining means comprises means for storing reference attribute data which corresponds to the predetermined computer-aided diagnosis algorithm and means for comparing the attribute data of the medical image and the reference attribute data, thereby determining that the medical image is adapted to the predetermined computer-aided diagnosis algorithm when the attribute data of the medical image coincides with the reference attribute data.

40. A system according to claim 8, wherein said analyzing means comprises means for determining a position, a type, and a degree of abnormality, and said displaying means comprises means for displaying the position of abnormality and means for displaying a text representing the type and the degree of abnormality.

41. A system according to claim 40, wherein said analyzing means comprises means for hierarchically determining the position, the type, and the degree of abnormality, and said displaying means comprises means for displaying the position of abnormality, and means for stopping display of the position of abnormality as well as for displaying the text representing the type and the degree of the abnormality when a display command is input while the position of abnormality is displayed.

42. A system according to claim 8, wherein said displaying means comprises means for flickering display of the result of said analyzing means.

43. A system according to claim 8, which further comprises means for sounding the analysis result of said analyzing means.

44. A system according to claim 8, wherein said displaying means comprises means for displaying the medical image and means for starting display of the analysis result after a predetermined period of time has elapsed from start of display of the medical image.

45. A system according to claim 8, wherein said displaying means comprises means for displaying the medical image, means for counting the number of times a medical image has been displayed, and means for starting display of the analysis result if the medical image is displayed at predetermined times.

46. A system according to claim 8, which further comprises means for stopping display of the analysis result after a predetermined period of time has elapsed from start of the display of the analysis result.

47. A system according to claim 8, wherein said attribute data denotes an imaging source of the medical image, an object to be diagnosed, and an imaging direction of the medical image.

48. A system according to claim 8, wherein said determining means comprises means for storing reference attribute data which corresponds to the predetermined computer-aided diagnosis algorithm and means for comparing the attribute data of the medical image and the reference attribute data, thereby determining that the medical image is adapted to the predetermined computer-aided diagnosis algorithm when the attribute data of the medical image coincides with the reference attribute data.

49. A system according to claim 12, wherein said analyzing means comprises means for determining a position, a type, and a degree of abnormality, and said displaying means comprises means for displaying the position of abnormality and means for displaying a text representing the type and the degree of abnormality.

50. A system of claim 49, wherein said analyzing means comprises means for hierarchically determining the position, the type, and the degree of abnormality, and said displaying means comprises means for displaying the position of abnormality, and means for stopping display of the position of abnormality as well as for displaying the text representing the type and the degree of the abnormality when a display command is input while the position of abnormality is displayed.

51. A system according to claim 12, wherein said displaying means comprises means for flickering display of the result of said analyzing means.

52. A system according to claim 12, which further comprises means for sounding the analysis result of said analyzing means.

53. A system according to claim 12, wherein said displaying means comprises means for displaying the medical image and means for starting display of the analysis result after a predetermined period of time has elapsed from start of display of the medical image.

54. A system according to claim 12, wherein said displaying means comprises means for displaying the medical image, means for counting the number of times a medical image has been displayed, and means for starting display of the analysis result if the medical image is displayed at predetermined times.

55. A system according to claim 12, which further comprises means for stopping display of the analysis result after a predetermined period of time has elapsed from start of the display of the analysis result.

56. A system according to claim 12, wherein said attribute data denotes an imaging source of the medical image, an object to be diagnosed, and an imaging direction of the medical image.

57. A system according to claim 12, wherein said determining means comprises means for storing reference attribute data which corresponds to the predetermined computer-aided diagnosis algorithm and means for comparing the attribute data of the medical image and the reference attribute data, thereby determining that the medical image is adapted to the predetermined computer-aided diagnosis algorithm when the attribute data of the medical image coincides with the reference attribute data.

Description Submit all comments and votes

BACKGROUND OF THE INVENTION

1. Field of the Invention

The present invention relates to a computer-aided diagnosis system for medical use, which outputs computer-aided diagnosis data for medical images using a computer.

2. Description of the Related Art

Recently, a computer-aided diagnosis system (hereinafter referred to as a CAD system) for medical use has been developed in which the features of medical image data are determined and computer-aided diagnosis data (hereinafter referred to as CAD data) for assisting a doctor are obtained by using a computer. It is, however, cumbersome for a doctor to operate a computer to obtain the CAD data during the diagnosis, resulting in an adverse effect on a reading operation of image in terms of both time and labor. Further, the conventional CAD system itself cannot provide a high precision CAD data required for the diagnosis.

Examples of such CAD systems are disclosed in U.S. Pat. No. 4,851,984 and U.S. Pat. No. 4,839,807. The CAD systems described in the above USPs comprise means for inputting a medical image, means for analyzing the medical image using a predetermined CAD algorithm, and means for displaying an analysis result.

The doctor refers to the output of the CAD system at the time of reading of the medical image to prevent an oversight of a shadow image of the abnormal portion.

To obtain the CAD data, the following proceedings are required. Locations of one type of abnormal shadow images, e.g., an abnormal shadow image of the interstitial lung disease, are detected on a conventional X-ray radiograph and the result of the detection is output. Therefore, the medical image on the X-ray film is digitized. A rib, an object of the analysis, is identified in the medical image. A region of interest (hereinafter referred to as a ROI) is set on the medical image, as described in the U.S. Pat. No. 4,851,984. The data in the ROI is frequency-analyzed to extract the amount of physical texture of the image. The shadow image is classified into groups based on the amount of physical texture. A display device displays the digital image and the type, degree, and position of the shadow image in an overlapping manner.

The reading operation by the doctor is to draft the reading report. Before drafting the report, the doctor refers to the CAD data to prevent an oversight of a shadow image.

If the doctor needs the CAD data, the above proceedings must be performed. That is, the medical image must be digitized before the CAD system starts to operate. The digitized image is analyzed by the computer using the above proceedings and the analysis result is output to an attached display device. The doctor continues the reading of the image after watching the CAD result.

The above described CAD system has the following drawbacks.

The same CAD algorithm which is included in the CAD system is applied to the image data regardless of the type of the image. For example, the same CAD algorithm is applied to a conventional X-ray radiograph of chest as well as a CT image. Therefore, an unexpected CAD result is obtained thus lowering the ability of diagnosis.

The CAD system includes only one CAD algorithm for a given disease. Therefore, it is not possible to obtain a plurality of CAD data for a plurality of diseases. Therefore, if ten diseases are to be detected from one image based on the CAD data, the image data must be input to ten CAD systems and ten CAD data must be output. This increases the time and labor for the CAD operation.

A time for merely reading the image without outputting the CAD data is about three minutes. A time from requesting a kind of CAD operation to output the CAD data is about two minutes. If the CAD operation is performed during the reading, it takes a long time for reading and a difficulty occurs for the reading.

The CAD data includes many items, e.g., the position, type, and degree of the abnormality. In the conventional CAD system, all the items of data are output, thereby the output becomes complicated.

The CAD system does not store the CAD result, therefore, if the CAD operation is requested for the image which has been once analyzed, the same CAD operation is repeated thus wasting the time.

Meanwhile, a picture archiving communication system (hereinafter referred to as a PACS) for transferring, storing, and displaying the medical images has been developed. In the PACS, digital medical image data archived by modalities including a digitizer and attribute data thereof are transferred via a network and are stored in a large capacity recording means such as an optical disk device. Desired data are retrieved by using a data base system. The image data is transferred to a workstation via the network and is displayed However, the prior PACS does not function a CAD operation.

SUMMARY OF THE INVENTION

Accordingly, it is an object of the present invention to provide a computer-aided diagnosis system for medical use, which outputs computer-aided diagnosis data with a high precision by a simple operation having no adverse effect on diagnosis made by doctors.

Another object of the present invention is to provide a picture archiving communication system incorporating the computer-aided diagnosis system for medical use and having a high diagnosis precision.

According to one aspect of the present invention, there is provided a computer-aided diagnosis system comprising means for inputting a medical image and attribute data of the medical image, means for storing a plurality of computer-aided diagnosis algorithms, means for selecting, based on the attribute data, an optimum computer-aided diagnosis algorithm suitable for the medical image, means for analyzing the medical image using the optimum computer-aided diagnosis algorithm selected by said selecting means, and means for displaying an analysis result of said analyzing means.

Additional objects and advantages of the present invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the present invention. The objects and advantages of the present invention may be realized and obtained by means of the instrumentalities and combinations particularly pointed out in the appended claims.

BRIEF DESCRIPTION OF THE DRAWINGS

The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate presently preferred embodiments of the present invention and, together with the general description given above and the detailed description of the preferred embodiments given below, serve to explain the principles of the present invention in which:

FIG. 1 is a block diagram showing the arrangement of a first embodiment of a computer-aided diagnosis system for medical use according to the present invention;

FIG. 2 shows items of examination data;

FIG. 3 shows a practical example of the examination data for a conventional X-ray radiograph of chest;

FIG. 4 is a block diagram showing the arrangement of a film digitizer shown in FIG. 1;

FIG. 5 shows items of relevant data;

FIG. 6 shows a practical example of the relevant data;

FIG. 7 is a view for defining an imaging direction in the conventional X-ray radiography;

FIG. 8 is a block diagram showing the arrangement of a data base shown in FIG. 1;

FIG. 9 shows an examination directory included in a data retrieving device shown in FIG. 8;

FIG. 10 shows the relationship between a doctor ID and a requesting doctor ID which is used when the image is transferred to a workstation at the time of reading;

FIG. 11 shows an operation for transferring the images which has been examined to the workstation at the time of reading;

FIG. 12 is a block diagram showing the arrangement of the workstation shown in FIG. 1;

FIG. 13 shows an example of the images displayed on the workstation in the PACS at the time of diagnosis of the conventional X-ray radiograph;

FIG. 14 shows a CRT image display control table for managing the display of the workstation;

FIG. 15 shows a table registering the relationship between the name of a CAD algorithm and associated attribute data of the image which is applied with the CAD algorithm;

FIG. 16 is a view showing a practical example of ROI setting in lungs;

FIG. 17 is a block diagram schematically showing an algorithm for automatically setting an ROI;

FIG. 18 is a detailed block diagram for explaining the diagram of FIG. 16;

FIG. 19 is a block diagram schematically showing an algorithm for obtaining the amount of textures in the ROI;

FIG. 20 is a flow chart schematically showing an algorithm for determining based on the amount of textures whether the ROI is normal or abnormal;

FIG. 21 is a block diagram performing the operation shown in FIG. 20;

FIG. 22 shows an example of the data format of a CAD result;

FIG. 23 is a view showing a practical example of the CAD result data;

FIG. 24 is a perspective view showing a touch panel as an example of an input device of the workstation;

FIG. 25 is a view showing a display example of the touch panel;

FIG. 26 is a view for explaining an example of a schematic naming of abnormal positions;

FIG. 27 shows a relationship between locations and coordinates of the abnormal positions;

FIG. 28 shows a table for explaining an example of detailed naming of the abnormal positions;

FIG. 29 shows an example of a text sentence display;

FIG. 30 shows an example of marker display;

FIG. 31 shows an example of detailed CAD display using the marker shown in FIG. 30;

FIG. 32 shows another example of the marker display;

FIG. 33 shows an ROC curve display as an optional CAD output;

FIG. 34 shows the data format of a CAD result;

FIG. 35 shows a practical example of the CAD result;

FIG. 36 is a block diagram showing the arrangement of a CAD processor included in a second embodiment of a computer-aided diagnosis system for medical use according to the present invention;

FIG. 37 is a block diagram showing the arrangement of a sound output device as a main part of a third embodiment of the present invention;

FIGS. 38A and 38B show examples of a menu window display according to a seventh embodiment of the present invention;

FIG. 39 is a block diagram showing the arrangement of a computer-aided diagnosis system according to an eleventh embodiment of the present invention;

FIGS. 40A to 40E show modifications of marker display according to a twelfth embodiment;

FIGS. 41A to 41F show other modifications of the marker display according to the twelfth embodiment;

FIGS. 42A and 42B show still another modifications of the marker display according to the twelfth embodiment; and

FIG. 43 shows an example of a table formed of names of algorithms stored in a memory in a seventeenth embodiment of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

A preferred embodiment of a computer-aided diagnosis system for medical use according to the present invention will now be described with reference to the accompanying drawings. Though it is possible to embody the CAD system as a stand-alone system, an embodiment of the CAD system incorporated into the PACS will be described. FIG. 1 is a block diagram showing the first embodiment constructed on the basis of the PACS. In general, the PACS is a system for performing storage and transferring of various types of digital image data produced in a single or a plurality of hospitals, and is formed of an image data source 10 (hereinafter referred to as a modality), a data base 12, a workstation 14 as a display unit, and a network 16 for connecting these components.

The modality 10 includes various diagnosis devices for generating medical digital images, such as a film digitizer 18 for digitizing an image of an X-ray film obtained by an X-ray radiography apparatus, an angiography imaging apparatus 20, a computed tomography (CT) scanner 22, a magnetic resonance imaging (MRI) system 24, a nuclear medicine diagnosis apparatus 26, an ultrasound diagnosis apparatus 28, and an electric endoscope 30.

An examination ordering system 32 is also connected to the network 16 via a gateway 34. The examination ordering system 32 supplies examination data indicating details of examination on individual patients to the network 16. In this manner, the PACS performs control of data on the basis of correspondence between image data obtained by examination by the modality 10 and attribute data (including examination data, relevant data, and amend and/or update data for these data supplied from the workstation 14 and the data base 12). It is noted that the number of each of the modalities 10, the data base 12, and the workstation 14 are not limited to these of the above arrangement but can be increased or decreased as needed.

FIG. 2 shows an example of items of examination data input by the examination ordering system 32 and supplied to the network 16. An examination ID number is issued every time examination is performed. In the examination ordering system 32, such examination data is input by a doctor or a person in charge at the start of examination, and a technician of the modality executes examination on a patient upon receiving the examination request, thus obtaining image data. Each frame of the image data is associated with the relevant data. An example of the relevant data is shown in FIG. 5.

When, for example, radiographic examination using a conventional X-ray radiography apparatus is necessary, examination data as shown in FIG. 3 is input from the examination ordering system 32. A radiographic technician of the conventional X-ray radiography apparatus (not shown) takes conventional X-ray radiographs according to the input examination data. In the case of a conventional X-ray radiograph, digital image data can be obtained by digitizing the image of the X-ray film by the film digitizer 18. The image data, for example, consists of an array of data obtained by dividing the X-ray film into a matrix of 1,024.times.1,024 pixels and representing the density of each pixel by a digital number of 10-bit.

FIG. 4 shows the arrangement of the film digitizer 18. The film digitizer 18 comprises a controller 40, an input device 42, a display device 43, a read-only memory (ROM) 44, an examination/relevant data storing device 46, an image data storing device 48, a semiconductor memory 50, a film density detector 52, a central processing unit (CPU) 54, and a network interface (I/F) 56. Of these components, the controller 40, the input device 42, the display device 43, the ROM 44, the examination/relevant data storing device 46, the image data storing device 48, the semiconductor memory 50, the film density detector 52, the CPU 54, and the network I/F 56 are connected to a control bus line 58. The ROM 44, the image data storing device 48, the semiconductor memory 50, the film density detector 52, and the network I/F 56 are connected to an image bus line 60. The network I/F 56 is connected to the network 16.

The film density detector 52 divides an X-ray radiograph into a matrix of 1,024.times.1,024 pixels. The density detector 52 scans each pixel with a laser beam and measures the intensity of transmitted light to obtain the density of the pixel, thereby forming an intensity distribution of the transmitted light of the X-ray radiograph. This intensity distribution is converted into digital intensity data, and the data is supplied to the data storing device 48 through the image bus 60 and is stored therein as the image data. At the same time, examination data, together with relevant data, is stored in the examination/relevant data storing device 46. At this time, the display device 43 displays a prompt message for urging a technician to input an imaging direction of radiograph if the imaging direction is not input. When the text character denoting the imaging direction is input from the input device 42 such as a keyboard, this data is written in the column of the imaging direction of relevant data (FIG. 5) stored in the storing device 46.

FIG. 6 shows a practical example of the relevant data. The imaging direction of radiograph is defined, as shown in FIG. 7, such that when X-rays radiated from the back of a patient are detected on an X-ray film placed in front of the patient, the resulting image is referred to as a front image. Similarly, a right-side (left-side) image is defined as an image obtained when X-rays radiated from the left (right) side of the patient are detected on a X-ray film placed on the right (left) side of the patient. When digitizing of one frame of the X-ray radiograph is completed, the image data and the corresponding relevant data are associated with each other by means of the image ID number. The examination data and the corresponding relevant data are associated with each other by means of the examination ID number. The image data, the corresponding examination data, and the corresponding relevant data are supplied to the network 16 via the network I/F 56 and transferred to the data base 12 or the workstation 14 as data flowing through the network 16.

FIG. 8 shows the arrangement of the data base 12. The data base 12 comprises a CPU 62, a ROM 64, a semiconductor memory 66, a controller 68, a data retrieving device (including an examination directory) 70, a data compression circuit 71, an image data storing device 72, and a network interface (I/F) 74. Of these components, the CPU 62, the ROM 64, the semiconductor memory 66, the controller 68, the data retrieving device 70, the data compression circuit 71, the image data storing device 72, and the network I/F 74 are connected to a control bus line 76. The ROM 64, the semiconductor memory 66, the data compression circuit 71, the image data storing device 72, and the network I/F 74 are connected to an image bus line 78. The network I/F 74 is connected to the network 16.

The image data, the corresponding examination data, and the corresponding relevant data, which are flowing through the network 16, are input to the data base 12 via the network I/F 74, and stored in the image data storing device 72. If necessary, these data, particularly the image data is temporarily stored in the semiconductor memory 66 as a buffer memory. In this case, after the amount of the data is compressed to 1/2 or 1/10 by the data compression circuit 71, the data is stored in the image data storing device 72. The examination data and the relevant data are registered in the examination directory of the data retrieving device 70 to retrieve desired examination data and relevant data using an examination ID and read out items of data.

FIG. 9 shows an example of data contained in the examination directory of the data retrieving device 70 of the data base 12. Referring to FIG. 9, reference symbol N denotes the number of images obtained in one examination. The examination directory is formed of examination data (FIG. 2), address data for storing the reading report, amount of data of the reading report, and N number of image data included in the examination. Each of the image data is formed of address data for storing the relevant data, amount of data of the relevant data, address data for storing the image data, amount of image data, and first CAD result to n-th CAD result. The CAD result is formed of a CAD ID number and address data for storing the CAD result.

Next, an image reading operation performed by a doctor for the digital images whose attribute data are stored in the data base 12 as described above will be described. In hospitals, the image reading is performed to obtain a diagnosis result from medical images. The image reading in the PACS is that images are displayed on a display device such as a CRT of the workstation 14 and a doctor makes a diagnosis from the displayed images or X-ray film obtained in the conventional X-ray radiography examination.

When a doctor for image reading inputs his or her ID number with the power source of the workstation 14 ON, the workstation 14 is set ready for receiving an image reading request. This is the same procedure as the log-in opera