JP6563214B2 - Medical image processing apparatus and medical image processing method - Google Patents

Description

  Embodiments described herein relate generally to a medical image processing apparatus and a medical image processing method.

  In an application that performs image analysis, image analysis data is subjected to image processing based on a parameter such as an arbitrary threshold value, and the processing result is displayed. For example, in segmentation using a CT image, the bone CT value is subjected to image processing using an arbitrary threshold value.

  FIG. 14A is a diagram showing a CT image according to a conventional example. The numerical value described in each grid is the CT value of each pixel, and is indicated by the unit HU (Hounsfield_Unit). HU is a unit of CT value expressed as 0 HU for water and -1000 HU for air, and about 1000 HU for metals and bones. FIG. 14B is a diagram for explaining a conventional example in which image processing using a threshold (hereinafter referred to as threshold processing) is performed on the CT image of FIG. 14A. For example, when the threshold value is set to 50 HU and threshold processing is performed on FIG. 14A, FIG. 14B is obtained. FIG. 14B shows that a pixel having a CT value of 50 HU or higher is displayed with high luminance, and a pixel having a CT value lower than 50 HU is displayed with low luminance.

  FIG. 15 is a diagram for explaining a typical flow of threshold processing according to a conventional example. The threshold storage unit stores a default threshold for each threshold type based on a human body part or the like. For example, the default threshold for the bone region is 950HU. The default threshold value of the blood vessel region has a default threshold value different from that of the bone region. Next, threshold determination is performed. A threshold type is determined, and the threshold is determined based on the threshold storage unit. For example, the operator inputs the threshold type via the input unit according to the imaging region. The threshold value storage unit selects a default threshold value from the input threshold type. The threshold is determined by adjusting the default threshold if necessary. Finally, threshold processing is performed. Threshold processing is performed on the image according to the determined threshold.

  FIG. 16A is a diagram showing a CT image different from the CT image of FIG. 14A according to the conventional example. FIG. 16B is a diagram showing a CT image obtained by subjecting the CT image of FIG. 16A to threshold processing with a threshold of 50 HU according to a conventional example. FIG. 16C is a diagram showing a CT image obtained by subjecting the CT image of FIG. 16A to threshold processing with a threshold of 60 HU according to a conventional example. FIG. 16D is a diagram showing a CT image obtained by subjecting the CT image of FIG. 16A to threshold processing with a threshold of 40 HU according to a conventional example. 16B-D after the threshold processing, FIG. 16C is the same CT image as FIG. 14B. That is, in the case of FIG. 16A, a more appropriate image analysis result can be obtained by performing threshold processing at 60 HU. However, the operator often does not realize that it is better to change the threshold from 50 HU to 60 HU.

  For example, there is a CT image for bone. Human bones are known to have differences in race, age, sex, medical history, and so on. A prominent example is the disease called osteoporosis. The bones of patients with osteoporosis have a smaller bone density than normal bones. The CT image for the bone of an osteoporosis patient has a low bone density, that is, the amount of air that enters the bone gap increases, so the CT value decreases overall. Therefore, when threshold processing is performed after acquiring a CT image of bone, it is necessary to perform threshold processing with a threshold lower than that of a normal bone.

  Since an appropriate threshold value in threshold processing depends on many factors such as race, age, sex, etc. in addition to medical history, it is difficult to determine an appropriate threshold value.

JP 2009-18065 A JP 2008-43564 A JP 2007-135858 A Japanese Patent No. 5054252 Patent 4087640

  An object is to provide a medical image processing apparatus that improves the accuracy of image processing using accumulated medical data.

The medical image processing apparatus according to this embodiment, the medical information storage unit for storing medical data and a plurality types of attribute information items relating to a plurality of types of the plurality of patient medical information item relating to a plurality of patients, the plurality of An image information storage unit that stores image processing parameter values used when creating each medical image related to a patient, and the medical information item, the attribute information item, and the image processing parameter value are analyzed, and the attribute information item And an analysis unit that outputs association information for obtaining an image processing parameter value from at least one of the medical information items, and using one of the stored association information, the plurality of types of medical information items, Candidates for determining candidate parameter values for performing image processing based on the attribute information items and the image processing parameter values related to a desired patient It comprises a parameter value determination unit.

The figure which shows the structure of the medical image processing apparatus which concerns on this embodiment. The figure which shows the structure of the medical image processing apparatus which concerns on this embodiment functionally The figure for demonstrating the example which analyzes a some non-image data set by the data analysis part of FIG. The figure which shows the memory table of medical knowledge managed by the medical knowledge storage part of FIG. The figure for demonstrating the example which classify | categorizes the new patient a into any existing group by the data analysis part of FIG. The figure which shows the parameter value storage table by the parameter value memory | storage part of FIG. The figure for demonstrating feeding back the frequency | count of results to the memory | storage table of a parameter value memory | storage part by the performance feedback part of FIG. The figure which shows the typical flow of the threshold-value determination which concerns on this embodiment. The figure which shows the memory | storage table of the threshold value candidate regarding the medical knowledge acquired by the medical knowledge search part of FIG. The figure which represented simply the CT image which performed the threshold value process using three candidate threshold values by the display part of FIG. The figure which represented concretely the CT image which performed the threshold value process using the three candidate threshold values by the display part of FIG. The figure which shows the unit which does not necessarily exist in an apparatus among the medical image processing apparatuses which concern on this embodiment. The figure which shows the structure of the medical image processing apparatus which concerns on an application example The figure which shows a certain CT image based on a prior art example The figure for demonstrating the image processing by a threshold value to CT image of FIG. 14A based on a prior art example The figure for demonstrating the typical flow of the threshold value process based on a prior art example The figure which shows CT image different from the CT image of FIG. 14A based on a prior art example The figure which shows the CT image which performed the threshold value process with the threshold value 50HU on the CT image of FIG. 16A based on a prior art example The figure which shows the CT image which threshold-processed with the threshold value 60HU to the CT image of FIG. 16A based on a prior art example The figure which shows the CT image which applied the threshold value process with the threshold value 40HU to the CT image of FIG. 16A based on a prior art example

  The medical image processing apparatus according to this embodiment will be described below with reference to the drawings. In the following description, components having substantially the same function and configuration are denoted by the same reference numerals, and redundant description will be given only when necessary.

  FIG. 1 is a diagram illustrating a configuration of a medical image processing apparatus according to the present embodiment. As shown in FIG. 1, the medical image processing apparatus 10 according to the present embodiment includes a control unit 20, a medical data storage unit 21, a medical knowledge storage unit 25, a parameter value storage unit 29, a display unit 100, An input unit 110, a main storage unit 120, and an interface unit 130 are provided. FIG. 3 is a diagram functionally illustrating the configuration of the medical image processing apparatus according to the present embodiment.

  The control unit 20 comprehensively controls various components included in the control unit 20. The control unit 20 is realized by a central processing unit (Central_Processing_Unit: hereinafter referred to as CPU).

  The display unit 100 displays various information on the monitor. The display unit 100 displays candidate threshold values. As the display unit 100, for example, a CRT display, a liquid crystal display, an organic EL display, or the like can be used as appropriate.

  The input unit 110 receives various commands and information input from an operator by an input device. As an input device, a keyboard, a mouse, various switches, and the like can be used.

  The main storage unit 120 is a storage device that stores various information. This is a large-capacity storage device realized by an HDD (Hard_Disk_Drive) or the like. In recent years, SSD (Solid_State_Drive) may be used due to an increase in capacity.

  The interface unit 130 is connected to a computer (Picture_Archiving_and_Communication_System: PACS) (not shown) or another computer via a network. The interface unit 130 performs data communication with a connected external device in compliance with DICOM (Digital_Imaging_and_Communication_in_Medicine) standards.

  Next, the control unit 20, the medical data storage unit 21, the medical knowledge storage unit 25, and the parameter value storage unit 29 will be described in more detail. The control unit 20 centralizes the data analysis unit 23, the medical knowledge search unit 27, the parameter value determination unit 31, the image processing unit 33, and the performance feedback unit 35 as the center of the medical image processing apparatus 10. Control.

The medical data storage unit 21 stores medical data sets related to a plurality of patients. Medical data sets include image data sets and non-image data sets. An image data set is image data generally output from a medical image diagnostic apparatus or the like. Data output from the medical image diagnostic apparatus is normally stored on the medical image storage system PACS and can be taken in and out according to the DICOM standard or the like. The non-image data set includes, for example, age, sex, race, medical history, and the like. Generally speaking, the non-image data set is data managed on a medical information system. The medical information system is an information system used in the hospital, and representative examples thereof include an electronic medical record system, a receipt computer processing system, an ordering system, a reception system, a medical assistance system, and a department system. The non-image data set stores medical data including a plurality of types of medical information items related to a plurality of patients and a plurality of types of attribute information items related to a plurality of patients . Attribute information, including age, gender, information such as body weight. Further, the medical data storage unit 21 stores image processing parameters used when creating each of medical images related to a plurality of patients.

  Hereinafter, in order to simplify the description, a series of processes in the present embodiment will be described using a non-image data set as a medical data set. Of course, a series of processing may be performed using an image data set as a medical data set.

  The data analysis unit 23 analyzes a plurality of non-image data sets stored in the medical data storage unit 21 based on the similarity of a plurality of types of medical information item values included in each of the non-image data sets. Classify into sets. The data analysis unit 23 analyzes the medical information item, the attribute information item, and the image processing parameter, and outputs association information for obtaining an image processing parameter value from at least one of the attribute information item and the medical information item. The multiple types of medical information items are, for example, race, age, sex, medical history, and the like. The medical information item value represents an age value such as 1 year old or 90 year old as it is. The medical information item value is expressed by using, for example, a value of 1 when there is a history of osteoporosis and 0 when there is no history. The data analysis unit 23 classifies the set by data analysis. Specifically, for example, data mining is used for classifying a set. Data mining, for example, is a technique for searching for correlations, patterns, and the like between information items lurking in a plurality of pieces of medical information possessed by many patients in the present embodiment. In the present embodiment, for example, a pattern between items such as “an older person tends to have osteoporosis in the medical history” is obtained. For data analysis, other clustering methods may be used instead of data mining. An engine capable of searching for similar patients or similar cases obtained by data analysis as shown in FIG. 3 is hereinafter referred to as medical knowledge. The medical knowledge includes, for example, a calculation model representing the medical knowledge. The calculation model includes a plurality of segments. The medical knowledge in FIG. 3 is medical knowledge mainly related to similar patients whose medical information items are similar. Medical knowledge may be referred to as association information.

  FIG. 3 is a diagram for explaining an example in which a plurality of non-image data sets are analyzed by the data analysis unit 23 of FIG. 1 and classified into a plurality of sets. For example, the data analysis unit 23 analyzes data sets relating to five non-image data sets, that is, patient A, patient B, patient C, patient D, and patient E, and classifies them into three sets (hereinafter referred to as segments). Actually, the medical data storage unit 21 stores more medical data, and the data analysis unit 23 classifies them into a plurality of sets. More medical data is, for example, medical data accumulated so far in a certain hospital. The data analysis unit 23 converts a plurality of non-image data sets into a plurality of non-image data sets by attribute information items or medical information items I (race) and attribute information items or medical information items II (age) included in the five non-image data sets. The data is classified into segments (three segments in the example of FIG. 3).

  The medical knowledge storage unit 25 stores the medical knowledge obtained by the data analysis unit 23 so as to be searchable. FIG. 4 is a diagram showing a medical knowledge storage table managed by the medical knowledge storage unit 25 of FIG. In the example of the table in FIG. 4, the calculation model and the number of classifications are associated with medical knowledge. Knowledge A is medical knowledge about the similar patient generated in FIG. The calculation model is a model for calculating knowledge. In Knowledge A, the calculation model is represented by “model X f (x, y) = {1, 2, 3}”. This means that the model X is represented by the function f, and outputs 1, 2, or 3 are obtained by two arguments of medical information items x and y. Outputs 1, 2, or 3 indicate classification into segments 1, 2, or 3, respectively. FIG. 5 is a diagram for explaining that the new patient a is classified into any existing set by the data analysis unit 23 of FIG. 1. When the attribute information item or medical information item I (race) of the new patient a and the attribute information item or medical information item II (age) are input to the function f, the result of output 3, that is, segment 3, is obtained. means. The number of classifications is the number of classifications obtained by the calculation model, and the knowledge A is the output 1, 2 or 3, that is, the number of classifications 3. In FIGS. 3 and 4, data analysis is performed on two medical information items of race and age, but actually there are more medical information items.

  The parameter value storage unit 29 stores a plurality of analysis target parts and default parameter values in association with each other. In order to make the description more specific, in the following description, it is assumed that the parameter value is a default threshold value. The parameter value may be a filter value for performing filter processing, or may be a window width and a window level. The analysis application is set to have a threshold type of a plurality of parts according to the analysis target part. The analysis application is selected by the operator via the input unit 110. In order to make the description more specific, in the following description, it is assumed that threshold processing is performed on a CT image targeting bone, and the operator selects the bone system application 1 in FIG. 6 as an analysis application. The bone system application 1 has a bone region, a blood vessel region, and other regions as threshold types. In the table of FIG. 6, a default threshold value and a randomization coefficient are stored in association with each threshold type. Here, the randomization coefficient is a coefficient for adjusting the default threshold and giving the candidate threshold a width, that is, an option. The randomization coefficient may not be used, but for the sake of specific explanation, the randomization coefficient is used in the following description. The randomization coefficient is used by the parameter value determination unit 31. In order to simplify the following description, it is assumed that threshold processing is performed using only the bone region threshold type (default threshold: 950 HU, randomization coefficient: 10 in FIG. 6) in the bone system application 1.

  The medical knowledge search unit 27 searches the medical knowledge storage unit 25 for medical knowledge selected by an instruction from the operator via the input unit 110. In order to make the description concrete, it is assumed that the medical knowledge search unit 27 searches and acquires knowledge A (similar patient).

  The parameter value determination unit 31 determines a candidate parameter value for image processing based on the association of the parameter value storage unit 29. In other words, the parameter value determination unit 31 uses one of the association information stored in the medical data storage unit 21 and based on a plurality of types of medical information items, attribute information items regarding desired patients, and image processing parameters. Thus, candidate parameter values for image processing are determined. Specifically, the parameter value determination unit 31 determines a default threshold value corresponding to the analysis target part, that is, the bone of the medical image data set to be processed based on the association of the parameter value storage unit 29, and the determined default threshold value Based on the acquired medical knowledge A (similar patient), a candidate threshold value for image processing is determined. The parameter value determination unit 31 selects a final threshold value from among the candidate threshold values sequentially displayed on the display unit 100 according to an operator instruction via the input unit 110. The parameter value determination unit 31 may determine the final threshold value without an operator instruction.

  The image processing unit 33 processes the medical image data set to be processed according to the final threshold value. Specifically, the image processing unit 33 uses the threshold value selected by the operator via the input unit 110 among the candidate threshold values determined by the parameter value determination unit 31, that is, the medical image data set to be processed, that is, the patient a. Threshold processing is performed on the medical image data set.

  When the final parameter value is determined by the operator via the input unit 110, the actual result feedback unit 35 feeds back the actual number of times that the parameter value has been determined as the final parameter value to the parameter value storage unit. Remember. FIG. 7 is a diagram for explaining that the number of results is fed back to the storage table of the parameter value storage unit 29 by the result feedback unit 35 of FIG. 1. In the storage table of FIG. 7, analysis applications, medical knowledge, optimization candidates, and support numbers are stored in association with each other. In the storage table of FIG. 7, four candidates are listed as optimization candidates. The optimization candidates are stored in the table of FIG. 7 as “If f (x, y) = 3 then bone region = 960 HU”, for example. This means that in the case of segment 3 where medical information items x and y are input to the function f of knowledge A, the threshold candidate for the bone region is 960 HU. When the final threshold value is determined as “If f (x, y) = 3 then bone region = 960 HU”, the performance feedback unit 35 stores “If f (x, y) = 3 then in the parameter value storage unit 29. The actual number of times when “bone region = 960 HU” is selected is overwritten from 9 to 10.

  Heretofore, each component of the medical image processing apparatus 10 according to the present embodiment has been described. Below, the typical flow of the threshold value determination which concerns on this embodiment is demonstrated. FIG. 8 is a diagram showing a typical flow of threshold determination according to the present embodiment.

  First, the control unit 20 causes the medical knowledge search unit 27 to search for medical knowledge of the patient a (step S11). As described above, the patient a is determined to belong to the segment 3 of the knowledge A by the storage table of FIG. The medical knowledge search unit 27 searches the medical knowledge storage unit 25 that the patient a belongs to the segment 3 of the knowledge A.

  When step S11 is performed, the control unit 20 acquires the parameter value of the target analysis application in accordance with an instruction from the operator via the input unit 110, and determines a candidate threshold value for the searched medical knowledge (step S12). As described above, the operator selects the bone system application 1 as the analysis application via the input unit 110. Referring to FIG. 6, in the target bone system application 1, the default threshold value of the bone region is 950 HU and the randomization coefficient is 10. Therefore, the parameter value determination unit 31 generates three candidate threshold values by adding or subtracting the randomization coefficient to or from the default threshold value. That is, three candidate threshold values of 950 HU and 950 ± 10 HU are generated. The three candidate threshold values are “If f (x, y) = 3 then bone region = 960 HU”, “If f (x, y) = 3 then bone region = 950 HU”, “If f (x , Y) = 3 then bone area = 940 HU ”. The parameter value determining unit 31 sets the candidate threshold value of the segment 2 close to the segment 3 to which the patient a belongs as the fourth candidate threshold value as shown in FIG. 9, and “If f (x, y) = 2 then bone region = 960 HU”. May be presented.

  If step S12 is performed, the control part 20 will display a candidate threshold value on the display part 100 (step S13). The display unit 100 may display a CT image that has been subjected to threshold processing using candidate thresholds. FIG. 10 is a diagram simply showing a CT image subjected to threshold processing using three candidate threshold values by the display unit 100 of FIG. The display unit 100 may display a CT image subjected to threshold processing using three candidate thresholds as shown in FIG. 10 as shown in FIG. The display unit 100 highlights the candidate 3 based on the number of supports stored in the table of FIG. FIG. 11 is a diagram specifically showing a CT image subjected to threshold processing using three candidate thresholds by the display unit 100 of FIG. More specifically, the display unit 100 displays a CT image that has been subjected to threshold processing using, for example, three candidate thresholds in an array as shown in FIG. The display unit 100 highlights one with a large number of supports stored in the table of FIG.

  When step S13 is performed, the final threshold value is selected from the candidate threshold values (step S14). In step S14, the final threshold value may be selected by the operator via the input unit 110, or the parameter value determination unit 31 may determine the final threshold value.

  When step S14 is performed, the result feedback unit 35 causes the parameter value storage unit 29 to feedback-store the number of results (step S15). Specifically, since it demonstrated in FIG. 8, description is not performed again.

  Note that FIG. 12 is a diagram illustrating units that are not necessarily included in the medical image processing apparatus according to the present embodiment. The medical data storage unit 21, the data analysis unit 23, the medical knowledge storage unit 25, the parameter value storage unit 29, and the performance feedback unit 35 are not necessarily provided in the medical image processing apparatus 10. Specifically, the above components may be in the cloud. For example, since the storage unit and storage unit such as the medical data storage unit 21, the medical knowledge storage unit 25, and the parameter value storage unit 29 are on the cloud, not only in a single hospital but also between multiple hospitals or international medical institutions Medical data, medical knowledge, etc. can be shared. Then, since a large amount of medical data is accumulated, the accuracy of data mining is improved.

  As described above, according to the medical image processing apparatus according to the present embodiment, medical knowledge can be stored in a searchable manner by performing data analysis on stored medical data. Medical knowledge suitable for the image data set to be processed can be searched and acquired from the stored medical knowledge. A suitable threshold value can be determined based on the acquired medical knowledge. Image processing accuracy can be improved with a suitable threshold.

  Next, various application examples of this embodiment will be described. In the following description, components having substantially the same functions as those of the present embodiment are denoted by the same reference numerals, and redundant description will be given only when necessary.

(Application examples)
The medical image processing apparatus in the above embodiment is used for image processing on a CT image obtained by CT imaging. However, the medical image processing apparatus according to the present embodiment is not limited thereto. The medical image processing apparatus according to the application example can be used for setting imaging conditions.

  FIG. 13 is a diagram illustrating a configuration of a medical image processing apparatus 10 ′ according to an application example. The medical image processing apparatus 10 ′ according to the application example includes an imaging control unit 140 instead of the image processing unit 33. The parameter value determination unit 31 determines candidate imaging conditions based on the association of the parameter value storage unit 29 and medical knowledge. The parameter value determination unit 31 selects a final shooting condition from the candidate shooting conditions sequentially displayed on the display unit 100 according to an instruction from the operator via the input unit 110. Note that the parameter value determination unit 31 may determine final imaging conditions without an instruction from the operator. Using the imaging conditions determined by the parameter value determining unit 31, the imaging control unit 140 controls the CT apparatus to perform CT imaging.

  Specifically, the medical knowledge storage unit 27 analyzes a plurality of medical data sets based on the similarity of a plurality of types of medical information item values included in each of the medical data sets related to a plurality of patients, and is stored so as to be searchable. Accumulate multiple medical knowledge.

  The parameter value storage unit 29 stores each of the plurality of imaging target parts in association with the default parameter value.

  The medical knowledge search unit 27 acquires a desired medical knowledge from the accumulated medical knowledge.

  The parameter value determination unit 31 determines a default parameter value corresponding to the imaging target region based on the association of the parameter value storage unit 29, and based on the determined default parameter value and the acquired medical knowledge, candidate imaging is performed. Determine the conditions.

  Note that the order of the doctor in charge, for example, a prescription order for medicine and an inspection order, can be determined using medical knowledge in the same manner as the imaging conditions.

  As described above, according to the medical image processing apparatus according to the application example, medical knowledge can be stored in a searchable manner by performing data analysis on the stored medical data. Medical knowledge suitable for the image data set to be processed can be searched and acquired from the stored medical knowledge. Based on the acquired medical knowledge, it is possible to determine suitable imaging conditions, prescription orders for medicines, or inspection orders. Image processing accuracy or medical efficiency can be improved by appropriate imaging conditions, medicine prescription order or inspection order.

  Although several embodiments of the present invention have been described, these embodiments are presented by way of example and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the scope of the invention. These embodiments and modifications thereof are included in the scope and gist of the invention, and are included in the invention described in the claims and the equivalents thereof.

  DESCRIPTION OF SYMBOLS 10 ... Medical image processing apparatus, 20 ... Control part, 21 ... Medical data storage part, 23 ... Data analysis part, 25 ... Medical knowledge storage part, 27 ... Medical knowledge search part, 29 ... Parameter value storage part, 31 ... Parameter value Determining unit 33 ... Image processing unit 35 ... Result feedback unit 100 ... Display unit 110 ... Input unit 120 ... Main storage unit 130 ... Interface unit 140 ... Shooting control unit

Claims (16)

A medical information storage unit that stores medical data including a plurality of types of medical information items related to a plurality of patients and a plurality of types of attribute information items related to the plurality of patients;
An image information storage unit that stores image processing parameter values used when creating each of the medical images related to the plurality of patients;
Analysis that analyzes the medical information item, the attribute information item, and the image processing parameter value, and outputs association information for obtaining an image processing parameter value from at least one of the attribute information item and the medical information item And
Using one of the stored association information, a candidate parameter value when performing image processing based on the plurality of types of medical information items, the attribute information item relating to a desired patient, and the image processing parameter value A candidate parameter value determination unit to determine;
A medical image processing apparatus comprising:   The medical image processing apparatus according to claim 1, further comprising an association information storage unit that stores the output association information. The medical information storage unit stores a default parameter in association with each of a plurality of analysis target parts,
The candidate parameter value determination unit determines a default parameter corresponding to an analysis target part of a medical image data set to be image-processed based on an association between each of a plurality of analysis target parts and a default parameter, and the determined default The medical image processing apparatus according to claim 1, wherein a candidate parameter for image processing is determined based on a parameter value and association information output by the analysis unit.   The medical image processing apparatus according to claim 1, wherein the image processing parameter value includes a threshold value for extracting a bone region.   The association information storage unit includes a data analysis unit that analyzes the plurality of medical data based on the similarity of a plurality of types of medical information item values included in each of the medical data, and classifies the plurality of medical data into a plurality of sets. The medical image processing apparatus according to 1.   The medical image processing apparatus according to claim 5, wherein the data analysis unit classifies the plurality of medical data into a plurality of sets by performing data mining.   The data analysis unit classifies the plurality of medical data into a plurality of sets based on similarity of attribute information items related to a plurality of types of patients included in each of the plurality of medical data. Item 6. The medical image processing apparatus according to Item 5.   The data analysis unit classifies the plurality of medical data into a plurality of sets based on similarity of attribute information items related to a plurality of types of cases included in each of the plurality of medical data. Item 6. The medical image processing apparatus according to Item 5. The candidate parameter value determination unit is responsive to the obtained association information, a set to which the medical image data to be image processed belongs in the obtained association information, and an analysis target portion of the medical image data to be image processed. Determining the plurality of candidate parameter values,
When the plurality of candidate parameter values are determined by the candidate parameter value determination unit, an input unit for an operator to input an instruction to select a final parameter value from the determined plurality of candidate parameter values The medical image processing apparatus according to claim 1, further comprising: A display for displaying the final parameter value and the plurality of candidate parameter values;
When a final parameter value is selected by the operator via the input unit, an actual result feedback unit that feeds back and stores the actual number of times that the parameter value has been determined as the final parameter value in the parameter value storage unit The medical image processing apparatus according to claim 9 , further comprising:   The medical image processing apparatus according to claim 1, further comprising: a processing unit that performs processing on medical image data to be processed according to the determined candidate parameter value. The medical image processing apparatus according to claim 11 , wherein the candidate parameter value is a threshold for the processing unit to perform threshold processing based on the candidate parameter value. The medical image processing apparatus according to claim 11 , wherein the candidate parameter value is a filter value for the processing unit to perform a filtering process using the candidate parameter value. The medical image processing apparatus according to claim 11 , wherein the candidate parameter values are a window width and a window level. Medical data including a plurality of types of medical information items relating to a plurality of patients, a plurality of types of attribute information items relating to the plurality of patients, and image processing parameter values used in creating each of the medical images relating to the plurality of patients; Parse the
Outputting association information for obtaining an image processing parameter value from at least one of the attribute information item and the medical information item;
Using one of the stored association information, a candidate parameter value when performing image processing based on the plurality of types of medical information items, the attribute information item relating to a desired patient, and the image processing parameter value decide,
A medical image processing method. A medical information storage unit that stores medical data including a plurality of types of medical information items related to a plurality of patients and a plurality of types of attribute information items related to the plurality of patients;
An image information storage unit that stores image processing parameter values used when creating each of the medical images related to the plurality of patients;
Analysis that analyzes the medical information item, the attribute information item, and the image processing parameter value, and outputs association information for obtaining an image processing parameter value from at least one of the attribute information item and the medical information item And
An association information storage unit for storing the output at least one association information;
Based on one of the stored associations, an image parameter value corresponding to an imaging target region is determined, and based on the determined image parameter value and one of the stored associations, candidate imaging A candidate shooting condition determination unit for determining a condition;
A medical image processing apparatus comprising: