Information processing device, information processing method, program, and information processing system

Abstract

To provide an information processing device, an information processing method, a program, and an information processing system capable of determining common processing in a plurality of inference processing packages applied to medical data.SOLUTION: An information processing device according to the present invention includes: an inference processing package acquisition unit for acquiring an inference processing package composed of single processing or a plurality of items of processing including inference processing applied to medical data; a determination unit for determining processing common to two or more inference processing packages of the processing that constitutes a plurality of inference processing packages when the plurality of inference processing packages are acquired; and a setting unit for setting procedures of the plurality of items of processing including the common processing applied to the medical data on the basis of a result of the determination by the determination unit.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to an information processing apparatus, an information processing method, and a program for determining a process common to a plurality of inference processing packages applied to medical data.

Background Art

[0002] In the medical field, doctors use medical data such as image data of a patient's body taken by an image diagnostic apparatus such as an X-ray CT (Computed Tomography) apparatus, an MRI (Magnetic Resonance Imaging) apparatus, or an ultrasonic diagnostic apparatus, and electrocardiogram information obtained by an electrocardiograph to diagnose patients.

[0003] For the purpose of assisting doctors' diagnoses, various methods have been proposed for performing inference processing (for example, detection of lung nodules from chest CT images) on medical data using an inference model learned by machine learning.

[0004] A method of performing a plurality of inference processes on one piece of medical data has also been proposed by using a plurality of such inference models. For example, Patent Document 1 proposes a method of applying each of a plurality of inference models to one piece of medical image data and inferring a plurality of image findings (such as the calcification concentration ratio of lung nodules and the drawing-in of arteries and veins).

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0006] Patent Document 1 describes how, in multiple inference processing packages consisting of multiple processes including inference processing, the number of processes required to derive image findings can be reduced by pre-setting common processes. However, if the combination of multiple inference processes to be applied changes depending on the medical data, pre-setting common processes for multiple inference processing packages including such inference processing is time-consuming.

[0007] Therefore, the present invention aims to provide an information processing device, an information processing method, a program, and an information processing system that can determine common processing in multiple inference processing packages applied to medical data. [Means for solving the problem]

[0008] To solve the above problems, an information processing device according to one aspect of the present invention includes: an inference processing package acquisition unit that acquires an inference processing package consisting of one or more processes including inference processing to be applied to medical data; a determination unit that, when multiple inference processing packages are acquired, determines which processes are common to two or more inference processing packages among the processes constituting the multiple inference processing packages; and a setting unit that sets the procedures for multiple processes including common processes to be applied to medical data based on the determination result by the determination unit. [Effects of the Invention]

[0009] According to the present invention, it is possible to determine common processing in multiple inference processing packages applied to medical data, and to perform multiple inference processing efficiently. [Brief explanation of the drawing]

[0010] [Figure 1] A diagram showing the functional configuration of the information processing system in the first embodiment. [Figure 2] A diagram showing the configuration of the computer in the information processing device according to the first embodiment. [Figure 3]A flowchart showing the processing procedure of the information processing device in the first embodiment. [Figure 4] A diagram showing specific examples of processing included in multiple inference processing packages in the first embodiment. [Figure 5] A flowchart illustrating the processing procedure of the information processing device in the second embodiment. [Figure 6] A diagram showing the functional configuration of the information processing system in the third embodiment. [Modes for carrying out the invention]

[0011] Embodiments of the present invention will be described below with reference to the drawings. In principle, identical components will be denoted by the same reference numerals, and their descriptions will be omitted. However, the scope of the invention is not limited to the illustrated examples.

[0012] <First Embodiment> The following describes an information processing system according to the first embodiment. In this embodiment, the information processing device 130 constituting the information processing system determines common processing from a plurality of inference processing packages to be applied to the acquired medical data, sets an appropriate processing procedure based on the determination result, and executes processing on the medical data based on the set processing procedure.

[0013] The following describes, as an example, the use of chest CT image data obtained by imaging a subject with an X-ray CT scanner as the medical data to be processed. Note that the imaging device used to acquire the image data is not limited to an X-ray CT scanner; it may also be an MRI scanner, ultrasound diagnostic device, etc. Furthermore, the medical data is not limited to image data; it may also consist of text data, audio data, etc.

[0014] Figure 1 is a block diagram showing an example configuration of the information processing system in this embodiment. The information processing system includes an imaging device (X-ray CT device) 110, a data server 120, and an information processing device 130. Each component of the information processing system is connected to each other via a network, for example.

[0015] The information processing system stores the medical data (chest CT image data) captured by the imaging device 110 in the data server 120. In addition to the medical data captured by the imaging device 110, the data server 120 also holds a plurality of inference processing packages described later. Also, the processed medical data stored by the storage unit 136 in the information processing device 130 described later may also be stored in the data server 120. For data management of the data server 120, for example, a system such as a PACS (Picture Archiving and Communication Systems) that stores and manages medical data such as image data through a network can be used.

[0016] The information processing device 130 includes a medical data acquisition unit 131, an inference processing package acquisition unit 132, a determination unit 133, and a setting unit 134. The information processing device 130 further includes a processing unit 135, a storage unit 136, and an output unit 137.

[0017] The information processing device 130 acquires the medical data captured by the imaging device 110 from the data server 120 through the medical data acquisition unit 131.

[0018] Next, the inference processing package acquisition unit 132 acquires an inference processing package composed of one or more processes including inference processing to be applied to the medical data acquired by the medical data acquisition unit 131. In addition to the inference processing, the inference processing package further includes, for example, processes attached to the inference. When a plurality of inference processing packages are acquired, the determination unit 133 determines the processes common to two or more of the inference processing packages among the processes constituting the plurality of inference processing packages.

[0019] The setting unit 134 sets procedures for a plurality of processes including common processes to be applied to medical data based on the determination result by the determination unit 133. With the information processing apparatus 130 configured in this way, it is possible to determine common processes for a plurality of inference processing packages for medical data, and it is possible to set procedures for efficiently performing a plurality of inference processes.

[0020] The information processing apparatus 130 further includes a processing unit 134 that performs processing based on the processing procedure set by the setting unit 134. Also, a storage unit 136 that stores the result of the processing by the processing unit 134 stores the processing result. The storage unit 136 may store the processing result in the data server 120. The information processing apparatus 130 further has an output unit 137 that outputs the processing result by the processing unit 135. With this configuration, the processing unit 135 performs processing according to the processing procedure set by the setting unit 134, the processing result can be stored by the storage unit 136, and can be output by the output unit 137, and for medical data, it is possible to grasp the processing with an appropriate number of times of processing and the processing result by the processing. In addition, in the present embodiment, although the functions of each unit are described as being performed by the information processing apparatus 130, it may function as an information processing system in which each unit constituting the information processing apparatus 130 is realized by a plurality of apparatuses.

[0021] Hereinafter, details of each unit in the information processing apparatus 130 according to the present embodiment will be described.

[0022] (Medical data acquisition unit 131) The medical data acquisition unit 131 acquires medical data from the data server 120 in response to a user's instruction. Here, the medical data may be not only image data acquired by the imaging apparatus 110, but also any of voice data, waveform data, and text data. Also, the medical data acquisition unit 131 may be realized by different apparatuses, and the medical data 131 acquired by different apparatuses may be transmitted to the information processing apparatus 130.

[0023] (Inference processing package acquisition unit 132) The inference processing package acquisition unit 132 acquires multiple inference processing packages from the data server 120 to be applied to the medical data acquired by the medical data acquisition unit 131. The acquisition of inference processing packages may be performed according to the user's instructions, or this process may be performed automatically when medical data is acquired by the medical data acquisition unit 131.

[0024] Here, an inference processing package consists of one or more processes, including inference processing using an inference model. Processes constituting an inference processing package may include, in addition to inference processing, preprocessing applied to medical data to enable the inference model to perform inference, and postprocessing applied to the inference results. Furthermore, the inference processing package may include processes other than preprocessing and postprocessing.

[0025] (Judgment unit 133) When the inference processing package acquisition unit 132 acquires multiple inference processing packages, the determination unit 133 determines which processes are common to each of the multiple inference processing packages. The determination of common processes by the determination unit 133 will be described in detail later with reference to the drawings.

[0026] (Settings section 134) The setting unit 134 sets the processing procedure to be applied to the medical data based on the determination result from the determination unit 133. As the processing procedure to be applied to the medical data, the setting unit 134 sets the processing procedure so that processing common to multiple inference processing packages is performed preferentially.

[0027] (Processing Unit 135) The processing unit 135 executes processing on the medical data according to the processing procedures set by the setting unit 134. In this process, processing determined to be common to multiple inference processing packages is executed only once, and the results are shared in the next processing in the multiple inference processing packages.

[0028] (Storage unit 136) The storage unit 136 stores the processing results from the processing unit 135 in the data server 120. Alternatively, the storage unit 136 may also store these processing results in a storage device such as a hard disk provided in the information processing device 130.

[0029] (Output section 137) The output unit 137 outputs the results of the processing performed on the medical data by the processing unit 135. The output from the output unit 137 may be displayed on a display unit (not shown) consisting of a display or the like provided in the information processing device 130, or the processing results may be output to an external device.

[0030] Here, the arithmetic circuits used in the medical data acquisition unit 131, inference processing package acquisition unit 132, determination unit 133, setting unit 134, processing unit 135, storage unit 136, and output unit 137 may be specially designed processors. Furthermore, each component of these arithmetic circuits may be composed of different hardware. Also, at least a portion of the components of the arithmetic circuits may be composed of a single piece of hardware. In other words, the medical data acquisition unit 131, inference processing package acquisition unit 132, determination unit 133, setting unit 134, processing unit 135, storage unit 136, and output unit 137 can be composed of processors such as CPUs and GPUs (Graphics Processing Units), and arithmetic circuits such as FPGA (Field Programmable Gate Array) chips. These units may be composed of a single processor or arithmetic circuit, or of multiple processors or arithmetic circuits.

[0031] Figure 2 shows a specific example of the configuration of the arithmetic circuits used in the medical data acquisition unit 131, inference processing package acquisition unit 132, determination unit 133, setting unit 134, processing unit 135, storage unit 136, and output unit 137. The arithmetic circuits used in each part of the information processing device 130 consist of a CPU 201, GPU 202, RAM 203, ROM 204, and external storage device 205, which are connected by a system bus 200. In addition, the information processing device 130 may also be connected to a mouse or keyboard (not shown) as an input interface and a display (not shown) as an output interface.

[0032] Furthermore, the functions of each component of the information processing device 130 may be executed as an on-premise system, or some of its functions may exist as programs on a network such as a server or on the cloud and execute processing from there. Alternatively, the system may be configured to acquire medical data from an information terminal held separately by the user and output the processed results to the information terminal.

[0033] Furthermore, each part of the information processing device 130 may be configured as a separate device, or at least some of the components of the information processing device 130 may be integrated into an information processing system.

[0034] (Decision flow) Next, the processes performed by the information processing device 130 in this embodiment will be described with reference to the flowchart in Figure 3. The information processing device 130 receives instructions from the user and starts the processes shown in the flowchart in Figure 3.

[0035] In step S21, the medical data acquisition unit 131 communicates with the data server 120, obtains a list of medical data stored in the data server 120, and presents it to the user through an interface (not shown). Next, the medical data acquisition unit 131 acquires the medical data selected by the user. Then, the medical data acquisition unit 131 transmits the acquired medical data to the inference processing package acquisition unit 132 and / or processing unit 134, and proceeds to step S22. In step S21, the medical data acquired by the medical data acquisition unit 131 is not limited to the above; the medical data to be processed may be acquired directly, or medical data selected by the user may be transmitted by an external device or the like.

[0036] In step S22, the inference processing package acquisition unit 132 communicates with the data server 120 and presents the user with a list of inference processing packages, which are packages containing inference processing based on the inference model held by the data server 120, along with pre-processing and post-processing associated with the inference processing. The unit then acquires the inference processing package selected by the user. Here, the inference processing package may be selected by referring to a set table or selection criteria according to the medical data information acquired by the medical data acquisition unit 131. The inference processing package acquisition unit 132 selects the inference package to acquire according to the medical data. This selection may also be implemented by a different device such as an information terminal. Once the inference processing package acquisition unit 132 acquires an inference processing package to apply to the medical data, it transmits the acquired inference processing package to the determination unit 133 and proceeds to step S23. The inference processing packages may be pre-configured and stored in the data server. Alternatively, the processing selected by the user may be stored as a package. Furthermore, the single or multiple processing constituting the inference processing package may be changed, modified, or selected by the user as appropriate.

[0037] In step S23, the determination unit 133 determines whether there are two or more inference processing packages acquired. If the inference processing package acquisition unit 132 has acquired two or more inference processing packages, the determination unit 133 proceeds to step S24. On the other hand, if there is only one inference processing package acquired, the determination unit 133 proceeds to step S25.

[0038] In step S24, the determination unit 133 determines whether the processing is common to two or more of the acquired inference processing packages. The determination flow by the determination unit 133 is illustrated below.

[0039] For example, suppose the inference processing package acquisition unit 132 acquires three inference processing packages: inference processing package A, inference processing package B, and inference processing package C. The processing configuration of the three inference processing packages will be explained using Figure 4. Note that the processing and procedures that constitute a processing package are not limited to the examples below. In Figure 4(a), inference processing package A consists of preprocessing a (all organ extraction processing), preprocessing b (brain region sectioning processing), inference processing A (tumor detection processing), and postprocessing α (overlay processing on the original image). Inference processing package B shown in Figure 4(b) consists of preprocessing a (all organ extraction processing), preprocessing d (lung region sectioning processing), preprocessing e (binarization processing), inference processing B, and postprocessing α. Also, inference processing package C shown in Figure 4(c) consists of preprocessing a (all organ extraction processing), preprocessing b (brain region sectioning processing), preprocessing c (CT tomographic image orientation determination processing), inference processing C (difference detection processing with a normal example), and postprocessing β (difference gradient map generation processing).

[0040] Here, we show a specific example of the determination made by the determination unit 133 for the inference processing packages described above. Here, the single or multiple processes constituting each inference processing package in Figure 4 are executed in the order described in the configuration. In step S24, the determination unit 133 first determines whether there are any common processes in the first stage of each inference processing package. In the example in Figure 4, preprocessing a (steps S41A, S41B, and S41C) is a process common to inference processing packages A, B, and C. Next, the determination unit 133 determines whether the next process is common to each inference processing package that has a common first stage process (first common process). In the example in Figure 4, preprocessing b (steps S42A and S42C) is a process common to inference processing packages A and C, so the determination unit 133 determines that steps S42A and S42C are the second common process. The same determination is repeated until there are no more inference processing packages with common processes. In other words, the determination unit 133 determines common processes among the single or multiple processes that constitute the inference package, starting with the processes that are performed before the inference process. In the example above, the processes following inference processing packages A and C are not common, so the determination ends there. Here, the determination unit 133 determines a process to be common if it is common to two or more of the acquired multiple inference processing packages, and does not need to determine if it is common to all of the acquired multiple inference processing packages. When multiple inference processing packages are acquired by the inference processing package acquisition unit 132, the determination unit 133 determines whether a process is common to two or more of the processes that constitute the multiple inference processing packages. Once the determination unit 133 has determined whether a process is common, it transmits the determination result and the inference processing package information to the setting unit 134 and proceeds to step S25.

[0041] In step S25, the setting unit 134 sets a processing procedure that defines the order in which processing will be applied to the medical data, based on the information of multiple inference processing packages obtained from the inference processing package acquisition unit 132. Here, the setting unit 134 sets the processing procedure so that processing common to multiple inference processing packages determined by the determination unit 133 is applied first, and then other processing is performed. That is, after applying processing common to multiple inference processing packages, the setting unit 134 sets the procedure so that other processing constituting the multiple inference processing packages is carried out individually in each inference processing package. Furthermore, the individual processing is performed based on the processing results of the processing common to multiple inference processing packages.

[0042] In the example shown in Figure 4, the processing procedure set by the setting unit 134 is as follows: First, preprocessing a (steps S41A, S41B, and S41C) is applied to the medical data, followed by preprocessing b (steps S42A and S42C). Then, inference processing packages A and C apply the remaining processing (steps S43A and S44A in package A, and steps S43C, S44C, and S45C in package C) to the medical data to which preprocessing a and b have been applied, and inference processing package B applies the remaining processing (steps S42B, S43B, S44B, and S45B) to the medical data to which preprocessing a has been applied. After setting this processing procedure, the setting unit 134 outputs the processing procedure information to the processing unit 135 and proceeds to step S26.

[0043] In step S26, the processing unit 135 acquires the medical data to be processed from the medical data acquisition unit 131. The processing unit 135 also acquires the processing procedure to be applied to the medical data set by the setting unit 134, and acquires the necessary inference model and processing information from the medical data acquisition unit 131. If there is a common process among multiple inference processing packages, the processing unit 135 applies the common process to the medical data first, in accordance with the processing procedure set by the setting unit 134, and temporarily stores the application result in the storage unit 136. After executing the process common to the multiple inference packages determined by the determination unit 133, the processing unit 135 executes the remaining processes of each inference processing package on the medical data to which the temporarily held common processing result has been applied. If there is no common process, the processing unit 134 executes the processing of each inference processing package on the medical data acquired from the medical data acquisition unit 131, in accordance with the processing procedure set by the setting unit 134. The processing unit 135 executes all the processes included in the applied inference processing package and then sends the processing results to the storage unit 136. It also sends the processing results to the output unit 137.

[0044] In step S27, the storage unit 136 obtains the processing result from the processing unit 135, stores the processing result in the data server 120, and then proceeds to step S28.

[0045] In step S28, the output unit 137 outputs the processing result transmitted from the processing unit 135 to a display unit (not shown). Alternatively, it outputs the processing result to an external device. The output unit 137 also outputs the output result from the processing unit 135 in association with the inference processing package that performed the processing.

[0046] By performing the above-described flow using the information processing device 130, the determination unit 133 can determine the common processing for the processes constituting the multiple inference processing packages acquired by the inference processing package acquisition unit 132. Furthermore, based on the determination result by the determination unit 133, the setting unit 134 sets the processing procedure, and the processing unit 135 performs the processing according to the set processing procedure, thereby enabling processing of medical data with an appropriate number of processing steps. Note that any of the processes in the above-described flowchart may be executed by different devices, or any of the processes may be omitted.

[0047] As described above, the information processing device 130 according to this embodiment can perform inference processing and other related processes with the minimum number of processing steps, even if it includes processing common to multiple inference processing packages applied to medical data. This makes it possible to perform multiple inference processes efficiently.

[0048] Furthermore, while the above example illustrates a case where the preprocessing applied to medical data in order to perform inference processing is common, the information processing device 130 will also perform processing in the same manner as described above when the preprocessing and inference processing are common, or when some of the preprocessing, inference processing, and postprocessing applied to the results of the inference processing are common.

[0049] <Second Embodiment> Next, an information processing system according to the second embodiment will be described. In inference processing applied to medical data, for example, when an abnormality is detected, it may be necessary to decide whether to perform other inference processing based on the result of one inference processing.

[0050] Therefore, in this embodiment, we will describe a case in which, after processing by the inference processing package is completed, the processing results are checked and then additional processing by another inference processing package is performed. In the following description, components the same as in the first embodiment are denoted by the same reference numerals, and detailed explanations are omitted.

[0051] (Decision flow) The following describes the processes performed by the information processing device 130 in this embodiment, with reference to the flowchart in Figure 5. Since this embodiment performs the same processes as the first embodiment up to step S28, the explanation will begin from step S31 onwards.

[0052] In step S31, the information processing device 130 decides whether or not to perform additional inference processing in response to the user's instructions. If the information processing device 130 decides to perform additional inference processing, it proceeds to step S32. On the other hand, if it decides not to perform additional inference processing, the information processing device 130 terminates processing.

[0053] In step S32, the inference processing package acquisition unit 132 communicates with the data server 120, for example, to present a list of inference processing package information to the user and acquires additional inference processing package information according to the user's selection. However, the method of acquiring inference processing packages by the inference processing package acquisition unit 132 is not limited to this. For example, the inference processing package acquisition unit 132 may select packages by referring to a table according to the type of medical data acquired by the medical data acquisition unit 131, or it may store conditions in advance and acquire inference processing packages that satisfy the conditions. The inference processing package acquisition unit 132 also communicates with the data server 120 to acquire each processing result and the processing information associated with it. Then, the inference processing package acquisition unit 132 outputs the acquired information to the determination unit 133 and proceeds to step S33.

[0054] In step S33, the determination 133 determines whether there are any common processes between the processes included in the additionally acquired inference processing package and the processes applied to each processing result acquired from the data server 120. The method for determining common processes is the same as in step S24. When the determination result from the determination unit 133 is sent to the setting unit 134, the process proceeds to step S34.

[0055] In step S34, the setting unit 134 sets the processing procedure to be applied to the medical data, similar to step S25. However, for processing that is common between the processed data stored in the data server 120 and the additionally acquired inference processing package, the setting unit 134 sets the processing procedure so that the processing unit 135 replaces the processing by acquiring the processed medical data from the data server 120. In the following description, the aforementioned replacement of processing will be referred to as the replacement processing. After setting the processing procedure, the setting unit 134 transmits the set processing procedure information to the processing unit 135 and proceeds to step S35.

[0056] In step S35, the processing unit 135 obtains the processing procedure set by the setting unit 134. It also obtains the necessary inference model and processing information from the data server 120 via the medical data acquisition unit 131. If the processing procedure includes alternative processing, it obtains the alternative processed medical data from the data server 120 via the medical data acquisition unit 131. Then, the processing unit 134 executes the processing of the inference processing package on the processed medical data or unprocessed medical data obtained from the data server 120 according to the processing procedure, in the same manner as in step S26, and transmits the processing results to the storage unit 136 and the output unit 137, before proceeding to step S36.

[0057] In step S36, the storage unit 136 obtains the processing result from the processing unit 135, stores the processing result in the data server 120, and then proceeds to step S37.

[0058] In step S37, the output unit 137 outputs the processing result of the medical data by the processing unit 135. Then, the process returns to step S31.

[0059] As described above, according to the information processing device 130 of this embodiment, even when performing another inference process after confirming the result of the inference process, the result of the common process that has already been performed can be used. As a result, even when additional inference processing is performed, the determination unit 133 can determine the common process and perform the inference process efficiently.

[0060] <Example 1> In the above embodiment, image data obtained by imaging with an imaging device was used as an example of medical data, but the present invention is not limited to this. In addition to image data, waveform data such as electrocardiograms, text data such as electronic medical record information, etc., may also be used, and any combination of these medical data may be used. Medical data is data that includes at least one of image data, waveform data, and text data. Furthermore, the inference processing package acquisition unit 132 may change the target inference processing package depending on the input data format.

[0061] Furthermore, while an inference processing package consisting of preprocessing, inference processing, and postprocessing was given as an example of an inference processing package, the configuration of an inference processing package is not limited to this. An inference processing package only needs to include one inference processing step, and does not need to include preprocessing or postprocessing. The minimum configuration is an inference processing package that includes only one inference processing step, in which case it does not include preprocessing, and the determination is made whether the processing is common to the inference processing for each inference processing package that performs the inference processing first.

[0062] Furthermore, while the inference processing package acquisition unit 132 acquired inference processing packages by allowing the user to select the inference processing package to apply to the medical data, the method of acquiring inference processing packages is not limited to this. For example, multiple inference processing packages may be automatically acquired for the input medical data using a machine learning model that has learned combinations of inference processing packages to acquire.

[0063] <Modification 2> In the above embodiment, the case in which all medical data to which the inference processing package has been applied is described in the storage unit 136 and stored in the data server 120, but the implementation of the present invention is not limited to this. For example, the storage unit 136 may output to the input / output interface of the information processing device 130 via the output unit 137, and the user may select the processing results to be stored in the data server 120 through the interface. Alternatively, each processing result by the processing unit 135 may be displayed to the output interface of the information processing device 130. The storage unit 136 may store each inference processing package information stored in the data server 120 in association with the display method when output by the output unit 137. In the above case, when the output unit 137 outputs each processing result, it changes the display method of the result based on the display method information associated with the inference processing package information.

[0064] This allows the output unit 137 to change the display method of the processing results according to the processing content of the inference processing package, making it easier for the user to check the processing results.

[0065] <Third Embodiment> Next, an information processing system according to a third embodiment will be described. The information processing system in this embodiment further includes an information terminal 740 that can communicate with the information processing device 130 via a network, in addition to the configuration of the information processing system described above. The user can operate the information terminal 740 to select an inference processing package and display the output results from the information processing device 130.

[0066] The information terminal 740 further includes a selection unit 741 for selecting an inference processing package and a display unit 742 for displaying the output from the information processing device 100. The information terminal 740 can be, for example, a PC terminal, a mobile phone such as a smartphone, a notebook computer, or a tablet computer.

[0067] The information processing device 130 outputs the output from the output unit 137 described in the above embodiment to the display unit 742 of the information terminal 740 via the network. For example, the information processing device 130 displays a list of inference processing packages on the display unit 742 of the information terminal 740, and the user may select an inference processing package via the selection unit 741 of the information terminal 740. In response to the selection of an inference processing package by the selection unit 741, the inference processing package acquisition unit 132 in the information processing device 130 acquires the inference processing package.

[0068] Furthermore, the information processing device 130 outputs the processing results to the information terminal 740, and the information terminal displays the output received by the display unit 742. With this configuration, even if the information processing device 130 is composed of a different device, such as a cloud or the information terminal 740 operated by the user, it is possible to select an inference processing package and confirm the processing results in accordance with the optimized processing procedure.

[0069] (Other examples) Furthermore, the present invention can also be realized by performing the following process: that is, supplying software (program) that realizes the functions of the above-described embodiment to a system or device via a network or various storage media, and having the computer (or CPU or MPU, etc.) of that system or device read and execute the program.

Claims

1. An inference processing package acquisition unit acquires an inference processing package consisting of one or more processes, including inference processing, to be applied to medical data. A processing unit that performs processing on the medical data based on the inference processing package, A storage unit that stores the results of one or more processes included in the inference processing package processed by the processing unit, When multiple inference processing packages are obtained, a determination unit determines which processes are common to two or more of the processes that constitute the multiple inference processing packages, An information processing device having a setting unit that sets a set of procedures for a plurality of processes, including the common process, to be applied to the medical data based on the determination result by the determination unit, The storage unit stores one or more processing results obtained when the processing unit performs a first processing on the medical data based on the processing procedure set by the setting unit for a plurality of inference processing packages acquired by the inference processing package acquisition unit. If the inference processing package acquisition unit acquires a second inference processing package for performing an additional second processing step on the medical data after the execution of the first processing step, The determination unit determines which processes are common to the first process and the processes that constitute the second inference processing package. The processing unit is characterized in that it obtains the results of a process determined to be common to the first process and the process constituting the second inference processing package from the storage unit, and uses the results in the second process.

2. The information processing apparatus according to claim 1, further comprising a medical data acquisition unit for acquiring the aforementioned medical data.

3. The information processing apparatus according to claim 1 or 2, wherein the inference processing package further includes processing incidental to inference.

4. The information processing apparatus according to any one of claims 1 to 3, characterized in that the setting unit sets other processes constituting the inference processing package as steps after the common process.

5. The information processing apparatus according to any one of claims 1 to 4, characterized in that the determination unit determines the common process from among the single or multiple processes constituting the inference processing package that are applied before the inference processing.

6. The information processing apparatus according to any one of claims 1 to 5, characterized in that the inference processing package acquisition unit acquires a plurality of inference processing packages selected by the user.

7. The information processing apparatus according to any one of claims 1 to 6, further comprising an output unit that outputs the result of processing by the processing unit and the inference processing package that performed the processing in association with each other.

8. The information processing apparatus according to any one of claims 1 to 7, characterized in that the medical data includes at least one of the following: image data, waveform data, and text data.

9. The information processing apparatus according to claim 8, characterized in that the inference processing package acquisition unit selects an inference processing package to acquire according to the medical data.

10. The determination unit includes a first determination process that determines which processes are common to two or more inference processing packages among the processes that constitute the plurality of inference processing packages acquired by the inference processing package acquisition unit, The information processing apparatus according to any one of claims 1 to 9, characterized in that it performs a second determination process for determining a process common to the first process and the process constituting the second inference processing package.

11. An inference processing package acquisition step to obtain an inference processing package consisting of one or more processes, including inference processing, to be applied to medical data, A processing step of performing processing based on the inference processing package on the medical data, A storage step for storing the results of one or more processes included in the inference processing package processed in the processing step, When multiple inference processing packages are obtained, a determination step is made to determine which processes are common to two or more of the processes that constitute the multiple inference processing packages. An information processing method having a setting step of setting a procedure for a plurality of processes, including the common process, to be applied to the medical data based on the determination result of the determination step, In the storage step, one or more processing results are stored for the medical data in the processing step, where a first processing based on the processing procedure set in the setting step is performed on the medical data for the plurality of inference processing packages acquired in the inference processing package acquisition step. If, after the execution of the first process described above, a second inference processing package is obtained for performing a second additional process, Determine the processes that are common to the first process and the processes that constitute the second inference processing package. An information processing method characterized by obtaining the results of a process determined to be common to the first process and the process constituting the second inference processing package from the information stored in the storage step, and using the results in the second process.

12. The information processing method includes a first determination process that determines which processes are common to two or more inference processing packages among the processes that constitute the plurality of inference processing packages obtained by the inference processing package acquisition step, The information processing method according to claim 11, characterized in that a second determination process is performed to determine which processes are common to the first process and the processes that constitute the second inference processing package.

13. A program for causing a computer to execute the information processing method described in claim 11 or 12.

14. An information processing system comprising an information processing device and an information terminal capable of communicating with the information processing device via a network, The information processing device includes an inference processing package acquisition unit that acquires an inference processing package consisting of one or more processes, including inference processing, to be applied to medical data, A processing unit that performs processing on the medical data based on the inference processing package, A storage unit that stores the results of one or more processes included in the inference processing package processed by the processing unit, When multiple inference processing packages are obtained, a determination unit determines which processes are common to two or more of the processes that constitute the multiple inference processing packages, An information processing system having a setting unit that sets a set of procedures for a plurality of processes, including the common process, to be applied to the medical data based on the determination result by the determination unit, The storage unit stores one or more processing results obtained when the processing unit performs a first processing on the medical data based on the processing procedure set by the setting unit for a plurality of inference processing packages acquired by the inference processing package acquisition unit. If the inference processing package acquisition unit acquires a second inference processing package for performing an additional second processing step on the medical data after the execution of the first processing step, The determination unit determines which processes are common to the first process and the processes that constitute the second inference processing package. The information processing system is characterized in that the processing unit obtains from the storage unit the results of the processing that is determined to be common to the first processing and the processing that constitutes the second inference processing package, and uses the results in the second processing.

15. The information processing device includes a processing unit that performs processing on the medical data based on a set processing procedure, It has an output unit that outputs the result of processing by the processing unit to the information terminal, The information processing system according to claim 14, wherein the information terminal further comprises a display unit that displays information corresponding to the output.

16. The information processing system according to claim 14 or 15, wherein the information terminal has a selection unit for selecting an inference processing package, and the inference processing package acquisition unit acquires an inference processing package in accordance with the selection by the selection unit.

17. The determination unit includes a first determination process that determines which processes are common to two or more inference processing packages among the processes that constitute the plurality of inference processing packages acquired by the inference processing package acquisition unit, The information processing system according to any one of claims 14 to 16, characterized in that it performs a second determination process to determine which processes are common to the first process and the processes constituting the second inference processing package.

Images