Information processing system, information processing method, and program

Abstract

To provide an information processing system, etc. capable of securing anonymity of a medical image.SOLUTION: There is provided an information processing system. The information processing system includes a control unit. The control unit is configured so as to execute the following steps. In a reconstruction step, first volume data indicating at least part of a subject is reconstructed on the basis of a plurality of first continuous tomographic images of the subject. The first volume data includes first contour data indicating an outer appearance of the subject and inner data including the inside of the body of the subject. In a conversion step, the first volume data is converted to the second volume data on the basis of reference contour data other than the first contour data. The second volume data includes the second contour data different from the first contour data, and inner data including the inside of the subject.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to an information processing system, an information processing method, and a program. [Background technology]

[0002] In recent years, medical images captured by medical image diagnostic devices are being used as training data for machine learning (for example, Patent Literature 1). In addition, by using such a program based on machine learning, a doctor can be supported in making a diagnosis. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2019-180866 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, for example, when medical images are continuous cross-sectional images taken by an X-ray CT scanner, the face of the subject can be reproduced to a degree that makes it possible to recognize it by reconstructing them. For this reason, concerns have been raised about the use of such data as training data from the perspective of protecting personal information.

[0005] In view of the above circumstances, the present invention provides an information processing system and the like that can guarantee the anonymity of medical images. [Means for solving the problem]

[0006] According to one aspect of the present invention, there is provided an information processing system. The information processing system includes a control unit. The control unit is configured to execute the following steps. In the reconstruction step, first volume data showing at least a part of the subject is reconstructed based on a plurality of first continuous tomographic images of the subject. The first volume data has first contour data representing the appearance of the subject and internal data including the inside of the subject's body. In the conversion step, the first volume data is converted into second volume data based on reference contour data other than the first contour data. The second volume data has second contour data different from the first contour data and internal data including the inside of the subject's body.

[0007] According to this aspect, the anonymity of the medical image can be guaranteed. [Brief description of the drawings]

[0008] [Figure 1] 1 is a configuration diagram illustrating an information processing system 1 according to an embodiment of the present invention. [Diagram 2] 2 is a block diagram showing a hardware configuration of an information processing device 2 according to the present embodiment. FIG. [Diagram 3] 2 is a block diagram showing functions realized by a control unit 23 and the like in an information processing device 2 according to the present embodiment. FIG. [Figure 4] 2 is an activity diagram showing the flow of information processing executed by the information processing device 2 according to the first embodiment. FIG. [Diagram 5] FIG. 2 is a schematic diagram showing an example of a first sequential tomographic image IM1 (sequential tomographic image IM). [Figure 6] FIG. 2 is a schematic diagram showing a first image 4 which is one of first continuous tomographic images IM1. [Figure 7] 2 is a schematic diagram showing an example of first volume data V1 from which the face of a subject can be recognized. FIG. [Figure 8] 1 is a schematic diagram showing an example of reference volume data V0 forming the face of a fictional person. FIG. [Figure 9]1 is a schematic diagram showing the setting of landmarks LM for volume data V. FIG. [Figure 10] 13 is a schematic diagram showing an example of second volume data V2 generated by conversion. FIG. [Figure 11] 13 is a schematic diagram showing a second image 8 which is one of second successive tomographic images IM2 generated from the second volume data V2. FIG. [Figure 12] 13 is a schematic diagram showing a correction by modifying the internal data 6. FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, embodiments of the present invention will be described with reference to the drawings. Various features shown in the following embodiments can be combined with each other.

[0010] Incidentally, the program for realizing the software appearing in this embodiment may be provided as a non-transitory computer-readable recording medium, or may be provided so as to be downloadable from an external server, or may be provided so that the program is started on an external computer and its functions are realized on a client terminal (so-called cloud computing).

[0011] In addition, in this embodiment, the term "unit" may include, for example, a combination of hardware resources implemented by a circuit in the broad sense and software information processing that can be specifically realized by these hardware resources. In addition, in this embodiment, various information is handled, and this information is represented, for example, by physical values ​​of signal values ​​representing voltage and current, high and low signal values ​​as a binary bit collection consisting of 0 or 1, or quantum superposition (so-called quantum bits), and communication and calculation can be performed on the circuit in the broad sense.

[0012] In addition, a circuit in the broad sense is a circuit realized by at least appropriately combining a circuit, circuitry, a processor, a memory, etc. In other words, it includes an application specific integrated circuit (ASIC), a programmable logic device (e.g., a simple programmable logic device (SPLD), a complex programmable logic device (CPLD), and a field programmable gate array (FPGA)), etc.

[0013] [Embodiment] 1. Hardware Configuration In this section, the hardware configuration of this embodiment will be described.

[0014] 1.1 Information Processing System 1 FIG. 1 is a configuration diagram showing an information processing system 1 according to this embodiment. The information processing system 1 includes at least one information processing device 2, which are connected via a network 11. Here, the information processing device 2 is depicted as a plurality of information processing devices 2. The information processing device 2 is configured to be capable of managing various information in a distributed manner using a blockchain BC or the like. In addition, a system exemplified as the information processing system 1 is composed of one or more devices or components. Therefore, even the information processing device 2 alone is an example of a system.

[0015] 1.2 Information processing device 2 2 is a block diagram showing a hardware configuration of the information processing device 2 according to this embodiment. The information processing device 2 has a communication unit 21, a storage unit 22, a control unit 23, a display unit 24, and an input unit 25, and these components are electrically connected via a communication bus 20 inside the information processing device 2. Each component will be further described.

[0016] The communication unit 21 is preferably a wired communication means such as USB, IEEE1394, Thunderbolt (registered trademark), wired LAN network communication, etc., but may also include wireless LAN network communication, mobile communication such as 3G / LTE / 5G, Bluetooth (registered trademark) communication, etc. as necessary. In other words, it is more preferable to implement it as a collection of these multiple communication means.

[0017] In this embodiment, the information processing device 2 is configured to communicate transaction information related to the blockchain BC with external devices including other information processing devices 2 via the network 11 through the communication unit 21. The blockchain BC will be described later in the next description of the storage unit 22.

[0018] The storage unit 22 stores various pieces of information defined by the above description. This can be implemented, for example, as a storage device such as a solid state drive (SSD) that stores various programs related to the information processing device 2 executed by the control unit 23, or as a memory such as a random access memory (RAM) that stores temporarily required information (arguments, arrays, etc.) related to the calculation of the programs. It may also be a combination of these.

[0019] Particularly in this embodiment, the storage unit 22 stores a program that causes a computer to execute each step in the information processing system 1. That is, by installing such a program in the information processing device 2, the information processing device 2 is configured to have each functional unit described below and to execute each step.

[0020] The storage unit 22 is configured to store the tokenized information in a blockchain BC, which is an example of a distributed ledger. The distributed ledger is an electronic ledger. The distributed ledger is shared by multiple nodes of multiple information processing devices 2.

[0021] In the blockchain BC, data is recorded as multiple blocks linked together, and each node is implemented to share these blocks. Each information processing device 2 functions as a node of the distributed ledger. It is assumed that the origin block, which is the first block, is registered in the distributed ledger as an initial value. A newly generated block is linked to the origin block. The block includes transaction information. The transaction information in this embodiment includes a second continuous tomographic image IM2 described later.

[0022] The control unit 23 performs processing and control of the overall operation related to the information processing device 2. The control unit 23 is, for example, a central processing unit (CPU) not shown. The control unit 23 realizes various functions related to the information processing device 2 by reading out a predetermined program stored in the storage unit 22. That is, information processing by software stored in the storage unit 22 is specifically realized by the control unit 23, which is an example of hardware. That is, the information processing system 1 includes the control unit 23, and the control unit 23 includes each functional unit described below.

[0023] The display unit 24 may be, for example, included in the housing of the information processing device 2, or may be externally attached. The display unit 24 displays a screen of a graphical user interface (GUI) that can be operated by the user. This is preferably implemented by using display devices such as a CRT display, a liquid crystal display, an organic EL display, and a plasma display according to the type of the information processing device 2.

[0024] The input unit 25 may be included in the housing of the information processing device 2, or may be externally attached. For example, the input unit 25 may be implemented as a touch panel integrated with the display unit 24. If it is a touch panel, the user can input a tap operation, a swipe operation, or the like. Of course, a switch button, a mouse, a QWERTY keyboard, or the like may be adopted instead of the touch panel. That is, the input unit 25 accepts an operation input made by the user. The input is transferred as a command signal to the control unit 23 via the communication bus 20, and the control unit 23 can execute a predetermined control or calculation as necessary.

[0025] 2. Functional configuration In this section, the functional configuration of the present embodiment will be described. As described above, information processing by the software stored in the storage unit 22 is specifically realized by the control unit 23, which is an example of hardware, and can be executed as each functional unit included in the control unit 23.

[0026] 3 is a block diagram showing functions realized by the control unit 23 and the like in the information processing device 2 according to this embodiment. Specifically, the information processing device 2, which is an example of the information processing system 1, includes a receiving unit 231, a reading unit 232, a reconstruction unit 233, a position adjustment unit 234, a setting unit 235, a conversion unit 236, an imaging unit 237, a correction unit 238, and a transmission unit 239.

[0027] The receiving unit 231 is configured to receive various information from the outside via the network 11 or through a recording medium (not shown). For example, the receiving unit 231 may receive first successive tomographic images IM1 of a subject provided from the hospital 12 through a recording medium (not shown). The first successive tomographic images IM1 received by the receiving unit 231 are stored in the storage unit 22 of the information processing device 2. This will be described in more detail later.

[0028] The reading unit 232 is configured to read out various information accepted by the accepting unit 231 or previously stored in the storage unit 22. For example, the reading unit 232 may read out the first continuous tomographic images IM1 stored in the storage unit 22, or reference volume data V0 or reference contour data 50, which are examples of reference information. This will be described in more detail later.

[0029] The reconstruction unit 233 is configured to reconstruct the successive tomographic images IM to reconstruct the volume data V. For example, the reconstruction unit 233 may reconstruct the first volume data V1 showing at least a part of the subject based on the first successive tomographic images IM1 stored in the storage unit 22. This will be described in further detail later.

[0030] The registration unit 234 is configured to perform a registration process between the first volume data V1 and the reference volume data V0 having reference contour data 50 representing the appearance of a fictional character, as will be described in further detail below.

[0031] The setting unit 235 is configured to set landmarks LM for the first volume data V1 and the reference contour data 50, which are registered with each other. This will be described in further detail later.

[0032] As a conversion step, the conversion unit 236 is configured to convert the first volume data V1 into the second volume data V2 based on the reference contour data 50. This will be described in further detail below.

[0033] The imaging unit 237 is configured to generate a plurality of successive tomographic images IM with a predetermined slice thickness from the volume data V. For example, the imaging unit 237 may generate a plurality of second successive tomographic images IM2 from the second volume data V2, which will be described in further detail below.

[0034] The correction unit 238 is configured to perform a correction to expand or shrink the intermediate data 7 in accordance with the second outline data 52. This will be described in more detail below.

[0035] The transmission unit 239 is configured to transmit various information to the outside via the communication unit 21 and the network 11. For example, the transmission unit 239 may transmit at least a part of the second continuous tomographic images IM2 to an external device, for example, another information processing device 2. This will be described in further detail later.

[0036] 3. Information processing method In this section, the information processing method of the information processing system 1 described above will be described. In the following, it is assumed that a subject using the information processing device 2 undergoes medical image diagnosis at a hospital 12, and the first continuous tomographic image IM1 resulting from the diagnosis is provided as teacher data. Examples of devices used in medical image diagnosis include an X-ray CT scanner and a magnetic resonance imaging device. For example, in the case of an X-ray CT scanner, an X-ray detector detects X-rays irradiated from an X-ray tube (not shown) and outputs detection data corresponding to the amount of X-rays as an electrical signal to a DAS (not shown). Then, a rotating frame (not shown) that supports the X-ray tube and the X-ray detector in an opposing relationship is rotated around the subject to collect multiple views, that is, detection data for the entire circumference of the subject. In this way, a continuous tomographic image IM is obtained.

[0037] Furthermore, volume data V obtained by reconstructing the successive tomographic images IM has contour data 5 representing the external appearance and internal data 6 including the inside of the body. Furthermore, the volume data V has intermediate data 7 indicating the area between the contour data 5 and the internal data 6. Furthermore, when one of the successive tomographic images IM is extracted, the data will be similarly referred to as the contour data 5, the internal data 6, and the intermediate data 7 of the successive tomographic images IM, respectively. In this embodiment, in medical image diagnosis, a doctor identifies a case by observing the internal data 6 in the successive tomographic images IM.

[0038] 3.1 Overview of Information Processing 4 is an activity diagram showing the flow of information processing executed by the information processing device 2 according to the first embodiment. First, the flow of information processing will be outlined along each activity in FIG.

[0039] First, the reception unit 231 receives the first successive tomographic images IM1 as a reception step. Specifically, the subject, who is the user of the information processing device 2, reads the first successive tomographic images IM1 recorded on a recording medium (not shown) provided by the hospital 12 into his / her own information processing device 2, thereby storing the first successive tomographic images IM1 in the storage unit 22 (activity A101).

[0040] Next, as a reconstruction step, the reconstruction unit 233 reconstructs first volume data V1 showing at least a part of the subject based on the plurality of first continuous tomographic images IM1 of the subject. Specifically, the control unit 23 reads out a program having a reconstruction function stored in the storage unit 22, thereby executing the reconstruction step (activity A102).

[0041] Next, the reading unit 232 reads out reference volume data V0, which is an example of reference information previously stored in the storage unit 22, and writes it out to a temporary storage area of ​​the storage unit 22 (activity A103). At this time, if the reference contour data 50 included in the read reference volume data V0 is calculated by averaging the values ​​of multiple human images, the processing proceeds to activities A104 and A105. On the other hand, if the reference contour data 50 is generated based on a trained model such as GAN, the processing described in activities A104 and A105 can be omitted. Below, activities A104 and A105 will be described.

[0042] As a registration step, the registration unit 234 executes registration processing between the first volume data V1 and the reference volume data V0 having the reference contour data 50. Specifically, the control unit 23 reads out a program having a registration function stored in the storage unit 22, whereby an iteration calculation (repetition of activity A104) is executed and the positional relationship between the reference volume data V0 and the first volume data V1, at which the evaluation function has an extreme value, is automatically calculated.

[0043] Next, as a setting step, the setting unit 235 sets landmarks LM for the first volume data V1 and the reference volume data V0 that are aligned with each other. The landmarks LM are tracking points that can be characteristic locations, which will be described further below. Specifically, the control unit 23 reads out a program having a landmark setting function stored in the storage unit 22, thereby executing this setting step (activity A105).

[0044] Next, as a conversion step, the conversion unit 236 converts the first volume data V1 into second volume data V2 having second contour data 52 based on the landmarks LM. Here, the internal data 6 does not change before and after the conversion, and only the contour data changes from the first contour data 51 to the second contour data 52. Specifically, the control unit 23 reads out a program having a conversion function stored in the storage unit 22, thereby executing this conversion step (activity A106).

[0045] Next, the imaging unit 237 generates a plurality of second continuous tomographic images IM2 from the second volume data V2 as an imaging step. Specifically, the imaging step is executed by the control unit 23 reading out a program having an imaging function stored in the storage unit 22 (activity A107).

[0046] Next, as a correction step, the correction unit 238 corrects the second consecutive tomographic images IM2 by executing a correction to expand or shrink the intermediate data 7 in accordance with the second contour data 52. Specifically, the control unit 23 reads out a program having a correction function stored in the storage unit 22, thereby executing the correction step (activity A108).

[0047] Finally, the transmitting unit 239 transmits at least a part of the second continuous tomographic images IM2 to an external device as a transmitting step. This transmission may be determined by an input to the input unit 25 of the subject operating the information processing device 2. More specifically, the second continuous tomographic images IM2 corrected in the activity A108 are recorded in a block of the blockchain BC and shared (here, distributed ledger management) among a plurality of information processing devices 2 via the network 11 (activity A109). According to this embodiment, the subject can provide his / her own medical image, here the second continuous tomographic images IM2, as teacher data at his / her own free will while ensuring anonymity.

[0048] In summary, the information processing method includes the following steps. In the reconstruction step, first volume data V1 showing at least a part of the subject is reconstructed based on a plurality of first continuous tomographic images IM1 of the subject. The first volume data V1 has first contour data 51 showing the appearance of the subject and internal data 6 including the inside of the subject's body. In the conversion step, the first volume data V1 is converted into second volume data V2 based on reference contour data 50 other than the first contour data 51. The second volume data V2 has second contour data 52 different from the first contour data 51 and internal data 6 including the inside of the subject's body.

[0049] According to this embodiment, the anonymity of the medical image can be guaranteed. In addition to the anonymity, the accuracy of the machine learning can be maintained. The second continuous tomographic image IM2 provided as the training data is obtained by replacing only the contour data 5 from the first contour data 51 to the second contour data 52, so that the accuracy of the machine learning can be maintained without compromising the internal data 6, which is important as the training data.

[0050] 3.2 Details of data processing Next, the details of the information processing outlined in FIG. 4 will be described.

[0051] FIG. 5 is a schematic diagram showing an example of a first continuous tomographic image IM1 (continuous tomographic image IM). As shown in FIG. 5, the continuous tomographic image IM is composed of a plurality of images. That is, the first continuous tomographic image IM1 is composed of a plurality of first images 4. Here, first images 4a, 4b, 4c, 4d, 4e, 4f, and 4g are illustrated, and each is an image captured for each predetermined slice thickness. The slice thickness is not particularly limited, and is, for example, 0.1 to 20 mm, preferably 0.4 to 10 mm, and more preferably 1 to 5 mm, and specifically, for example, 0.1, 0.15, 0.2, 0.25, 0.3, 0.35, 0.4, 0.45, 0.5, 0.55, 0.6, 0.65, 0.7, 0.75, 0.8, 0.85, 0.9, 0.95, 1, 1.5, 2 , 2.5, 3, 3.5, 4, 4.5, 5, 5.5, 6, 6.5, 7, 7.5, 8, 8.5, 9, 9.5, 10, 10.5, 11, 11.5, 12, 12.5, 13, 13.5, 14, 14.5, 15, 15.5, 16, 16.5, 17, 17.5, 18, 18.5, 19, 19.5, 20 mm, and may be within a range between any two of the values ​​exemplified here. In particular, when the slice thickness value is small, the accuracy of identifying a face from the reconstructed volume data V increases, and the risk of it being personal information increases.

[0052] FIG. 6 is a schematic diagram showing a first image 4 which is one of the first continuous tomographic images IM1. As shown in FIG. 6, the first image 4 includes a body surface 41, intermediate tissue 42, bone 43, and an area 44 inside the bone 43. The body surface 41 is an element that determines the appearance when the first continuous tomographic images IM1 are reconstructed into the first volume data V1, and the body surface 41 constitutes the first contour data 51. From a pathological perspective, the body surface 41 includes at least the epidermis and the dermis. The intermediate tissue 42 includes at least one of subcutaneous tissue, muscle, fat, and blood vessels, and constitutes intermediate data 7. The bone 43 and the area 44 inside the bone 43 constitute internal data 6 that may include a case.

[0053] In other words, the first contour data 51 is data representing the body surface 41 of the subject, and the internal data 6 is data representing the bones 43 and the region 44 inside the bones 43 of the subject. The intermediate data 7 also includes intermediate tissue 42 including at least one of subcutaneous tissue, muscle, fat, and blood vessels. In this embodiment, the intermediate tissue 42 is excluded as a portion for identifying a case, and therefore this region may be stretched or contracted. Such stretching will be described in detail later with reference to FIG. 11. In this way, anonymity can be ensured while ensuring consistency as a human body.

[0054] 7 is a schematic diagram showing an example of first volume data V1 from which the subject's face can be recognized. As described above, the first volume data V1 is obtained by reconstructing the first continuous tomographic images IM1. The first volume data V1 from which the first continuous tomographic images IM1 are reconstructed has first contour data 51 representing the subject's appearance and internal data 6 including the subject's interior. Since the first volume data V1 has the first contour data 51, the subject's face (appearance) can be recognized, and therefore the first volume data V1 and the first continuous tomographic images IM1 from which the first volume data V1 is derived may be subject to personal information protection.

[0055] FIG. 8 is a schematic diagram showing an example of reference volume data V0 forming a face of a fictitious person. As shown in FIG. 7 and FIG. 8, a face recognized from the reference volume data V0 is different from a face recognized from the first volume data V1. For example, the reference contour data 50 is calculated from contour data of a person other than the subject. In this way, the contour data of a person other than the subject can be reused from the contour data captured in the past, so that the reference contour data 50 can be easily generated. Preferably, the reference contour data 50 is calculated from an average value of a plurality of person images. Specifically, the reference contour data 50 may be calculated as an average value of faces reconstructed from a plurality of medical images of the subject captured in the past. According to this embodiment, the reference contour data 50, which is the contour data 5 of a fictitious person, can be generated by a simple algorithm of averaging.

[0056] Here, it is preferable that the reference contour data 50 is determined for at least one of age, sex, and race. Since facial features vary greatly depending on age, sex, and race, it is preferable to generate in advance a face that is an average value of a plurality of faces, i.e., reference contour data 50, taking these conditions into consideration. According to this embodiment, it is possible to select reference contour data 50 that is close to or identical to the subject's attributes, particularly age, sex, and race, which contributes to generating the second volume data V2 and the second continuous tomographic images IM2 more naturally.

[0057] More preferably, the reference contour data 50 may be directly used as the second contour data 52. In this case, the reference volume data V0 including the reference contour data 50 may itself be data obtained by transforming the first volume data V1. More specifically, the second contour data 52 may be obtained by transforming at least a part of the first contour data 51 based on preset reference information, for example, a trained model using GAN. GAN is a type of generative model, and can generate non-existent data or convert existing data according to the characteristics by learning features from various data without correct answer data. In this way, if the reference contour data 50 is originally obtained by transforming the first contour data 51, it can be more easily converted into the second volume data V2 including the second contour data 52 without reducing the processing by the positioning unit 234 and the setting unit 235 described above.

[0058] FIG. 9 is a schematic diagram showing the setting of landmarks LM for volume data V. In the example shown in FIG. 9, the landmarks LM are set at the centers of the eyes, the center of the mouth, the space between the eyebrows, the tip of the nose, and the tip of the ear in the reference volume data V0 (FIG. 9A) and the first volume data V1 (FIG. 9B), respectively. For example, the receiving unit 231 may receive an input from the subject using the input unit 25, and the setting unit 235 may set the landmarks LM based on the input. Alternatively, the control unit 23 may read out a program having an automatic detection function stored in the storage unit 22, so as to automatically detect at least one of the centers of the eyes, the center of the mouth, the space between the eyebrows, the tip of the nose, and the tip of the ear. Furthermore, these may be combined to enable manual adjustment by input of the subject after automatic detection of the recommended location for setting the landmark LM.

[0059] FIG. 10 is a schematic diagram showing an example of the second volume data V2 generated by conversion. As shown in FIG. 7 to FIG. 10, the face of the person formed in the second volume data V2 is different from the face of the imaginary person formed in the reference volume data V0 and the face of the subject formed in the first volume data V1. More specifically, after setting landmarks LM in the reference contour data 50 included in the reference volume data V0 and the first contour data 51 included in the first volume data V1, the reference volume data V0 is transformed using these as guides to obtain the second volume data V2 having the second contour data 52. Preferably, the reference volume data V0 can be transformed using the thin spline method so as to obtain the second volume data V2. As described above, the internal data 6 is not transformed before and after the conversion, and only the contour data is transformed from the first contour data 51 to the second contour data 52.

[0060] In other words, the conversion unit 236 converts the first volume data V1 into the second volume data V2 having the second contour data 52 based on the landmarks LM as a conversion step. By setting the landmarks LM in this way and then converting, it is possible to change only the external appearance of the subject more naturally, and further ensure anonymity while ensuring consistency as a human body. In other words, the internal data 6 in the second volume data V2 is the same as the intermediate data 7 of the subject in the first volume data V1, and in other words, the second volume data V2 has the second contour data 52 different from the first contour data 51 and the internal data 6 including the inside of the subject.

[0061] FIG. 11 is a schematic diagram showing a second image 8, which is one of the second continuous tomographic images IM2 generated from the second volume data V2. More specifically, from the left, second contour data 52 (FIG. 11A), a first image 4 (FIG. 11B), and a second image 8 (FIG. 11C) combining the second contour data 52 and the first image 4 are shown. The second image 8 generated by the imaging unit 237 has the second contour data 52 in appearance, and the second volume data V2 shown in FIG. 10 can be obtained by reconstructing it. However, as shown in FIG. 11C, in a state where only the contour data 5 is replaced, a blank area R1 or a protruding area R2 is included in the data.

[0062] Therefore, preferably, the correction unit 238 can execute a correction to expand or contract the intermediate data 7 in accordance with the second outline data 52 as a correction step. FIG. 12 is a schematic diagram showing a correction by transforming the internal data 6. Before the correction (FIG. 12A), a blank area R1 exists between the first outline data 51 and the second outline data 52. Therefore, the subcutaneous area 71 and the muscle 72, which are the intermediate data 7, are expanded by image processing to become the subcutaneous area 71' and the muscle 72', in other words, the first outline data 51 is made to be aligned with the second outline data 52, so that the blank area R1 between the first outline data 51 and the second outline data 52 is not included in the data. Although not shown, in order to remove the protruding area R2, it is preferable to shrink the subcutaneous area 71 and the muscle 72, which are also the intermediate data 7, by image processing. According to this embodiment, not only can the appearance be changed by replacing the contour data 5, but anonymity can also be guaranteed while ensuring consistency as a human body.

[0063] [others] The information processing system 1 according to the above embodiment may be configured as follows.

[0064] The first sequential tomographic images IM1 provided by the hospital 12 may be transmitted to the information processing device 2 via the network 11.

[0065] In this embodiment, the reception unit 231, the readout unit 232, the reconstruction unit 233, the alignment unit 234, the setting unit 235, the conversion unit 236, the imaging unit 237, the correction unit 238, and the transmission unit 239 are described as functional units realized by the control unit 23 of the information processing device 2, but at least a part of them may be implemented as functional units realized by a server (not shown), which is an example of an external device. That is, a service for anonymizing the first continuous tomographic images IM1 may be provided via the network 11.

[0066] Instead of the information processing device 2, the first successive tomographic images IM1 may be directly stored in a server owned by the hospital 12, and the second successive tomographic images IM2 may be generated by executing the above-mentioned processing on the first successive tomographic images IM1. In such a case, it is preferable to obtain consent in advance to provide the second successive tomographic images IM2 as training data for machine learning when imaging the subject. Furthermore, the hospital 12 may provide first volume data V1 reconstructed from the first successive tomographic images IM1.

[0067] In this embodiment, an example has been described in which the correction unit 238 corrects the second continuous tomographic image IM2. However, the correction unit 238 may be configured to perform correction on the second volume data V2 before the imaging unit 237 images the second volume data V2.

[0068] Depending on the reference volume data V0, there is a possibility that the first volume data V1 and the second volume data V2 may be similar. In order to prevent such a situation, the control unit 23 may read out a face recognition program stored in advance in the storage unit 22 and check each time whether the face of a person identified by the reference volume data V0 and the first volume data V1 is recognized as the same person.

[0069] The reference contour data 50 may be contour data other than that of a person different from the subject, for example, it may be contour data of a fictitious person, or contour data obtained by previously processing contour data of the subject.

[0070] The second continuous tomographic images IM2 may be managed centrally in a server (not shown) instead of the distributed ledger management by the block chain BC. Also, instead of the second continuous tomographic images IM2, the second volume data V2 may be shared.

[0071] The present embodiment may be implemented as a distributable program. This program causes a computer to execute each step in the information processing system 1.

[0072] Furthermore, it may be provided in the following aspects: In the information processing system, the control unit is configured to further execute an imaging step, in which a plurality of second continuous tomographic images are generated from the second volume data. In the information processing system, the control unit is configured to further execute the following steps: in a receiving step, receiving the first continuous tomographic images; and in a transmitting step, transmitting at least a portion of the second continuous tomographic images to an external device. The information processing system is further configured to execute a correction step, wherein the volume data has intermediate data indicating an area between the contour data and the internal data, and the correction step executes a correction to stretch or shrink the intermediate data to match the second contour data. In the information processing system, the intermediate data includes intermediate tissue including at least one of subcutaneous tissue, muscle, fat, and blood vessels. In the information processing system, the reference contour data is calculated using at least one of contour data of a person different from the subject, contour data of a fictitious person, and contour data obtained by previously processing the contour data of the subject. In the information processing system, the reference contour data is calculated by averaging contour data of a plurality of the persons. In the information processing system, the reference contour data is determined for at least one of age, sex, and race. In the information processing system, the control unit is configured to further execute the following steps: in an alignment step, executing alignment processing between the first volume data and reference volume data having the reference contour data; in a setting step, setting landmarks for the first volume data and the reference volume data which are aligned with each other; and in the conversion step, converting the first volume data into second volume data having the second contour data based on the landmarks. In the information processing system, the reference contour data is the second contour data, and the second contour data is obtained by transforming at least a portion of the first contour data based on predetermined reference information. In the information processing system, the first contour data is data representing a body surface of the subject, and the internal data is data representing bones and areas inside the bones of the subject. An information processing method comprising the steps of: in the information processing system. A program that causes a computer to execute each step in the information processing system. Of course, this is not the case.

[0073] Finally, although various embodiments of the present invention have been described, these are presented as examples and are not intended to limit the scope of the invention. The novel embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. The embodiments and their modifications are included within the scope and spirit of the invention, and are included in the scope of the invention and its equivalents described in the claims. [Explanation of symbols]

[0074] 1: Information processing system 11: Network 12:Hospital 2: User terminal 20: Communication bus 21: Communications Department 22: Storage section 23: Control section 231: Reception 232:Reading section 233:Reconstruction part 234: Alignment section 235: Setting section 236: Conversion section 237: Imaging Department 238: Correction section 239: Transmission unit 24: Display section 25: Input section 4: First image 4a: First image 4b: First image 4c: First image 4d: First image 4e: First image 4f: First image 4g: First image 41: Epidermis 42: Subcutaneous tissue 43: Bones 44 :Area 5: Contour data 50: Reference contour data 51: First contour data 51': First contour data 52: Second outline data 6: Internal data 7: Intermediate data 71: Subcutaneous 71': Subcutaneous 72: Muscle 72': Muscle 8: Second image BC: Blockchain IM: Continuous tomographic images IM1: First continuous slice image IM2: Second continuous tomographic image LM: Landmark R1: Blank area R2: Excess area V: Volume data V0: Reference volume data V1: First volume data V2: Second volume data

Claims

1. An information processing system, A control unit is provided, The control unit is configured to execute the following steps: In the reconstruction step, first volume data showing at least a part of the subject is reconstructed based on a plurality of first continuous tomographic images of the subject, wherein the first volume data has first contour data showing an external appearance of the subject and internal data including an inside of the subject; In the conversion step, the first volume data is converted into second volume data based on reference contour data representing an appearance of a first person different from the subject of the first contour data, wherein the second volume data has second contour data different from the first contour data and the internal data including an inside of the subject; The conversion step converts the first volume data into the second volume data based on the reference contour data so that the second contour data represents an appearance of a second person different from the subject corresponding to the first contour data.

2. 2. The information processing system according to claim 1, The control unit is configured to further perform an imaging step; The imaging step generates a plurality of second continuous tomographic images from the second volume data.

3. 3. The information processing system according to claim 2, The control unit is configured to further execute the following steps: In the receiving step, the first continuous tomographic images are received; The transmitting step transmits at least a portion of the second continuous tomographic images to an external device.

4. 2. The information processing system according to claim 1, configured to further perform a correction step; the volume data has intermediate data indicating a region between the contour data and the internal data, The correction step includes executing a correction for expanding or contracting the intermediate data in accordance with the second outline data.

5. 5. The information processing system according to claim 4, The intermediate data includes intermediate tissues including at least one of subcutaneous tissue, muscle, fat, and blood vessels.

6. 2. The information processing system according to claim 1, The reference contour data is calculated from at least one of contour data of a person different from the subject, contour data of a fictitious person, and contour data obtained by previously processing contour data of the subject.

7. 7. The information processing system according to claim 6, The reference contour data is calculated by averaging contour data of a plurality of the persons.

8. 2. The information processing system according to claim 1, The reference contour data is determined for at least one of age, sex, and race.

9. 2. The information processing system according to claim 1, The control unit is configured to further execute the following steps: In the registration step, a registration process is performed between the first volume data and reference volume data having the reference contour data; In the setting step, landmarks are set for the first volume data and the reference volume data which are registered with each other; In the conversion step, the first volume data is converted into second volume data having the second contour data based on the landmarks.

10. 2. The information processing system according to claim 1, the reference contour data is the second contour data, The second outline data is obtained by modifying at least a part of the first outline data based on preset reference information.

11. 2. The information processing system according to claim 1, The first contour data is data representing a body surface of the subject, The internal data is data representing bones and areas inside the bones of the subject.

12. 1. An information processing method, comprising: A method comprising the steps of: performing a process for detecting a plurality of information processing devices in accordance with any one of claims 1 to 11;

13. A program, A method for causing a computer to execute each step in the information processing system according to any one of claims 1 to 11.

Images