Medical image processing system, medical image processing device, and medical imaging device

Abstract

To easily identify medical images suitable for additional analysis processes planned to be performed based on the results of the medical image analysis. [Solution] The medical image processing system according to the embodiment comprises a medical image processing device and a medical imaging device that are connected to each other in a manner that allows them to communicate with each other. The medical image processing device has a receiving unit, an analysis unit, a determination unit and a decision unit. The receiving unit receives a first medical image relating to a subject from the medical imaging device. The analysis unit performs a first analysis process on the first medical image and outputs a first analysis result. The determination unit determines whether an additional second analysis process is necessary based on the first analysis result. If the decision unit determines that the second analysis process is necessary, it determines the image characteristics that are recommended to be present in the second medical image to be subjected to the second analysis process, according to the processing content of the second analysis process.

Description

Technical Field

[0001] The embodiments disclosed in this specification and the drawings relate to a medical image processing system, a medical image processing apparatus, and a medical imaging apparatus.

Background Art

[0002] There is a medical image processing apparatus for performing automatic analysis, which is communicably connected to a medical imaging apparatus. The medical image processing apparatus receives a medical image generated by the medical imaging apparatus, performs analysis processing on the received medical image, and transmits the analysis result to a PACS (Picture Archiving and Communication System) or the like. Here, depending on the analysis result, medical staff such as radiological technologists and doctors may decide to perform additional analysis processing. However, it is not easy to identify a medical image appropriate for the additional analysis processing, and even if a medical image is identified, imaging the medical image additionally will impose a burden on medical staff and patients.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Patent Document 2

Patent Document

Patent Document 4

Summary of the Invention

Problems to be Solved by the Invention

[0004] One of the problems that the embodiments disclosed herein and in the drawings aim to solve is to easily identify medical images suitable for additional analysis processing to be performed in response to the results of medical image analysis. However, the problems that the embodiments disclosed herein and in the drawings aim to solve are not limited to the above problem. Problems corresponding to the effects of each configuration shown in the embodiments described later can also be positioned as other problems. [Means for solving the problem]

[0005] The medical image processing system according to the embodiment comprises a medical image processing device and a medical imaging device that are communicated with each other. The medical image processing device has a receiving unit, an analysis unit, a determination unit, and a decision unit. The receiving unit receives a first medical image relating to a subject from the medical imaging device. The analysis unit performs a first analysis process on the first medical image and outputs a first analysis result. The determination unit determines whether an additional second analysis process is necessary based on the first analysis result. If the decision unit determines that the second analysis process is necessary, it determines the image characteristics that are recommended to be present in the second medical image to be subjected to the second analysis process, according to the processing content of the second analysis process. [Brief explanation of the drawing]

[0006] [Figure 1] Figure 1 shows an example of the configuration of a medical image processing system. [Figure 2] Figure 2 shows an example of the configuration of a medical imaging device. [Figure 3] Figure 3 shows an example of the configuration of a medical image processing device. [Figure 4] Figure 4 shows the flow of automated analysis processing by a medical image processing system. [Figure 5] Figure 5 is a schematic representation of the results of the first analysis. [Figure 6] Figure 6 shows an example of a head MRI image. [Figure 7] Figure 7 shows an example of the display screen for the first and second analysis results. [Figure 8]Figure 8 shows an example of the confirmation window display. [Figure 9] Figure 9 shows the flow of automatic analysis processing by the medical image processing system according to Modification Example 2. [Figure 10] Figure 10 shows an example configuration of a medical image processing apparatus according to Example 7. [Figure 11] Figure 11 is a diagram showing the flow of automated analysis processing by a medical image processing system according to Modification Example 7. [Modes for carrying out the invention]

[0007] The medical image processing system, medical image processing apparatus, and medical imaging apparatus according to this embodiment will be described in detail below with reference to the drawings.

[0008] Figure 1 shows an example configuration of a medical image processing system 100. The medical image processing system 100 is a computer network system that performs medical image acquisition, automatic analysis of medical images, and provision of analysis results. As shown in Figure 1, the medical image processing system 100 includes a medical imaging device 200, a medical image processing device 300, and a medical image display device 400. The medical imaging device 200, the medical image processing device 300, and the medical image display device 400 are connected to any network so that they can communicate with each other. The network refers to any information and communication network that utilizes telecommunications technology. The network may be a wireless / wired LAN such as a hospital's backbone LAN (Local Area Network), the Internet network, a telephone communication network, an optical fiber communication network, a cable communication network, a satellite communication network, etc.

[0009] The medical imaging device 200 performs medical imaging on a subject to collect medical images of the subject. The medical imaging device 200 is also called a modality device. The medical images are transmitted to the medical image processing device 300. The medical image processing device 300 is a computer that performs analysis processing on the medical images. The analysis results are transmitted to the medical image display device 400. The medical image display device 400 is a computer that displays the analysis results. The medical image display device 400 is implemented, for example, by a computer included in a PACS (Picture Archiving and Communication System), which is a medical image storage system.

[0010] Figure 2 shows an example configuration of a medical imaging device 200. As shown in Figure 2, the medical imaging device 200 includes an imaging mechanism 21, a processing circuit 22, a storage device 23, a display device 24, an input interface 25, and a communication interface 26. The imaging mechanism 21, processing circuit 22, storage device 23, display device 24, input interface 25, and communication interface 26 are connected to each other via a bus so that they can communicate with one another.

[0011] The imaging device 21 is a machine that performs medical imaging on a subject. By performing medical imaging, the imaging device 21 collects raw data about the subject using various detectors. Specifically, the imaging device 21 may be a single modality device such as a magnetic resonance imaging (MRI) device, an X-ray computed tomography (X-ray CT) device, an X-ray diagnostic device, an ultrasound diagnostic device, a PET (Positron Emission Tomography) device, and a SPECT (Single Photon Emission CT) device, or it may be a composite modality device such as a PET / CT device, a SPECT / CT device, a PET / MRI device, or a SPECT / MRI device.

[0012] As an example, when the imaging mechanism 21 is an MRI device, the imaging mechanism 21 repeats the application of a gradient magnetic field through a gradient magnetic field coil and the application of an RF pulse through a transmission coil under the application of a static magnetic field through a static magnetic field magnet. An MR signal is emitted from the subject due to the application of the RF pulse. The emitted MR signal is received through a reception coil. The received MR signal is subjected to signal processing such as A / D conversion by a reception circuit. The MR signal after A / D conversion is called k-space data. The k-space data is an example of raw data.

[0013] The processing circuit 22 includes a processor such as a CPU (Central Processing Unit). By the processor starting various programs installed in a storage device 23 or the like, a collection function 221, an image acquisition function 222, a conversion function 223, a communication control function 224, and a display control function 225 are realized. Each of the functions 221 to 225 is not limited to being realized by a single processing circuit. It is also possible to configure a processing circuit by combining a plurality of independent processors, and each function 221 to 225 is realized by each processor executing a program.

[0014] The collection function 221 controls the imaging mechanism 21 to perform medical imaging on a subject and collects raw data regarding the subject. For example, when the imaging mechanism 21 is an MRI device, k-space data is collected as raw data. The collection function 221 is an example of a collection unit.

[0015] The image acquisition function 222 acquires medical images related to a subject. The medical image means digital data of pixel values arranged in a two-dimensional or three-dimensional manner. The image acquisition function 222 functions in the first medical image generation stage (medical imaging stage) and the second medical image acquisition stage (second analysis processing stage). The first medical image is a medical image used for the first analysis processing. The first analysis processing means the initially set analysis processing. The second medical image is a medical image used for the analysis processing (second analysis processing) determined to be necessary according to the analysis result (first analysis result) of the first analysis processing for the first medical image. The second medical image has image characteristics recommended to be provided according to the processing content of the second analysis processing. The acquisition stage of the second medical image means the stage of acquiring such a second medical image. The image acquisition function 222 related to the second analysis processing stage acquires the second medical image having the image characteristics without performing additional medical imaging. The image acquisition function 222 is an example of an image acquisition unit.

[0016] As shown in FIG. 2, specifically, the image acquisition function 222 has a search function 226 and an image generation function 227. The search function 226 can be used in the acquisition stage of the second medical image. When the second medical image is stored in the storage device 23, the second medical image is searched for in the storage device 23 and read out from the storage device 23. The second medical image is acquired by the search process. The search function 226 is an example of a search unit.

[0017] The image generation function 227 can be used in the first medical image generation stage and the second medical image acquisition stage. In the first medical image generation stage, the image generation function 227 generates a first medical image of the subject from the raw data collected by the collection function 221. In the second medical image acquisition stage, the image generation function 227 reads the raw data necessary for reconstructing the second medical image from the storage device 23 and generates a second medical image of the subject from the read raw data based on image generation conditions corresponding to the image characteristics of the second medical image. Alternatively, in the second medical image acquisition stage, the image generation function 227 reads the original image of the second medical image from the storage device 23 and generates a second medical image from the read raw image based on image generation conditions corresponding to the image characteristics of the second medical image. The image generation function 227 is an example of an image generation unit.

[0018] The conversion function 223 converts the image characteristics of the second medical image into image generation conditions for generating the second medical image, as defined by the specifications adopted by the device. These image generation conditions are used, for example, to generate the second medical image by the image acquisition function 222. Note that if the image generation conditions are determined by the medical image processing device 300 or the like, the conversion function 223 does not need to be provided. The conversion function 223 is an example of a conversion unit.

[0019] The communication control function 224 transmits and receives various data to and from the medical image processing device 300 and the medical image display device 400 via the communication interface 26. For example, the communication control function 224 receives from the medical image processing device 300 a request to acquire a second medical image and the image characteristics that the second medical image is recommended to possess. As another example, the communication control function 224 transmits the generated second medical image to the medical image processing device 300. The communication control function 224 is an example of a transmitting and receiving unit.

[0020] The display control function 225 displays various data on the display device 24. For example, the display control function 225 displays a window on the display device 24 to confirm with the user whether or not to provide a second medical image.

[0021] The storage device 23 is a storage device that stores various types of data, such as ROM (Read Only Memory), RAM (Random Access Memory), HDD (Hard Disk Drive), SSD (Solid State Drive), or integrated circuit memory. In addition to the above storage devices, the storage device 23 may also be a drive device that reads and writes various types of information to and from portable storage media such as CDs (Compact Discs), DVDs (Digital Versatile Discs), flash memory, or semiconductor memory elements. The storage device 23 may also be located in another computer connected to the medical imaging device 200 via a network.

[0022] The display device 24 displays various data. The display device 24 can be a liquid crystal display (LCD), a cathode ray tube (CRT), an organic electroluminescent display (OELD), a plasma display, or any other suitable display. Alternatively, the display device 24 may be a projector.

[0023] The input interface 25 receives various input operations from the user, converts the received input operations into electrical signals, and outputs them to the processing circuit 22. Specifically, the input interface 25 is connected to input devices such as a mouse, keyboard, trackball, switch, button, joystick, touchpad, and touch panel display. The input interface 25 outputs electrical signals to the processing circuit 22 corresponding to the input operations to the input device. The input device connected to the input interface 25 may also be an input device provided on another computer connected via a network or the like. The input interface 25 may also be a voice recognition device that converts voice signals collected by a microphone into instruction signals.

[0024] The communication interface 26 includes a NIC (Network Interface Card) or the like that enables communication connections with external devices such as a medical image processing device 300 and a medical image display device 400 via a network.

[0025] Figure 3 shows an example configuration of a medical image processing device 300. As shown in Figure 3, the medical image processing device 300 includes a processing circuit 31, a storage device 32, a display device 33, an input interface 34, and a communication interface 35. The processing circuit 31, storage device 32, display device 33, input interface 34, and communication interface 35 are connected to each other via a bus so that they can communicate with one another.

[0026] The processing circuit 31 has a processor such as a CPU (Central Processing Unit). By starting various programs installed in the storage device 32, the processor realizes the acquisition function 311, analysis function 312, judgment function 313, decision function 314, conversion function 315, communication control function 316, and display control function 317. Each of the functions 311 to 317 is not limited to being realized by a single processing circuit. A processing circuit may be configured by combining multiple independent processors, and each of the functions 311 to 317 may be realized by each processor executing a program.

[0027] The acquisition function 311 acquires the first medical image of the subject collected by the medical imaging device 200. Specifically, the acquisition function 311 acquires the first medical image received from the medical imaging device 200 via the communication interface 35. The processing circuit 31 may also acquire various other data. The acquisition function 311 is an example of an acquisition unit.

[0028] The analysis function 312 performs analysis processing on medical images and outputs the analysis results. The analysis processing according to this embodiment is implemented by software such as an application and includes various processes depending on the purpose of the analysis. Examples of analysis processing include processing to detect the location of a specific lesion such as a brain tumor, processing to identify an arbitrary anatomical site, processing to measure the volume of an arbitrary anatomical site or lesion site, processing to measure the partial pressure of oxygen, and other arbitrary processes. The analysis function 312 is an example of an analysis unit.

[0029] As shown in Figure 3, the analysis function 312 has a first analysis function 318 and a second analysis function 319. The first analysis function 318 applies a first analysis process to the first medical image and outputs a first analysis result. The second analysis function 319 applies a second analysis process to the second medical image and outputs a second analysis result.

[0030] The determination function 313 determines whether an additional second analysis process is necessary based on the first analysis result output by the first analysis function 318. The determination function 313 can also determine whether a second analysis process is necessary by considering data other than the first analysis result. The determination function 313 is an example of a determination unit.

[0031] The determination function 314, when the judgment function 313 determines that a second analysis process is required, determines the image characteristics that the second medical image to be subjected to the second analysis process should possess, according to the processing content of the second analysis process. Specifically, image characteristics refer to properties related to the appearance of the medical image, such as spatial resolution, inter-tissue contrast, slice thickness, matrix size, and / or cross-sectional position. Spatial resolution, inter-tissue contrast, slice thickness, matrix size, cross-sectional position, etc., are called image characteristic parameters. Data representing image characteristics are called image characteristic data. Image characteristics may be defined by numerical values ​​or symbols of image characteristic parameters, or by text or strings that qualitatively express the image characteristic parameters. The determination function 314 is an example of a determination unit.

[0032] The conversion function 315 converts the image characteristics of the second medical image into image generation conditions. The image generation conditions refer to the reconstruction conditions of the image reconstruction process and / or the image processing conditions of the image processing performed to generate a medical image having the said image characteristics. The reconstruction conditions refer to the numerical values ​​and symbols of the various reconstruction parameters of the image reconstruction process, and the image processing conditions refer to the numerical values ​​and symbols of the various image processing parameters of the image processing. The image generation conditions are used to acquire the second medical image by the medical imaging device 200. The conversion function 315 is an example of a conversion unit.

[0033] The communication control function 316 transmits and receives various data to and from the medical imaging device 200 and the medical image display device 400 via the communication interface 35. For example, the communication control function 316 transmits to the medical imaging device 200 a request to acquire a second medical image of the subject and its image characteristics. Alternatively, the communication control function 316 may transmit the first analysis result and the second analysis result to the medical image display device 400. In this case, the medical image display device 400 displays the first analysis result and the second analysis result on a display device. As another example, the communication control function 316 receives the second medical image acquired by the medical imaging device 200 in response to the acquisition request. Alternatively, the communication control function 316 may receive the first medical image of the subject from the medical imaging device 200. The communication control function 316 is an example of a transmitting unit and a receiving unit.

[0034] The display control function 317 displays various data on the display device 33.

[0035] The storage device 32 is a storage device such as ROM, RAM, HDD, SSD, or integrated circuit storage device that stores various types of data. The storage device 23 may also be a drive device that reads and writes various types of information to portable storage media such as CDs, DVDs, or flash memory, or to semiconductor memory elements, in addition to the above-mentioned storage devices. The storage device 32 may also be located in another computer connected to the medical image processing device 300 via a network.

[0036] The display device 33 displays various data. The display device 33 can be an LCD, CRT, OLED, plasma display, or any other suitable display. Alternatively, the display device 33 may be a projector.

[0037] The input interface 34 receives various input operations from the user, converts the received input operations into electrical signals, and outputs them to the processing circuit 31. Specifically, the input interface 34 is connected to input devices such as a mouse, keyboard, trackball, switch, button, joystick, touchpad, and touch panel display. The input interface 34 outputs electrical signals to the processing circuit 31 corresponding to the input operations to the input device. The input device connected to the input interface 34 may also be an input device provided on another computer connected via a network or the like. The input interface 34 may also be a voice recognition device that converts voice signals collected by a microphone into instruction signals.

[0038] The communication interface 35 includes a network interface card (NIC) that establishes communication connections with external devices such as a medical imaging device 200 and a medical image display device 400 via a network.

[0039] The following describes an example of the operation of the medical image processing system 100 according to this embodiment.

[0040] Figure 4 shows the flow of automatic analysis processing by the medical image processing system 100. In the following explanation, it is assumed that the medical imaging device 200 is a magnetic resonance imaging device, the examination site of the subject is the head, and the target of diagnosis is a brain tumor.

[0041] As shown in Figure 4, first, the imaging mechanism 21 of the medical imaging device 200 performs one or more medical imaging scans on the subject according to a pre-planned imaging protocol (step SA1). For example, in a head MRI scan, the imaging protocol may include calibration scans, T1-weighted imaging, T2-weighted imaging, FLAIR (Fluid Attenuated Inverse Recovery) imaging, diffusion-weighted imaging, and other medical imaging scans. In each medical imaging scan, raw data about the subject is collected by the imaging mechanism 21. The collected raw data is stored in the storage device 23.

[0042] When step SA1 is performed, the processing circuit 22 generates a medical image from the collected raw data using the image generation function 227 (step SA2). Medical images are generated sequentially for each medical imaging. The generated medical images are sequentially stored in the storage device 32. Of the medical images generated sequentially by the implementation of the imaging protocol, the medical image to be used for the first analysis process is generated as the first medical image.

[0043] When step SA2 is performed, the processing circuit 22 transmits the first medical image to the medical image processing device 300 using the communication control function 224 (step SA3). The medical image processing device 300 receives the first medical image. The received first medical image is acquired by the processing circuit 31 using the acquisition function 311.

[0044] When step SA3 is performed, the processing circuit 31 uses the first analysis function 318 to perform the first analysis processing on the received first medical image and outputs the first analysis result (step SA4).

[0045] When step SA4 is performed, the processing circuit 31 determines whether a second analysis process is necessary using the determination function 313 (step SA5). If it is determined in step SA5 that a second analysis process is unnecessary (step SA5: no), the processing circuit 31 transmits the first analysis result to the medical image display device 400 using the communication control function 316 (step SA6). The medical image display device 400 receives the first analysis result. Subsequently, the medical image display device 400 displays the received first analysis result (step SA13). The physician, who is the user of the medical image display device 400, makes a diagnosis for the subject by referring to the first analysis result.

[0046] On the other hand, if it is determined in step SA5 that a second analysis process is necessary (step SA5: required), the processing circuit 31 uses the determination function 314 to determine the image characteristics that the second medical image is recommended to have, which are necessary for the second analysis process, according to the processing content of the second analysis process (step SA7). After step SA7 is performed, the processing circuit 31 uses the conversion function 315 to convert the image characteristics determined in step SA7 into image generation conditions using a rule-based or machine learning model (step SA8). Here, we assume that the medical image processing device 300 and the medical imaging device 200 have the same manufacturer (vendor). In this case, the processing circuit 31 can output detailed image generation conditions defined in the specifications adopted by its own device and the medical imaging device 200.

[0047] Furthermore, the number of second analysis processes derived from a single first analysis result may be one or multiple. Image characteristics and image generation conditions will be obtained for each of the multiple second analysis processes. Also, the number of image characteristics corresponding to a single second analysis process may be one or multiple. Image generation conditions will be obtained for each of the multiple image characteristics.

[0048] Here, we will describe three embodiments relating to the first analysis process (SA4), the process for determining whether a second analysis process is necessary (SA5), the process for determining image characteristics (SA6), and the process for converting to image generation conditions (SA7). The first analysis process is assumed to be a brain tumor detection process that calculates a spatial distribution of probability values ​​representing tumor-likeness (hereinafter referred to as a probability value map) based on the first medical image, divides the tumor region from the first medical image based on a comparison of the probability values ​​with a first threshold, and outputs the location of the divided tumor region. In this case, the first analysis result is the probability value map and the location of the tumor region. The brain tumor detection process is assumed to use a deep neural network that takes a head MR image as input and outputs the location of the tumor region.

[0049] Example 1: The second analysis process in Example 1 is the same as the first analysis process, but is performed to improve the accuracy of tumor area detection compared to the first analysis process. Specifically, the second analysis process in Example 1 is the same brain tumor detection process as the first analysis process, but is performed to improve the accuracy of brain tumor area detection compared to the first analysis process. The image characteristics that the second medical image used in this second analysis process is recommended to have are that the contrast between the normal tissue area and the brain tumor area is greater than that of the first medical image. An example of the operation of Example 1 will be described below.

[0050] Figure 5 schematically represents the first analysis results for Example 1. The first analysis results shown in Figure 5 represent a probability value map indicating the likelihood of a brain tumor, and are enlarged views of the image region suspected of being a brain tumor. The numerical values ​​shown for each pixel in Figure 5 are probability values. The numerical range of the probability values ​​is set to 0 to 1 as an example. In the brain tumor detection process, the first threshold is set to 0.5, and the set of pixels with a probability value of 0.5 or higher is classified as the brain tumor region. In the case of Figure 5, the maximum probability value included in the first analysis results is 0.496, which is slightly smaller than the first threshold for determining a brain tumor. If it is slightly smaller than the first threshold, there is a possibility of a brain tumor, so additional analysis processing (second analysis processing) is performed on the MR image where the contrast between the normal tissue region and the tumor region is large. The operation example of Example 1 will be described below.

[0051] In step SA5, if the processing circuit 31 determines that all probability values ​​included in the probability value map are smaller than the first threshold, it determines whether the difference between the probability values ​​and the first threshold is smaller than the second threshold. If the difference is smaller than the second threshold, the processing circuit 31 determines that a second analysis process is required, and if the difference is larger than the second threshold, it determines that a second analysis process is not required. Here, the "probability value" may be the maximum value among the probability values ​​of the pixels included in the probability value map, or it may be the average or median value of the probability values ​​that are lower than the first threshold but above the third threshold.

[0052] If it is determined that a second analysis process is required (SA5: Required), the processing circuit 31 determines the processing content of the second analysis process based on the first analysis result in step SA7. The processing content of the second analysis process can be determined based on a rule base. Specifically, a first LUT (Look Up Table) is used as the rule base, which associates the specific content of the first analysis result with the processing content of the second analysis process. The first LUT defines a rule that if the first analysis result has the specified content, the second analysis process with the specified content is performed. In the case of Example 1, the specific content of the first analysis result is "the difference between the probability value and the first threshold is smaller than the second threshold," and the processing content of the second analysis process is set to "brain tumor detection processing." Alternatively, a machine learning model that has learned the correlation between the input (specific content of the first analysis result) and output (processing content of the second analysis process) of the above first LUT may be used instead of a rule base.

[0053] Once the processing content of the second analysis process is determined, the processing circuit 31 determines the image characteristics of the second medical image according to that processing content. The image characteristics can be determined based on a rule base. Specifically, a second LUT is used as the rule base, which associates the processing content of the second analysis process with the image characteristics of the second medical image. The second LUT defines a rule that if the second analysis result matches the processing content, the second analysis process with that processing content is performed. In the case of Example 1, the processing content of the second analysis process is "brain tumor detection processing," and the image characteristics of the second medical image are set to "the contrast between the normal tissue area and the brain tumor area is greater than in the first medical image." Alternatively, a machine learning model that has learned the correlation between the input (processing content of the second analysis process) and output (image characteristics of the second medical image) of the above-mentioned second LUT may be used instead of a rule base.

[0054] Next, the processing circuit 31 converts the image characteristics into image generation conditions (SA8). Image generation conditions are a concept that includes image reconstruction conditions and image processing conditions. Specifically, a T2-weighted image is used as the input image (first medical image) for the brain tumor detection process. To increase the contrast compared to the first medical image, image processing conditions such as "perform edge enhancement on the brain tumor region" are determined. If edge enhancement has already been applied to the first medical image, it is desirable that the edge intensity, which is a parameter of the edge enhancement, be set to a higher value than the edge enhancement applied to the first medical image. Alternatively, to increase the contrast compared to the first medical image, image processing conditions such as "apply an image filter" are determined. The image filter applied here should preferably be one that makes pixels whiter, or in other words, one example of a pixel value, the grayscale value, which is smaller. If an image filter has already been applied to the first medical image, it is desirable that the filter intensity, which is a parameter of the image filter, be set to a higher value than the image filter applied to the first medical image.

[0055] Example 2: The second analysis process in Example 2 is performed to obtain additional information that cannot be obtained in the first analysis process. Specifically, the second analysis process is a nutrient vessel detection process performed to obtain additional information, such as the presence or absence of nutrient vessels to the tumor, which cannot be obtained in the first analysis process. The image characteristics that the second medical image used in this second analysis process is recommended to have are that the contrast between the blood flow area and other areas is greater than that of the first medical image.

[0056] For example, as the oxygen partial pressure increases from an anaerobic state (0 mmHg), radiosensitivity increases. When the oxygen partial pressure reaches approximately 3 mmHg, the relative value of radiosensitivity becomes 2.0, and when the oxygen partial pressure reaches approximately 30 mmHg, the relative value of radiosensitivity plateaus at 3.0. In other words, if a tumor is close to an anaerobic state, it has low radiosensitivity, and the effect of radiotherapy (tumor reduction effect due to radiation irradiation) cannot be expected. If there are blood vessels supplying the tumor, the oxygen partial pressure of the tumor will be relatively high, and therefore the radiosensitivity will also be relatively high, and the effect of radiotherapy can be expected (Al-Waili, Noori S., et al. "Hyperbaric oxygen and malignancies: a potential role in radiotherapy, chemotherapy, tumor surgery and phototherapy." Medical science monitor 11.9 (2005): RA279.). The operation example of Example 2 will be described below.

[0057] In step SA5, the processing circuit 31 determines whether all or part of the probability values ​​included in the probability value map are greater than the first threshold. If all or part of the probability values ​​are greater than the first threshold, it means that a tumor region has been detected. If a tumor region is detected, the processing circuit 31 determines that a second analysis process is required, and if no tumor region is detected, it determines that a second analysis process is not required.

[0058] If it is determined that a second analysis process is required (SA5: Required), the processing circuit 31 determines the content of the second analysis process in step SA7 based on the first analysis result and whether or not it is necessary to predict the effect of radiotherapy. The content of the second analysis process can be determined based on a rule base. Specifically, a first LUT is used as the rule base, which associates the specific content of the first analysis result and whether or not it is necessary to predict the effect of radiotherapy with the content of the second analysis process. The first LUT defines a rule that if the first analysis result has the specified content and it is necessary to predict the effect of radiotherapy, then the second analysis process with the specified content is performed. In the case of Example 2, the specific content of the first analysis result is "A tumor area was detected by the brain tumor detection process." The content of the second analysis process is set to "Nutrient vessel detection process." Whether or not it is necessary to predict the effect of radiotherapy may be specified by the user via the input interface 34, or it may be linked to patient information concerning the subject. Furthermore, a machine learning model that has learned the correlation between the input (specific content of the first analysis result) and output (processing content of the second analysis process) of the first LUT described above may be used instead of a rule-based model.

[0059] Once the processing content of the second analysis process is determined, the processing circuit 31 determines the image characteristics of the second medical image according to the processing content of the second analysis process. The image characteristics can be determined based on a rule base. Specifically, a second LUT is used as the rule base, which associates the processing content of the second analysis process with the image characteristics of the second medical image. The second LUT defines a rule that if the second analysis result matches the processing content, the second analysis process with that processing content is performed. In the case of Example 2, the processing content of the second analysis process is "nutrient vessel detection processing," and the image characteristics of the second medical image are set to "higher contrast between blood flow regions and other regions than in the first medical image." Alternatively, a machine learning model that has learned the correlation between the input (processing content of the second analysis process) and output (image characteristics of the second medical image) of the above-mentioned second LUT may be used instead of a rule base.

[0060] Next, the processing circuit 31 converts the image characteristics into image generation conditions (step SA8). Specifically, as the input image for the nutrient vessel detection process (first medical image), an MR image (blood flow image) in which the blood flow component to the brain tumor is enhanced by contrast-enhanced or non-contrast imaging is used. As a non-contrast blood flow image, an ASL (Arterial Spin Labeling) image can also be used. To enhance the contrast of the blood flow region, image processing conditions such as "perform edge enhancement on the blood flow region" may be determined. Alternatively, to enhance the contrast of the blood flow region compared to the first medical image, image processing conditions such as "apply an image filter" may be determined.

[0061] Example 3: The second analysis process in Example 3 is performed to detect other diseases that are incidentally found in the first analysis process. Specifically, the second analysis process in Example 3 is a hippocampal volume measurement process performed to detect Alzheimer's disease that is incidentally found in the first analysis process. The image characteristics that the second medical image used in this second analysis process is recommended to have are that it has a higher spatial resolution than the first medical image.

[0062] Figure 6 shows an example of a head MR image. The left image in Figure 6 is a coronal cross-sectional image, and the right image is an axial cross-sectional image. As shown in Figure 6, the head MR image is displayed as the first analysis result of the first analysis process. Since the hippocampus is present in the brain, the hippocampal region 71 may be visible in the head MR image, which is the first analysis result, depending on the cross-sectional position. The volume of the hippocampus tends to decrease with age, but if it is smaller than the standard volume for the subject's age, the subject may be suffering from Alzheimer's disease. The operation example of Example 3 will be described below.

[0063] In step SA5, the processing circuit 31 determines whether or not the second analysis process, which is a hippocampal volume measurement process, is necessary. As an example, the processing circuit 31 determines whether or not the second analysis process is necessary based on whether or not there is a possibility of having Alzheimer's disease. Whether or not there is a possibility of having Alzheimer's disease may be specified by the user via the input interface 34, or it may be linked to patient information about the subject, or it may be estimated from patient information using any algorithm such as machine learning. If there is a possibility of having Alzheimer's disease, the processing circuit 31 determines that the second analysis process is necessary, and if there is no possibility of having Alzheimer's disease, it determines that the second analysis process is not necessary.

[0064] If it is determined that a second analysis process is required, the processing circuit 31 determines the image characteristics of the second medical image according to the processing content of the second analysis process. The image characteristics can be determined based on a rule base. Specifically, a second LUT is used as the rule base, which associates the processing content of the second analysis process with the image characteristics of the second medical image. The second LUT defines a rule that if the second analysis result matches the processing content, the second analysis process with that processing content is performed. In the case of Example 3, the processing content of the second analysis process is "hippocampal volume measurement processing," and the image characteristics of the second medical image are set to "higher spatial resolution than the first medical image." Alternatively, a machine learning model that has learned the correlation between the input (processing content of the second analysis process) and output (image characteristics of the second medical image) of the above-mentioned second LUT may be used instead of a rule base.

[0065] Next, the processing circuit 31 converts the image characteristics into image generation conditions. Specifically, a high spatial resolution 3D T1-weighted image is used as the input image (first medical image) for the hippocampal volume measurement process. To enhance the contrast of the hippocampal region, image processing conditions such as "perform edge enhancement on the hippocampal region" may be determined. Alternatively, to enhance the contrast of the hippocampal region compared to the first medical image, image processing conditions such as "apply an image filter" may be determined.

[0066] This concludes the description of the embodiments. Note that it is possible to arbitrarily set which of the 1 to 3 processes to be performed on the first analysis result of the brain tumor detection process. The processing circuit 31 may perform any one of the 1 to 3 processes on the first analysis result, or it may perform two or all of the processes from the 1 to 3 processes.

[0067] As shown in Figure 4, when step SA8 is performed, the processing circuit 31 transmits the request to acquire the second medical image, image characteristics, and image generation conditions to the medical imaging device 200 via the communication control function 3161 (step SA9). The medical imaging device 200 receives the request to acquire the second medical image, image characteristics, and image generation conditions.

[0068] When step SA9 is performed, the processing circuit 22 of the medical imaging device 200 acquires a second medical image with the received image characteristics using the image acquisition function 222 without performing additional medical imaging (steps SA10 to SA12). Specifically, the processing circuit 22 determines whether a second medical image exists in the storage device 23 (step SA10). For example, the processing circuit 22 uses the search function 226 to display a list of image characteristics and / or image generation conditions related to medical images stored in the storage device 23 on the display device 24. The user selects a medical image from this list as the second medical image via the input interface 25. If selected, the processing circuit 22 determines that a second medical image exists. If not selected, the processing circuit 22 determines that a second medical image does not exist.

[0069] If it is determined that a second medical image exists (step SA10: exists), the processing circuit 22 extracts the second medical image from the storage device 23 using the search function 226 (step SA11). This acquires the second medical image.

[0070] If it is determined that a second medical image does not exist (step SA10: not present), the processing circuit 22 generates a second medical image using the image generation function 227 (step SA12). Specifically, the processing circuit 22 reads the raw data necessary for generating the second medical image from the storage device 23, and generates the second medical image from the read raw data based on the image generation conditions received in step SA9. As an example, the processing circuit 22 reconstructs a medical image by applying image reconstruction processing to the raw data according to the reconstruction conditions among the image generation conditions. If only the reconstruction conditions are specified as image generation conditions, the medical image is reconstructed as the second medical image. If image processing conditions are specified in addition to the reconstruction conditions as image generation conditions, the processing circuit 22 reconstructs a medical image by applying image reconstruction processing to the raw data according to the reconstruction conditions among the image generation conditions, and then generates a second medical image by applying image processing to the medical image according to the image processing conditions among the image generation conditions.

[0071] When step SA11 or SA12 is performed, the processing circuit 22 transmits the second medical image to the medical image processing device 300 using the communication control function 224 (step SA13). The medical image processing device 300 receives the second medical image. The received second medical image is acquired by the processing circuit 31 using the acquisition function 311.

[0072] When step SA13 is performed, the processing circuit 31 uses the second analysis function 319 to perform a second analysis on the second medical image and outputs the second analysis result (step SA14). The processing circuit 31 uses the communication control function 316 to transmit the first analysis result output in step SA4 and the second analysis result output in step SA14 to the medical image display device 400 (step SA15). The medical image display device 400 receives the first analysis result and the second analysis result.

[0073] When step SA15 is performed, the medical image display device 400 displays the received first and second analysis results on the display device (step SA16). The display format of the first and second analysis results can be arbitrarily set. As an example, the medical image display device 400 displays the first and second analysis results side by side on one screen. In this case, the medical image display device 400 adds a visual effect to the second analysis result to indicate that it is an additional analysis process. The physician, who is the user of the medical image display device 400, makes a diagnosis of the subject by referring to both the first and second analysis results.

[0074] Figure 7 shows an example of the display screen I1 for the first analysis result I11 and the second analysis results I12, I13, and I14. As shown in Figure 7, the medical image display device 400 displays the first analysis result I11 and the second analysis results I12, I13, and I14 side by side on a single screen. Figure 7 illustrates the display screen I1 corresponding to the above embodiment. Image A, which is the analysis result of the brain tumor detection process, is displayed as the first analysis result I11. In image A, the detected tumor region I112 is visually highlighted with color, etc.

[0075] As shown in Figure 7, Image B, which is the analysis result of the brain tumor detection process according to Example 1, is displayed as the second analysis result I12. In Image B, the detected tumor regions I122, I123, and I124 are visually highlighted with color, etc. Compared to Image A, Image B has a greater contrast of tumor regions and is expected to detect tumor regions with higher accuracy. Therefore, Image B may highlight not only the tumor region I122 detected in Image A, but also the tumor regions I123 and I124 that were not detected in Image A. By displaying the first analysis result I11 and the second analysis result I12 side by side, it becomes possible to visually compare both the first analysis result I11 and the second analysis result I12, which have different inter-tissue contrasts.

[0076] As shown in Figure 7, Image C, which is the analysis result of the nutrient vessel detection process according to Example 2, is displayed as the second analysis result I13. Image C is assigned a color value corresponding to the partial pressure of oxygen (pO2), and Image C represents the spatial distribution of partial pressure of oxygen. Tumor region I134, where nutrient vessels run, tends to have a high partial pressure of oxygen due to the transport of a large amount of oxygen. Tumor regions I132 and I133, where nutrient vessels do not run, tend to have a low partial pressure of oxygen. A low partial pressure of oxygen tends to indicate low radiosensitivity, meaning that the effect of radiotherapy on the tumor region is low. In other words, Image C can also be said to represent the spatial distribution of the effect of radiotherapy. By observing Image C, the user can estimate the effect of radiotherapy on the detected tumor regions I132, I133, and I134.

[0077] As the second analysis result I14, image D, which is the analysis result of the hippocampal volume measurement process according to Example 3, is displayed. In image D, the measured hippocampal region I142 is visually highlighted with color, etc. Since image D has a higher spatial resolution than image A, the highlighting of the hippocampal region I142 in image D makes it possible to provide the user with a highly accurate detection of the hippocampal region I142. Alternatively, as the second analysis result I14, a numerical value representing the measured volume of the hippocampal region I142, such as "AAml", may be displayed. By highlighting the hippocampal region I142 and displaying the numerical value of the measured volume, it becomes possible to determine the possibility of Alzheimer's disease based on the diagnosis of a brain tumor.

[0078] As shown in Figure 7, the first analysis result I11 and the second analysis results I12, I13, I14 are displayed in parallel on a single screen, making it possible to comprehensively provide the information necessary for diagnosing the subject. In this case, the medical image display device 400 should attach flags I121, I131, I141 to the second analysis results I12, I13, I14 to indicate that they are the result of additional analysis processing (hereinafter referred to as additional analysis flags). By attaching the additional analysis flags I121, I131, I141, it becomes possible to clearly indicate that the second analysis results I12, I13, I14 are different from the analysis results of the first analysis processing which is executed by default. This makes it possible to provide the second analysis results I12, I13, I14 while reducing confusion for the physician.

[0079] Once step SA16 is performed, the automatic analysis process by the medical image processing system 100 is completed.

[0080] As described above, the medical image processing system 100 according to this embodiment includes a medical image processing device 300 and a medical imaging device 200 that are connected to each other in a manner that allows them to communicate with each other. The medical image processing device 300 implements a communication control function 316, an analysis function 312, a judgment function 313, and a decision function 314. The communication control function 316 receives a first medical image relating to the subject from the medical imaging device 200. The analysis function 312 performs a first analysis process on the first medical image and outputs a first analysis result. The judgment function 313 determines whether an additional second analysis process is necessary based on the first analysis result. If it is determined that a second analysis process is necessary, the decision function 314 determines the image characteristics that are recommended to be present in the second medical image to be subjected to the second analysis process, according to the processing content of the second analysis process.

[0081] According to the above configuration, it becomes possible to automatically determine whether additional second analysis processing is necessary and what image characteristics the second medical image should possess, thus making it possible to easily identify the second medical image. Furthermore, according to the automatic analysis processing shown in Figure 4, the medical imaging device 200 can acquire the second medical image using already existing data according to image processing conditions based on the image characteristics, eliminating the need for additional medical imaging. Therefore, it becomes possible to acquire the second medical image without burdening medical personnel or patients with additional medical imaging.

[0082] The automated analysis process shown in Figure 4 is just one example, and various steps can be deleted, added, and / or modified. Several modifications according to this embodiment will be described below.

[0083] <Example 1> In the automated analysis process shown in Figure 4, the medical imaging device 200 unconditionally executes the acquisition process for the second medical image (SA10-SA12) upon receiving a request to acquire a second medical image. In the modified version 1, the medical imaging device 200 confirms with the user, such as a radiologist, whether or not to execute the acquisition process for the second medical image. The process related to modified version 1 will be described below.

[0084] When a request to acquire a second medical image is received in step SA9, the processing circuit 22 of the medical imaging device 200 displays a window (hereinafter referred to as the confirmation window) on the display device 24 using the display control function 225 to allow the user to confirm whether or not to provide the second medical image.

[0085] Figure 8 shows an example of the display of confirmation window I2. As shown in Figure 8, confirmation window I2 displays a message to confirm with the user of the medical imaging device 200 whether or not to provide a second medical image, such as "You have been asked to provide additional data regarding the examination of patient ID: XX. Do you want to send it?". Note that "additional data" refers to the second medical image. At this time, a string of characters indicating the reason for requesting the second medical image, such as "Reason: To improve the accuracy of analysis in the △△ application," may also be displayed. The display content regarding the reason, such as the name of the application for the second analysis process, can be provided by the medical image processing device 300.

[0086] As shown in Figure 8, the confirmation window I2 contains a GUI button (hereinafter referred to as the "Yes" button) I21 for indicating consent to provision and a GUI button (hereinafter referred to as the "No" button) I22 for indicating refusal to provide. The user looks at the confirmation window I2 and decides whether or not to consent to the provision of the second medical image. For example, if high-load processing such as medical imaging is scheduled to be performed continuously on the medical imaging device 200 from the time of acquisition of the acquisition request, or if it is determined that the second analysis processing is unnecessary for clinical reasons, the user decides not to consent to the provision of the second medical image and presses the "No" button I22 via the input interface 25. On the other hand, if there is available time on the medical imaging device 200 or if it is determined that the second analysis processing is necessary, the user decides to consent to the provision of the second medical image and presses the "Yes" button I21 via the input interface 25.

[0087] If the "Yes" button I21 is pressed, the processing circuit 22 executes the processes shown in steps SA10 to SA13 in Figure 4. If the "No" button I22 is pressed, the processing circuit 22 does not execute the processes shown in steps SA10 to SA13, and the communication control function 224 sends a signal to the medical image processing device 300 indicating that the user does not consent to the transmission of the second medical image (hereinafter referred to as the "disagreement signal"). When the processing circuit 31 of the medical image processing device 300 receives the disagreement signal, it does not execute the second analysis process (SA14), and the communication control function 316 sends the first analysis result to the medical image display device 400, which then displays the first analysis result on the display device.

[0088] As described above, the medical imaging device 200 according to Modification 1 performs the acquisition process of a second medical image only when the user expresses an intention to provide a second medical image. This makes it possible to reduce unnecessary image generation processing, transfer of the second medical image, second analysis processing, etc.

[0089] <Modification 2> In the automated analysis process shown in Figure 4, the medical image processing device 300 and the medical imaging device 200 are from the same manufacturer, and the medical image processing device 300 converts image characteristics into image generation conditions. In Modification 2, the medical image processing device 300 and the medical imaging device 200 are from different manufacturers, and the medical imaging device 200 converts image characteristics into image generation conditions. Below, an example of the processing of the medical image processing system 100 according to Modification 2 will be described.

[0090] Figure 9 shows the flow of automatic analysis processing by the medical image processing system 100 according to Modification 2. Steps SB1 to SB7 shown in Figure 9 are the same as steps SA1 to SA7 shown in Figure 4, so their explanation is omitted.

[0091] When step SB7 is performed, the processing circuit 31 transmits the request to acquire the second medical image and its image characteristics to the medical imaging device 200 via the communication control function 316 (step SB8). The medical imaging device 200 receives the request to acquire the second medical image and its image characteristics.

[0092] When step SB8 is performed, the processing circuit 22 of the medical imaging device 200 determines whether a second medical image exists in the storage device 23 using the image acquisition function 222 (step SB9). For example, the processing circuit 22 uses the search function 226 to display a list of image characteristics related to medical images stored in the storage device 23 on the display device 24, and the user designates a medical image as the second medical image from this list via the input interface 25. If designated, the processing circuit 22 determines that a second medical image exists. If not designated, the processing circuit 22 determines that a second medical image does not exist (is absent).

[0093] If it is determined that a second medical image exists (step SB9: exists), the processing circuit 22 extracts the second medical image from the storage device 23 using the search function 226 (step SB10).

[0094] If it is determined that a second medical image does not exist (step SB9: absent), the processing circuit 22 uses the conversion function 315 to convert the image characteristics received in step SB8 into image generation conditions defined by the specifications adopted by the device (step SB11). The conversion from image characteristics to image generation conditions can be performed using a rule-based method that associates image characteristics with image generation conditions defined by the specifications adopted by the device, or using a machine learning model trained to take image characteristics as input and output image generation conditions defined by the specifications adopted by the device.

[0095] Once step SB11 is performed, the processing circuit 22 generates a second medical image using the image generation function 227 (step SB12). Step SB12 is the same as step SA12 in Figure 4.

[0096] When step SB10 or SB12 is performed, the processing circuit 22 transmits the second medical image to the medical image processing device 300 via the communication interface 26 using the communication control function 224 (step SB13). The medical image processing device 300 receives the second medical image. The received second medical image is acquired by the processing circuit 31 using the acquisition function 311. Subsequently, the second analysis process (step SB14), transmission of the first and second analysis results (SB15), and display of the analysis results (SB16) are performed. Steps SB14, SB15, and SB16 are the same as steps SA14, SA15, and SA16, respectively.

[0097] When step SB16 is performed, the automatic analysis process by the medical image processing system 100 according to the modified example 2 is completed.

[0098] According to Modification 2, by performing a conversion from image characteristics to image generation conditions in the medical imaging device 200, it becomes possible to acquire a second medical image with image characteristics in the medical imaging device 200, even when the medical imaging device 200 and the medical image processing device 300 are manufactured by different companies.

[0099] <Variation 3> The medical image processing system 100 according to Modification 3 assigns priority to multiple second medical images when it issues acquisition requests for multiple second medical images. Modification 3 assumes a scenario in which multiple second medical images are requested for a single second analysis process. The following describes an example of processing by the medical image processing system 100 according to Modification 3.

[0100] If there are multiple second medical images, the processing circuit 22 of the medical imaging device 200 acquires the second medical images using the image acquisition function 222, according to a priority based on whether the second medical image can be acquired and the time required to acquire it. Specifically, the processing circuit 22 assigns a priority to the multiple second medical images based on whether the second medical image can be acquired and the time required to acquire it. The processing circuit 22 can calculate the acquisition possibility information, such as whether the second medical image can be acquired, based on whether the second medical image exists in the storage device 23, and if the second medical image does not exist in the storage device 23, whether the raw data necessary to generate the second medical image exists in the storage device 23, etc. Furthermore, the processing circuit 22 can calculate the acquisition time, which is the time required to acquire the second medical image, based on the time required to read the second medical image from the storage device 23 if the second medical image exists in the storage device 23, or the standard time required to generate the second medical image from the raw data if the second medical image does not exist in the storage device 23, etc. The processing circuit 22 should be given a higher priority when a second medical image can be acquired compared to when a second medical image cannot be acquired. The processing circuit 22 should be given a higher priority the shorter the acquisition time required.

[0101] The processing circuit 22 may allow the user to manually determine the priority to be assigned to the second medical image. For example, the processing circuit 22 displays a list of second medical images related to acquisition feasibility information and required acquisition time on the display device 24. The user looks at the displayed list and decides the priority to be assigned to each second medical image. The processing circuit 22 may also display a list of image characteristics, image generation conditions, and processing details of the second analysis process, and the user may decide the priority taking this information into account. The processing circuit 22 assigns the priority entered by the user via the input interface 25 to each second medical image.

[0102] Once priority is assigned to the second medical images, the processing circuit 22 acquires the second medical images in order from highest priority (SA11~SA12, SB10~SB12). The acquired second medical images are sequentially transmitted to the medical image processing device 300, and the second analysis process is executed. The processing circuit 22 may also limit the acquisition to second medical images with a priority above a threshold. This makes it possible to reduce the load on the medical imaging device 200 associated with the acquisition of lower-priority second medical images and the load on the medical image processing device 300 associated with the second analysis process.

[0103] <Modification 4> The medical image processing system 100 according to Modification 4 avoids performing a determination process (SA5) on the second medical image to determine whether or not a second analysis process is necessary. Specifically, the processing circuit 22 of the medical imaging device 200 assigns a flag (hereinafter referred to as the additional image flag) to the second medical image acquired by the image acquisition function 222. The additional image flag is digital data used to identify that it is a second medical image, in other words, a medical image to be used for the second analysis process. The second medical image with the additional image flag is transmitted to the medical image processing device 300.

[0104] The processing circuit 31 of the medical image processing device 300 does not perform a determination process to determine whether additional analysis processing is necessary for the second medical image with the additional image flag. In other words, for the second medical image with the additional image flag, the image characteristic determination process (SA7), the conversion process to image generation conditions (SA8), and the acquisition process of the second medical image (SA9~SA13) are not performed. By avoiding the repetition of steps SA5~SA13, it is possible to reduce the load and processing time required for unnecessary processing.

[0105] As described in the above embodiment, the second medical image with the additional image flag is subjected to the second analysis processing by the second analysis function 319. The additional image flag is also added to the second analysis result output by the second analysis processing. The medical image display device 400 displays the second analysis result with the additional image flag by adding the additional analysis flag, as shown in Figure 7.

[0106] The process of determining whether or not the second analysis process is necessary may be allowed to be repeated a predetermined number of times. In this case, the processing circuit 22 of the medical imaging device 200 assigns numerical information representing the number of times the process of determining whether or not the second analysis process is necessary is assigned to the additional image flag. The processing circuit 31 of the medical image processing device 300 refers to the number of repetitions assigned to the additional image flag of the second medical image and determines whether or not the number of repetitions is below a threshold. If the number of repetitions is below the threshold, the processing circuit 31 executes the second analysis process on the second medical image and also executes the process of determining whether or not the second analysis process is necessary. If the number of repetitions is not below the threshold, the processing circuit 31 does not execute the process of determining whether or not the second analysis process is necessary on the second medical image and executes the second analysis process. This avoids the event in which steps SA5 to SA13 are repeated beyond a predetermined number of repetitions, and makes it possible to reduce the load and processing time required for unnecessary processing.

[0107] <Modification 5> The medical image processing device 300 according to Modification 5 performs a second analysis process only if the second medical image received from the medical imaging device 200 is the expected image. Specifically, the processing circuit 31 of the medical image processing device 300 determines whether to accept or reject the second medical image received from the medical imaging device 200. For example, the processing circuit 31 may calculate an arbitrary image quality evaluation index value for the second medical image and decide whether to accept or reject the second medical image depending on whether the calculated image quality evaluation index value exceeds a threshold. Alternatively, the user may specify whether to accept or reject the second medical image via the input interface 34, etc. If the processing circuit 31 determines that the second medical image should be accepted, it performs a second analysis process on the second medical image; if it determines that the second medical image should not be accepted, it does not perform a second analysis process on the second medical image. This avoids performing unnecessary second analysis processes, making it possible to reduce the overall processing time related to the automatic analysis process.

[0108] <Variation 6> The first analysis process in Modification 6 is a common analysis process included in all of the multiple applications (hereinafter referred to as the common analysis process). The second analysis process in Modification 6 is a non-common analysis process included in each of the multiple applications (hereinafter referred to as the non-common analysis process). The processing circuit 31 of the medical image processing device 300 determines the image characteristics for all or part of the multiple applications according to the non-common analysis process.

[0109] As an example, let's consider applications A, B, and C, which perform brain tumor detection processing as a common analysis process. Application A has no non-common analysis processing, application B has brain tumor volume measurement processing as a non-common analysis process, and application C has nutrient vessel detection processing as a non-common analysis process.

[0110] In the processing circuit 31 according to Modification 6, the first analysis process (SA4) executes the brain tumor detection processes of applications A, B, and C on the first medical image. As an example, let's assume that a brain tumor is detected only by the brain tumor detection process of application B. In this case, in the image characteristic determination process (SA7), the processing circuit 31 determines the image characteristics of the second medical image by using the brain tumor volume measurement, which is a non-common analysis process of application B, as the second analysis process. From a clinical standpoint, a brain tumor should also be detected in application C in addition to application B, so the processing circuit 31 may also determine the image characteristics of the second medical image by using the nutrient vessel detection process, which is a non-common analysis process of application C, as the second analysis process in the image characteristic determination process (SA7). Alternatively, the processing circuit 31 may also determine the image characteristics of the second medical image by using the non-common analysis process of another application D as the second analysis process in the image characteristic determination process (SA7). For example, if application D is an application that detects the onset of Alzheimer's disease, the non-common analysis process of application D is the hippocampal region volume measurement process. In this case, the processing circuit 31 may determine the image characteristics of the second medical image by performing the volume measurement process of the hippocampal region of application D as the second analysis process in the image characteristic determination process (SA7).

[0111] <Example 7> In the medical image processing system 100 according to the above embodiment, the medical imaging device 200 acquires a second medical image. However, this embodiment is not limited to this. In the medical image processing system 100 according to Modification 7, the medical image processing device 300 generates a second medical image based on image generation conditions.

[0112] Figure 10 shows an example configuration of the medical image processing device 300 according to Example 7. As shown in Figure 10, the processing circuit 31 of the medical image processing device 300 implements functions 311 to 319 as well as a generation function 320. The generation function 320 generates a second medical image from a first medical image based on the image generation conditions obtained by the conversion function 315.

[0113] Figure 11 shows the flow of the automated analysis process by the medical image processing system 100 according to Modification 7. Steps SC1 to SC7 shown in Figure 11 are the same as steps SA1 to SA7 shown in Figure 4, so their explanation is omitted.

[0114] When step SC7 is performed, the processing circuit 31 uses the conversion function 315 to convert the image characteristics determined in step SC7 into image processing conditions defined by the specifications adopted by the device (step SC8). In the modified example 7, a second medical image is generated in a way that is possible even when raw data does not exist in the medical image processing device 300. Specifically, a second medical image is generated from a first medical image already supplied to the medical image processing device 300. In step SC8, the processing circuit 31 outputs image processing conditions for generating a second medical image from the first medical image.

[0115] When step SC8 is performed, the processing circuit 31 generates a second medical image from the first medical image based on the image processing conditions using the generation function 320 (step SC9). For example, if the slice thickness is reduced to improve accuracy, a second slice thickness smaller than the first slice thickness of the first medical image is output as an image characteristic, and image processing parameters to achieve the second slice thickness are output as image processing conditions. In this case, the processing circuit 31 performs a re-slicing process on the first medical image based on the image processing conditions to generate a second medical image having the second slice thickness.

[0116] As another example, when increasing the matrix number to improve accuracy, a second matrix number larger than the first matrix number of the first medical image is output as an image characteristic, and image processing parameters to realize the second matrix number are output as image processing conditions. In this case, the processing circuit 31 performs zero-padding on the first medical image based on the image processing conditions and generates a second medical image having the second matrix number.

[0117] As another example, if a medical image of a second cross-section is added to the first medical image of the first cross-section to improve accuracy, the second cross-section, which is different from the first cross-section, is output as an image characteristic, and the image processing parameters for realizing the second cross-section are output as image processing conditions. For example, suppose the first cross-section is an axial cross-section and the second cross-section is a sagittal cross-section. In this example, the volume data that will be the basis of the axial cross-sectional image is supplied from the medical imaging device 200 to the medical image processing device 300 in step SA13, etc. In this case, the image processing parameters for generating a sagittal cross-sectional image from the volume data are determined as image processing conditions. The processing circuit 31 performs MPR processing on the volume data based on these image processing conditions and generates a sagittal cross-sectional image (second medical image).

[0118] As another example, when adding non-contrast images in addition to contrast-enhanced images to improve accuracy, the contrast-enhanced image is output as image characteristics, and the image processing parameters for realizing the contrast-enhanced image are output as image processing conditions. For example, based on the differences in features between contrast-enhanced and non-contrast images relating to the same anatomical site, image processing parameters for generating a non-contrast image from a contrast-enhanced image are determined. The contrast-enhanced and non-contrast images used to determine the image processing conditions can be selected from medical images stored in the PACS database. Based on the determined image processing conditions, the processing circuit 31 performs image processing such as signal value conversion on the contrast-enhanced image (first medical image) relating to the subject to generate a non-contrast image (second medical image). Alternatively, image processing using a deep neural network may be performed to generate a non-contrast image from a contrast-enhanced image.

[0119] Subsequently, the second analysis process (step SC10), transmission of the first and second analysis results (SC11), and display of the analysis results (SC12) are performed. Steps SC10, SC11, and SC12 are the same as steps SA14, SA15, and SA16, respectively.

[0120] Once step SC12 is performed, the automatic analysis process by the medical image processing system 100 according to the modified example 7 is completed.

[0121] According to Modification 7, the medical image processing device 300 can acquire the second medical image without requesting the medical imaging device 200 to acquire the second medical image. This reduces the load on the medical imaging device 200 to acquire the second medical image, and since the second medical image can be acquired without going through the medical imaging device 200, the time required to acquire the second medical image can be shortened.

[0122] According to at least one embodiment described above, it is possible to easily identify medical images suitable for additional analysis processing performed in response to the analysis results of medical images.

[0123] In the above description, the term "processor" refers to circuits such as CPUs, GPUs, or Application Specific Integrated Circuits (ASICs), programmable logic devices (e.g., Simple Programmable Logic Devices (SPLDs), Complex Programmable Logic Devices (CPLDs), and Field Programmable Gate Arrays (FPGAs)). A processor functions by reading and executing a program stored in a memory circuit. Alternatively, instead of storing the program in a memory circuit, the program may be directly incorporated into the processor's circuitry. In this case, the processor functions by reading and executing the program incorporated into the circuitry. On the other hand, if the processor is an ASIC, for example, the program is not stored in a memory circuit, but rather the function is directly incorporated into the processor's circuitry as a logic circuit. In this embodiment, each processor is not limited to being configured as a single circuit; multiple independent circuits may be combined to form a single processor and realize its functions. Furthermore, the multiple components shown in Figures 1 to 3 and Figure 10 may be integrated into a single processor to realize their functions.

[0124] While several embodiments have been described, these embodiments are presented as examples only and are not intended to limit the scope of the invention. These embodiments can be implemented in a variety of other forms, and various omissions, substitutions, modifications, and combinations of embodiments are possible without departing from the spirit of the invention. These embodiments and their variations are included in the scope and spirit of the invention, as well as in the claims and their equivalents. [Explanation of Symbols]

[0125] 21 Imaging mechanism 22 Processing Circuit 23 Storage device 24 Display equipment 25 Input Interfaces 26 Communication Interfaces 31 Processing Circuit 32 Storage device 33 Display equipment 34 Input Interfaces 35 Communication Interfaces 100 Medical Image Processing Systems 200 Medical Imaging Devices 221 Collection function 222 Image acquisition function 223 Conversion function 224 Communication control function 225 Display control function 226 Search function 227 Image generation function 300 Medical Image Processing Equipment 311 Acquisition function 312 Analysis Functions 313 Judgment Function 314 Decision Function 315 Conversion function 316 Communication control function 317 Display control function 318 First analysis function 319 Second analysis function 320 generation function 400 Medical Image Display Devices

Claims

1. It comprises a medical image processing device and a medical imaging device that are connected to each other in a manner that allows them to communicate with one another. The aforementioned medical image processing device is A receiving unit that receives a first medical image of the subject from the aforementioned medical imaging device, An analysis unit that performs a first analysis process on the first medical image and outputs a first analysis result, A determination unit that determines whether an additional second analysis process is necessary based on the first analysis result, If it is determined that the second analysis process is required, the system includes a determination unit that determines the image characteristics that are recommended to be present in the second medical image to be subjected to the second analysis process, according to the processing content of the second analysis process. Medical image processing system.

2. The medical image processing device further comprises a first transmission unit, The first transmitting unit transmits to the medical imaging device a request to acquire the second medical image relating to the subject and the image characteristics. The receiving unit receives the second medical image acquired by the medical imaging device in response to the acquisition request from the medical imaging device. The analysis unit applies the second analysis process to the second medical image and outputs the second analysis result. The medical image processing system according to claim 1.

3. The medical image processing device further comprises a medical image display device that is communicatively connected to the aforementioned medical image processing device. The medical image processing device further includes a second transmission unit that transmits the first analysis result and the second analysis result to a medical image display device. The medical image display device displays the first analysis result and the second analysis result on a display device. The medical image processing system according to claim 2.

4. The aforementioned medical image display device is The first analysis result and the second analysis result are displayed side by side on a single screen. A visual effect is added to the second analysis result to indicate that it is an additional analysis process. The medical image processing system according to claim 3.

5. The aforementioned medical imaging device is An acquisition unit that acquires the second medical image having the aforementioned image characteristics without performing additional medical imaging, The system includes a third transmitting unit that transmits the second medical image to the medical image processing device. The medical image processing system according to claim 2.

6. The acquisition unit is, If the second medical image is stored in the storage device, read the second medical image from the storage device. If the second medical image is not stored in the storage device, the second medical image is generated from the raw data stored in the storage device based on the image generation conditions corresponding to the image characteristics. The medical image processing system according to claim 5.

7. The system further includes a conversion unit that converts the aforementioned image characteristics into the aforementioned image generation conditions defined in the specifications adopted by the medical imaging device, The first transmitting unit transmits the image generation conditions to the medical imaging device. If the acquisition unit does not have the second medical image stored in the storage device, it generates the second medical image from the raw data based on the image generation conditions. The medical image processing system according to claim 6.

8. The aforementioned medical imaging device further comprises a conversion unit, The first transmitting unit transmits the image characteristics to the medical imaging device. The conversion unit converts the image characteristics into the image generation conditions defined by the specifications adopted by the device, If the acquisition unit does not have the second medical image stored in the storage device, it generates the second medical image from the raw data based on the image generation conditions. The medical image processing system according to claim 6.

9. The medical imaging device further includes a display control unit that displays a window on a display device for the user to confirm whether or not to provide the second medical image. The acquisition unit acquires the second medical image when it receives an instruction via the window to provide the second medical image. The medical image processing system according to claim 5.

10. The medical image processing system according to claim 5, wherein, if there are multiple second medical images, the acquisition unit acquires the second medical images according to a priority based on whether the second medical image can be acquired and the time required to acquire the second medical image.

11. The acquisition unit attaches a flag to the second medical image to that effect. The determination unit does not perform a determination process to determine whether additional analysis processing is necessary for the second medical image that has the flag attached. The medical image processing system according to claim 5.

12. The aforementioned analysis unit, The decision to accept or reject the second medical image is made. If it is determined that the second medical image should be adopted, the second analysis process is applied to the second medical image. If it is determined that the second medical image will not be used, the second analysis process will not be applied to the second medical image. The medical image processing system according to claim 5.

13. The first analysis process involves calculating the spatial distribution of probability values ​​representing tumor-likeness based on the first medical image, detecting tumor regions from the first medical image based on a comparison of the probability values ​​with a first threshold, and outputting the location of the detected tumor region. The determination unit determines that the second analysis process is required if the difference between the probability value and the first threshold is smaller than the second threshold. The second analysis process has the same processing content as the first analysis process and is performed to improve the accuracy of detecting the tumor region compared to the first analysis process. The aforementioned image characteristic is that the contrast between the normal tissue area and the tumor area is greater than that of the first medical image. The medical image processing system according to claim 1.

14. The first analysis process involves calculating the spatial distribution of probability values ​​representing tumor-likeness based on the first medical image, detecting tumor regions from the first medical image based on a comparison of the probability values ​​with a first threshold, and outputting the location of the detected tumor region. The determination unit determines that the second analysis process is required if the location of the tumor region is output by the first analysis process and a determination of the effectiveness of radiotherapy is required. The second analysis process is a process for detecting the presence or absence of nutrient vessels to the tumor region, The aforementioned image characteristic is that the contrast between the blood flow region and other regions is greater than that of the first medical image. The medical image processing system according to claim 1.

15. The first analysis process involves calculating the spatial distribution of probability values ​​representing tumor-likeness based on the first medical image, detecting tumor regions from the first medical image based on a comparison of the probability values ​​with a first threshold, and outputting the location of the detected tumor region. The determination unit determines that the second analysis process is required if the location of the tumor region is not output by the first analysis process and the hippocampal region is included in the first medical image. The second analysis process is a process for measuring the volume of the hippocampal region, The aforementioned image characteristic is that it has higher spatial resolution than the first medical image. The medical image processing system according to claim 1.

16. The aforementioned first analysis process is an analysis process common to all of the multiple applications, and is included in all of the multiple applications. The aforementioned second analysis process is an analysis process included in each of the multiple applications, but which is not common to the multiple applications. The determination unit determines the image characteristics corresponding to the non-common analysis processing for all or part of the plurality of applications. The medical image processing system according to claim 1.

17. The medical image processing system according to claim 1, further comprising a generation unit that generates a second medical image from the first medical image based on image processing conditions corresponding to the image characteristics.

18. The medical image processing system according to claim 1, wherein the image characteristics are spatial resolution, inter-tissue contrast, slice thickness, matrix size, and / or cross-sectional position.

19. A first analysis unit performs a first analysis process on the first medical image of the subject and outputs the first analysis result, A determination unit that determines whether an additional second analysis process is necessary based on the first analysis result, If it is determined that the second analysis process is required, a determination unit determines the image characteristics that are recommended to be present in the second medical image to be subjected to the second analysis process, according to the processing content of the second analysis process. A transmission unit transmits a request to acquire the second medical image and the image characteristics to the medical imaging device that generated the first medical image. A receiving unit that receives the second medical image of the subject, acquired by the medical imaging device in response to the acquisition request, from the medical imaging device, A second analysis unit that applies the second analysis process to the second medical image and outputs a second analysis result, A medical image processing device equipped with the necessary components.

20. A receiving unit that receives a request to acquire a specific medical image and image characteristics that the specific medical image is recommended to possess from a medical image processing device, A storage unit that stores the raw data of the aforementioned specific medical image, A conversion unit that converts the aforementioned image characteristics into image generation conditions for generating the specific medical image defined by the specifications adopted by the device, An image generation unit generates a specific medical image having the image characteristics described above from the raw data based on the image generation conditions described above. A transmission unit that transmits the generated specific medical image to the medical image processing device, A medical imaging device equipped with the following features.

Images