Medical image processing apparatus, method, and program

Abstract

To execute proper analysis even when analyzing medical image data having a possibility of being fabricated due to gravitational effects.SOLUTION: A medical image processing device includes an acquisition part, an identification part, a first setup part and an analysis part. The acquisition part acquires medical image data to become an analysis object. The identification part identifies a direction of gravity for the medical image data. The first setup part sets up a first weight for pixels constituting the medical image data based on the direction of gravity. The analysis part analyzes the medical image data based on the first weight.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] Embodiments disclosed herein and in the drawings relate to medical image processing apparatus, methods, and programs. [Background technology]

[0002] Conventionally, techniques have been known to identify medical image data that is highly likely to contain false images, known as gravity effects, which occur during the acquisition of medical image data. For example, a technique has been described in which, based on clinical knowledge, locations where false images due to gravity effects are likely to occur are determined, and medical image data that is highly likely to contain false images is identified based on the continuity of high-absorption regions at those locations. [Prior art documents] [Patent Documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2020-058472 [Patent Document 2] International Publication No. 2017 / 150947 [Overview of the project] [Problems that the invention aims to solve]

[0004] One of the problems that the embodiments disclosed in this specification and drawings aim to solve is to perform appropriate analysis even when analyzing medical image data that is highly likely to be forged due to gravity effects. However, the problems that the embodiments disclosed in this specification and drawings aim to solve are not limited to the above problem. Problems corresponding to each effect 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 apparatus according to the embodiment comprises an acquisition unit, an identification unit, a first setting unit, and an analysis unit. The acquisition unit acquires medical image data to be analyzed. The identification unit identifies the direction of gravity for the medical image data. The first setting unit sets a first weight for each pixel constituting the medical image data based on the direction of gravity. The analysis unit performs analysis of the medical image data based on the first weight. [Brief explanation of the drawing]

[0006] [Figure 1] Figure 1 shows an example of the configuration of a medical image processing apparatus according to the first embodiment. [Figure 2] Figure 2 is a flowchart showing the processing procedure performed by each processing function of the processing circuit of the medical image processing apparatus according to the first embodiment. [Figure 3] Figure 3 is a diagram illustrating an example of the first weight setting process according to the first embodiment. [Figure 4] Figure 4 is a diagram illustrating an example of the first weight setting process related to Modification Example 2. [Figure 5] Figure 5 is a diagram illustrating an example of the analysis process related to Modification Example 3. [Figure 6] Figure 6 shows an example of the configuration of a medical image processing apparatus according to the second embodiment. [Figure 7] Figure 7 is a flowchart showing the processing procedure performed by each processing function of the processing circuit of the medical image processing apparatus according to the second embodiment. [Figure 8] Figure 8 is a diagram illustrating an example of the determination process according to the second embodiment. [Figure 9] Figure 9 shows an example of the configuration of a medical image processing apparatus according to the third embodiment. [Figure 10] Figure 10 is a flowchart showing the processing procedure performed by each processing function of the processing circuit of the medical image processing apparatus according to the third embodiment. [Figure 11A]FIG. 11A is a diagram for explaining an example of the setting process of the second weight according to the third embodiment. [Figure 11B] FIG. 11B is a diagram for explaining an example of the setting process of the second weight according to the third embodiment. Embodiment for Carrying out the Invention

[0007] Hereinafter, embodiments of a medical image processing apparatus, method, and program will be described in detail with reference to the drawings. Note that the medical image processing apparatus, method, and program according to the present application are not limited to the following embodiments. In the following description, the same components are given common reference numerals and redundant descriptions are omitted.

[0008] (First Embodiment) FIG. 1 is a diagram showing a configuration example of a medical image processing apparatus according to the first embodiment. For example, as shown in FIG. 1, a medical image processing apparatus 3 according to the present embodiment is communicably connected to a medical image diagnostic apparatus 1 and a medical image storage apparatus 2 via a network. Note that various other apparatuses and systems may be connected to the network shown in FIG. 1.

[0009] The medical image diagnostic apparatus 1 images a subject to generate medical image data. Then, the medical image diagnostic apparatus 1 transmits the generated medical image data to various apparatuses on the network. For example, the medical image diagnostic apparatus 1 is an X-ray diagnostic apparatus, an X-ray CT (Computed Tomography) apparatus, an MRI (Magnetic Resonance Imaging) apparatus, an ultrasonic diagnostic apparatus, a SPECT (Single Photon Emission Computed Tomography) apparatus, a PET (Positron Emission computed Tomography) apparatus, or the like.

[0010] The medical image storage device 2 stores various medical image data related to the subject. Specifically, the medical image storage device 2 receives medical image data from the medical image diagnostic device 1 via a network and stores the medical image data in its internal memory circuit. For example, the medical image storage device 2 can be implemented using computer equipment such as a server or workstation. Alternatively, for example, the medical image storage device 2 can be implemented using a PACS (Picture Archiving and Communication System) and store medical image data in a format compliant with DICOM (Digital Imaging and Communications in Medicine).

[0011] The medical image processing device 3 performs various processes related to medical image data. Specifically, the medical image processing device 3 receives medical image data from the medical image diagnostic device 1 or the medical image storage device 2 via a network and performs various information processing using the medical image data. For example, the medical image processing device 3 is implemented using computer equipment such as a server or workstation.

[0012] For example, the medical image processing device 3 includes a communication interface 31, an input interface 32, a display 33, a storage circuit 34, and a processing circuit 35.

[0013] The communication interface 31 controls the transmission and communication of various data sent and received between the medical image processing device 3 and other devices connected via the network. Specifically, the communication interface 31 is connected to the processing circuit 35 and transmits data received from other devices to the processing circuit 35, or transmits data transmitted from the processing circuit 35 to other devices. For example, the communication interface 31 can be implemented by a network card, network adapter, NIC (Network Interface Controller), etc.

[0014] The input interface 32 receives various instructions and input operations for various information from the user. Specifically, the input interface 32 is connected to the processing circuit 35 and converts the input operations received from the user into electrical signals and transmits them to the processing circuit 35. For example, the input interface 32 can be implemented by a trackball, switch buttons, mouse, keyboard, touchpad that performs input operations by touching the operating surface, touchscreen that integrates a display screen and a touchpad, a non-contact input interface using an optical sensor, and an audio input interface. In this specification, the input interface 32 is not limited to those equipped with physical operating components such as a mouse or keyboard. For example, an electrical signal processing circuit that receives electrical signals corresponding to input operations from an external input device provided separately from the device and transmits these electrical signals to a control circuit is also included as an example of the input interface 32.

[0015] The display 33 displays various information and data. Specifically, the display 33 is connected to the processing circuit 35 and displays various information and data received from the processing circuit 35. For example, the display 33 can be implemented as a liquid crystal display, a CRT (Cathode Ray Tube) display, a touch panel, etc.

[0016] The memory circuit 34 stores various data and programs. Specifically, the memory circuit 34 is connected to the processing circuit 35 and stores data received from the processing circuit 35, or reads stored data and transmits it to the processing circuit 35. For example, the memory circuit 34 can be implemented using semiconductor memory elements such as RAM (Random Access Memory) or flash memory, or a hard disk or optical disc.

[0017] The processing circuit 35 controls the entire medical image processing device 3. For example, the processing circuit 35 performs various processes in response to input operations received from the user via the input interface 32. For example, the processing circuit 35 receives data transmitted from other devices via the communication interface 31 and stores the received data in the storage circuit 34. Also, for example, the processing circuit 35 transmits the data received from the storage circuit 34 to other devices by sending it to the communication interface 31. Also, for example, the processing circuit 35 displays the data received from the storage circuit 34 on the display 33.

[0018] The configuration example of the medical image processing device 3 according to this embodiment has been described above. For example, the medical image processing device 3 according to this embodiment is installed in medical facilities such as hospitals and clinics and supports various diagnoses and the formulation of treatment plans performed by users such as doctors. For example, in the analysis of medical image data, the medical image processing device 3 performs various processes to appropriately analyze the medical image data even when false images and abnormal shadows similar to false images appear simultaneously in the medical image data.

[0019] As mentioned above, there are known techniques to identify medical image data that is highly likely to contain false images caused by gravity, based on clinical knowledge. However, it is difficult to completely distinguish such false images from abnormal shadows that resemble false images (for example, ground-glass opacity (GGO)). Therefore, even when using the above techniques, if false images and abnormal shadows appear simultaneously, they are all treated as abnormal shadows.

[0020] Therefore, the medical image processing apparatus 3 according to this embodiment is configured to perform appropriate analysis even when false images and abnormal shadows similar to false images appear simultaneously in the medical image data, by setting weights for the pixels constituting the medical image data based on the direction of gravity in the medical image data and performing analysis based on the set weights. The medical image processing apparatus 3 having such a configuration will be described in detail below.

[0021] For example, as shown in Figure 1, in this embodiment, the processing circuit 35 of the medical image processing device 3 performs a control function 351, an acquisition function 352, an extraction function 353, an identification function 354, a first setting function 355, and an analysis function 356. Here, the acquisition function 352 is an example of an acquisition unit. The extraction function 353 is an example of an extraction unit. The identification function 354 is an example of an identification unit. The first setting function 355 is an example of a first setting unit. The analysis function 356 is an example of an analysis unit.

[0022] The control function 351 controls the generation of various GUIs (Graphical User Interfaces) and various display information in response to operations via the input interface 32, and displays them on the display 33. For example, the control function 351 displays on the display 33 a GUI for performing image processing on medical image data, or the results of analysis related to the medical image data. The control function 351 also generates various display images based on the medical image data acquired by the acquisition function 352 and displays them on the display 33.

[0023] The acquisition function 352 acquires medical image data to be analyzed from the medical image diagnostic device 1 or the medical image storage device 2 via the communication interface 31. Specifically, the acquisition function 352 acquires two-dimensional medical image data or three-dimensional medical image data (volume data) that are the subject of image analysis for various diagnoses. The acquisition function 352 can also acquire multiple volume data obtained by taking multiple images in three dimensions in the time direction. For example, the acquisition function 352 acquires CT image data, ultrasound image data, MRI image data, X-ray image data, Angio image data, PET image data, SPECT image data, etc., as the above-mentioned medical image data. The processing circuit 35 receives the medical image data of the subject from the medical image diagnostic device 1 or the medical image storage device 2 by executing the acquisition function 352 and stores the received medical image data in the storage circuit 34.

[0024] The extraction function 353 extracts at least one structure of the subject from the medical image data. Specifically, the extraction function 353 extracts a region representing a biological organ contained in the medical image data acquired by the acquisition function 352. For example, the extraction function 353 extracts a region corresponding to the lungs, etc., contained in the medical image data. The processing performed by the extraction function 353 will be described in detail later.

[0025] The identification function 354 identifies the gravity direction for medical image data acquired by the acquisition function 352. The processing performed by the identification function 354 will be described in detail later.

[0026] The first setting function 355 sets a first weight for each pixel constituting the medical image data based on the direction of gravity. The processing performed by the first setting function 355 will be described in detail later.

[0027] The analysis function 356 analyzes the medical image data based on the first weight. The processing performed by the analysis function 356 will be described in detail later.

[0028] The processing circuit 35 described above is implemented, for example, by a processor. In this case, each of the processing functions described above is stored in the memory circuit 34 in the form of a program that can be executed by a computer. The processing circuit 35 then reads and executes each program stored in the memory circuit 34, thereby realizing the function corresponding to each program. In other words, the processing circuit 35, with each program read, has the processing functions shown in Figure 1.

[0029] The processing circuit 35 may be composed of a combination of multiple independent processors, with each processor executing a program to realize each processing function. Furthermore, each processing function of the processing circuit 35 may be implemented by appropriately distributing or integrating them across one or more processing circuits. Also, each processing function of the processing circuit 35 may be implemented by a mixture of hardware such as circuits and software. While this example describes a case where programs corresponding to each processing function are stored in a single memory circuit 34, the embodiments are not limited to this. For example, programs corresponding to each processing function may be stored in a distributed manner across multiple memory circuits, and the processing circuit 35 may read and execute each program from each memory circuit.

[0030] Next, the processing procedure by the medical image processing device 3 will be explained using Figure 2, and then the details of each process will be described. Figure 2 is a flowchart showing the processing procedure performed by each processing function of the processing circuit 35 of the medical image processing device 3 according to the first embodiment.

[0031] For example, as shown in Figure 2, in this embodiment, the acquisition function 352 acquires medical image data of a subject from the medical image diagnostic device 1 or the medical image storage device 2 (step S101). For example, the acquisition function 352 acquires specified medical image data in response to a medical image data acquisition operation via the input interface 32. This process is realized, for example, by the processing circuit 35 calling and executing a program corresponding to the acquisition function 352 from the storage circuit 34.

[0032] Next, the identification function 354 identifies the direction of gravity in the acquired medical image data (step S102). This is achieved, for example, by the processing circuit 35 calling and executing a program corresponding to the identification function 354 from the storage circuit 34.

[0033] Next, the extraction function 353 extracts structures from the acquired medical image data (step S103). This process is realized, for example, by the processing circuit 35 calling and executing a program corresponding to the extraction function 353 from the storage circuit 34. Although Figure 2 shows an example in which structures are extracted after the direction of gravity is identified, the embodiment is not limited to this, and the direction of gravity may be identified after the structures are extracted, or the identification of the direction of gravity and the extraction of structures may be performed simultaneously.

[0034] Next, the first setting function 355 sets a first weight for each pixel of the medical image data based on the direction of gravity (step S104). This process is realized, for example, by the processing circuit 35 calling and executing a program corresponding to the first setting function 355 from the storage circuit 34.

[0035] Then, the analysis function 356 analyzes the medical image data using the first weight (step S105). This process is realized, for example, by the processing circuit 35 calling and executing a program corresponding to the analysis function 356 from the storage circuit 34.

[0036] Although not shown in Figure 2, after analyzing the medical image data, the control function 351 can display the analysis results on the display 33. This process is achieved, for example, by the processing circuit 35 calling and executing a program corresponding to the control function 351 from the memory circuit 34.

[0037] The details of each process performed by the medical image processing device 3 will be described below. In this description, we will use the process of acquiring 3D chest X-ray CT image data as medical image data and performing analysis on the lungs as an example. However, the processes described in this embodiment are not limited to this, and can be applied to various other biological organs.

[0038] (Medical image data acquisition process) As explained in step S101 of Figure 2, the acquisition function 352 acquires three-dimensional X-ray CT image data captured on the chest in response to the medical image data acquisition operation via the input interface 32.

[0039] The medical image data acquisition process in step S101 may be initiated by user instructions via the input interface 32, as described above, but it may also be initiated automatically. In the latter case, for example, the acquisition function 352 monitors the medical image storage device 2 and automatically acquires new 3D chest X-ray CT image data whenever it is stored.

[0040] Furthermore, as described above, after the 3D chest X-ray CT image data is acquired by the acquisition function 352, the acquired image data may be displayed on the display 33.

[0041] (Identification process of the direction of gravity) As explained in step S102 of Figure 2, the identification function 354 identifies the direction of gravity in the 3D chest X-ray CT image data acquired by the acquisition function 352. Specifically, the identification function 354 identifies the direction of gravity acting on the subject when the 3D chest X-ray CT image data was acquired (i.e., the direction of gravity relative to the subject as depicted in the 3D chest X-ray CT image data).

[0042] For example, the identification function 354 identifies the direction of gravity based on the subject's position captured in the 3D chest X-ray CT image data. To give one example, the identification function 354 estimates the subject's position from the imaging information of the 3D chest X-ray CT image data and identifies the direction of gravity based on the estimated position. Here, the identification function 354 obtains imaging information from Patient position, which is one of the header information of DICOM (Digital Imaging and Communications in Medicine), a standard for medical image data. For example, if the imaging information is HFS (Head First-Supine) or FFS (Feet First-Supine), the identification function 354 estimates that the image was taken in a supine position. Also, if the imaging information is HFP (Head First-Prone), the identification function 354 estimates that the image was taken in a prone position, and if it is HDFL (Head First-Decubitus Left), it estimates that the image was taken in a left lateral decubitus position.

[0043] The identification function 354 identifies the direction of gravity as dorsal if the body position is supine, as ventral if the body position is prone, and as left lateral if the body position is left lateral. In the following explanation, it is assumed that the 3D chest X-ray CT image data was acquired in the supine position and that the direction of gravity is dorsal.

[0044] (Structural extraction process) As explained in step S103 of Figure 2, the extraction function 353 extracts structures contained in the three-dimensional chest X-ray CT image data. Specifically, the extraction function 353 acquires coordinate information of pixels that represent lungs, etc., in the three-dimensional chest X-ray CT image data. Here, the extraction function 353 can extract structures using various methods. For example, the extraction function 353 can extract a region specified on the three-dimensional chest X-ray CT image data as a lung via the input interface 32. That is, the extraction function 353 extracts a region manually specified by the user as a lung.

[0045] Furthermore, for example, the extraction function 353 can extract the lungs based on anatomical structures depicted in 3D chest X-ray CT image data using known region extraction techniques. For example, the extraction function 353 extracts the lungs in 3D chest X-ray CT image data using methods such as Otsu's binarization method based on CT values, region expansion method, snake method, graph cut method, and mean shift method.

[0046] Furthermore, the extraction function 353 can extract the lungs from 3D chest X-ray CT image data using a trained model constructed based on pre-prepared training data using machine learning techniques (including deep learning). By extracting the lungs using any of the above methods, the extraction function 353 can also extract the chest wall on the lateral side (non-mediastinal side) of the lungs based on anatomical knowledge.

[0047] (First weight setting process) As explained in step S104 of Figure 2, the first setting function 355 sets a first weight for each pixel of the three-dimensional chest X-ray CT image data. Specifically, the first setting function 355 sets the first weight based on the direction of gravity and at least one structure. For example, the first setting function 355 sets the first weight based on the direction of gravity and the distance from the edge of the extracted structure.

[0048] The gravity effect described above occurs when soft tissues susceptible to gravity (e.g., the lungs) are supported by hard tissues less affected by gravity (e.g., the chest wall), causing the soft tissues to compress. The probability of soft tissue compression increases the closer it is to the load-bearing area, i.e., the hard tissue.

[0049] Therefore, the first setting function 355 assumes that a chest wall exists outside the extracted lung, and determines the edge of the extracted lung that is approximately perpendicular to the direction of gravity, and is in the direction indicated by the gravity vector. Then, the first setting function 355 sets a first weight according to the distance from the determined edge.

[0050] Figure 3 is a diagram illustrating an example of the first weight setting process according to the first embodiment. Here, Figure 3 shows one cross-sectional image data 400 of an axial section in three-dimensional chest X-ray CT image data. For example, the cross-sectional image data 400 is selected by the user as the image data to be analyzed. The identification function 354 identifies the gravity direction shown in Figure 3 based on the imaging information of the three-dimensional chest X-ray CT image data. The extraction function 353 extracts the lungs included in the three-dimensional chest X-ray CT image data and extracts the lung margins 410 based on the extracted lungs.

[0051] For example, the first setting function 355 determines the edge 420 in the extracted lung edge 410 that is approximately perpendicular to the direction of gravity and is located in the direction indicated by the arrow in the direction of gravity (hereinafter, edge 420 will be referred to as the reference edge 420). Then, the first setting function 355 sets a first weight for each pixel according to the distance from the determined reference edge 420. For example, the first setting function 355 sets a first weight for each pixel based on the following equation (1).

[0052]

number

[0053] Here, in equation (1), "w1(i)" represents the first weight of pixel i. Also, "l1(i)" represents the distance in the direction of gravity (number of pixels) from the reference edge to the pixel in question. Furthermore, "min(l1(i),5)" represents a function that takes a value smaller than "l1(i)" and "5".

[0054] For example, the first setting function 355 sets the first weight "w1=0.5+0.1×0=0.5" for pixels 430 touching the reference edge 420 by inputting "l1=0" into equation (1) above. Also, the first setting function 355 sets the first weight "w1=0.5+0.1×2=0.7" for pixels 440 whose number of pixels in the direction of gravity from the reference edge 420 is "2" by inputting "l1=2" into equation (1) above. Also, the first setting function 355 sets the first weight "w1=0.5+0.1×5=1.0" for pixels 450 whose number of pixels in the direction of gravity from the reference edge 420 is greater than "5".

[0055] In other words, equation (1) shows that when the distance in the direction of gravity from the reference edge is less than a threshold (5 pixels in this example), the shorter the distance in the direction of gravity from the reference edge, the smaller the first weight becomes. This equation takes into account the mechanism of gravity effect described above. Of course, this method of setting the weight using this equation is just one example, and the first weight may be set by other methods as well.

[0056] In Figure 3, the reference margins are in the same position for both the left and right lungs, but the reference margins may be in different positions for the left and right lungs. Furthermore, the first weight may be set using different formulas for the right and left lungs.

[0057] Furthermore, although the example shown in Figure 3 uses a two-dimensional space for simplicity, it is also possible to set a reference edge (point / tangent surface) in three-dimensional space and set the first weight. In such a case, the first setting function 355 determines the reference edge in three-dimensional space based on the lung edge extracted in the volume data and the direction of gravity, and sets the first weight for each voxel according to the distance from the reference edge.

[0058] Furthermore, although the example shown in Figure 3 describes the case where the distance from the reference edge is determined by the number of pixels, the embodiment is not limited to this, and it may also be determined by the distance in real space. In such a case, for example, similar to equation (1), a threshold is set for the distance in real space in the direction of gravity from the reference edge, and the first weight is set such that the shorter the distance in the direction of gravity from the reference edge, the smaller the first weight is for distances below the set threshold.

[0059] Furthermore, while equation (1) above describes an example where the threshold is constant (5 pixels), the embodiment is not limited to this and may be dynamically changed. For example, it may be dynamically determined according to the size of the subject's body (for example, the larger the body, the larger the threshold).

[0060] (Analysis process) As explained in step S105 of Figure 2, the analysis function 356 performs analysis processing on the three-dimensional chest X-ray CT image data using the first weight set for each pixel by the first setting function 355. For example, the analysis function 356 can analyze the distribution of CT values ​​(mean, variance, etc.) within the lungs. In this case, the analysis function 356 multiplies the CT value of each pixel by the first weight and calculates a weighted mean or weighted variance using the sum of the CT values ​​after multiplying by the first weight. Here, the analysis function 356 can analyze the entire cross-sectional image data 400 shown in Figure 3, or it can analyze a localized region within the cross-sectional image data 400.

[0061] The analysis function 356 then analyzes the 3D chest X-ray CT image data by inputting the calculated weighted mean and weighted variance into a classifier that performs disease name inference, or as input features for similar case searches. Note that the above analysis example is merely one example, and the analysis function 356 can also perform weighted analysis using other image processing methods.

[0062] (Variation 1) In the embodiment described above, in step S102, imaging information of 3D chest X-ray CT image data is obtained from the DICOM header information to estimate the subject's position at the time of imaging, and the direction of gravity is identified based on the estimated position. However, the embodiment is not limited to this, and the position may be estimated and the direction of gravity identified by other methods. For example, the identification function 354 may estimate the subject's position at the time of imaging from a RIS (Radiology Information Systems) or electronic medical record, and identify the direction of gravity based on the estimated position.

[0063] Furthermore, the identification function 354 may also identify the direction of gravity by image analysis of medical image data. For example, the identification function 354 estimates the subject's position from the results of image analysis of medical image data and identifies the direction of gravity based on the estimated position. To give one example, the identification function 354 measures the diameter of the opening between the spine and posterior mediastinum, and the contact area between the mediastinum and the chest wall, etc., in 3D chest X-ray CT image data through image processing, and estimates the subject's position at the time of acquisition of the 3D chest X-ray CT image data based on the measured diameter of the opening and contact area, etc. Then, the identification function 354 identifies the direction of gravity based on the estimated position.

[0064] (Modification 2) In the embodiment described above, the case in step S104 where the first weight is set based on the direction of gravity and the extracted structure was explained. However, the embodiment is not limited thereto, and the first weight may be set in other ways. For example, the first setting function 355 calculates the angle at which the part corresponding to the pixel is supported by the structure based on the direction of gravity and the structure extracted from the medical image data, and sets the first weight for the pixel based on the calculated angle and the distance to the structure.

[0065] Figure 4 is a diagram illustrating an example of the first weight setting process according to Modification 2. Here, Figure 4 shows an enlarged view of one cross-sectional image data of an axial section in three-dimensional chest X-ray CT image data. The identification function 354 identifies the direction of gravity shown in Figure 4. The extraction function 353 extracts the lungs included in the three-dimensional chest X-ray CT image data and extracts the lung margins 510 based on the extracted lungs.

[0066] For example, the first setting function 355 extracts an approximated edge 512 obtained by curve-approximating the lung edge 510. Then, the first setting function 355 identifies a pixel j whose edge is tangent to the approximated edge 512, and calculates the angle "θ" between the tangent at the identified pixel j and the direction of gravity. j The calculation is performed, where "0≦θ" is calculated. j Let's assume "≤π / 2".

[0067] For example, the first setting function 355 sets the angle between the tangent line 514 to the approximate edge 512 and the direction of gravity in the pixel 530 shown in Figure 4 as "θ". 530 The first setting function 355 calculates "θ = 0". In addition, the first setting function 355 sets the angle between the tangent line 516 to the approximate edge 512 and the direction of gravity in the pixel 535 to "θ 535 This is how it is calculated.

[0068] The first setting function 355 sets the first weight by determining the Euclidean distance "l" from the pixel i to each pixel j that is in contact with the edge. 1j (i) and θ j The smallest value calculated from this is set as the first weight "w1(i)". For example, the first setting function 355 sets the first weight for each pixel based on the following equation (2).

[0069]

number

[0070] Here, in equation (2), "min j The (·) indicates the value for the pixel j in which the expression in parentheses is smallest among the pixels j that the edges touch. In equation (2), the Euclidean distance "l1j (i) is added with |sinθ j |, and for θ j >0, if so, |sinθ j |>0. Therefore, for pixels other than those having a tangent perpendicular to the gravitational direction, a positive value is assigned to the distance and the value increases, and the first weight "w1(i)" increases. As described above, the smaller the first weight, the more the influence of the gravitational effect is considered. That is, Equation (2) is an equation considering that the first weight increases because the gravity is dispersed at locations not perpendicular to the gravitational direction.

[0071] Note that the first weight is not limited to the above example, and various other weights may be set. For example, the first setting function 355 can also set a weight smaller than "1" uniformly for pixels whose distance from the structure is less than the threshold value.

[0072] (Modified Example 3) In the above-described embodiment, in step S105, the case where image processing is performed as the analysis process has been described. However, the embodiment is not limited to this, and for example, the analysis by a learning device may be performed. In such a case, for example, the analysis function 356 generates weight image data based on the first weight, and analyzes the medical image data based on the weight image data.

[0073] FIG. 5 is a diagram for explaining an example of the analysis process according to Modified Example 3. For example, as shown in FIG. 5, the analysis function 356 generates weight image data "W(I k )" 610 with the first weight as the pixel value based on the first weight set for each pixel of the medical image data "I k )". Then, the analysis function 356 inputs the medical image data "I k " 600 and the weight image data "W(I k )" 610 to a learning device by deep learning, and outputs a final analysis result through a plurality of convolutional layers. Here, the learning device shown in FIG. 5 is, for example, the medical image data "I k " 600 and the weight image data "W(I kThis learning device takes 610 as input and outputs whether or not the disease is present. The learning device shown in Figure 5 is pre-generated and stored in the memory circuit 34.

[0074] As described above, according to the first embodiment, the acquisition function 352 acquires medical image data to be analyzed. The identification function 354 identifies the direction of gravity relative to the medical image data. The first setting function 355 sets a first weight for each pixel constituting the medical image data based on the direction of gravity. The analysis function 356 performs analysis of the medical image data based on the first weight. Therefore, the medical image processing apparatus 3 according to the first embodiment can perform analysis that takes into account the occurrence of gravity effects, enabling appropriate analysis of medical image data.

[0075] Furthermore, according to the first embodiment, the extraction function 353 extracts at least one structure of the subject from the medical image data. The first setting function 355 sets a first weight based on the direction of gravity and at least one structure. Therefore, the medical image processing apparatus 3 according to the first embodiment can set a first weight in the medical image data for areas where gravity effects are likely to occur, enabling more appropriate analysis of the medical image data.

[0076] Furthermore, according to the first embodiment, the identification function 354 estimates the subject's position from the imaging information of the medical image data and identifies the direction of gravity based on the estimated position. Therefore, the medical image processing device 3 according to the first embodiment makes it possible to easily identify the direction of gravity in medical image data.

[0077] Furthermore, according to the first embodiment, the identification function 354 estimates the subject's body position from the results of image analysis of medical image data and identifies the direction of gravity based on the estimated body position. Therefore, the medical image processing device 3 according to the first embodiment makes it possible to identify the direction of gravity from an image.

[0078] Furthermore, according to the first embodiment, the first setting function 355 sets a first weight for each pixel based on the direction of gravity and the distance from the edge of the structure extracted from the medical image data. Therefore, the medical image processing device 3 according to the first embodiment makes it possible to set a first weight according to the ease with which a load is applied.

[0079] Furthermore, according to the first embodiment, the first setting function 355 calculates the angle at which the part corresponding to the pixel is supported by the structure based on the direction of gravity and the structure extracted from the medical image data, and sets a first weight for the pixel based on the calculated angle and the distance to the structure. Therefore, the medical image processing device 3 according to the first embodiment makes it possible to set a first weight that better reflects the ease with which a load is applied.

[0080] Furthermore, according to the first embodiment, the analysis function 356 generates weighted image data based on the first weight and performs analysis of medical image data based on the weighted image data. Therefore, the medical image processing device 3 according to the first embodiment makes it possible to perform analysis easily.

[0081] (Second embodiment) In the first embodiment described above, the case in which a first weight is set for the entire medical image data was explained. In the second embodiment, the case in which it is determined whether there is a shadow in the medical image data that suggests a gravity effect, and if it is determined that there is, the first weight is set only for the pixels in the region corresponding to the shadow that suggests a gravity effect. In other words, it is determined whether a gravity effect can occur in at least one pixel of the medical image data, and if it is determined that it can occur, the first weight is set for the location (at least one pixel) where a gravity effect can occur. In the following, as in the first embodiment, the image data to be analyzed will be 3D chest X-ray CT image data, and the lungs will be extracted as the structure. Of course, the subjects are not limited to these, and each is merely an example to explain the process of the medical image processing device.

[0082] Figure 6 shows an example configuration of a medical image processing apparatus according to the second embodiment. In Figure 6, the same reference numerals are used to indicate components that operate similarly to those in the medical image processing apparatus 3 according to the first embodiment shown in Figure 1. That is, the medical image processing apparatus 3a according to the second embodiment differs from the medical image processing apparatus 3 according to the first embodiment in that the processing circuit 35a newly executes a determination function 357, and the processing content of the first setting function 355a executed by the processing circuit 35a is different. These differences will be explained below.

[0083] Figure 7 is a flowchart showing the processing procedure performed by each processing function of the processing circuit 35a of the medical image processing apparatus 3a according to the second embodiment.

[0084] Steps S201 to S203 in Figure 7 are implemented by the processing circuit 35a reading and executing the program corresponding to each processing function from the storage circuit 34, similar to steps S101 to S103 in Figure 2.

[0085] For example, in this embodiment, as shown in Figure 7, when the extraction function 353 extracts a structure (step S203), the determination function 357 determines whether or not a gravity effect is occurring in the medical image data (step S204). This process is realized, for example, by the processing circuit 35a calling and executing a program corresponding to the determination function 357 from the storage circuit 34.

[0086] Next, the first setting function 355a sets a first weight for the pixels in which the gravitational effect is determined to be occurring (step S205). This process is realized, for example, by the processing circuit 35a calling and executing a program corresponding to the first setting function 355a from the storage circuit 34.

[0087] Step S206 in Figure 7 is realized, similar to step S105 in Figure 2, by the processing circuit 35a calling and executing a program corresponding to the analysis function 356 from the storage circuit 34.

[0088] The details of each process performed by the medical image processing device 3a are described below.

[0089] (Gravity effect detection process) As explained in step S204 of Figure 7, the determination function 357 determines whether or not a gravity effect is occurring in the three-dimensional chest X-ray CT image data acquired by the acquisition function 352. Specifically, the determination function 357 determines whether or not a gravity effect may occur in at least one pixel of the three-dimensional chest X-ray CT image data.

[0090] For example, the determination function 357 determines whether there is a shadow suggesting a gravity effect based on the three-dimensional chest X-ray CT image data, the direction of gravity identified from the subject's position, and the structure of the subject. In this embodiment, the edge in the direction indicated by the gravity vector is determined by the method described in the first embodiment, and the presence of a shadow suggesting a gravity effect is determined based on the CT value of a pixel at a certain distance from the determined edge. That is, the determination function 357 determines whether a gravity effect can occur in at least one pixel of the three-dimensional chest X-ray CT image data based on the results of image analysis of the medical image data.

[0091] Figure 8 is a diagram illustrating an example of the determination process according to the second embodiment. Here, Figure 8 shows one cross-sectional image data 700 of an axial section in three-dimensional chest X-ray CT image data. The identification function 354 identifies the direction of gravity shown in Figure 8. The extraction function 353 extracts the lungs included in the three-dimensional chest X-ray CT image data and extracts the lung margins 710 based on the extracted lungs.

[0092] For example, the judgment function 357 first determines a reference edge 720 in the lung margin 710 that is approximately perpendicular to the direction of gravity and is located in the direction indicated by the arrow in the direction of gravity. Then, the judgment function 357 determines a threshold distance "l" from the reference edge 720 in the direction of gravity. th The threshold line 760 is set at the position of "". Note that in Figure 8, the threshold distance "l thThe example shows the case where "" is 4 pixels, but the threshold distance "l th The threshold distance "l" can be set arbitrarily. For example, depending on the body type of the subject or the biological organ to be analyzed, the threshold distance "l" can be set arbitrarily. th It is also acceptable to change the threshold distance "l" at which the user operates the input interface 32. th You can also change this manually.

[0093] As shown in Figure 8, when a threshold line 760 is set, the judgment function 357 determines whether there are shadows suggesting gravity effects for pixels inside the lung between the reference edge 720 and the threshold line 760. For example, the judgment function 357 determines that pixels inside the lung between the reference edge 720 and the threshold line 760 that have a CT value range higher than a predetermined range are pixels corresponding to shadows suggesting gravity effects.

[0094] Here, the CT value range used for determination can be set arbitrarily. For example, the determination function 357 determines pixels in a CT value range (e.g., -800HU to -600HU) that are higher than a predetermined value (normal CT value in the lung (approximately -1000HU)) as pixels corresponding to shadows suggesting gravity effects. Alternatively, for example, the determination function 357 can also use the average value of the CT values ​​of pixels inside the lung other than those between the reference edge 720 and the threshold line 760 in the cross-sectional image data 700 as a reference value, and determine pixels in a CT value range higher than this reference value as pixels corresponding to shadows suggesting gravity effects.

[0095] The judgment function 357 can also change the CT value range used depending on the situation. For example, the judgment function 357 changes the CT value range used for judgment depending on the subject's body type and the respiratory phase (inspiration or expiration) in which the 3D chest X-ray CT image data was acquired.

[0096] As described above, the judgment function 357 targets pixels inside the lung between the reference edge 720 and the threshold line 760 and determines whether there are shadows suggesting the gravity effect, thereby identifying the region 770 shown in Figure 8 as the region corresponding to the shadow suggesting the gravity effect. It should be noted that the judgment processing by the judgment function 357 is not limited to the process described above; various other processes can be applied. For example, the judgment function 357 can determine locations where false images due to the gravity effect are likely to occur based on clinical knowledge, and then determine regions where false images are likely to occur based on the continuity of high-attenuation areas at those locations.

[0097] (First weight setting process) As explained in step S205 of Figure 7, the first setting function 355a sets a first weight for pixels included in region 770, which has been determined by the determination function 357 to be a region corresponding to shading that suggests a gravity effect. For example, the first setting function 355a uniformly sets "0.7" as the first weight for all pixels constituting region 770. Note that the setting of the first weight described above is merely an example, and it is possible to set the first weight in various other ways. For example, the first setting function 355a can also set "0" as the first weight for pixels in region 770 in order to not consider regions that suggest a gravity effect. Alternatively, the first setting function 355a can also set a first weight for each pixel within region 770 using the method described in the first embodiment.

[0098] (Variation 1) In the embodiment described above, a case was explained in which a shadow suggesting a gravity effect is determined in step S204 based on the CT value of a pixel at a certain distance from the reference edge. However, the embodiment is not limited to this, and the determination may also be made using a classifier that takes medical image data as input and determines whether it suggests a gravity effect. In such a case, the determination function 357 determines, based on the classifier, whether or not a gravity effect may occur in at least one pixel of the medical image data.

[0099] The classifier used for the determination may either determine whether or not each pixel suggests a gravitational effect, or it may extract regions where a gravitational effect is thought to be occurring. For example, a classifier trained to determine regions (pixels) where a gravitational effect is occurring when medical image data is input, using manually labeled medical image data as training images, could be used.

[0100] As described above, according to the second embodiment, the determination function 357 determines whether or not a gravity effect may occur in at least one pixel of the medical image data. The first setting function 355a sets a first weight for the pixel based on the determination result. Therefore, the medical image processing apparatus 3a according to the second embodiment sets the first weight only in areas where there is a high probability that a gravity effect is occurring, thereby enabling more appropriate analysis of medical image data.

[0101] Furthermore, according to the second embodiment, the determination function 357 determines whether or not a gravity effect can occur in at least one pixel of the medical image data, based on the results of image analysis of the medical image data. Therefore, the medical image processing apparatus 3a according to the second embodiment makes it possible to perform the determination process easily.

[0102] Furthermore, according to the second embodiment, the determination function 357 determines, based on the classifier, whether or not a gravity effect can occur in at least one pixel of the medical image data. Therefore, the medical image processing apparatus 3a according to the second embodiment makes it possible to perform the determination process easily.

[0103] (Third embodiment) The first and second embodiments described above describe the case in which analysis is performed using a first weight based on the direction of gravity. In the third embodiment, a second weight is set for parts of the medical image data that are considered important for analysis for reasons other than the effect of gravity, and the case in which analysis is performed using the first and second weights is described. In the following, as in the first embodiment, the image data to be analyzed will be 3D chest X-ray CT image data, and the lungs will be extracted as structures. Furthermore, the analysis will focus on disease estimation of the lungs, particularly analysis related to interstitial lung abnormalities.

[0104] Figure 9 shows an example configuration of a medical image processing apparatus according to the third embodiment. In Figure 9, the same reference numerals are used to indicate components that operate similarly to those in the medical image processing apparatus 3 according to the first embodiment shown in Figure 1. That is, the medical image processing apparatus 3b according to the third embodiment differs from the medical image processing apparatus 3 according to the first embodiment in that the processing circuit 35b newly executes a second setting function 358, and the processing content of the analysis function 356b executed by the processing circuit 35b. These differences will be explained below.

[0105] Figure 10 is a flowchart showing the processing procedure performed by each processing function of the processing circuit 35b of the medical image processing apparatus 3b according to the third embodiment.

[0106] Steps S301 to S304 in Figure 10 are implemented by the processing circuit 35b reading and executing the program corresponding to each processing function from the storage circuit 34, similar to steps S101 to S104 in Figure 2.

[0107] For example, in this embodiment, as shown in Figure 10, when the first setting function 355 sets the first weight (step S304), the second setting function 358 sets the second weight for the pixels of the medical image data based on the structure of the subject extracted from the medical image data (step S305). This process is realized, for example, by the processing circuit 35b calling and executing a program corresponding to the second setting function 358 from the storage circuit 34.

[0108] Next, the analysis function 356b performs an analysis of the medical image data based on the first and second weights set for the medical image data (step S306). This process is achieved, for example, by the processing circuit 35b calling and executing a program corresponding to the analysis function 356b from the storage circuit 34.

[0109] The details of each process performed by the medical image processing device 3b are described below.

[0110] (Second weight setting process) As explained in step S305 of Figure 10, the second setting function 358 sets a second weight for the pixels of the 3D chest X-ray CT image data based on the lungs extracted from the 3D chest X-ray CT image data. Here, the second weight is set according to the purpose of the analysis. For example, in the case of interstitial lung disease, as in this embodiment, the second setting function 358 sets the second weight according to the distance from the chest wall, based on prior knowledge that information near the chest wall is important.

[0111] Figures 11A and 11B illustrate an example of the second weight setting process according to the third embodiment. Here, Figure 11A shows one cross-sectional image data 800 of an axial section in three-dimensional chest X-ray CT image data. Figure 11B shows an enlarged view of a part of Figure 11A. The identification function 354 identifies the direction of gravity shown in Figure 11A. The extraction function 353 extracts the lungs included in the three-dimensional chest X-ray CT image data and extracts the lung margins 810 based on the extracted lungs. The first setting function 355 determines the reference margin 820 based on the direction of gravity and the lung margins 810.

[0112] For example, the second setting function 358 assumes that a chest wall exists outside the extracted lung and sets a second weight for each pixel based on the distance from the edge of the extracted lung. For example, the second setting function 358 sets a second weight for each pixel based on the following equation (3).

[0113]

number

[0114] Here, in equation (3), "w2(i)" represents the second weight of pixel i. "l2(i)" represents the shortest distance (in terms of pixel count) from the edge of the lung to the pixel in question. "min(l2(i),4)" represents a function that takes a smaller value between "l2(i)" and "4".

[0115] For example, the second setting function 358 sets the second weight "w2=2-0.25×0=2" by inputting "l2=0" into equation (3) above for pixels 830 and 880 that are in contact with the lung margin 810 in Figure 11A. The second setting function 358 also first calculates the shortest distance to the lung margin 810, "l2=√2", for pixel 840, as shown in Figure 11B. Then, the second setting function 358 inputs "l2=√2" into equation (3) above for setting the second weight "w2=2-0.25×√2=1.7". Furthermore, the second setting function 358 sets the second weight "w2=2-0.25×4=1" for pixel 850, for which the shortest distance to the lung margin 810 is greater than "4".

[0116] In other words, equation (3) shows that when the distance to the lung margin is less than the threshold (4 in this example), the shorter the distance from the lung margin, the larger the second weight becomes. This equation takes into account the prior knowledge mentioned above. Of course, this method of setting the weight is just one example, and the second weight may be set by other methods. For example, using the prior knowledge that the margin in the mediastinal direction (for example, the direction closer to the heart and liver) is not given much weight, the distance to the lung margin in the mediastinal direction may be ignored (set to infinity).

[0117] (Analysis process) As explained in step S306 of Figure 10, the analysis function 356b performs analysis processing on the 3D chest X-ray CT image data using the first weight set for each pixel by the first setting function 355 and the second weight set by the second setting function 358. For example, the analysis function 356b performs the same analysis as in the first embodiment based on a weight obtained by linearly combining the first weight and the second weight. Here, the analysis function 356b combines the weights using, for example, the following equation (4).

[0118]

number

[0119] Here, in equation (4), "w(i)" represents the combined weight and "α" represents the coefficient. For example, increasing "α" will result in a weight that emphasizes the first weight "w1(i)", while decreasing it will result in a weight that emphasizes the second weight "w2(i)". In this embodiment, "α = 0.5". That is, the first weight and the second weight are treated similarly.

[0120] For example, taking the pixels in Figure 11A as an example, the analysis function 356b calculates the weight "w=1.3" for pixel 830 by substituting the first weight "w1=0.5" and the second weight "w2=2.0" into equation (4). Similarly, the analysis function 356b calculates the weight "w=1.2" for pixel 840 by substituting the first weight "w1=0.7" and the second weight "w2=1.7" into equation (4).

[0121] Furthermore, for pixel 850, the analysis function 356b calculates the weight "w=1.0" by substituting the first weight "w1=1.0" and the second weight "w2=1.0" into equation (4). Then, for pixel 880, the analysis function 356b calculates the weight "w=1.5" by substituting the first weight "w1=1.0" and the second weight "w2=2.0" into equation (4).

[0122] Comparing the calculated weights, we find that, based on prior knowledge, pixel 830 ("w=1.3"), which is considered important as it is closest to the chest wall, and pixel 880 ("w=1.5"), have a lower weight because pixel 830 is more likely to experience the gravitational effect. In other words, according to equation (4), even for pixels closest to the chest wall, weights are set that take into account the influence of the gravitational effect.

[0123] Furthermore, the combination of the first and second weights is not limited to the method given by equation (4) above; other methods may also be used. For example, the weights may be combined using linear products, nonlinear sums, or nonlinear products. Alternatively, the system may be configured to learn appropriate coefficients through machine learning.

[0124] As described above, once the weights are calculated, the analysis function 356b performs analysis processing of medical image data based on the image processing described in the first embodiment.

[0125] (Variation 1) In the embodiment described above, the case in step S305 where a second weight is set based on prior knowledge corresponding to the object to be analyzed was explained. However, the embodiment is not limited to this, and the second weight may also be set based on motion artifacts. In such a case, for example, the extraction function 353 extracts structures such as the heart and diaphragm.

[0126] The second setting function 358 sets a second weight according to the distance from the extracted heart and diaphragm. In other words, based on prior knowledge that motion artifacts occur due to the beating of the heart and the up and down movement of the diaphragm, the second setting function 358 sets the second weight so that the closer the pixel is to the heart and diaphragm, the smaller the second weight. In other words, the second setting function 358 sets a second weight that becomes smaller for pixels that are more likely to have motion artifacts.

[0127] (Modification 2) In the embodiment described above, the case in which analysis using image processing is performed in step S306 was explained. However, the embodiment is not limited thereto, and analysis may be performed using a learning model, similar to the first embodiment. That is, the analysis function 356b generates weighted image data based on the first weight and the second weight, and performs analysis of medical image data based on said weighted image data. For example, the analysis function 356b generates synthesized weighted image data from the synthesized weights, and obtains the analysis result by using the medical image data (3D chest X-ray CT image data) and the synthesized weighted image data as input to the learning model.

[0128] Furthermore, the weight image data based on the first and second weights is not limited to the composite weight image data described above. For example, it may be possible to generate first weight image data and second weight image data for each of the first and second weights, and then perform deep learning using medical image data, the first weight image data, and the second weight image data as input. In this case, there is the advantage that it is not necessary to determine the coefficients for the composite weights.

[0129] As described above, according to the third embodiment, the second setting function 358 sets a second weight for each pixel of the medical image data based on structures extracted from the medical image data. The analysis function 356b performs analysis of the medical image data based on the first weight and the second weight. Therefore, the medical image processing apparatus 3b according to the third embodiment can perform analysis that takes into account both gravity effects and prior knowledge, enabling more appropriate analysis of medical image data.

[0130] Furthermore, according to the third embodiment, the second setting function 358 sets a second weight for the pixel based on the distance from the edge of the structure. Therefore, the medical image processing apparatus 3b according to the third embodiment makes it possible to set a second weight according to the purpose of analysis.

[0131] Furthermore, according to the third embodiment, the analysis function 356b generates weighted image data based on the first weight and the second weight, and performs analysis of medical image data based on said weighted image data. Therefore, the medical image processing apparatus 3b according to the third embodiment makes it possible to easily perform analysis using the first weight and the second weight.

[0132] (Other embodiments)

[0133] The above-described embodiment explains the case in which three-dimensional chest X-ray CT image data is used as the medical image data to be analyzed. However, the embodiment is not limited to this, and medical image data acquired by other modalities or medical image data targeting other body parts may also be used as the subject of analysis.

[0134] Furthermore, the above-described embodiment explained the case in which three-dimensional chest X-ray CT image data is used as the medical image data to be analyzed. However, the embodiment is not limited to this, and for example, sinograms may be used as the medical image data to be analyzed.

[0135] Furthermore, the above-described embodiment described the case in which CT image data acquired by an X-ray CT device imaging a subject in a lying position was used. However, the embodiment is not limited to this, and for example, the embodiment may also describe the case in which CT image data acquired by an X-ray CT device imaging a subject in an upright position was used. In such a case, the direction in which gravity is affected is the downward direction in the Z-axis direction in the sagittal or coronal section.

[0136] In the embodiments described above, the case of displaying the analysis results was explained, but various display formats for the analysis results can be implemented. For example, the analysis function 356 performs an analysis that considers the effect of gravity and an analysis that does not consider the effect of gravity. The control function 351 may display each analysis result separately. In addition, the control function 351 may be controlled to notify the user if the analysis results from the analysis that considers the effect of gravity and the analysis results from the analysis that does not consider the effect of gravity are different.

[0137] In the embodiments described above, examples were given in which the acquisition unit, extraction unit, identification unit, first setting unit, analysis unit, determination unit, and second setting unit in this specification are implemented by the acquisition function, extraction function, identification function, first setting function, analysis function, determination function, and second setting function of the processing circuit, respectively. However, the embodiments are not limited to these. For example, the acquisition unit, extraction unit, identification unit, first setting unit, analysis unit, determination unit, and second setting unit in this specification may be implemented not only by the acquisition function, extraction function, identification function, first setting function, analysis function, determination function, and second setting function described in the embodiments, but also by hardware only, software only, or a combination of hardware and software.

[0138] Furthermore, the term "processor" used in the above-described embodiment refers to circuits such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an Application Specific Integrated Circuit (ASIC), or a programmable logic device (e.g., a Simple Programmable Logic Device (SPLD), a Complex Programmable Logic Device (CPLD), and a Field Programmable Gate Array (FPGA)). Here, instead of storing the program in a memory circuit, the processor may be configured to directly incorporate the program into its circuitry. In this case, the processor realizes its function by reading and executing the program incorporated into the circuitry. Moreover, each processor in this embodiment is not limited to being configured as a single circuit; multiple independent circuits may be combined to form a single processor, and its function may be realized in this way.

[0139] Here, the medical image processing program executed by the processor is provided pre-installed in ROM (Read Only Memory) or memory circuits. Alternatively, this medical image processing program may be provided as a file in an installable or executable format on a computer-readable, non-transient storage medium such as a CD (Compact Disk)-ROM, FD (Flexible Disk), CD-R (Recordable), or DVD (Digital Versatile Disk). Furthermore, this medical image processing program may be stored on a computer connected to a network such as the Internet and provided or distributed by downloading it via the network. For example, this medical image processing program consists of modules containing the processing functions described above. In actual hardware, the CPU reads the medical image processing program from a storage medium such as ROM and executes it, loading each module onto the main memory and generating it in the main memory.

[0140] Furthermore, in the embodiments and modifications described above, each component of each illustrated device is a functional concept and does not necessarily have to be physically configured as shown. In other words, the specific form of distribution or integration of each device is not limited to that shown, and all or part of them can be functionally or physically distributed or integrated in any unit according to various loads and usage conditions. Moreover, each processing function performed by each device can be realized in whole or in any part by a CPU and a program that is analyzed and executed by the CPU, or by hardware using wired logic.

[0141] Furthermore, among the processes described in the embodiments and modifications described above, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by known methods. In addition, the processing procedures, control procedures, specific names, and information including various data and parameters shown in the above document and drawings can be arbitrarily changed unless otherwise specified.

[0142] According to at least one embodiment described above, even when analyzing medical image data that is highly likely to be forged due to gravity effects, appropriate analysis can be performed.

[0143] 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 carried out in a variety of other forms, and various omissions, substitutions, and modifications can be made 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]

[0144] 3, 3a, 3b Medical image processing equipment 35, 35a, 35b Processing circuits 351 Control Functions 352 Acquisition function 353 Extraction function 354 Identification function 355, 355a First setting function 356, 356b analysis function 357 Judgment function 358 Second setting function

Claims

1. An acquisition unit that acquires medical image data including the area to be analyzed, An identification unit that estimates the subject's body position from the results of image analysis of the medical image data, and identifies the direction of gravity relative to the medical image data based on the estimated body position, A first setting unit sets a first weight for the pixels constituting the area in the medical image data based on the gravity direction, An analysis unit that performs analysis of the medical image data based on the first weight, Equipped with, The first setting unit sets the first weight for the pixel based on the distance between the pixel and the boundary surrounding the part and indicating the edge of the part, and the direction of gravity.

2. The medical image processing apparatus according to claim 1, further comprising an extraction unit for extracting at least one of the subject's body parts from the medical image data.

3. The medical image processing apparatus according to claim 1 or 2, wherein the identification unit estimates the position of the subject from the imaging information of the medical image data and identifies the direction of gravity based on the estimated position.

4. The system further includes a determination unit that determines whether or not a gravity effect may be occurring in at least one pixel of the medical image data. The medical image processing apparatus according to any one of claims 1 to 3, wherein the first setting unit sets the first weight for pixels that the determination unit has determined may be experiencing a gravity effect.

5. The medical image processing apparatus according to claim 4, wherein the determination unit determines, based on the results of image analysis of the medical image data, whether or not a gravity effect may be occurring in at least one pixel of the medical image data.

6. The medical image processing apparatus according to claim 4, wherein the determination unit determines, based on the classifier, whether or not a gravity effect may be occurring in at least one pixel of the medical image data.

7. The medical image processing apparatus according to any one of claims 1 to 6, wherein the first setting unit sets the first weight for the pixel based on the angle formed between the tangent to the boundary and the direction of gravity at each position of the boundary, and the distance between the pixel and each position of the boundary.

8. The system further includes a second setting unit that sets a second weight for each pixel of the medical image data based on the region extracted from the medical image data. The medical image processing apparatus according to any one of claims 1 to 7, wherein the analysis unit performs analysis of the medical image data based on the first weight and the second weight.

9. The medical image processing apparatus according to claim 8, wherein the second setting unit sets the second weight for the pixel based on the distance between the pixel and the boundary that surrounds the part extracted from the medical image data and indicates the edge of the part.

10. The medical image processing apparatus according to any one of claims 1 to 7, wherein the analysis unit generates weighted image data based on the first weight and performs analysis of the medical image data based on the weighted image data.

11. The medical image processing apparatus according to claim 8 or 9, wherein the analysis unit generates weighted image data based on the first weight and the second weight, and performs analysis of the medical image data based on the weighted image data.

12. A medical image processing method performed by a processor, The steps include acquiring medical image data including the area to be analyzed, The steps include: estimating the subject's body position from the results of image analysis of the medical image data, and identifying the direction of gravity relative to the medical image data based on the estimated body position; A step of setting a first weight for the pixels constituting the region in the medical image data based on the gravity direction, The steps include: performing analysis of the medical image data based on the first weight described above; Includes, A medical image processing method comprising the step of setting the first weight, which includes setting the first weight for the pixel based on the distance between the pixel and a boundary that surrounds the part and indicates the edge of the part, and the direction of gravity.

13. A function to acquire medical image data including the area to be analyzed, An identification function that estimates the subject's body position from the results of image analysis of the aforementioned medical image data, and identifies the direction of gravity relative to the aforementioned medical image data based on the estimated body position, A setting function that sets a first weight for the pixels constituting the area in the medical image data based on the gravity direction, An analysis function that performs analysis of the medical image data based on the first weight described above, Have the computer run it, The setting function is a medical image processing program that sets the first weight for the pixel based on the distance between the pixel and the boundary surrounding the part and indicating the edge of the part, and the direction of gravity.

14. An acquisition unit that acquires medical image data to be analyzed, An identification unit that estimates the subject's body position from the results of image analysis of the medical image data, and identifies the direction of gravity relative to the medical image data based on the estimated body position, A first setting unit sets a first weight for the pixels constituting the medical image data based on the gravity direction, An analysis unit that performs analysis of the medical image data based on the first weight, A medical image processing device equipped with [a specific feature].

15. A medical image processing method performed by a processor, The steps include acquiring medical image data to be analyzed, The steps include: estimating the subject's body position from the results of image analysis of the medical image data, and identifying the direction of gravity relative to the medical image data based on the estimated body position; A step of setting a first weight for the pixels constituting the medical image data based on the gravity direction, The steps include: performing analysis of the medical image data based on the first weight described above; A medical image processing method, including [the specified term].

16. The system includes an acquisition function to obtain medical image data to be analyzed, and An identification function that estimates the subject's body position from the results of image analysis of the aforementioned medical image data, and identifies the direction of gravity relative to the aforementioned medical image data based on the estimated body position, A setting function that sets a first weight for the pixels constituting the medical image data based on the gravity direction, An analysis function that performs analysis of the medical image data based on the first weight described above, A medical image processing program that causes a computer to perform certain actions.

Images