Image processing apparatus, method, program, and storage medium

Abstract

To highly accurately extract a columnar region from a medical image even when there is a deficit in the columnar region.SOLUTION: An image processing device according to an embodiment comprises: an acquisition unit; a positioning unit; an extraction unit; and a collection arithmetic unit. The acquisition unit acquires a first medical image and a second medical image collected from a subject. The positioning unit executes positioning processing of positioning the second medical image relative to the first medical image. The extraction unit extracts a first columnar region from the first medical image and extracts a second columnar region from the second medical image after the positioning processing. The collection arithmetic unit executes collection arithmetic of the first columnar region and the second columnar region to output the columnar region subjected to arithmetic.SELECTED DRAWING: Figure 1

Description

Technical Field

[0004] , ,

[0001] The embodiments disclosed in this specification and the drawings relate to an image processing apparatus, method, program, and storage medium.

Background Art

[0002] In order to grasp the risk of bone-related events in bone metastasis, a technique for visualizing the intraspinal canal invasion of a tumor and measuring the degree of invasion is required. For this purpose, it is necessary to extract the correct intraspinal canal region from a medical image, visualize the invasion based on it, and measure the degree of invasion.

[0003] When visualizing the temporal change of invasion, image registration between the current image and the past image may be performed within the intraspinal canal region, and a difference image obtained by subtracting the pixel value of the past image from the pixel value of the current image may be used. Also, when measuring the degree of invasion, the occupancy rate of the invasion region within the intraspinal canal region may be used.​​​​​​​​​​​​​​​​​​​​​​

[0006] One of the problems that the embodiments disclosed herein and in the drawings aim to solve is to extract columnar regions from medical images with high accuracy, even when there are defects in the columnar regions. 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]

[0007] The image processing apparatus according to the embodiment comprises an acquisition unit, a alignment unit, an extraction unit, and a set calculation unit. The acquisition unit acquires a first medical image and a second medical image collected from a subject. The alignment unit performs an alignment process to align the position of the second medical image with that of the first medical image. The extraction unit extracts a first columnar region from the first medical image and a second columnar region from the second medical image after the alignment process. The set calculation unit performs a set calculation on the first columnar region and the second columnar region and outputs the calculated columnar region. [Brief explanation of the drawing]

[0008] [Figure 1] Figure 1 shows an example of the configuration of an image processing apparatus according to the first embodiment. [Figure 2] Figure 2 is a flowchart showing the entire process of the image processing apparatus according to the first embodiment. [Figure 3] Figure 3 is a diagram illustrating an example of the columnar region extraction process according to the first embodiment. [Figure 4A] Figure 4A shows an example of a set operation according to the first embodiment. [Figure 4B] Figure 4B shows an example of a set operation according to the first embodiment. [Figure 4C] Figure 4C shows an example of a set operation according to the first embodiment. [Figure 5]Figure 5 is a flowchart showing the entire process of the image processing apparatus according to Modification 1. [Figure 6] Figure 6 is a diagram illustrating an example of the alignment and extraction processes related to Modification Example 1. [Figure 7] Figure 7 is a flowchart showing the entire process of the image processing apparatus according to the second embodiment. [Modes for carrying out the invention]

[0009] The following describes in detail embodiments of the image processing apparatus, method, program, and storage medium with reference to the drawings. However, the image processing apparatus, method, program, and storage medium according to this application are not limited to the embodiments described below.

[0010] (First Embodiment) In this embodiment, past images are deformed and aligned to match the current image, and a calculated columnar region is obtained by performing a set operation between the columnar region of the deformed and aligned past image and the columnar region of the current image. In particular, by using an AND operation as the set operation, it is possible to obtain a columnar region that is close to the original shape of the spinal canal. Furthermore, a derived image of the input image is obtained using the obtained calculated columnar region. In particular, by using a difference operation between corresponding pixels, it is possible to obtain a difference image between the current image and the past image after deformation and alignment within the spinal canal region.

[0011] Figure 1 shows an example of the configuration of an image processing device 10 according to the first embodiment. As shown in Figure 1, the image processing device 10 includes a processing circuit 11, a communication interface 12, a storage circuit 13, a display 14, an input interface 15, and a connection unit 16. The image processing device 10 is also connected to medical imaging diagnostic equipment (modalities), medical image storage equipment, and various departmental systems via a network (not shown).

[0012] Medical imaging diagnostic equipment includes X-ray CT (Computed Tomography) devices, Magnetic Resonance Imaging (MRI) devices, and X-ray diagnostic devices. Medical image storage systems are implemented using PACS (Picture Archiving and Communication System), etc., and store medical images in a format compliant with DICOM (Digital Imaging and Communications in Medicine). Departmental systems include various systems such as Hospital Information Systems (HIS), Radiology Information Systems (RIS), Diagnostic Reporting Systems, and Laboratory Information Systems (LIS).

[0013] The processing circuit 11 controls the image processing device 10 by executing a control function 11a, a positioning function 11b, an extraction function 11c, a set calculation function 11d, and an image generation function 11e in response to input operations received from the user via the input interface 15. Here, the control function 11a is an example of an acquisition function. The positioning function 11b is an example of a positioning unit. The extraction function 11c is an example of an extraction unit. The set calculation function 11d is an example of a set calculation unit. The image generation function 11e is an example of an image generation unit.

[0014] The control function 11a controls to generate various GUIs (Graphical User Interfaces) and various display information according to operations via the input interface 15 and display them on the display 14. Also, the control function 11a controls the transmission and reception of information with devices and systems on a network (not shown) via the communication interface 12. Specifically, the control function 11a acquires three-dimensional medical images (volume data) from modalities connected to the network, medical image storage devices, etc. Further, the control function 11a acquires information regarding the subject from each department system connected to the network. Also, the control function 11a outputs the processing results to devices and systems on the network.

[0015] For example, the control function 11a acquires the first medical image and the second medical image collected from the subject. To give an example, as the second medical image, the control function 11a acquires a medical image collected from the subject earlier than the first medical image. The processing by the control function 11a will be described in detail later.

[0016] The alignment function 11b executes alignment processing on the three-dimensional medical image acquired by the control function 11a. Specifically, the alignment function 11b executes alignment processing to align the position of the second medical image with respect to the first medical image. The processing by the alignment function 11b will be described in detail later.

[0017] The extraction function 11c executes extraction processing of columnar regions on the three-dimensional medical image acquired by the control function 11a. Specifically, the extraction function 11c extracts the first columnar region from the first medical image and extracts the second columnar region from the second medical image. For example, the extraction function 11c extracts the first columnar region from the first medical image and extracts the second columnar region from the second medical image after the alignment processing. The processing by the extraction function 11c will be described in detail later.

[0018] The set operation function 11d performs a set operation on the columnar regions extracted by the extraction function 11c to obtain the processed columnar regions. Specifically, the set operation function 11d performs a set operation on the first columnar region and the second columnar region and outputs the processed columnar regions. The processing by the set operation function 11d will be described in detail later.

[0019] The image generation function 11e generates a derived image using the processed columnar regions. Specifically, the image generation function 11e generates a derived image based on the first medical image using the processed columnar regions. For example, the image generation function 11e generates a derived image using the processed columnar regions from the first medical image and the second medical image. As an example, the image generation function 11e identifies the regions corresponding to the processed columnar regions in the first medical image and the second medical image respectively, and generates a derived image by performing a difference process between the first medical image and the second medical image on the identified regions. The processing by the image generation function 11e will be described in detail later.

[0020] The above-described processing circuit 11 is realized by, for example, a processor. In that case, each of the above-described processing functions is stored in the storage circuit 13 in the form of a program executable by a computer. Then, the processing circuit 11 reads and executes each program stored in the storage circuit 13 to realize the functions corresponding to each program. In other words, the processing circuit 11 has each of the processing functions shown in FIG. 1 when each program is read out.

[0021] The processing circuit 11 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 11 may be implemented by appropriately distributing or integrating them across one or more processing circuits. Also, each processing function of the processing circuit 11 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 13, 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 11 may read and execute each program from each memory circuit.

[0022] The communication interface 12 controls the transmission and communication of various data sent and received between the image processing device 10 and other devices and systems connected via the network. Specifically, the communication interface 12 is connected to the processing circuit 11 and outputs data received from other devices and systems to the processing circuit 11, or transmits data output from the processing circuit 11 to other devices and systems. For example, the communication interface 12 can be implemented by a network card, network adapter, NIC (Network Interface Controller), etc.

[0023] The memory circuit 13 stores various data and programs. Specifically, the memory circuit 13 is connected to the processing circuit 11 and stores data input from the processing circuit 11, or reads stored data and outputs it to the processing circuit 11. For example, the memory circuit 13 can be implemented using semiconductor memory elements such as RAM (Random Access Memory) or flash memory, or a hard disk or optical disc.

[0024] The display 14 displays various information and data. Specifically, the display 314 is connected to the processing circuit 11 and displays various information and data output from the processing circuit 11. For example, the display 14 can be implemented using a liquid crystal display, a CRT (Cathode Ray Tube) display, an organic EL display, a plasma display, a touch panel, etc.

[0025] The input interface 15 receives various instructions and information input operations from the user. Specifically, the input interface 15 is connected to the processing circuit 11 and converts the input operations received from the user into electrical signals and outputs them to the processing circuit 11. For example, the input interface 15 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 15 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 outputs these electrical signals to a control circuit is also included as an example of the input interface 15.

[0026] The connection section 16 is a bus or the like that connects the processing circuit 11, the communication interface 12, the memory circuit 13, the display 14, and the input interface 15.

[0027] The overall configuration of the image processing device 10 has been described above. With this configuration, the image processing device 10 can extract columnar regions from medical images with high accuracy, even when there are defects in the columnar regions. As mentioned above, techniques for extracting columnar regions such as the spinal canal are known. However, in the extraction of the spinal canal region, the shape of the columnar region, which is the spinal canal region, can be greatly distorted due to osteolytic bone metastases, etc., so high-precision extraction of the columnar region may not be possible with image processing on a single medical image, as in the above techniques. Therefore, the image processing device 10 according to this embodiment is configured to extract columnar regions from medical images with high accuracy, even when there are defects in a part of the columnar region due to osteolytic bone metastases, for example. The details of the image processing device 10 will be described below.

[0028] Figure 2 is a flowchart showing the entire process of the image processing device 10 according to the first embodiment. The image processing device 10 takes a grayscale medical image as input and outputs a region image representing a low-density columnar region surrounded by a high-density region that is the target of extraction. The image processing device 10 also outputs a derived image of the input image (grayscale medical image) using the obtained columnar region. Here, both the grayscale medical image and the region image are three-dimensional volume data. In this embodiment, the grayscale medical image is an X-ray CT image, the high-density region is the vertebral region constituting the spine, and the low-density columnar region represents the spinal cord region within the spinal canal. In this explanation, the spinal cord region within the spinal canal is referred to as the spinal canal region. The region image is a binary image in which the pixel values ​​within the region are 1 and the pixel values ​​outside the region are 0.

[0029] For example, as shown in Figure 2, in this embodiment, the control function 11a acquires the most recent X-ray CT image of a subject as the first image, the current image I1 (step S101). Next, the control function 11a acquires the X-ray CT image collected in the previous scan of the same subject as the second image, the past image I2 (step S102). This process is realized, for example, by the processing circuit 11 calling and executing a program corresponding to the control function 11a from the storage circuit 13.

[0030] Next, the alignment function 11b calculates (estimates) a correspondence relationship V between the positions of each pixel in the current image I1 and each pixel in the past image I2 (step S103), and based on the correspondence relationship V, it deforms the past image I2 so that each pixel in the past image I2 matches the corresponding pixel in the current image I1 (step S104). Hereafter, the result of this deformation of the past image I2 will be referred to as past image I2'. This process is realized, for example, by the processing circuit 11 calling and executing a program corresponding to the alignment function 11b from the storage circuit 13.

[0031] Next, the extraction function 11c extracts a low-density columnar region R2' surrounded by a high-density region from the deformed past image I2' (step S105). Similarly, the extraction function 11c extracts a columnar region R1 from the current image I1 (step S106). This process is realized, for example, by the processing circuit 11 calling and executing a program corresponding to the extraction function 11c from the storage circuit 13.

[0032] Next, the set calculation function 11d performs a set calculation between columnar region R1 and columnar region R2' to obtain the calculated columnar region R3 (step S107), and outputs the calculated columnar region R3 (step S108). For example, the set calculation function 11d outputs a region image showing the calculated columnar region R3 to the storage circuit 13 or to other devices on the network. This process is realized, for example, by the processing circuit 11 calling and executing a program corresponding to the set calculation function 11d from the storage circuit 13.

[0033] Next, the image generation function 11e uses the calculated columnar region R3 to perform calculations between the current image I1 and the past image I2' after deformation alignment to generate a derived image D (step S109), and outputs the derived image D (step S110). For example, the image generation function 11e outputs the derived image D to the memory circuit 13 or to other devices on the network. This process is realized, for example, by the processing circuit 11 calling and executing a program corresponding to the image generation function 11e from the memory circuit 13.

[0034] The details of each process performed by the image processing device 10 are described below.

[0035] (Medical image acquisition process) As described in steps S101 and S102 of Figure 2, the control function 11a acquires the current image I1 and the past image I2 in response to the volume data acquisition operation via the input interface 15. Here, the control function 11a can acquire the current image I1 and the past image I2 from images stored in the memory circuit 13 or from images stored in other devices on the network.

[0036] Furthermore, in step S102, the control function 11a can acquire images other than those collected in the previous scan as past images I2. For example, the control function 11a can acquire images collected in scans prior to the previous scan as past images I2.

[0037] Furthermore, the control function 11a can acquire medical images collected from the subject before bone metastasis as past images I2 (second medical images). In such cases, the control function 11a identifies the subject's admission date from the electronic medical record included in the HIS and acquires X-ray CT images taken on dates close to the identified date from PACS, etc., as images from a period without bone metastasis. Alternatively, the control function 11a performs bone metastasis detection processing using machine learning, etc., on the X-ray CT images collected from the subject at each period to identify X-ray CT images without bone metastasis and acquires the identified X-ray CT images as past images I2.

[0038] In step S102, information retrieval from the electronic medical record can be achieved using HL7 (Health Level 7) or by directly issuing SQL queries to the electronic medical record database. Furthermore, image acquisition from the PACS can be achieved using the DICOM protocol.

[0039] (Alignment process) As explained in steps S103 and S104 of Figure 2, the alignment function 11b performs alignment between the current image I1 and the past image I2 by deforming the past image I2 so that each pixel in the past image I2 matches the corresponding pixel in the current image I1, based on the correspondence relationship V between the positions of each pixel in the current image I1 and each pixel in the past image I2. Here, the alignment function 11b can calculate (estimate) the correspondence relationship V using an existing linear alignment algorithm, a nonlinear alignment algorithm, or a method that combines them.

[0040] The alignment function 11b calculates a positional correspondence V between the current image I1 and the past image I2 using the method described above, and deforms the past image I2 using the calculated correspondence V. Through the deformed alignment between the images described above, the alignment function 11b can align the positions of feature points indicating characteristic parts in the current image I1 with feature points indicating characteristic parts in the past image I2.

[0041] (Extraction process of columnar regions) As explained in steps S105 and S106 of Figure 2, the extraction function 11c extracts columnar regions from the current image I1 and the past image I2' after the alignment process. Figure 3 is a diagram illustrating an example of the columnar region extraction process according to the first embodiment. Here, Figure 3 also includes an example of the alignment process performed before the extraction of the columnar regions. Although Figure 3 illustrates the process using a two-dimensional cross-sectional image, in reality, the extraction function 11c extracts three-dimensional columnar regions from volume data.

[0042] For example, as shown in Figure 3, the alignment function 11b calculates the correspondence relationship V between the current image I1 and the past image I2, and transforms the past image I2 into past image I2' based on the calculated correspondence relationship V. The extraction function 11c extracts the columnar region R1 in the current image I1, as shown in Figure 3. The extraction function 11c also extracts the columnar region R2' in the transformed past image I2'. Here, if the shape of the columnar region has changed due to osteolytic bone metastasis, etc., the extracted columnar region will include the change in shape, as shown in Figure 3.

[0043] Furthermore, the extraction function 11c can extract columnar regions in medical images using various existing methods. For example, the extraction function 11c can extract columnar regions using methods such as image binarization, morphological operations, machine learning-based region extraction, or a combination of these methods.

[0044] (Set operations) As explained in steps S107 and S108 of Figure 2, the set calculation function 11d performs a set calculation between the columnar region R1 extracted from the current image I1 and the columnar region R2' extracted from the past image I2' after alignment to obtain the calculated columnar region R3, and outputs the obtained calculated columnar region R3.

[0045] Figures 4A to 4C show examples of set operations according to the first embodiment. Although Figures 4A to 4C illustrate the process using two-dimensional cross-sectional images, in reality, the set operation function 11d performs set operations on three-dimensional columnar regions. For example, as shown in Figure 4A, the set operation function 11d obtains region 41 as the calculated columnar region R3 by performing an OR operation (R1∪R2') between columnar region R1 and columnar region R2'. In other words, the set operation function 11d obtains a region by superimposing columnar region R1 and columnar region R2'. This region 41 represents a columnar region that includes all locations where osteolysis has occurred in the past and present.

[0046] Furthermore, for example, the set operation function 11d performs an AND operation (R1∩R2') between columnar region R1 and columnar region R2', as shown in Figure 4B, to obtain region 42 as the calculated columnar region R3. In other words, the set operation function 11d obtains a region that is included in both columnar region R1 and columnar region R2'. This region 42 represents a columnar region that is close to the original shape of the spinal canal, excluding the osteolytic portion.

[0047] Furthermore, for example, the set calculation function 11d obtains region 43 as the calculated columnar region R3 by performing a special difference calculation (R1-R1∩R2') between columnar region R1 and columnar region R2', as shown in Figure 4C. In other words, the set calculation function 11d obtains the region that is included only in columnar region R1. This region 43 represents the region of osteolysis in the current image.

[0048] Note that the examples shown in Figures 4A to 4C are merely examples, and the set calculation function 11d can perform any set calculation between columnar region R1 and columnar region R2'. For example, the set calculation function 11d can perform a special difference calculation (R2'-R1∩R2') to obtain the region of osteolysis in past images.

[0049] As shown in Figures 4A to 4C, when the aggregate calculation function 11d acquires the calculated columnar region R3 (regions 41 to 43), it outputs a region image representing the acquired calculated columnar region R3 to the memory circuit 13 or other devices on the network. That is, the aggregate calculation function 11d generates a binary image in which the pixel values ​​within the region corresponding to the calculated columnar region R3 in the current image I1 or the transformed past image I2' are set to 1, and the pixel values ​​outside the region are set to 0, and outputs the generated binary image.

[0050] Furthermore, the set operation function 11d can transmit region images to the PACS using the DICOM protocol. In addition, the control function 11a can display the generated binary image on the display 14.

[0051] (Process for generating derived images) As explained in steps S109 and S110 of Figure 2, the image generation function 11e generates a derived image D using the calculated columnar region R3 and outputs the generated derived image D. For example, the image generation function 11e generates the derived image D by subtracting the current image I1 and the transformed past image I2' within the calculated columnar region R3. In this case, the image generation function 11e acquires, for example, a region image (binary image) showing the calculated columnar region R3 (region 41, region 42, or region 43). Then, based on the acquired region image, the image generation function 11e identifies the position of the calculated columnar region R3 in the current image I1 and the transformed past image I2', and generates the derived image D by performing a pixel value difference process between the pixels contained within the calculated columnar region R3.

[0052] Furthermore, any of the acquired pre-calculated columnar regions R3 may be used to generate the derived image D. Also, when generating a single derived image D, only one pre-calculated columnar region R3 may be used, or multiple regions may be used together.

[0053] By using the derived image D generated in this way, it is possible to visualize, for example, the temporal changes in tumor infiltration into the spinal canal, and to accurately measure the degree of infiltration.

[0054] In the example described above, the case in which difference processing is performed to generate derived image D was explained. However, the embodiment is not limited to this, and other calculations may be used. Also, in the example described above, the case in which derived image D is generated using the current image I1, the deformed past image I2', and the calculated columnar region R3 was explained. However, the embodiment is not limited to this, and derived image D may be generated using only the current image I1 and the calculated columnar region R3 without using the deformed past image I2'. In such a case, for example, the image generation function 11e may use machine learning or the like to generate a derived image showing the infiltration region present within the calculated columnar region R3 of the current image I1.

[0055] As described above, when the image generation function 11e generates a derived image D, it outputs the generated derived image D to the memory circuit 13 or other devices on the network. The image generation function 11e can transmit the derived image D to the PACS using the DICOM protocol. The control function 11a can also display the generated derived image D on the display 14.

[0056] (Variation 1) In the embodiment described above, the case in which the columnar region R2' is extracted after transforming the past image I2 into past image I2' was explained. In Modification 1, the case in which the columnar region R2 is extracted from the past image I2 and then transformed into columnar region R2' is explained. That is, the extraction function 11c in Modification 1 extracts the first columnar region from the first medical image and the second columnar region from the second medical image. The alignment function 11b in Modification 1 performs an alignment process to align the position of the second columnar region with that of the first columnar region. The set calculation function 11d in Modification 1 performs a set calculation between the first columnar region and the second columnar region after the alignment process and outputs the calculated columnar region.

[0057] Figure 5 is a flowchart showing the entire process of the image processing apparatus 10 according to Modification 1. Here, all processes except for the two processes (steps S204 and S205) shown in step S200 of Figure 5 are the same as the processes of the corresponding steps in Figure 2. That is, steps S201 to S203 in Figure 5 perform the same processes as steps S101 to S103 in Figure 2. Also, steps S206 to S208 in Figure 5 are the same as the processes of steps S106 to S108 in Figure 2. Furthermore, step 209 in Figure 5 is the same as the process of step S104 in Figure 2. In addition, steps S210 to S211 in Figure 5 are the same as the processes of steps S109 to S110 in Figure 2.

[0058] In the image processing device 10 according to Modification 1, the alignment function 11b calculates (estimates) the correspondence relationship V between the positions of each pixel in the current image I1 and each pixel in the past image I2 (step S203), and the extraction function 11c extracts the columnar region R2 from the past image I2 (step S204). This process is realized, for example, by the processing circuit 11 calling and executing a program corresponding to the extraction function 11c from the storage circuit 13.

[0059] Next, the alignment function 11b uses the correspondence relationship V to obtain a columnar region R2' obtained by deforming the columnar region R2 so that each pixel in the columnar region R2 matches the corresponding pixel in the current image I1 (step S205). This process is realized, for example, by the processing circuit 11 calling and executing a program corresponding to the alignment function 11b from the storage circuit 13.

[0060] (Alignment and extraction processes) As explained in steps S204 and S205 of Figure 5, the image processing device 10 extracts the columnar region R2 from the past image I2 and performs alignment processing to align the position of the columnar region R2 with that of the columnar region R1. Figure 6 is a diagram illustrating an example of the alignment processing and extraction processing according to Modification 1. Although Figure 6 illustrates the processing using a two-dimensional cross-sectional image, in reality, the alignment function 11b and the extraction function 11c perform the alignment processing and extraction processing on a three-dimensional region.

[0061] For example, as shown in Figure 6, the alignment function 11b calculates the correspondence relationship V between the current image I1 and the past image I2. Then, the extraction function 11c extracts the columnar region R2 in the past image I2, as shown in Figure 6. The alignment function 11b then transforms the columnar region R2 into columnar region R2' based on the calculated correspondence relationship V. The extraction function 11c also extracts the columnar region R1 in the current image I1, as shown in Figure 6.

[0062] (Modification 2) In the embodiment described above, the case in which a single past image I2 is used as the second medical image was explained. Modification 2 describes the case in which multiple past images I2 are used as the second medical image. In this case, the image processing device 10 repeatedly executes the steps S102 to S107 while replacing the past images I2. At that time, the set operation in step S107 becomes a set operation between the columnar region of the current image and the columnar regions of multiple past images.

[0063] (Medical image acquisition process) The control function 11a in the modified example 2 acquires a first medical image and multiple second medical images. Specifically, the control function 11a acquires multiple past images with different conditions for medical image acquisition as second medical images. For example, the control function 11a acquires the most recent X-ray CT image as the current image I1, the X-ray CT image acquired in the previous scan as the past image I2-1, and the X-ray CT image acquired in the scan before that as the past image I2-2.

[0064] The control function 11a uses conditions such as the date and time of acquisition, the type of reconstruction function, the magnitude of the tube voltage and tube current, and the presence or absence of contrast agent as conditions for acquiring medical images. In other words, the control function 11a can acquire not only images with different acquisition dates and times as described above, but also multiple medical images with different other conditions as past images.

[0065] (Alignment process) The alignment function 11b in the modified example 2 performs alignment processing between the first medical image and multiple second medical images. For example, the alignment function 11b calculates a correspondence relationship V1 between the positions of each pixel in the current image I1 and the past image I2-1, and uses the calculated correspondence relationship V1 to transform the past image I2-1 into past image I2'-1. Similarly, the alignment function 11b calculates a correspondence relationship V2 between the positions of each pixel in the current image I1 and the past image I2-2, and uses the calculated correspondence relationship V2 to transform the past image I2-2 into past image I2'-2.

[0066] (Extraction process of columnar regions) The extraction function 11c in the modified example 2 extracts columnar regions from a first medical image and from multiple second medical images. For example, the extraction function 11c extracts columnar region R1 from the current image I1, extracts columnar region R2'-1 from past image I2'-1, and extracts columnar region R2'-2 from past image I2'-2.

[0067] (Set operations) The set calculation function 11d in the modified example 2 performs a set calculation on a first columnar region based on a first medical image and a plurality of second columnar regions based on a plurality of second medical images, and outputs a calculated columnar region. For example, the set calculation function 11d performs a set calculation on columnar region R1, columnar region R2'-1, and columnar region R2'-2 to obtain a calculated columnar region. To give one example, the set calculation function 11d performs an AND operation on columnar region R1, columnar region R2'-1, and columnar region R2'-2 to obtain a calculated columnar region R3.

[0068] As described above, the image processing device 10 according to Modification 2 acquires a calculated columnar region using multiple past images. This allows the image processing device 10 to obtain a columnar region that is closer to the original shape of the spinal canal. The image processing device 10 can also perform the processing described in Modification 2 and the processing described in Modification 1 in combination. For example, the image processing device 10 extracts columnar region R2-1 and columnar region R2-2 from past image I2-1 and past image I2-2, respectively, and acquires columnar region R2'-1 and columnar region R2'-2 by deforming each extracted columnar region. Then, the image processing device 10 performs a set operation on columnar region R1, columnar region R2'-1, and columnar region R2'-2 to acquire a calculated columnar region R3.

[0069] As described above, according to the first embodiment, the control function 11a acquires a first medical image (current image) and a second medical image (past image) collected from the subject. The alignment function 11b performs an alignment process to align the position of the second medical image with that of the first medical image. The extraction function 11c extracts a first columnar region from the first medical image and a second columnar region from the second medical image after the alignment process. The set calculation function 11d performs a set calculation on the first columnar region and the second columnar region and outputs the calculated columnar region. Therefore, the image processing device 10 according to the first embodiment can extract columnar regions with accurate shapes and can extract columnar regions from medical images with high accuracy even when there are defects in the columnar regions. For example, the image processing device 10 can extract columnar regions that are close to the original shape of the spinal canal from columnar regions that have been damaged by osteolytic bone metastases, etc.

[0070] Furthermore, according to the first embodiment, the control function 11a acquires a medical image as a second medical image, which is a medical image collected from the subject in the past before the first medical image. Therefore, the image processing apparatus 10 according to the first embodiment can take into account the change in the shape of the columnar region over time, and enables the extraction of the columnar region with high accuracy.

[0071] Furthermore, according to the first embodiment, the control function 11a acquires a medical image collected from the subject before bone metastasis occurs as a second medical image. Therefore, the image processing device 10 according to the first embodiment makes it possible to extract a columnar region from the medical image using the original shape of the spinal canal before the defect occurred.

[0072] Furthermore, according to the first embodiment, the image generation function 11e generates a derived image based on the first medical image using the calculated columnar region. Therefore, the image processing apparatus 10 according to the first embodiment makes it possible to generate a highly accurate derived image.

[0073] Furthermore, according to the first embodiment, the image generation function 11e generates a derived image using a calculated columnar region from the first medical image and the second medical image. Therefore, the image processing apparatus 10 according to the first embodiment makes it possible to generate a derived image that shows the changes in the columnar region over time.

[0074] Furthermore, according to the first embodiment, the image generation function 11e identifies regions corresponding to the calculated columnar regions in the first medical image and the second medical image, respectively, and generates a derived image by performing difference processing between the first medical image and the second medical image for the identified regions. Therefore, the image processing apparatus 10 according to the first embodiment makes it possible to generate a derived image that visualizes the changes in the columnar regions over time.

[0075] Furthermore, according to Modification 1, the control function 11a acquires a first medical image (current image) and a second medical image (past image) collected from the subject. The extraction function 11c extracts a first columnar region from the first medical image and a second columnar region from the second medical image. The alignment function 11b performs an alignment process to align the position of the second columnar region with that of the first columnar region. The set calculation function 11d performs a set calculation on the first columnar region and the aligned second columnar region and outputs the calculated columnar region. Therefore, the image processing device 10 according to Modification 1 can extract columnar regions with accurate shapes and can extract columnar regions from medical images with high accuracy even when there are defects in the columnar regions.

[0076] Furthermore, according to Modification 2, the control function 11a acquires a first medical image and a plurality of the second medical images. The set calculation function 11d performs a set calculation on a first columnar region based on the first medical image and a plurality of second columnar regions based on the plurality of second medical images, and outputs the calculated columnar region. Therefore, the image processing device 10 according to Modification 2 can extract columnar regions from medical images with higher accuracy, making it possible to obtain columnar regions that are closer to the original shape of the spinal canal.

[0077] (Second embodiment) Another embodiment of the present invention involves generating a derived image from the current image using past images under different conditions than those used to calculate the calculated spinal canal region. For example, to calculate the spinal canal region, it is appropriate to use past images taken immediately after hospitalization, when osteolysis has not yet occurred. However, to observe changes within the spinal canal region over time, it is necessary to calculate a time-series difference image from the current image using the most recent past image. This embodiment is useful in such cases. This embodiment is also useful in generating derived images other than time-series difference images, such as generating a fused image by superimposing time-series difference information onto the current image. The second embodiment differs from the first embodiment in that it processes the data after acquiring the calculated columnar region. Specifically, the control function 11a according to the second embodiment acquires a third medical image collected from the subject under different conditions than the second medical image. The image generation function 11e according to the second embodiment generates a derived image using the calculated columnar region from the first medical image and the third medical image. These will be described in detail below.

[0078] Figure 7 is a flowchart showing the entire process of the image processing apparatus 10 according to the second embodiment. Here, the process shown in step S300 in Figure 7 is the same as the process in steps S101 to S108 in Figure 2, or steps S201 to S208 in Figure 5.

[0079] As shown in Figure 7, once the calculated columnar region R3 is obtained, the control function 11a obtains a derived past image I3, which is a third medical image taken under different conditions than the past image I2, which is a second medical image acquired in the process corresponding to step S102 or S202 (step S309). This process is realized, for example, by the processing circuit 11 calling and executing a program corresponding to the control function 11a from the storage circuit 13.

[0080] Next, the alignment function 11b calculates (estimates) the correspondence relationship W between the position of each pixel in the current image I1 and each pixel in the derived past image I3 (step S310). Then, based on the correspondence relationship W, the alignment function 11b transforms the derived past image I3 so that each pixel in the derived past image I3 matches the corresponding pixel in the current image I1, and obtains the aligned derived past image I3' (step S311). This process is realized, for example, by the processing circuit 11 calling and executing a program corresponding to the alignment function 11b from the storage circuit 13.

[0081] Next, the image generation function 11e uses the calculated columnar region R3 to perform calculations between the current image I1 and the deformed derived past image I3' to generate a derived image D (step S312), and outputs the derived image D (step S313). For example, the image generation function 11e outputs the derived image D to the memory circuit 13 or to another device on the network. This process is realized, for example, by the processing circuit 11 calling and executing a program corresponding to the image generation function 11e from the memory circuit 13.

[0082] (Medical image acquisition process) As explained in step S309 of Figure 7, the control function 11a acquires a derived past image I3 in response to the volume data acquisition operation via the input interface 15. Here, the control function 11a can acquire the derived past image I3 from an image stored in the memory circuit 13 or from an image stored in another device on the network.

[0083] (Alignment process) In steps S310 and S311 of Figure 7, the alignment process between the current image I1 and the derived past image I3 was explained, but since this process is the same as in steps S103 and S104, the explanation is omitted.

[0084] (Process for generating derived images) As described in steps S312 and S313 of Figure 7, the image generation function 11e generates a derived image D using the calculated columnar region R3 and outputs the generated derived image D. For example, the image generation function 11e generates the derived image D by subtracting the current image I1 and the deformed past image I3' for derivatives inside the calculated columnar region R3. In the example described above, the case in which a subtraction process is performed to generate the derived image D was explained. However, the embodiment is not limited to this, and other calculations may be used.

[0085] As described above, when the image generation function 11e generates a derived image D, it outputs the generated derived image D to the memory circuit 13 or other devices on the network. The control function 11a can also display the generated derived image D on the display 14.

[0086] In addition, the acquisition of the calculated columnar region in the second embodiment may be performed using a process that utilizes multiple past images, as described in Modification 2 of the first embodiment. In this case, a columnar region with less influence from osteolysis can be acquired, thus enabling the creation of more appropriate derived images.

[0087] As described above, according to the second embodiment, the control function 11a acquires a third medical image collected from the subject under different conditions than the second medical image. The image generation function 11e generates a derived image using the calculated columnar region from the first medical image and the third medical image. Therefore, the image processing device 10 according to the second embodiment makes it possible to efficiently obtain a derived image of the input image using the obtained columnar region, even when the past image used for columnar region extraction and the past image used for derived image calculation are different. As a result, the image processing device 10 makes it possible to easily generate derived images for various analyses.

[0088] (Other embodiments) In the embodiments described above, the case where the columnar region to be extracted is the spinal canal region was explained. However, the embodiments are not limited to this, and any low-concentration columnar region surrounded by a high-concentration region may be used as the extraction target. For example, the medullary cavity region within the long bones of the limbs may be used as the columnar region to be extracted. Alternatively, by reversing the density, a high-concentration columnar region surrounded by a low-concentration region may be used as the columnar region to be extracted.

[0089] Furthermore, in the embodiments described above, the use of X-ray CT images as medical images was given as an example. However, the embodiments are not limited to this, and any medical image acquired by any modality may be used as long as it is a grayscale medical image.

[0090] Furthermore, the above-described embodiment explained the case in which a positioning process is performed to align the position of a past image with the current image. However, the embodiment is not limited to this, and a positioning process (a process that deforms the current image) may also be performed to align the position of the current image with the past image. That is, the control function 11a may acquire a past image as the first medical image and acquire the current image as the second medical image.

[0091] Although examples of embodiments have been described in detail above, the present invention can take the form of, for example, a system, apparatus, method, program, or recording medium (storage medium). Specifically, it may be applied to a system consisting of multiple devices (for example, a host computer, interface devices, imaging devices, web applications, etc.), or to an apparatus consisting of a single device.

[0092] 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.

[0093] Here, the image processing program executed by the processor is provided pre-installed in ROM (Read Only Memory) or memory circuits. Alternatively, this 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 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 image processing program consists of modules containing the processing functions described above. In actual hardware, the CPU reads and executes the medical information processing program from a storage medium such as ROM, thereby loading each module onto the main memory and generating it in the main memory.

[0094] Furthermore, in the embodiments 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 implemented, 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.

[0095] 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.

[0096] According to at least one embodiment described above, columnar regions can be extracted from medical images with high accuracy even when defects occur in the columnar regions.

[0097] 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]

[0098] 10 Image Processing Device 11a Control Function 11b Alignment function 11c Extraction Function 11d Set Operations Function 11e Image generation function

Claims

1. An acquisition unit that acquires a first medical image and a second medical image collected from a subject, A positioning unit that performs a positioning process to align the position of the second medical image with that of the first medical image, An extraction unit extracts a first columnar region of low density surrounded by high density regions from the first medical image, and extracts a second columnar region of low density surrounded by high density regions from the second medical image after the alignment process, A set calculation unit performs a set calculation on the first columnar region and the second columnar region and outputs a calculated columnar region, An image processing device equipped with the following features.

2. An acquisition unit that acquires a first medical image and a second medical image collected from a subject, An extraction unit extracts a first columnar region from the first medical image and a second columnar region from the second medical image, A positioning unit that performs a positioning process to align the position of the second columnar region with the position of the first columnar region, A set calculation unit performs a set calculation on the first columnar region and the second columnar region after the alignment process, and outputs a calculated columnar region. An image processing device equipped with the following features.

3. The image processing apparatus according to claim 1 or 2, wherein the acquisition unit acquires a medical image collected from the subject prior to the first medical image as the second medical image.

4. The acquisition unit acquires the first medical image and a plurality of the second medical images. The image processing apparatus according to any one of claims 1 to 3, wherein the set calculation unit performs a set calculation on a first columnar region based on the first medical image and a plurality of second columnar regions based on a plurality of second medical images, and outputs the calculated columnar region.

5. The image processing apparatus according to claim 3, wherein the acquisition unit acquires a medical image collected from the subject at a time before bone metastasis as the second medical image.

6. The image processing apparatus according to any one of claims 1 to 5, further comprising an image generation unit that generates a derived image based on the first medical image using the calculated columnar region.

7. The image processing apparatus according to claim 6, wherein the image generation unit generates the derived image using the calculated columnar region from the first medical image and the second medical image.

8. The image processing apparatus according to claim 7, wherein the image generation unit identifies regions corresponding to the calculated columnar regions in the first medical image and the second medical image, and generates the derived image by performing difference processing between the first medical image and the second medical image for the identified regions.

9. The acquisition unit acquires a third medical image collected from the subject under conditions different from those for the second medical image. The image processing apparatus according to claim 6, wherein the image generation unit generates the derived image using the calculated columnar region from the first medical image and the third medical image.

10. The image processing apparatus according to any one of claims 1 to 9, wherein the extraction unit extracts a second columnar region of the same type as the first columnar region from the second medical image.

11. The image processing apparatus according to any one of claims 1 to 10, wherein the set calculation unit performs an AND operation between the first columnar region and the second columnar region as a set calculation and outputs the calculated columnar region.

12. The first medical image and the second medical image collected from the subject are obtained. A positioning process is performed to align the position of the second medical image with that of the first medical image. A first columnar region of low density surrounded by high density regions is extracted from the first medical image, and a second columnar region of low density surrounded by high density regions is extracted from the second medical image after the alignment process. Perform a set operation on the first columnar region and the second columnar region, and output the calculated columnar region. An image processing method that includes the following.

13. An image processing program that causes a computer to execute the image processing method described in claim 12.

14. A storage medium comprising the image processing program described in claim 13.

15. The first medical image and the second medical image collected from the subject are obtained. A first columnar region is extracted from the first medical image, and a second columnar region is extracted from the second medical image. An alignment process is performed to align the position of the second columnar region with the position of the first columnar region. The first columnar region and the second columnar region after the alignment process are used to perform a set operation and output the calculated columnar region. An image processing method that includes the following.

16. An image processing program that causes a computer to execute the image processing method described in claim 15.

17. A storage medium comprising the image processing program described in claim 16.

18. An acquisition unit that acquires a first medical image and a second medical image collected from a subject, A positioning unit that performs a positioning process to align the position of the second medical image with that of the first medical image, An extraction unit extracts a first columnar region from the first medical image and a second columnar region from the second medical image after the alignment process, A set calculation unit performs a set calculation on the first columnar region and the second columnar region and outputs a calculated columnar region, The system includes an image generation unit that generates a derived image based on the first medical image using the calculated columnar region, The image generation unit generates a derived image using the calculated columnar region from the first medical image and the second medical image, identifies regions in the first medical image and the second medical image that correspond to the calculated columnar region, and generates the derived image by performing difference processing between the first medical image and the second medical image for the identified regions.

19. An acquisition unit that acquires a first medical image and a second medical image collected from a subject, A positioning unit that performs a positioning process to align the position of the second medical image with that of the first medical image, An extraction unit extracts a first columnar region from the first medical image and a second columnar region from the second medical image after the alignment process, A set calculation unit performs a set calculation on the first columnar region and the second columnar region and outputs a calculated columnar region, The system includes an image generation unit that generates a derived image based on the first medical image using the calculated columnar region, The acquisition unit acquires a third medical image collected from the subject under conditions different from those for the second medical image. The image generation unit is an image processing device that generates the derived image using the calculated columnar region from the first medical image and the third medical image.

Images