JP2024039641A - Medical information quantification device, medical information quantification method, medical information quantification program, and medical image diagnostic device - Google Patents

Abstract

[Problem] To obtain a feature value of a quantified circular enhancement feature. [Solution] A medical information quantification device according to an embodiment includes an acquisition unit, a stretch transformation unit, a coordinate conversion unit, an extraction unit, and a quantification unit. The acquisition unit acquires a medical image including a region of interest, and acquires region of interest information from the medical image, which is information related to the region of interest. The stretch transformation unit performs a stretch transformation on the region of interest in the medical image based on the region of interest information, to obtain a stretched output image. The coordinate conversion unit performs a polar coordinate transformation on the region of interest in the stretched output image, and converts a ring-shaped structure of the region of interest in the stretched output image into a tubular structure, to obtain a polar coordinate output image. The extraction unit extracts the tubular structure of the region of interest in the polar coordinate output image, and subdivides the tubular structure to obtain a subdivided output image. The quantification unit performs a quantification calculation of features from the subdivided output image to obtain a quantified numerical value. [Selected Figure] Figure 2

Description

Embodiments disclosed in this specification and the drawings relate to a medical information quantification device, a medical information quantification method, a medical information quantification program, and a medical image diagnostic device.

Enhancing rim features are widely used in clinical practice to determine tumor types. For example, in MR FLAIR images of the brain, whether lower-grade gliomas (LGGs) have ring-enhanced features is highly correlated with specific genes. This gene is an important indicator for determining tumor risk. Furthermore, in a specific phase image of CT/MR of the liver, whether or not a tumor has ring-enhanced features is an important index for determining malignant hepatocellular carcinoma (HCC).

Therefore, it is very important to automatically and quantitatively determine the ring-enhanced features of tumors.

On the other hand, in the prior art, there are mainly two methods for acquiring annular emphasis features: a method of direct classification using machine learning or deep learning technology, and a method of dividing an annular emphasis region using machine learning or deep learning technology. There are different methods.

However, both the method of direct classification using machine learning or deep learning technology and the method of dividing annular emphasis regions using machine learning or deep learning technology require a large amount of high-quality annotation to be performed on medical images. . Furthermore, the evaluation criteria actually differ depending on the doctor. For this reason, there is a possibility that the annotation on the medical image may vary depending on the doctor's experience, level, etc., and the obtained annular emphasis feature may differ greatly from the actual one.

In addition, direct classification methods using machine learning or deep learning techniques typically provide only binary classification results or probability values, so it is only possible to know whether an image includes a ring-enhanced feature. Furthermore, it is difficult to directly correspond such classification results to medical images, that is, it is difficult to know the specific position where the annular emphasis feature exists in the medical image.

Furthermore, in the method of dividing annular enhancement regions using machine learning or deep learning technology, it is necessary to perform pixel-level annotation on the image, but pixel-level annotation is very time-consuming and is difficult for medical images. This affects the real-time performance and practicality of dividing the annular emphasis region during the processing process. In addition, methods that segment annular enhancement regions using machine learning or deep learning techniques cannot output quantified annular enhancement features, so it is generally difficult to directly perform subsequent tasks using the segmentation results. be. This is because subsequent tasks, such as disease classification, typically require quantified feature values (eg, [0,1]) as input.

Therefore, it is desired to propose a technique that can solve the problems of the prior art described above and obtain quantified feature values of annular emphasis features. More specifically, it is possible to extract a ring-enhanced structure suitable for various tumors and calculate the quantification of the annular-enhanced features without the need for annotation. It is desired to propose a technique that can be easily obtained in the configuration, allows subsequent tasks to be performed easily, and eliminates the possibility that the size of the tumor, the position of the annular structure, etc. interfere with the quantification calculation. ing.

Riries Rulaningtyas, Lailatul Muqmiroh, Leonard Ferdian, Abidah Alfi, Isma Iba, “Automatic Identification of Ring Enhancing Lesion Pattern in Cases of Brain Infection and Metastasis Brain Tumor Based on Invariant Moment Features Classification”, Malaysian Journal of Science 38 (Special Issue 3) :42-52 (2019)

One of the problems to be solved by the embodiments disclosed in this specification and the drawings is to obtain quantified feature values of annular emphasis features. However, the problems to be solved by the embodiments disclosed in this specification and the drawings are not limited to the above problems. Problems corresponding to each effect of each configuration shown in the embodiments described later can also be positioned as other problems.

The medical information quantification device according to the embodiment includes an acquisition section, a stretch transformation section, a coordinate transformation section, an extraction section, and a quantification section. The acquisition unit acquires a medical image including a region of interest, and acquires region of interest information, which is information regarding the region of interest, from the medical image. The stretch conversion unit performs stretch conversion on the region of interest in the medical image based on the region of interest information to obtain a stretch output image. The coordinate transformation unit performs polar coordinate transformation on the region of interest in the stretch output image, transforms the annular structure of the region of interest in the stretch output image into a tubular structure, and obtains a polar coordinate output image. The extraction unit extracts the tubular structure of the region of interest in the polar coordinate output image, and subdivides the tubular structure to obtain a subdivided output image. The quantification unit performs a feature quantification calculation from the subdivided output image to obtain a quantified numerical value.

FIG. 1 is a diagram illustrating an example of the configuration of an X-ray computed tomography (CT) apparatus equipped with a medical information quantification apparatus according to a first embodiment. FIG. 2 is a flowchart of an example of the operation of the medical information quantification device according to the first embodiment. FIG. 3 is a schematic diagram of a specific example of the medical information quantification device according to the first embodiment. FIG. 4 is a diagram illustrating an example of stretch conversion in the medical information quantification device according to the first embodiment. FIG. 5 is a diagram showing an example of quantification in the medical information quantification device according to the first embodiment. FIG. 6 is a flowchart of an example of the operation of the medical information quantification device according to the modification of the first embodiment. FIG. 7 is a diagram illustrating an example of the configuration of an X-ray computed tomography (CT) apparatus equipped with a medical information quantification apparatus according to the second embodiment. FIG. 8 is a flowchart of an example of the operation in the medical information quantification device according to the second embodiment. FIG. 9 is a schematic diagram of a specific example of the medical information quantification device according to the second embodiment.

The present embodiment has been made to solve the above-mentioned problems, and aims to provide a medical information quantification device, a medical information quantification method, a medical information quantification program, and a medical image diagnostic device that can extract circularly enhanced structures suitable for various tumor regions and perform quantification calculations of circularly enhanced features without the need for annotation, can easily obtain feature values of quantified circularly enhanced features with a simple configuration, and can obtain position information of the circular structures in the original tumor region image, thereby allowing subsequent tasks to be easily performed, and can be widely applied by improving the conventional technology, and can avoid the inability to extract arcs or extract arcs as related circular structures due to excessively large differences in spoke angles by stretch transformation, eliminate interference caused by circular structures of the same length having different spoke angles depending on the tumor shape, improve the accuracy of extraction of circular features, present the extraction results of the circular structures, and can superimpose the extracted circular structures so as to be emphasized in the original tumor region image, and present the circular structures in a form that is easy to understand at a glance.

In order to achieve the above object, a medical information quantification device according to an aspect of the present embodiment acquires a medical image including a region of interest, and acquires region of interest information that is information regarding the region of interest from the medical image. a stretch transformation unit that performs stretch transformation on the region of interest in the medical image to obtain a stretch output image based on the region of interest information; and a stretch transformation unit that performs a stretch transformation on the region of interest in the stretch output image, a coordinate conversion unit that converts the annular structure of the region of interest in the stretch output image into a tubular structure to obtain a polar coordinate output image; and a coordinate conversion unit that extracts the tubular structure of the region of interest in the polar coordinate output image and subdivides the tubular structure. and a quantification unit that performs a quantification calculation of features from the segmented output image to obtain a numerical value after quantification.

Further, in the medical information quantification device according to one aspect of the present embodiment, the stretch conversion unit calculates an image stretch direction based on the region of interest information, and calculates an image stretch direction in the medical image based on the image stretch direction. Perform stretch transformation on the region of interest.

Further, the medical information quantification device according to one aspect of the present embodiment acquires a medical image including a ring-shaped structure of a region of interest, and acquires region-of-interest information and ring-shaped structure information that are information about the region of interest from the medical image. a stretch conversion unit that performs stretch transformation on the annular structure of the region of interest in the medical image to obtain a stretch output image based on the region of interest information and the annular structure information; a coordinate transformation unit that performs polar coordinate transformation on the annular structure of the region of interest in the stretched output image and converts the annular structure of the region of interest in the stretch output image into a tubular structure to obtain a polar coordinate output image; The image forming apparatus includes a subdivision section that performs subdivision to obtain subdivided output images, and a quantification section that performs quantification calculation of features from the subdivided output image to obtain numerical values after quantification.

Further, in the medical information quantification device according to one aspect of the present embodiment, the stretch conversion unit calculates an image stretch direction based on the region of interest information, and calculates an image stretch direction in the medical image based on the image stretch direction. Stretch transformation is performed on the annular structure of the region of interest.

Further, in the medical information quantification device according to one aspect of the present embodiment, the region of interest information includes shape information of the region of interest and position information of the region of interest.

Further, the medical information quantification device according to one aspect of the present embodiment further includes an output unit that outputs a quantified numerical value in a fixed range.

Furthermore, the medical information quantification device according to one aspect of the present embodiment further includes a display control unit that displays the segmented output image on a display.

Further, in the medical information quantification device according to one aspect of the present embodiment, the numerical value after quantification is a numerical value in a fixed range, and the fixed range is [0, 1] or [0, 2π].

Further, in the medical information quantification device according to one aspect of the present embodiment, the region of interest is a tumor region.

Further, the medical information quantification method according to one aspect of the present embodiment includes an acquisition step of acquiring a medical image including a region of interest, and acquiring region of interest information that is information regarding the region of interest from the medical image; a stretch transformation step of performing stretch transformation on the region of interest in the medical image based on region information to obtain a stretch output image; and performing polar coordinate transformation on the region of interest in the stretch output image to obtain the stretched output image. a coordinate conversion step of converting the annular structure of the region of interest into a tubular structure to obtain a polar coordinate output image; extracting the tubular structure of the region of interest in the polar coordinate output image; and subdividing the tubular structure to obtain a segmented output image; and a quantification step of performing a quantification calculation of features from the segmented output image to obtain a numerical value after quantification.

Further, the medical information quantification method according to one aspect of the present embodiment acquires a medical image including a ring structure of a region of interest, and acquires region of interest information and ring structure information that are information about the region of interest from the medical image. a stretch transformation step of performing stretch transformation on the annular structure of the region of interest in the medical image to obtain a stretch output image based on the region of interest information and the annular structure information; a coordinate transformation step of performing polar coordinate transformation on the annular structure of the region of interest in the stretched output image, converting the annular structure of the region of interest in the stretch output image into a tubular structure to obtain a polar coordinate output image; The method includes a subdivision step in which a subdivided output image is obtained by subdividing the subdivided output image, and a quantification step in which a quantification calculation of a feature is performed from the subdivided output image to obtain a numerical value after quantification.

Further, the medical information quantification program according to one aspect of the present embodiment includes an acquisition step of acquiring a medical image including a region of interest, and acquiring region of interest information that is information regarding the region of interest from the medical image; a stretch transformation step of performing stretch transformation on the region of interest in the medical image based on region information to obtain a stretch output image; and performing polar coordinate transformation on the region of interest in the stretch output image to obtain the stretched output image. a coordinate conversion step of converting the annular structure of the region of interest into a tubular structure to obtain a polar coordinate output image; extracting the tubular structure of the region of interest in the polar coordinate output image; and subdividing the tubular structure to obtain a segmented output image; and a quantification step of performing a quantification calculation of features from the segmented output image to obtain a numerical value after quantification.

Further, the medical information quantification program according to one aspect of the present embodiment acquires a medical image including a ring-shaped structure of a region of interest, and acquires region-of-interest information and ring-shaped structure information that are information about the region of interest from the medical image. a stretch transformation step of performing stretch transformation on the annular structure of the region of interest in the medical image to obtain a stretch output image based on the region of interest information and the annular structure information; a coordinate transformation step of performing polar coordinate transformation on the annular structure of the region of interest in the stretched output image, converting the annular structure of the region of interest in the stretch output image into a tubular structure to obtain a polar coordinate output image; A computer is caused to perform a subdivision step of subdividing the subdivided output image, and a quantification step of performing a quantification calculation of a feature from the subdivided output image to obtain a numerical value after quantification.

Further, a medical image diagnostic apparatus according to one aspect of the present embodiment includes a medical information quantification apparatus according to any one of the above aspects.

According to the medical information quantification device, the medical information quantification method, the medical information quantification program, and the medical image diagnostic device according to one aspect of the present embodiment, the annular enhancement structure is suitable for various tumor regions without requiring annotation. extraction and quantification calculation of the annular emphasis feature, the feature values of the quantified annular emphasis feature can be easily obtained with a simple configuration, and the position information of the annular structure in the original tumor region image can be easily obtained. can be obtained, so that subsequent tasks can be carried out conveniently, and the conventional technology can be improved and widely applied, and the stretch transformation can reduce the arc caused by the spoke angle difference being too large. It avoids not being able to extract arcs or arcs as related annular structures, eliminates the interference of annular structures of the same length having different spoke angles depending on the tumor shape, and improves the extraction accuracy of annular features. The extracted annular structure can be displayed in a superimposed manner so as to be emphasized on the original tumor region image, and the annular structure can be presented in a form that is easy to understand at a glance. .

Hereinafter, a medical information quantification apparatus, a medical information quantification method, a medical information quantification program, and a medical image diagnostic apparatus according to the present embodiment will be described with reference to the drawings. In the following description, components having the same or substantially the same functions as those described above with respect to the existing figures will be denoted by the same reference numerals, and will be described repeatedly only when necessary. Furthermore, even when the same part is shown, the dimensions and ratios may be shown differently depending on the drawing. In addition, for example, from the perspective of ensuring the visibility of the drawings, only the main or representative components are given reference numerals in the explanation of each drawing, and even if the components have the same or almost the same function, reference numerals are given. In some cases, it is not attached.

In each of the embodiments described below, a case will be exemplified in which a medical information quantification device according to each embodiment is installed in an X-ray computed tomography (CT) device.

Note that the medical information quantification device according to each embodiment is not limited to being installed in an X-ray CT device, and the medical information quantification device according to each embodiment is not limited to being installed in an X-ray CT device. It may also be realized as an independent device using a computer as a resource. In that case, a processor installed in the computer can implement various functions according to each embodiment by executing a program read from a ROM or the like and loaded into a RAM.

Further, the medical information quantification device according to each embodiment may be implemented by being installed in a medical image diagnostic device other than an X-ray CT device. In this case, the processor installed in each medical image diagnostic apparatus can implement the functions according to each embodiment by executing a program read from a ROM or the like and loaded into a RAM. For example, other medical image diagnostic devices include an X-ray diagnostic device, an MRI (Magnetic Resonance Imaging) device, an ultrasound diagnostic device, a SPECT (Single Photon Emission Computed Tomography) device, a PET (Positron Emission Computed Tomography) device, and a SPECT device. There may be various medical image diagnostic apparatuses such as a SPECT-CT apparatus in which a PET apparatus and an X-ray CT apparatus are integrated, and a PET-CT apparatus in which a PET apparatus and an X-ray CT apparatus are integrated.

For example, there are various types of X-ray CT devices, such as third generation CT and fourth generation CT, and any type can be applied to each embodiment. Here, the third generation CT is a Rotate/Rotate-type in which the X-ray tube and the detector rotate together around the subject. The fourth generation CT is a stationary/rotate-type CT in which a large number of X-ray detection elements arranged in an annular array are fixed, and only the X-ray tube rotates around the subject.

(First embodiment)
FIG. 1 is a diagram showing an example of the configuration of an X-ray CT apparatus 1 equipped with a medical information quantification apparatus according to a first embodiment. The X-ray CT apparatus 1 irradiates a subject P with X-rays from an X-ray tube 11, and detects the irradiated X-rays with an X-ray detector 12. The X-ray CT apparatus 1 generates a CT image regarding the subject P based on the output from the X-ray detector 12.

As shown in FIG. 1, the X-ray CT apparatus 1 includes a pedestal 10, a bed 30, and a console 40. In addition, in FIG. 1, a plurality of mounts 10 are drawn for convenience of explanation. The pedestal 10 is a scanning device having a configuration for performing X-ray CT imaging of the subject P. The bed 30 is a transport device on which a subject P to be subjected to X-ray CT imaging is placed and for positioning the subject P. The console 40 is a computer that controls the gantry 10. For example, the gantry 10 and bed 30 are installed in a CT examination room, and the console 40 is installed in a control room adjacent to the CT examination room. The gantry 10, the bed 30, and the console 40 are connected to each other by wire or wirelessly so that they can communicate with each other.

Note that the console 40 does not necessarily have to be installed in the control room. For example, the console 40 may be installed in the same room with the gantry 10 and the bed 30. Further, the console 40 may be incorporated into the pedestal 10.

In this embodiment, the rotation axis of the rotation frame 13 in a non-tilted state or the longitudinal direction of the top plate 33 of the bed 30 is the Z-axis direction, and the axis direction perpendicular to the Z-axis direction and horizontal to the floor surface is the X-axis direction. An axial direction that is orthogonal to the axial direction and the Z-axis direction and perpendicular to the floor surface is defined as the Y-axis direction.

As shown in FIG. 1, the gantry 10 includes an X-ray tube 11, an X-ray detector 12, a rotating frame 13, an X-ray high voltage device 14, a control device 15, a wedge 16, a collimator 17, and a data acquisition circuit (Data Acquisition System). :DAS) 18.

The X-ray tube 11 is a vacuum tube that has a cathode (filament) that generates thermoelectrons and an anode (target) that generates X-rays upon collision with the thermoelectrons. The X-ray tube 11 uses a high voltage supplied from the X-ray high voltage device 14 to irradiate the subject P with X-rays by irradiating thermoelectrons from the cathode to the anode.

Note that the hardware that generates X-rays is not limited to the X-ray tube 11. For example, instead of the X-ray tube 11, a fifth generation method may be used to generate X-rays. The fifth generation method consists of a focus coil that focuses the electron beam generated from the electron gun, a deflection coil that electromagnetically deflects it, and a target ring that surrounds half the circumference of the subject P and generates X-rays when the deflected electron beam collides with it. including.

The X-ray detector 12 detects the X-rays emitted from the X-ray tube 11 and passed through the subject P, and outputs an electrical signal corresponding to the dose of the detected X-rays to the DAS 18. The X-ray detector 12 has, for example, an X-ray detection element row in which a plurality of X-ray detection elements are arranged in the channel direction along one circular arc centered on the focal point of the X-ray tube 11. The X-ray detector 12 has, for example, a structure in which a plurality of X-ray detection elements are arranged in a slice direction (column direction, row direction) in a channel direction. Further, the X-ray detector 12 is, for example, an indirect conversion type detector having a grid, a scintillator array, and a photosensor array. A scintillator array has multiple scintillators. The scintillator has a scintillator crystal that outputs an amount of light depending on the amount of incident X-rays. The grid is disposed on the X-ray incident surface side of the scintillator array and has an X-ray shielding plate that has a function of absorbing scattered X-rays. Note that the grid is sometimes called a collimator (one-dimensional collimator or two-dimensional collimator). The optical sensor array has a function of converting the light from the scintillator into an electrical signal according to the amount of light. As the optical sensor, for example, a photomultiplier tube (PMT) or the like is used. Note that the X-ray detector 12 may be a direct conversion type detector having a semiconductor element that converts incident X-rays into electrical signals.

The rotating frame 13 is an annular frame that supports the X-ray tube 11 and the X-ray detector 12 facing each other, and rotates the X-ray tube 11 and the X-ray detector 12 by a control device 15, which will be described later. An image field of view (FOV) is set in the opening 19 of the rotating frame 13. For example, the rotating frame 13 is cast from aluminum. Note that, in addition to the X-ray tube 11 and the X-ray detector 12, the rotating frame 13 can also support an X-ray high voltage device 14, a wedge 16, a collimator 17, a DAS 18, and the like. Further, the rotating frame 13 can further support various configurations not shown in FIG. 1.

The X-ray high voltage device 14 includes a high voltage generator and an X-ray control device. The high voltage generator includes electric circuits such as a transformer and a rectifier, and generates a high voltage to be applied to the X-ray tube 11 and a filament current to be supplied to the X-ray tube 11. The X-ray control device controls the output voltage according to the X-rays emitted by the X-ray tube 11. The high voltage generator may be of a transformer type or an inverter type. The X-ray high voltage device 14 may be provided on the rotating frame 13 within the gantry 10, or may be provided on a fixed frame (not shown) within the gantry 10. Note that the fixed frame is a frame that rotatably supports the rotating frame 13.

The control device 15 includes a drive mechanism such as a motor and an actuator, and a processing circuit including a processor, memory, etc. that controls the drive mechanism. The control device 15 receives input signals from the input interface 43, an input interface provided on the pedestal 10, etc., and controls the operation of the pedestal 10 and the bed 30. The operation control by the control device 15 includes, for example, control to rotate the rotating frame 13, control to tilt the gantry 10, control to operate the bed 30, and the like. Note that the control for tilting the pedestal 10 is achieved by the control device 15 rotating the rotating frame 13 around an axis parallel to the X-axis direction based on the tilt angle information input by the input interface attached to the pedestal 10. be done. Note that the control device 15 may be provided on the pedestal 10 or may be provided on the console 40.

The wedge 16 is a filter for adjusting the amount of X-rays irradiated from the X-ray tube 11. Specifically, the wedge 16 transmits and attenuates the X-rays emitted from the X-ray tube 11 so that the X-rays emitted from the X-ray tube 11 to the subject P have a predetermined distribution. This is a filter that For example, the wedge 16 is a wedge filter or a bow-tie filter, and is formed by processing aluminum or the like to have a predetermined target angle and a predetermined thickness.

The collimator 17 limits the irradiation range of the X-rays that have passed through the wedge 16. The collimator 17 slidably supports a plurality of lead plates that shield X-rays, and adjusts the shape of the slit formed by the plurality of lead plates. Note that the collimator 17 is sometimes called an X-ray diaphragm.

The DAS 18 reads out an electrical signal from the X-ray detector 12 according to the dose of X-rays detected by the X-ray detector 12 . The DAS 18 amplifies the read electrical signal and integrates (adds) the electrical signal over the viewing period to collect detection data having a digital value corresponding to the X-ray dose over the viewing period. The detected data is called projection data. The DAS 18 is realized, for example, by an application specific integrated circuit (ASIC) equipped with circuit elements capable of generating projection data. The projection data is transmitted to the console 40 via a non-contact data transmission device or the like.

The detection data generated by the DAS 18 is sent to a non-rotating portion of the pedestal 10 (for example, a fixed frame, as shown in FIG. (omitted) is transmitted to a receiver equipped with a photodiode, and transferred to the console 40. Note that the method of transmitting the detection data from the rotating frame 13 of the rotating part to the non-rotating part of the pedestal 10 is not limited to the above-mentioned optical communication, but any method of non-contact data transfer may be used. .

In this embodiment, an X-ray CT apparatus 1 equipped with an integral type X-ray detector 12 will be explained as an example, but the technology according to this embodiment is applicable to a case where a photon-counting type X-ray detector is installed. It can also be realized as an X-ray CT apparatus 1.

The bed 30 is a device on which a subject P to be scanned is placed and moved. The bed 30 includes a base 31, a bed driving device 32, a top plate 33, and a support frame 34. The base 31 is a casing that supports the support frame 34 movably in the vertical direction. The bed driving device 32 is a drive mechanism that moves the top plate 33 on which the subject P is placed in the longitudinal direction of the top plate 33. The bed driving device 32 includes a motor, an actuator, and the like. The top plate 33 is a plate on which the subject P is placed. The top plate 33 is provided on the upper surface of the support frame 34. The top plate 33 can protrude from the bed 30 toward the gantry 10 so that the whole body of the subject P can be photographed. The top plate 33 is made of, for example, carbon fiber reinforced plastic (CFRP), which has good X-ray transparency and physical properties such as rigidity and strength. Further, for example, the inside of the top plate 33 is hollow. The support frame 34 supports the top plate 33 so as to be movable in the longitudinal direction of the top plate 33. In addition to the top plate 33, the bed driving device 32 may move the support frame 34 in the longitudinal direction of the top plate 33.

Console 40 has memory 41 , display 42 , input interface 43 and processing circuitry 44 . Data communication between the memory 41, display 42, input interface 43, and processing circuit 44 is performed via a bus (BUS). Although the console 40 will be described as being separate from the pedestal 10, the pedestal 10 may include the console 40 or a part of each component of the console 40.

The memory 41 is realized by, for example, a RAM, a semiconductor memory device such as a flash memory, a hard disk, an optical disk, or the like. For example, the memory 41 stores projection data and reconstructed image data. Further, for example, the memory 41 stores various programs. Note that the storage area of the memory 41 may be located within the X-ray CT apparatus 1 or may be located within an external storage device connected via a network.

The display 42 displays various information. For example, the display 42 displays a medical image (for example, a CT image) generated by the processing circuit 44, a GUI (Graphical User Interface) for accepting various operations from an operator, and the like. The information displayed on the display 42 includes a medical image including a region of interest, a stretched output image, a polar coordinate output image, a segmented output image, an annular structure, and a numerical value after quantification, according to the embodiment. As the display 42, various arbitrary displays can be used as appropriate. For example, as the display 42, a liquid crystal display (LCD), a cathode ray tube (CRT) display, an organic electro luminescence display (OELD), or a plasma display can be used.

Note that the display 42 may be provided anywhere in the control room. Further, the display 42 may be provided on the pedestal 10. Further, the display 42 may be of a desktop type, or may be configured of a tablet terminal or the like that can communicate wirelessly with the main body of the console 40. Furthermore, one or more projectors may be used as the display 42. Here, the display 42 is an example of a display section.

The input interface 43 receives various input operations from an operator, converts the received input operations into electrical signals, and outputs the electrical signals to the processing circuit 44 . For example, the input interface 43 receives from the operator acquisition conditions when collecting projection data, reconstruction conditions when reconstructing a CT image, image processing conditions when generating a post-processed image from a CT image, etc. . Further, for example, the input interface 43 receives calculation conditions and the like when calculating the distribution of lesion amount with respect to an anatomical structure from CT image data from the operator.

As the input interface 43, for example, a mouse, keyboard, trackball, switch, button, joystick, touch pad, touch panel display, etc. can be used as appropriate. Note that in this embodiment, the input interface 43 is not limited to one that includes these physical operation components. For example, examples of the input interface 43 include an electrical signal processing circuit that receives an electrical signal corresponding to an input operation from an external input device provided separately from the device and outputs this electrical signal to the processing circuit 44. . Further, the input interface 43 may be provided on the pedestal 10. Furthermore, the input interface 43 may be configured with a tablet terminal or the like that can communicate wirelessly with the console 40 main body.

The processing circuit 44 controls the overall operation of the X-ray CT apparatus 1 . The processing circuit 44 includes a processor and memory such as ROM and RAM as hardware resources. The processing circuit 44 has a system control function 441, an image generation function 442, an image processing function 443, an acquisition function 444, a stretch transformation function 445, a coordinate transformation function 446, an extraction function 447, and a processor that executes a program developed in the memory. Execute a quantification function 448, etc.

As the system control function 441, the processing circuit 44 can control various functions of the processing circuit 44 based on input operations received from the operator via the input interface 43. For example, processing circuit 44 can control a CT scan performed on gantry 10 . The processing circuit 44 can acquire volume data regarding the subject P using an image generation function 442 and an image processing function 443, which will be described later, based on the detection data obtained from the CT scan. In this embodiment, as an example, a case will be described in which volume data including at least a region of interest is acquired. Here, the region of interest is the tumor region. Note that the tumor region may be any part of the brain, liver, lung, or the like.

Note that the processing circuit 44 may acquire volume data regarding the subject P from outside the X-ray CT apparatus 1. Further, in this embodiment, a case is illustrated in which volume data obtained by, for example, the X-ray CT apparatus 1 is used, but volume data obtained by another medical image diagnostic apparatus may be used.

As the image generation function 442, the processing circuit 44 generates data by subjecting the detection data output from the DAS 18 to pre-processing such as logarithmic conversion processing, offset correction processing, inter-channel sensitivity correction processing, and beam hardening correction. can do. Processing circuit 44 can store the generated data in memory 41. Note that the data before preprocessing (detection data) and the data after preprocessing may be collectively referred to as projection data. The processing circuit 44 performs reconstruction processing on the generated projection data (projection data after preprocessing) using a filtered back projection method, a successive approximation reconstruction method, machine learning, etc., to convert the CT image data into CT image data. can be generated. The processing circuit 44 can store the generated CT image data in the memory 41.

As the image processing function 443, the processing circuit 44 converts the CT image data generated by the image generation function 442 into a tomographic image of an arbitrary cross section by a known method based on input operations received from the operator via the input interface 43. It can be converted into data or three-dimensional image data. For example, the processing circuit 44 performs three-dimensional image processing such as volume rendering, surface rendering, image value projection processing, MPR (Multi-Planar Reconstruction) processing, and CPR (Curved MPR) processing on the CT image data to perform arbitrary processing. Rendered image data in the viewpoint direction can be generated. Note that the image generation function 442 may directly generate three-dimensional image data such as rendered image data in an arbitrary viewpoint direction, that is, volume data. The processing circuit 44 can store tomographic image data and three-dimensional image data in the memory 41.

As the acquisition function 444, the processing circuit 44 acquires a medical image including a region of interest based on the CT image data generated by the image generation function 442, and acquires region of interest information, which is information regarding the region of interest, from the medical image. can do. As mentioned above, the region of interest is the tumor region. Further, the region of interest information includes shape information of the region of interest and position information of the region of interest. Furthermore, the processing circuit 44 can store the acquired medical image including the region of interest and region of interest information in the memory 41 . Here, the processing circuit 44 that implements the acquisition function 444 may be an example of an acquisition unit.

As the stretch transformation function 445, the processing circuit 44 can perform stretch transformation on the region of interest in the acquired medical image based on the region of interest information acquired by the acquisition function 444 to obtain a stretch output image. . Here, the stretch transformation performed on the region of interest in the acquired medical image means geometrically transforming the region of interest so that the region of interest has a perfect circular shape or a substantially perfect circular shape. Here, when the processing circuit 44 performs stretch conversion, existing techniques such as nearest neighbor and bilinear interpolation can be used. Further, the processing circuit 44 can store the obtained stretch output image in the memory 41. Here, the processing circuit 44 that implements the stretch conversion function 445 may be an example of a stretch conversion section.

As the coordinate transformation function 446, the processing circuit 44 performs polar coordinate transformation on the region of interest after stretch transformation, which is the region of interest in the stretch output image obtained by the stretch transformation function 445, to transform the annular shape of the region of interest in the stretch output image. The structure can be converted to a tubular structure to obtain a polar coordinate output image. Here, when the processing circuit 44 performs coordinate transformation, existing techniques such as nearest neighbor and bilinear interpolation can be used. Further, the processing circuit 44 can store the obtained polar coordinate output image in the memory 41. Here, the processing circuit 44 that implements the coordinate transformation function 446 may be an example of a coordinate transformation unit.

As the extraction function 447, the processing circuit 44 can extract the tubular structure of the region of interest in the polar coordinate output image obtained by the coordinate transformation function 446, and subdivide the tubular structure to obtain a subdivided output image. Here, the processing circuit 44 can extract the tubular structure of the region of interest in the polar coordinate output image based on an image segmentation algorithm. Image segmentation algorithms typically include threshold-based segmentation methods, region-based segmentation methods, edge-based segmentation methods, and specific theory-based segmentation methods. Here, for example, a division method based on edges is used. Available edge detection models include the first-order operators Roberts operator, Prewitt operator, Sobel operator, Canny operator, and second-order operator Laplacian operator. Further, the extracted tubular structure is refined by a fragmentation process. Various existing algorithms can be used for the subdivision process, such as the Hilditch algorithm, Rosenfeld algorithm, Pavlidis algorithm, Zhang-Suen algorithm, and subdivision algorithm based on index table inquiry. Further, the processing circuit 44 can store the obtained segmented output image in the memory 41. Here, the processing circuit 44 that implements the extraction function 447 may be an example of an extraction unit.

As the quantification function 448, the processing circuit 44 can perform a quantification calculation of the feature from the subdivided output image obtained by the extraction function 447, and obtain a numerical value after quantification. Here, the quantified feature calculation is, for example, calculating the ratio of the number of pixels of the tubular structure after segmentation in the segmented output image to the pixels of the entire image on the polar coordinate axis. Thereby, the numerical value after quantification may be a value of [0, 1], for example. Further, the numerical value after quantification may be, for example, a value of [0, 2π] obtained by multiplying a value within the range of [0, 1] by 2π. Further, the processing circuit 44 may store the obtained numerical value after quantification in the memory 41. Here, the processing circuit 44 that implements the quantification function 448 may be an example of a quantification unit.

Note that each of the functions 441 to 448 is not limited to being implemented by a single processing circuit. For example, the processing circuit 44 may be configured by combining a plurality of independent processors, and the functions 441 to 448 may be realized by each processor executing each program. Here, each of the functions 441 to 448 may be realized by being distributed or integrated in a single or multiple processing circuits as appropriate.

Furthermore, although the console 40 has been described as a single console that executes multiple functions, different consoles may execute the multiple functions. For example, different consoles may distribute and implement the functions of the processing circuit 44, such as the image generation function 442, the image processing function 443, the acquisition function 444, the stretch transformation function 445, the coordinate transformation function 446, the extraction function 447, and the quantification function 448. I don't mind if you do.

Furthermore, part or all of the processing circuit 44 is not limited to being included in the console 40, but may be included in an integrated server that collectively processes detection data acquired by a plurality of medical image diagnostic apparatuses.

Here, the processing circuit 44 implements an acquisition function 444, a stretch transformation function 445, a coordinate transformation function 446, an extraction function 447, and a quantification function 448, thereby providing an acquisition section, a stretch transformation section, a coordinate transformation section, an extraction section, and A medical information quantification device is configured as a quantification unit.

The operation and specific example of the medical information quantification device according to the first embodiment will be described below with reference to FIGS. 2 to 5. FIG. 2 is a flowchart of an example of the operation of the medical information quantification device according to the first embodiment. FIG. 3 is a schematic diagram of a specific example of the medical information quantification device according to the first embodiment. FIG. 4 is a diagram illustrating an example of stretch conversion in the medical information quantification device according to the first embodiment. FIG. 5 is a diagram showing an example of quantification in the medical information quantification device according to the first embodiment.

As shown in FIG. 2, in step 100, the acquisition unit of the medical information quantification device acquires a medical image including a region of interest, acquires region of interest information from the medical image, and then proceeds to step 200. Here, the medical image including the region of interest acquired by the acquisition unit may be, for example, the original tumor region image shown in FIG. 3(a). In this original tumor region image, only the tumor region that is the region of interest is shown, and irrelevant parts other than the tumor region have been removed by image processing. Furthermore, in the example shown in FIG. 3, the tumor region includes annular emphasis features (white bright areas). Further, in the example shown in FIG. 3, the region of interest information acquired by the acquisition unit may be shape information of the region of interest and position information of the region of interest. Here, the shape of the region of interest is, for example, an approximately ellipse circumscribing the tumor region, as shown in FIG. Including the direction and length of the major axis and minor axis. Further, the shape information of the region of interest may be indicated by position information of the region of interest in the medical image.

In step 200, the stretch conversion unit of the medical information quantification device performs stretch conversion on the region of interest in the medical image based on the region of interest information to obtain a stretch output image, and then proceeds to step 300. Here, the stretch output image may be, for example, the image shown in FIG. 3(b).

Here, with reference to FIG. 4, an example in which the stretch conversion unit performs stretch conversion on a region of interest in a medical image will be described. In FIG. 4, the ellipse in the left figure indicates the region of interest, the circle in the right figure indicates the circle obtained by stretch-transforming the region of interest, and points A, B, and C on the ellipse shown in the left figure are stretched and These are points A, B, and C on the circle shown in the figure.

In this embodiment, the stretch conversion unit calculates an image stretch direction based on the region of interest information, and stretches the region of interest in the medical image based on the image stretch direction. For example, in a medical image, stretch conversion is performed to change the short axis direction of the image based on region of interest information such as the position including the center of the ellipse shown in the left diagram of FIG. The stretch direction is calculated, and the region of interest in the medical image is stretch-transformed in the image stretch direction. As a result, the ellipse shown in the left diagram of FIG. 4 is stretched into a circle whose diameter is the long axis of the ellipse in the left diagram, as shown in the right diagram of FIG. This stretch transformation is performed, for example, so that the arcs included in the region of interest are arcs constituting approximately the same circle and have the same curvature at each location.

In the example shown in FIG. 4, in the left diagram, arc AB and arc BC have similar lengths but different spoke angles. If such a circular structure is extracted using a conventional circular structure extraction method, if the difference in spoke angle is too large, arc BC may not be extracted, or arc AB and arc BC may not be extracted as related circular structures. As a result, the accuracy of extracting a cyclic structure may decrease. On the other hand, when the region of interest is stretch-transformed as in this embodiment, the arc AB and the arc BC come to have similar lengths and similar spoke angles. This avoids the inability to extract arc BC or the inability to extract arc AB and arc BC as related annular structures when the difference in spoke angles is too large. Interference due to the annular structures having different spoke angles is eliminated, improving the accuracy of annular feature extraction.

Returning to FIG. 2, in step 300, the coordinate transformation unit of the medical information quantification device performs polar coordinate transformation on the region of interest in the stretch output image to transform the annular structure of the region of interest in the stretch output image into a tubular structure. A polar coordinate output image is obtained, and the process then proceeds to step 400. Here, the polar coordinate output image may be, for example, the image shown in FIG. 3(c).

Here, in the example shown in FIG. 3, when the coordinate transformation unit performs coordinate transformation, the circle center of the region of interest after stretching in the stretch output image shown in FIG. The right direction of the stretch output image shown in (b) is the polar angle of 0 degrees, the counterclockwise direction is the direction in which the polar angle increases in the positive direction, and the length of the center of each pixel of the region of interest is the radius vector. The region of interest in the output image is subjected to polar coordinate transformation for each pixel to obtain a polar coordinate output image shown in FIG. 3(c). In the polar coordinate output image shown in FIG. 3(c), the direction from the top to the bottom of the image is the polar angle direction from 0 degrees to 360 degrees. The direction from left to right of the image is the direction in which the radius vector increases from zero. As can be seen from FIGS. 3(b) and 3(c), the annular structure of the region of interest in the stretch output image has been converted into a tubular structure (white bright area).

Returning to FIG. 2, in step 400, the extraction unit of the medical information quantification device extracts the tubular structure of the region of interest in the polar coordinate output image, subdivides the tubular structure to obtain a segmented output image, and then, Proceed to step 500. Here, the segmented output image obtained by the extraction unit after the tubular structure is segmented may be, for example, the image shown in FIG. 3(d). In the segmented output image shown in FIG. 3(d), the white thin arc line represents the segmented tubular structure after the tubular structure obtained by the extraction unit is segmented, and each point on the arc line is , for example, represents one pixel.

Returning to FIG. 2, in step 500, the quantification unit of the medical information quantification device performs feature quantification calculations from the segmented output image to obtain numerical values after quantification.

Here, with reference to FIG. 5, an example in which the quantification unit performs quantification feature calculation from the segmented output image will be described. In Fig. 5, as in Figs. 3(c) and (d), the direction from top to bottom is the direction from the polar angle of 0 degrees to 360 degrees, and the direction from left to right is the direction of the radius vector. The direction increases from zero, and the black thin arc line represents the subdivided tubular structure after the tubular structure obtained by the extraction unit is subdivided, and each point on the black arc line represents one pixel, for example. represents. In the example shown in FIG. 5, it is assumed that there are a total of 512 pixels from top to bottom, that is, from a polar angle of 0 degrees to 360 degrees, and that there are 256 pixels on the black arc line. Therefore, the quantified numerical value of the black arch line can be defined as a numerical value within the range [0, 1], for example, 256 pixels/512 pixels=0.5. That is, in the circumferential direction from 0 degrees to 360 degrees, the annular structure occupies half. From this, it can be seen that the tumor region has a substantially semicircular annular structure. Further, the numerical value after quantification of the black arch line can be defined as an angular value within the range of [0, 2π], for example, 256 pixels/512 pixels*2π=π.

Furthermore, the pixels represented by each point on the black arc line are obtained through the known and reversible conversion process of original tumor region image→stitching output image→polar coordinate output image→segmentation output image, as described above. Therefore, by performing the inverse operation of the conversion process described above, it is possible to return the segmented tubular structure represented by the black arcs to the annular structure that is an element of the original tumor region image, and the original tumor region image of the annular structure. You can obtain location information at .

Returning to FIG. 3, the quantification unit performs quantification feature calculation on the segmented output image shown in FIG. .

Through the above-described processing, the annular structure of the region of interest can be extracted, the annular structure feature value of the region of interest can be calculated, and the position information of the annular structure in the original tumor region image can be obtained.

The medical information quantification device according to the first embodiment has been described in detail above, but the medical information quantification device according to the present application can be modified in various ways based on the first embodiment. . FIG. 6 is a flowchart of an example of the operation of the medical information quantification device according to the modification of the first embodiment.

As a first modification, for example, the medical information quantification device may further include an output unit (not shown) that outputs a numerical value in a fixed range after quantification. This output unit can be realized, for example, by the processing circuit 44 executing an output function (not shown). As a result, in the first modification, as shown in FIG. 6, step 600 is executed after step 500 of the first embodiment described above, and in step 600, the output unit A fixed range of numbers is output. Furthermore, as shown in FIG. 3(e), this output unit can superimpose and display the annular structure obtained by the inverse operation of the above-described conversion process so as to be emphasized on the original tumor region image. can. This allows the cyclic structure to be presented in a form that is obvious at a glance.

Further, as a second modification, for example, the medical information quantification device may further include a display control unit (not shown) that causes the segmented output image to be displayed on a display. This display control section can be realized, for example, by the processing circuit 44 executing a display control function (not shown). As a result, in the second modification, after step 400 of the first embodiment described above, step 700 is executed in parallel with step 500, and in step 700, the display control unit controls the segmented output. The image is displayed on display 42. Thereby, by displaying the segmented output image, it is possible to present the extraction results regarding the annular structure.

Note that Modification 1 and Modification 2 may be implemented individually or in combination.

As described above, according to the first embodiment and its modification, the medical information quantification device acquires a medical image including a region of interest, and acquires region of interest information, which is information regarding the region of interest, from the medical image. an acquisition unit; a stretch conversion unit that performs stretch transformation on the region of interest in the medical image based on the region of interest information to obtain a stretch output image; and a stretch transformation unit that performs polar coordinate transformation on the region of interest in the stretch output image and performs stretching. A coordinate conversion unit that converts the annular structure of the region of interest in the output image into a tubular structure to obtain a polar coordinate output image, and extracts the tubular structure of the region of interest in the polar coordinate output image, subdivides the tubular structure, and outputs the segmented structure. It includes an extraction unit that obtains an image, and a quantification unit that performs quantification calculation of features from the subdivided output image and obtains a numerical value after quantification.

As a result, it is possible to extract a ring-enhanced structure suitable for a tumor region and calculate the quantification of the annular-enhanced feature without the need for annotation, and easily calculate the feature value of the quantified annular-enhanced feature with a simple configuration. Obtainable. Also, the position information of the annular structure in the original tumor region image can be obtained, which allows subsequent tasks to be performed easily. The stretch transformation also avoids the inability to extract arcs due to too large differences in spoke angles, or the inability to extract arcs as related annular structures, causing annular structures of the same length to differ depending on the tumor shape. Interference due to the presence of spoke angles is eliminated, and the accuracy of extracting annular features is improved. Further, the extraction result of the annular structure can be presented, the extracted annular structure can be displayed in a superimposed manner so as to be emphasized on the original tumor region image, and the annular structure can be presented in a form that is obvious at a glance.

(Second embodiment)
In the first embodiment, for a medical image including a region of interest, the annular structure of the region of interest is converted into a tubular structure by storage transformation and polar coordinate transformation on the region of interest based on the region of interest information, and then the tubular structure is extracted. We have explained the case of subdividing the data and performing quantitative feature calculation. However, the embodiments are not limited to this, and the technology of the present application is applied to improve the results obtained by performing classification and annular emphasis area segmentation based on the conventional technology, and It is possible to solve the technical problem that the results obtained by performing classification and annular enhancement region segmentation cannot be directly applied to subsequent tasks that require annular structure feature quantification values. In the second embodiment, a case will be described below in which the technology of the present application is applied to results obtained by performing classification and annular emphasis area segmentation based on the conventional technology.

Hereinafter, a medical information quantification device according to the second embodiment and an X-ray computed tomography apparatus equipped with the medical information quantification device according to the second embodiment will be described with reference to FIGS. 7 to 9. . FIG. 7 is a diagram illustrating an example of the configuration of an X-ray computed tomography apparatus equipped with a medical information quantification apparatus according to the second embodiment. FIG. 8 is a flowchart of an example of the operation of the medical information quantification device according to the second embodiment. FIG. 9 is a schematic diagram of a specific example of the medical information quantification device according to the second embodiment.

Note that, in the second embodiment, the same or similar components as those in the first embodiment are denoted by the same reference numerals, and detailed explanations are omitted as appropriate.

As shown in FIG. 7, an X-ray computed tomography apparatus equipped with the medical information quantification device according to the second embodiment and an X-ray computer equipped with the medical information quantification device according to the first embodiment The difference from the tomography apparatus is that a console 40a is provided instead of the console 40.

Specifically, the processing circuit 44a according to the second embodiment has a system control function 441, an image generation function 442, an image processing function 443, an acquisition function 444a, and a stretch conversion function using a processor that executes a program developed in a memory. 445a, a coordinate transformation function 446a, a subdivision function 447a, a quantification function 448a, etc.

As the acquisition function 444a, the processing circuit 44a acquires a medical image including an annular structure of a region of interest based on the CT image data generated by the image generation function 442a, and extracts a region of interest, which is information regarding the region of interest, from the medical image. information and annular structure information can be obtained. As mentioned above, the region of interest is the tumor region. Further, the region of interest information includes shape information of the region of interest and position information of the region of interest. Further, the annular structure information may be a result obtained by performing classification or annular emphasis region segmentation based on conventional techniques. This annular structure information can be acquired from an external image diagnostic device that performs classification and annular emphasis area segmentation based on the conventional technology, and the medical information quantification device according to the present embodiment can classify the annular structure information based on the conventional technology. In the case where the annular structure information is installed in an image diagnostic apparatus that performs annular emphasis area division, this annular structure information may be acquired from the image diagnostic apparatus that performs this installation. Furthermore, the processing circuit 44a can store the acquired medical image including the region of interest and region of interest information in the memory 41. Here, the processing circuit 44a that implements the acquisition function 444a may be an example of an acquisition unit.

As the stretch conversion function 445a, the processing circuit 44a performs stretch conversion on the annular structure of the region of interest in the acquired medical image based on the region of interest information and annular structure information acquired by the acquisition function 444, and performs stretch conversion. You can get the output image. Here, the stretch transformation performed on the annular structure of the region of interest in the acquired medical image is a geometric transformation of the region of interest so that the region of interest has a perfect circular shape or a substantially perfect circular shape. Here, when the processing circuit 44a performs stretch conversion, existing techniques such as nearest neighbor and bilinear interpolation can be used. Furthermore, the processing circuit 44a can store the obtained stretched output image in the memory 41. Here, the processing circuit 44a that implements the stretch conversion function 445a may be an example of a stretch conversion unit.

As the coordinate transformation function 446a, the processing circuit 44a performs polar coordinate transformation on the annular structure of the region of interest after stretch transformation, which is the annular structure of the region of interest in the stretch output image obtained by the stretch transformation function 445a, and outputs the stretch. A polar coordinate output image can be obtained by converting the annular structure of the region of interest in the image into a tubular structure. Here, when the processing circuit 44a performs coordinate transformation, existing techniques such as nearest neighbor and bilinear interpolation can be used. Furthermore, the processing circuit 44a can store the obtained polar coordinate output image in the memory 41. Here, the processing circuit 44a that implements the coordinate transformation function 446a may be an example of a coordinate transformation unit.

As the subdivision function 447a, the processing circuit 44a can obtain subdivided output images by subdividing the tubular structure in the polar coordinate output image obtained by the coordinate transformation function 446a. Here, the tubular structure in the polar coordinate output image is miniaturized by the subdivision process. Various existing algorithms can be used for the subdivision process, such as the Hilditch algorithm, Rosenfeld algorithm, Pavlidis algorithm, Zhang-Suen algorithm, and subdivision algorithm based on index table inquiry. Further, the processing circuit 44a can store the obtained segmented output image in the memory 41. Here, the processing circuit 44a that implements the subdivision function 447a may be an example of an extraction unit.

The quantification function 448 is the same as the quantification function 448 of the processing circuit 44 in the first embodiment, so a description thereof will be omitted here.

Furthermore, the processing circuit 44a implements an acquisition function 444a, a stretch transformation function 445a, a coordinate transformation function 446a, a subdivision function 447a, and a quantification function 448, thereby providing an acquisition section, a stretch transformation section, a coordinate transformation section, and a subdivision section. and a medical information quantification device as a quantification unit.

The operation and specific example of the medical information quantification device according to the second embodiment will be described below with reference to FIGS. 8 and 9.

As shown in FIG. 8, in step 100a, the acquisition unit of the medical information quantification device acquires a medical image including the annular structure of the region of interest, acquires region of interest information and annular structure information from the medical image, and then , proceed to step 200a. Here, the medical image including the annular structure of the region of interest acquired by the acquisition unit may be, for example, the original tumor region image shown in FIG. 9(a). In this original tumor region image, only the tumor region that is the region of interest is shown, and irrelevant parts other than the tumor region have been removed by image processing. Furthermore, in the example shown in FIG. 9, the tumor region includes annular emphasis features (white bright areas). Further, the region of interest information acquired by the acquisition unit may be shape information of the region of interest and position information of the region of interest. Further, the annular structure information acquired by the acquisition unit may be an image shown in (aa) of FIG. 9 .

In step 200a, the stretch conversion unit of the medical information quantification device performs stretch conversion on the annular structure of the region of interest in the medical image based on the region of interest information and annular structure information to obtain a stretch output image, Thereafter, the process proceeds to step 300. Here, the stretch output image may be, for example, the image shown in (bb) of FIG.

In this embodiment, the stretch conversion unit calculates an image stretch direction based on the region of interest information, and performs stretch conversion on the annular structure of the region of interest in the medical image based on the image stretch direction. This stretch transformation is performed, for example, so that the arcs of the annular structure of the region of interest are arcs that constitute approximately the same circle, and the curvatures at various locations are the same.

In step 300a, the coordinate transformation unit of the medical information quantification device performs polar coordinate transformation on the annular structure of the region of interest in the stretch output image, converts the annular structure of the region of interest in the stretch output image into a tubular structure, and converts the annular structure of the region of interest in the stretch output image into a tubular structure, and After obtaining the output image, proceed to step 400a. Here, the polar coordinate output image may be, for example, the image shown in (cc) in FIG.

Here, in the example shown in FIG. 9, when the coordinate conversion unit performs coordinate conversion, the center of the circle drawn by the annular structure after stretching in the stretch output image shown in (bb) of FIG. The right direction of the stretched output image shown in (bb) of FIG. 9 is the polar angle of 0 degrees, the counterclockwise direction is the direction in which the polar angle increases in the positive direction, and the length of the center of each pixel of the annular structure is The annular structure in the stretch output image is converted into polar coordinates for each pixel to obtain a polar coordinate output image shown in (cc) in FIG. 9. In the polar coordinate output image shown in (cc) of FIG. 9, the direction from the top to the bottom of the image is the polar angle direction from 0 degrees to 360 degrees. The direction from left to right of the image is the direction in which the radius vector increases from zero. As can be seen from (bb) and (cc) in FIG. 9, the annular structure of the region of interest in the stretch output image has been converted into a tubular structure (white bright part).

Returning to FIG. 8, in step 400a, the fragmentation unit of the medical information quantification device fragments the tubular structure in the polar coordinate output image to obtain a fragmentation output image, and then proceeds to step 500. Here, the segmented output image may be, for example, the image shown in (dd) of FIG. In the segmented output image shown in (dd) of FIG. 9, the white thin arc line represents the segmented tubular structure after the tubular structure has been segmented, and each point on the arc line is, for example, one pixel. represents.

Returning to FIG. 8, in step 500, the quantification unit of the medical information quantification device performs feature quantification calculations from the segmented output image to obtain numerical values after quantification.

Here, the method by which the quantification unit performs quantification feature calculation from the segmented output image is the same as that described in the first embodiment described above, so it will not be described repeatedly here. In this way, the quantification feature calculation is performed by the quantification unit on the segmented output image shown in (dd) of FIG. 9, and a quantification result that is a quantified value of 0.6 is obtained.

When the annular structure of the region of interest is extracted through the above-described processing, the annular structure feature value can be easily calculated, and the position information of the annular structure in the original tumor region image can be obtained.

As described above, according to the second embodiment, the medical information quantification device acquires a medical image including the annular structure of the region of interest, and extracts region of interest information and annular structure information that are information about the region of interest from the medical image. an acquisition unit that obtains a stretch output image by performing stretch transformation on the annular structure of a region of interest in a medical image based on the region of interest information and annular structure information; a coordinate transformation section that performs polar coordinate transformation on the annular structure of the region and converts the annular structure of the region of interest in the stretch output image into a tubular structure to obtain a polar coordinate output image; It includes a subdivision section that obtains a subdivision output image, and a quantification section that performs quantification calculation of features from the subdivision output image and obtains a numerical value after quantification.

As a result, it is possible to perform quantification calculation of the annular emphasis feature on the annular emphasis structure of the extracted tumor region without requiring annotation, and the feature value of the quantified annular emphasis feature can be calculated with a simple configuration. Furthermore, the position information of the annular structure in the original tumor region image can be obtained easily, which makes it possible to perform subsequent tasks conveniently, improving the conventional technology and making it widely applicable. The stretch transformation avoids the inability to extract arcs due to too large a difference in spoke angles, or the inability to extract arcs as related annular structures, and the stretch transformation avoids the inability to extract arcs due to too large a difference in spoke angles, or the arcs cannot be extracted as related annular structures. Interference due to the annular structures having different spoke angles is eliminated, improving the accuracy of annular feature extraction.

Further, in the second embodiment, it is possible to apply modification 1 and/or modification 2 of the first embodiment described above, thereby making it possible to present the extraction result of the annular structure. The annular structure thus obtained can be displayed in a superimposed manner so as to be emphasized on the original tumor region image, and the annular structure can be presented in a form that is obvious at a glance.

(Other embodiments)
In addition, in the description and drawings of the embodiment and its modifications, an example of the X-ray CT apparatus 1 was shown and explained, but the technology of the present application is not limited to this, and various modifications are possible, and as necessary. Can be combined as required.

For example, in the above description and drawings, the case where the acquisition function 444 is provided as an independent function is shown, but the present invention is not limited to this. May be omitted.

Further, in the above description and drawings, the shape of the region of interest is, for example, a substantially ellipse circumscribing the tumor region, but the shape of the region of interest is not limited to this, for example, the length of the region of interest is It may be an ellipse whose major axis is the maximum direction, whose major axis is the maximum length, and whose minor axis is the maximum width of the region of interest perpendicular to the major axis direction.

Furthermore, the term "processor" used in the description of the above-described embodiments refers to, for example, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or an Application Specific Integrated Circuit (ASIC). Circuits such as programmable logic devices (e.g., Simple Programmable Logic Devices (SPLDs), Complex Programmable Logic Devices (CPLDs), and Field Programmable Gate Arrays (FPGAs)) means. Here, instead of storing the program in the memory circuit, the program may be directly incorporated into the circuit of the processor. In this case, the processor realizes its functions by reading and executing a program built into the circuit. Furthermore, each processor of this embodiment is not limited to being configured as a single circuit for each processor, but may also be configured as a single processor by combining multiple independent circuits to realize its functions. good.

Here, the program executed by the processor is provided by being pre-installed in a ROM (Read Only Memory), a storage circuit, or the like. This program is a file in a format that can be installed or executable on these devices, such as CD (Compact Disk)-ROM, FD (Flexible Disk), CD-R (Recordable), DVD (Digital Versatile Disk), etc. The information may be provided recorded on a computer readable non-transitory storage medium. Further, this program may be stored on a computer connected to a network such as the Internet, and may be provided or distributed by being downloaded via the network. For example, this program is composed of modules including each of the processing functions described above. In actual hardware, a CPU reads a program from a storage medium such as a ROM and executes it, so that each module is loaded onto the main storage device and generated on the main storage device.

Furthermore, in the embodiments and modifications described above, each component of each device illustrated is functionally conceptual, and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distributing or integrating each device is not limited to what is shown in the diagram, and all or part of the devices may be functionally or physically distributed or integrated in arbitrary units depending on various loads and usage conditions. Can be integrated and configured. Further, each processing function performed by each device may be realized in whole or in part by a CPU and a program that is analyzed and executed by the CPU, or may be realized as hardware using wired logic.

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 may be performed manually. All or part of the described processing can also be performed automatically using known methods. In addition, information including processing procedures, control procedures, specific names, and various data and parameters shown in the above documents and drawings may be changed arbitrarily, unless otherwise specified.

Note that the various data handled in this specification are typically digital data.

According to at least one embodiment described above, it is possible to obtain a quantified feature value of an annular emphasis feature.

Although several embodiments have been described, these embodiments are presented by way of example and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, substitutions, changes, and combinations of embodiments can be made without departing from the gist of the invention. These embodiments and their modifications are included within the scope and gist of the invention as well as within the scope of the invention described in the claims and its equivalents.

1 X-ray CT device 40, 40a Console 44, 44a Processing circuit 444, 444a Acquisition function 445, 445a Stretch conversion function 446, 446a Coordinate conversion function 447 Extraction function 447a Subdivision function 448 Quantification function

Claims (14)

an acquisition unit that acquires a medical image including a region of interest and acquires region of interest information that is information regarding the region of interest from the medical image;
a stretch transformation unit that performs stretch transformation on the region of interest in the medical image based on the region of interest information to obtain a stretch output image;
a coordinate transformation unit that performs polar coordinate transformation on the region of interest in the stretch output image, converting the annular structure of the region of interest in the stretch output image into a tubular structure to obtain a polar coordinate output image;
an extraction unit that extracts a tubular structure in the region of interest in the polar coordinate output image, and subdivides the tubular structure to obtain a segmented output image;
A quantification unit that performs feature quantification calculation from the segmented output image to obtain a numerical value after quantification. A medical information quantification device. The stretch conversion unit calculates an image stretch direction based on the region of interest information, and performs stretch conversion on the region of interest in the medical image based on the image stretch direction.
The medical information quantification device according to claim 1. an acquisition unit that acquires a medical image including an annular structure of a region of interest, and acquires region of interest information and annular structure information that are information regarding the region of interest from the medical image;
a stretch transformation unit that performs stretch transformation on the annular structure of the region of interest in the medical image based on the region of interest information and the annular structure information to obtain a stretch output image;
a coordinate transformation unit that performs polar coordinate transformation on the annular structure of the region of interest in the stretch output image, converts the annular structure of the region of interest in the stretch output image into a tubular structure, and obtains a polar coordinate output image;
a subdivision unit that subdivides the tubular structure in the polar coordinate output image to obtain a subdivision output image;
A quantification unit that performs feature quantification calculation from the segmented output image to obtain a numerical value after quantification. A medical information quantification device. The stretch conversion unit calculates an image stretch direction based on the region of interest information, and performs stretch conversion on the annular structure of the region of interest in the medical image based on the image stretch direction.
The medical information quantification device according to claim 3. The region of interest information includes shape information of the region of interest and position information of the region of interest,
The medical information quantification device according to any one of claims 1 to 4. further comprising an output unit that outputs a quantified numerical value in a fixed range;
The medical information quantification device according to any one of claims 1 to 4. further comprising a display control unit that displays the segmented output image on a display;
The medical information quantification device according to any one of claims 1 to 4. The numerical value after the quantification is a numerical value in a fixed range,
The fixed range is [0,1] or [0,2π],
The medical information quantification device according to any one of claims 1 to 4. the region of interest is a tumor region;
The medical information quantification device according to any one of claims 1 to 4. an acquisition step of acquiring a medical image including a region of interest, and acquiring region of interest information that is information regarding the region of interest from the medical image;
a stretch transformation step of performing stretch transformation on the region of interest in the medical image based on the region of interest information to obtain a stretched output image;
a coordinate transformation step of performing polar coordinate transformation on the region of interest in the stretch output image, converting the annular structure of the region of interest in the stretch output image into a tubular structure to obtain a polar coordinate output image;
extracting a tubular structure in the region of interest in the polar coordinate output image, and subdividing the tubular structure to obtain a segmented output image;
A method for quantifying medical information, comprising: a quantification step of performing quantification calculation of features from the segmented output image to obtain a numerical value after quantification. an acquisition step of acquiring a medical image including an annular structure of a region of interest, and acquiring region of interest information and annular structure information that are information about the region of interest from the medical image;
a stretch transformation step of performing stretch transformation on the annular structure of the region of interest in the medical image based on the region of interest information and the annular structure information to obtain a stretch output image;
a coordinate transformation step of performing polar coordinate transformation on the annular structure of the region of interest in the stretch output image, converting the annular structure of the region of interest in the stretch output image into a tubular structure to obtain a polar coordinate output image;
a subdivision step of subdividing the tubular structure in the polar coordinate output image to obtain a subdivision output image;
A method for quantifying medical information, comprising: a quantification step of performing quantification calculation of features from the segmented output image to obtain a numerical value after quantification. an acquisition step of acquiring a medical image including a region of interest, and acquiring region of interest information that is information regarding the region of interest from the medical image;
a stretch transformation step of performing stretch transformation on the region of interest in the medical image based on the region of interest information to obtain a stretched output image;
a coordinate transformation step of performing polar coordinate transformation on the region of interest in the stretch output image, converting the annular structure of the region of interest in the stretch output image into a tubular structure to obtain a polar coordinate output image;
extracting a tubular structure in the region of interest in the polar coordinate output image, and subdividing the tubular structure to obtain a segmented output image;
A medical information quantification program that causes a computer to execute a quantification step of performing quantification calculation of features from the segmented output image to obtain a numerical value after quantification. an acquisition step of acquiring a medical image including an annular structure of a region of interest, and acquiring region of interest information and annular structure information that are information about the region of interest from the medical image;
a stretch transformation step of performing stretch transformation on the annular structure of the region of interest in the medical image based on the region of interest information and the annular structure information to obtain a stretch output image;
a coordinate transformation step of performing polar coordinate transformation on the annular structure of the region of interest in the stretch output image, converting the annular structure of the region of interest in the stretch output image into a tubular structure to obtain a polar coordinate output image;
a subdivision step of subdividing the tubular structure in the polar coordinate output image to obtain a subdivision output image;
A medical information quantification program that causes a computer to execute a quantification step of performing quantification calculation of features from the segmented output image to obtain a numerical value after quantification. comprising the medical information quantification device according to any one of claims 1 to 4;
Medical imaging diagnostic equipment.

Images