A motion module for evaluating the stability of radiomics texture features

Abstract

The present invention relates to a motion module for evaluating the stability of texture features in imaging genomics. The motion module is a pneumatic motion module, including a slide rail base, a research phantom and a motion cylinder. It can be combined with a phantom submodule. It adopts a pneumatic drive form, does not require an external power supply, and provides power through high-pressure gas to achieve the reciprocating motion of the object. Moreover, the built-in non-magnetic conductive material structure is adopted, so the motion module supports MRI scanning imaging and can be used to evaluate the image of the stability of the image feature value of the MRI image due to motion factors.

Description

[0001] This application is a divisional application of a patent application entitled "Texture simulation device and motion module for evaluating the stability of image genomics texture features". This application is a divisional application filed in response to the first examination opinion notice of the original application. The application date of the original application is August 12, 2019, and the application number is 201910738934.8. Technical Field

[0002] The present invention relates to the technical field of radiomics in medical image processing, and in particular to a motion module for evaluating the stability of radiomics texture features. Background Art

[0003] Radiomics is a technology that performs quantitative analysis based on image features. Radiomics using CT and MRI images is of great significance in tumor diagnosis, tumor treatment, and prediction of treatment effects. At present, radiomics has important clinical significance in predicting distant metastasis of oropharyngeal cancer, predicting vascular damage and prognosis of hepatocellular carcinoma, and predicting the prognosis and molecular phenotype of epithelial ovarian cancer through radiomics. In addition, there are also applied studies on radiomics based on MRI images in reflecting the histopathological parameters of thyroid cancer; using CT image features to determine whether there is distant metastasis of lymph nodes in patients with rectal cancer; and using image features to predict the histological grade of pancreatic neuroendocrine tumors.

[0004] In the study of radiomics, the image features that can be applied clinically should have three characteristics: repeatability, non-redundancy, and rich information. Repeatability is the most basic and important issue in radiomics. In the entire radiomics workflow, scanning equipment, scanning parameters, image reconstruction methods, repeated imaging time, region of interest segmentation, feature extraction, etc. will affect the stability of image features. Only image textures with good stability can be used for subsequent research. Therefore, how to find repeatable image features in the research process of radiomics is a very important issue.

[0005] At present, the methods for finding stable image features are mainly divided into two categories: First, research methods based on artificial phantoms. Second, research methods based on patients. The phantoms used in related studies, such as the CCR phantom of Mackin et al., are uniform box-shaped phantoms made of ten different materials. Although the phantom adopts an integrated structure, the internal material is relatively small and does not support the expansion of materials. More importantly, the inside of each box is a uniform material, which has a large defect in studying the image features of object shapes. Zhao et al. used materials of various shapes to place in a human-like chest phantom. Although this model can be used to study shape features, due to the large size of the model, it will produce more scattering, which will interfere with the results of the experiment. Secondly, simply placing objects of different shapes into the human-shaped phantom will affect the position during the movement, which is not conducive to the use of the model between multiple research centers. In addition, there are studies using human-shaped solid water models. This type of material is not only expensive, but also has less internal density and texture changes. The second method based on human body scan images is to find stable textures. In Fave et al.'s study on CBCT texture stability, 15 patients were used to repeat CT scans at intervals of 15 minutes. This method is costly and difficult to implement. This method results in additional scan doses to the patients and does not allow for stability studies of texture values ​​across multiple centers. Summary of the invention

[0006] The purpose of the present invention is to provide a motion module for evaluating the stability of radiomics texture features, so as to realize the research on the stability of radiomics texture features and determine the repeatable image feature types.

[0007] To achieve the above object, the present invention provides the following solutions:

[0008] The present invention provides a motion module for evaluating the stability of image genomics texture features, the motion module comprising a slide rail base, a research phantom and a motion cylinder; the motion cylinder and the research phantom are both arranged on the slide rail base, and the output end of the motion cylinder is connected to the research phantom to drive the research phantom to reciprocate on the slide rail of the slide rail base.

[0009] Optionally, the motion module further includes a proximity switch, a flow regulating valve and a conduit;

[0010] The gas in the gas storage bottle is communicated with the moving cylinder through the flow regulating valve and the conduit, and the proximity switch is arranged at the upper limit position of the moving range of the moving cylinder on the slide rail base.

[0011] Optionally, the range of motion of the CT scan is adjusted by adjusting the position of the proximity switch.

[0012] Optionally, the motion range of the MRI image is adjusted by adjusting the motion range of the motion cylinder.

[0013] Optionally, the motion module also includes a motion module shell, the top of the motion module shell is provided with a cross line for correcting the position, and two opposite sides of the motion module shell are each provided with a straight line for correcting the position; another two opposite sides of the motion module shell are each provided with four connecting holes.

[0014] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0015] The present invention provides a motion module for evaluating the stability of image genomics texture features, and the motion module is a pneumatic motion module, including a slide rail base, a research phantom and a motion cylinder. It can be combined with a phantom submodule. It adopts a pneumatic drive form, does not require an external power supply, and uses high-pressure gas to provide power to achieve the reciprocating motion of the object. Moreover, the built-in non-magnetic conductive material structure is adopted, so the motion module supports MRI scanning imaging and can be used to evaluate the image of the stability of the image feature value of the MRI image due to motion factors. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0017] Figure 1 A structural diagram of a housing of a phantom submodule provided by the present invention;

[0018] Figure 2 A structural diagram of the phantom submodule 200 provided by the present invention;

[0019] Figure 3 A structural diagram of the motif submodule 201 provided by the present invention;

[0020] Figure 4 A structural diagram of the motif submodule 202 provided by the present invention;

[0021] Figure 5 A structural diagram of the motif submodule 203 provided by the present invention;

[0022] Figure 6 A structural diagram of the motif submodule 204 provided by the present invention;

[0023] Figure 7 A structural diagram of the motif submodule 205 provided by the present invention;

[0024] Figure 8A structural diagram of the motif submodule 206 provided by the present invention;

[0025] Fig. 9 A structural diagram of the motif submodule 207 provided by the present invention;

[0026] Fig.10 A structural diagram of the motif submodule 208 provided by the present invention;

[0027] Fig.11 A structural diagram of the motif submodule 209 provided by the present invention;

[0028] Fig.12 A structural diagram of the motif submodule 210 provided by the present invention;

[0029] Fig.13 A structural diagram of the motif submodule 211 provided by the present invention;

[0030] Fig.14 A structural diagram of the motion module provided by the present invention;

[0031] Fig.15 A structural diagram of the motion module housing provided by the present invention;

[0032] Fig.16 A structural diagram of the top of the "concave" scattering material provided by the present invention;

[0033] Fig.17 This is a structural diagram of the bottom of the "concave" scattering material provided by the present invention. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0035] The purpose of the present invention is to provide a texture simulation device and a motion module for evaluating the stability of radiomics texture features, so as to realize the research on the stability of radiomics texture features and determine repeatable image features.

[0036] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0037] Example 1

[0038] The present invention provides a texture simulation device for evaluating the stability of radiomics texture features, the texture simulation device comprising a plurality of phantom submodules; the plurality of phantom submodules are respectively used to simulate different textures;

[0039] The mold submodule is a rectangular structure, the top of the mold submodule is provided with a cross line for correcting the position, and one group of two opposite sides of the mold submodule are provided with a straight line for correcting the position; another group of two opposite sides of the mold submodule are provided with four connecting holes; multiple mold submodules are connected in a single row through the connecting holes by means of plug-in connection.

[0040] Specifically, considering the characteristics of objects during scanning and imaging, in order to reduce the mutual interference between objects during imaging and avoid the scattering of the model itself during CT imaging, the present invention adopts a single-row arrangement of multiple phantom submodules. Taking into account the portability of the texture simulation device while meeting the requirements of imaging genomics for the volume of the region of interest, the size of each phantom submodule in the texture simulation device of the present invention is defined as 10*10*5cm. There are devices for connecting modules to each other on the opposite sides of each phantom submodule. The phantom submodules are connected by plugs. The positions of the phantom submodules can be freely combined to form different combined phantoms. The phantom is made variable. There is a "cross" for positioning on the phantom submodule, and there is a "one" for positioning on the opposite sides. Cooperate with the laser light inside the equipment or in the treatment room to improve the repeatability of the model scanning position. In addition, the "one" on both sides can be trained into a straight line after the modules are assembled and formed, which is used to ensure the quality of the phantom splicing.

[0041] The model submodule of the present invention comprises a model submodule shell, which is printed with ABS-ESD7 material and filled with one or more of wood chips, sycamore wood, rubber, acrylonitrile butadiene styrene polymer or polyetherimide resin.

[0042] Each mold submodule housing of the present invention is printed with ABS-ESD7 (acrylonitrile butadiene styrene polymer) material. Figure 1As shown, the top 10 and bottom 11 of the model submodule shell are 10mm thick, and the other side 12 is 3mm. Four connection holes 13 with a depth of 10mm and a diameter of 5mm are reserved at the top 10 and bottom 11 of each model. In conjunction with the plug 14, the free combination of the relative positions of the models and the free selection and combination of the various parts of the models can be achieved. There is a "cross" 15 for positioning on the top of the sub-model, and a "one" 16 for positioning on both sides. In conjunction with the laser light inside the equipment or in the treatment room, the repeatability of the model scanning position is improved. In addition, after the modules are assembled and formed, the "one" on both sides can be trained into a straight line to ensure the quality of model splicing.

[0043] Each phantom submodule is composed of different filling materials. Considering the density variation range of human tissues and organs, the present invention also sets different densities for the phantom submodules with the same filling material, so as to facilitate the subsequent acquisition and analysis of image features within different density ranges. According to the density of human tissues and the stability of the materials, a suitable filling material is selected for each phantom submodule.

[0044] like Figure 2 As shown, the interior of the phantom submodule 200 is filled with wood chips as an unstable texture, which can be used for stability research of a single scan.

[0045] like Figure 3 As shown, the interior of the model submodule 201 is filled with a piece of sycamore wood 300 with a relatively tight texture. As a natural texture, the texture of 300 has good repeatability within a certain period of time. It can be used for multi-center and multi-equipment research. The two wood blocks are used for data comparison. Therefore, 201 is connected to 200 through four plug rods 14.

[0046] like Figure 4 As shown, the interior of the model submodule 202 is also filled with sycamore wood 301, which has a texture similar to that of 201. The texture of 301 is similar to that of 300, and can not only be used to find textures with good repeatability, but also by comparing the texture values ​​of 201 and 202, the difference between the two can be found, which is used to determine whether the properties of the wood itself have changed.

[0047] like Figure 5 As shown, the interior of the phantom submodule 203 is filled with rubber filling 302. The density of the rubber 302 is not uniform, and there will be continuous grayscale changes after CT imaging. Stable and repeatable textures can be simulated. It can be used for research between multiple centers, multiple devices, and multiple scanning parameters.

[0048] like Figure 6 As shown, the interior of the mold submodule 204 is filled with ABS (acrylonitrile butadiene styrene polymer) three-dimensional mesh filling with 15% volume of 303. The internal mesh structure of 303 is relatively large, and the density is about 0.156g / cm 3, equivalent to the density of human lung CT imaging. Used to evaluate the stability of image features in low-density areas. Can be used to find repeatable textures. Can be used for research between multiple centers, multiple devices, and multiple scanning parameters.

[0049] like Figure 7 The interior of the mold submodule 205 is filled with ABS (acrylonitrile butadiene styrene polymer) in a three-dimensional mesh shape, which accounts for 30% of the volume of the 304 module. The density of 304 is about 0.315 g / cm 3 . It is used to evaluate the stability of image features in low-density areas. It can be used to find repeatable textures. It can be used for multi-center, multi-equipment, and multi-scan parameter studies.

[0050] like Figure 8 As shown, the ABS (acrylonitrile butadiene styrene polymer) three-dimensional mesh fills 60% of the volume of the 305 module inside the mold submodule 206. The density of the 305 module is about 0.63g / cm 3 . It is used to evaluate the stability of image features in low- and medium-density areas. It can be used to find repeatable textures. It can be used for multi-center, multi-equipment, and multi-scan parameter studies.

[0051] like Fig. 9 As shown, the interior of the mold submodule 207 is filled with ABS (acrylonitrile butadiene styrene polymer) three-dimensional mesh filling 95% of the volume of the 306 module. The density of the 306 module is about 1g / cm 3 , equivalent to the density of human tissue CT imaging. Used to evaluate the stability of muscle tissue regional imaging features. Can be used to find repeatable textures. Can be used for multi-center, multi-equipment, and multi-scan parameter research.

[0052] like Fig.10 As shown, the interior of the phantom submodule 208 is filled with ULTEM 9085 resin (polyetherimide) three-dimensional mesh filling 95% of the volume of the square block 307. The density of 307 is 1.28-1.3. Its density is approximately the density of human bone tissue. It is used to evaluate the stability of the image characteristics of the density area of ​​bone tissue. It can be used to find repeatable textures. It can be used for research between multiple centers, multiple devices, and multiple scanning parameters.

[0053] like Fig.11 As shown, the phantom submodule 209 is filled with ABS+ULTEM 9085 resin 310. An elliptical ULTEM 9085 resin 309 is embedded inside the square 308 printed with ABS material. After imaging, this material is used to evaluate the stability of shape-based imaging features. It can be used for multi-center, multi-equipment, and multi-scanning parameter research.

[0054] like Fig.12As shown, the phantom submodule 210 is composed of ABS+ULTEM 9085 resin 311 filled with ABS material 312, and an irregular multi-angle ULTEM 9085 resin 313 is embedded inside. After printing, the material is used to evaluate the stability of shape-based imaging features. It can be used for multi-center, multi-equipment, and multi-scanning parameter research.

[0055] like Fig.13 As shown, the model submodule 211 is an empty box body printed using ABS. The top 10 of 211 is detachable. The boxed part is in an empty box state. It allows researchers to choose research materials suitable for them. Multiple boxes can be stacked to achieve the expansibility of this model.

[0056] The texture simulation device further comprises a motion module 212, and the motion module 212 is connected to the plurality of the phantom sub-modules in a single row by means of a plug-in connection.

[0057] like Figure 14-15 As shown, the motion module includes a slide rail base 401, a research model 402 and a motion cylinder 403; the motion cylinder 403 and the research model 402 are both arranged on the slide rail base 401, and the output end of the motion cylinder 403 is connected to the research model 402, which is used to drive the research model 402 to reciprocate on the slide rail of the slide rail base 401. The motion module also includes a proximity switch 406, a flow regulating valve 405 and a conduit 404; the gas in the gas storage bottle is connected to the motion cylinder 403 through the flow regulating valve 405 and the conduit 404, and the proximity switch 406 is arranged at the upper limit position of the motion range of the motion cylinder on the slide rail base. The motion module also includes a motion module housing 407 which is a transparent shell, a crosshair 408 for position correction is arranged on the top of the motion module housing 407, and a straight line 409 for position correction is arranged on one set of two opposite sides of the motion module housing; and four connection holes 410 are arranged on another set of two opposite sides of the motion module housing, which are connected to the mold body submodule through a plug rod to form a whole. In addition, gas power is provided externally through a nylon high-pressure gas cylinder.

[0058] The motion module of the present invention is pneumatically driven. 212 uses high-pressure gas as power. The driving force generated by the high-pressure gas drives the cylinder 403 to do reciprocating motion. When using CT scanning, the motion amplitude is adjusted by adjusting the position of the proximity switch 406. When used in nuclear magnetic resonance imaging, different motion ranges are achieved by replacing cylinders with different motion ranges. The research modules with different fillers carried by the matching platform are used to achieve different scientific research purposes. As the first motion platform dedicated to imaging genomics, the advantages of the motion module of the present invention are: 1. Pneumatic power output, avoiding iron components, and enabling MRT scanning. 2. It can be connected with the phantom sub-module, and relevant motion images can be obtained through one scan, saving scanning time and reducing experimental costs. 3. The matching supporting models are rich in variety and can achieve multiple functions. At the same time, the platform supports the further expansion of scanning models, allowing scientific researchers to build suitable scientific research imaging materials by themselves. 4. The outer shell of the motion module has a "cross" and a "one" for positioning, which can ensure the consistency of accurate scanning positions during multiple scans. 5. The motion module supports adjustable speed and can achieve different motion frequencies and motion amplitudes. Used to study the effects of different motion frequencies and amplitudes on image characteristics.

[0059] like Figure 16-17 As shown, the texture simulation device also includes a scattering accessory, and a plurality of the phantom submodules are arranged inside the scattering accessory. The scattering accessory is composed of a double "concave"-shaped equivalent water material, including a "concave"-shaped scattering material bottom 504 and a "concave"-shaped scattering material top 506. The "concave"-shaped scattering material bottom 504 has four connecting holes 505, and the "concave"-shaped scattering material top 506 also has four connecting holes 507. The two parts are connected by a plug 14 through the spaces 505 and 507. It is used to study the influence of scattering on texture.

[0060] The texture simulation device further includes a scattering accessory, and a plurality of the phantom submodules are arranged inside the scattering accessory. The phantom body scattering accessory includes a "concave"-shaped scattering material top 506 and a "concave"-shaped scattering material bottom 504, the "concave"-shaped scattering material top 506 and the "concave"-shaped scattering material bottom 504 are symmetrical to each other, the thickness of the "concave"-shaped scattering material top 506 is 2 cm, 4 cm or 6 cm, the thickness of the "concave"-shaped scattering material bottom 504 is 2 cm, 4 cm or 6 cm, and the thickness of the "concave"-shaped scattering material top 506 and the "concave"-shaped scattering material bottom 504 are different.

[0061] Example 2

[0062] The present invention also provides a motion module for evaluating the stability of image genomics texture features, the motion module comprising a slide rail base, a research phantom and a motion cylinder; the motion cylinder and the research phantom are both arranged on the slide rail base, and the output end of the motion cylinder is connected to the research phantom to drive the research phantom to reciprocate on the slide rail of the slide rail base.

[0063] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0064] The present invention adopts the phantom submodules to facilitate repeated scanning. Through the built-in materials of various textures and various shapes and densities, the repeatability of various image features can be evaluated in a single scan.

[0065] The phantom submodules in the present invention adopt an integrated manufacturing method, which is easy to carry and move, and can realize the stable research of the image characteristic values ​​of medical images between multiple centers.

[0066] The phantom submodules in the present invention are all arranged in a single layer, which can minimize the impact of scattering on the stability of image features during the research process.

[0067] The scattering accessories matched with the phantom submodule of the present invention can evaluate the influence of different degrees of scattering on the stability of image characteristic values ​​through equivalent water materials of different thicknesses.

[0068] The pneumatic motion module of the present invention can be used in conjunction with the phantom submodule or can be used alone, and can be used to study the effects of motion on CT and MRI image features.

[0069] The positioning auxiliary markers in the present invention can achieve position standardization during multi-center scanning, and minimize the impact of scanning position differences on image feature values.

[0070] In the present invention, the modules are freely connected by plug rods, and an expandable platform is left, allowing researchers to reasonably match and combine them according to their own needs and add imaging materials by themselves.

[0071] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0072] This article uses specific examples to illustrate the principles and implementation methods of the invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. The described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

Claims

1. A motion module for evaluating the stability of radiomics texture features. It is characterized in that The motion module includes a slide rail base, a research phantom and a motion cylinder; the motion cylinder and the research phantom are both arranged on the slide rail base, the output end of the motion cylinder is connected to the research phantom, and the motion cylinder is used to drive the research phantom to reciprocate on the slide rail of the slide rail base; The motion module further comprises a motion module housing; a cross line for correcting the position is arranged on the top of the motion module housing, and a straight line for correcting the position is arranged on one set of two opposite sides of the motion module housing; and four connection holes are arranged on another set of two opposite sides of the motion module housing; The motion module and the plurality of phantom submodules are connected in a single row by means of a plug-in connection; the plurality of phantom submodules are respectively used to simulate different textures; the phantom submodule is a rectangular parallelepiped structure, a cross line for position correction is provided on the top of the phantom submodule, and a straight line for position correction is provided on a set of two opposite sides of the phantom submodule; and four connection holes are provided on another set of two opposite sides of the phantom submodule; The texture simulation device also includes a scattering accessory, and multiple model sub-modules are arranged inside the scattering accessory. The scattering accessory is composed of a double "concave"-shaped equivalent water material, including a "concave"-shaped scattering material bottom and a "concave"-shaped scattering material top. The "concave"-shaped scattering material has four connecting holes at the bottom, and the "concave"-shaped scattering material also has four connecting holes at the top. The two parts are connected by connecting holes and plug rods.

2. The motion module for evaluating the stability of radiomics texture features according to claim 1, It is characterized in that The motion module also includes a proximity switch, a flow regulating valve and a conduit; The gas in the gas storage bottle is communicated with the moving cylinder through the flow regulating valve and the conduit, and the proximity switch is arranged at the upper limit position of the moving range of the moving cylinder on the slide rail base.

3. The motion module for evaluating the stability of radiomics texture features according to claim 2, It is characterized in that The range of motion of the CT scan is adjusted by adjusting the position of the proximity switch.

4. The motion module for evaluating the stability of radiomics texture features according to claim 1, It is characterized in that The motion range of the magnetic resonance imaging is adjusted by adjusting the motion range of the motion cylinder.

Images