Image information quantitative analysis method and device, computer equipment and storage medium

Abstract

The invention relates to an image information quantitative analysis method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining a first target image of a target part, and a second target image of the target part; identifying a plurality of first target blood vessels corresponding to the target part in the first target image and a plurality of second target blood vessels corresponding to the target part in the second target image; and comparing the first quantitative information corresponding to each first target blood vessel with the second quantitative information corresponding to each second target blood vessel to obtain a corresponding embolism condition comparison result. According to the method and the device, the problem that the embolism condition cannot be accurately evaluated is solved, and the embolism condition is accurately evaluated.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a method, device, computer equipment and storage medium for quantitative analysis of image information. Background Art

[0002] Embolization is an important technique in interventional therapy. It involves injecting a plug into the blood vessels supplying the diseased organ in a controlled manner through an arterial or intravenous catheter to block it and interrupt the blood supply in order to control bleeding, treat tumors and vascular lesions, etc. The embolization effect is an important factor affecting the patient's prognosis. In the prior art, the embolization of tumor blood vessels is usually qualitatively evaluated based on empirical information with reference to the collected angiography images. However, due to the influence of personal subjective factors, this method cannot accurately evaluate the embolization situation.

[0003] There is currently no effective solution to the problem that related technologies cannot accurately assess embolism conditions. Summary of the invention

[0004] In this embodiment, a method, apparatus, computer device and storage medium for quantitative analysis of image information are provided to solve the problem that the embolism situation cannot be accurately assessed in the related art.

[0005] In a first aspect, a method for quantitative analysis of image information is provided in this embodiment, the method comprising:

[0006] Acquire a first target image of a target part, and a second target image of the target part;

[0007] identifying a plurality of first target blood vessels corresponding to the target part in the first target image, and a plurality of second target blood vessels corresponding to the target part in the second target image;

[0008] The first quantitative information corresponding to each of the first target blood vessels is compared with the second quantitative information corresponding to each of the second target blood vessels to obtain a corresponding embolism situation comparison result.

[0009] In some embodiments, comparing the first quantitative information corresponding to each of the first target blood vessels with the second quantitative information corresponding to each of the second target blood vessels to obtain a corresponding embolism comparison result includes:

[0010] Determining first quantitative information corresponding to each of the first target blood vessels, and second quantitative information corresponding to each of the second target blood vessels;

[0011] Comparing the first quantitative information with the second quantitative information accordingly, and determining state change information between each of the first target blood vessels and each of the second target blood vessels according to the comparison result;

[0012] Based on the state change information, a corresponding embolism situation comparison result is determined.

[0013] In some embodiments, determining the first quantitative information corresponding to each of the first target blood vessels and the second quantitative information corresponding to each of the second target blood vessels includes:

[0014] Extracting features of each of the first target blood vessels and each of the second target blood vessels respectively to obtain blood vessel features of each of the first target blood vessels and blood vessel features of each of the second target blood vessels;

[0015] determining, based on the vascular characteristics of each of the first target blood vessels, the first quantitative information corresponding to each of the first target blood vessels;

[0016] Based on the blood vessel characteristics of each second target blood vessel, the second quantitative information corresponding to each second target blood vessel is determined.

[0017] In some embodiments, the comparing the first quantitative information with the second quantitative information, and determining the state change information between the first target blood vessel and the second target blood vessel according to the comparison result, includes:

[0018] Classifying each of the first target blood vessels into a plurality of categories, and classifying each of the second target blood vessels into a plurality of categories;

[0019] Traversing each of the categories, comparing the first quantitative information of each of the first target blood vessels with the second quantitative information of each of the second target blood vessels in the same category, to obtain a comparison result corresponding to each of the categories;

[0020] According to each of the comparison results, state change information between each of the first target blood vessels and each of the second target blood vessels is determined.

[0021] In some embodiments, determining the corresponding embolism comparison result based on the state change information includes:

[0022] Determine a ratio of the state change information to the first quantitative information; the state change information is a difference between the first quantitative information and the second quantitative information;

[0023] The ratio is used as the comparison result of the embolism situation.

[0024] In some embodiments, the first target image and the second target image are angiography images; and the identifying a plurality of first target blood vessels corresponding to the target part in the first target image and a plurality of second target blood vessels corresponding to the target part in the second target image comprises:

[0025] Performing subtraction processing on the first target image and the second target image respectively to obtain a first subtracted image corresponding to the first target image and a second subtracted image corresponding to the second target image;

[0026] A plurality of first target blood vessels corresponding to the target site in the first subtracted image and a plurality of second target blood vessels corresponding to the target site in the second subtracted image are identified.

[0027] In some of the embodiments, before performing subtraction processing on the first target image and the second target image to obtain a first subtracted image corresponding to the first target image and a second subtracted image corresponding to the second target image, the method further includes:

[0028] acquiring an original scan image of the target site before contrast agent injection;

[0029] Based on the original scanned image, the first target image and the second target image are respectively registered.

[0030] In a second aspect, in this embodiment, a device for quantitative analysis of image information is provided, the device comprising: an acquisition module, a recognition module and an evaluation module;

[0031] The acquisition module is used to acquire a first target image of the target part and a second target image of the target part;

[0032] The recognition module is used to recognize a plurality of first target blood vessels corresponding to the target part in the first target image, and a plurality of second target blood vessels corresponding to the target part in the second target image;

[0033] The evaluation module is used to compare the first quantitative information corresponding to each of the first target blood vessels with the second quantitative information corresponding to each of the second target blood vessels to obtain a corresponding embolism situation comparison result.

[0034] In a third aspect, a computer device is provided in this embodiment, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for quantitative analysis of image information described in the first aspect above is implemented.

[0035] In a fourth aspect, a storage medium is provided in this embodiment, on which a computer program is stored, and when the program is executed by a processor, the method for quantitative analysis of image information described in the first aspect is implemented.

[0036] Compared with the related art, the image information quantitative analysis method, device, computer equipment and storage medium provided in the present embodiment obtain a first target image of the target part and a second target image of the target part; identify multiple first target blood vessels corresponding to the target part in the first target image and multiple second target blood vessels corresponding to the target part in the second target image; compare the first quantitative information corresponding to each first target blood vessel with the second quantitative information corresponding to each second target blood vessel to obtain the corresponding embolism situation comparison result, thereby solving the problem of being unable to accurately evaluate the embolism situation and achieving accurate evaluation of the embolism situation.

[0037] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0039] Figure 1 It is a hardware structure block diagram of a terminal device of an image information quantitative analysis method provided in an embodiment of the present application;

[0040] Figure 2 is a flow chart of a method for quantitative analysis of image information provided by an embodiment of the present application;

[0041] Figure 3 is a schematic diagram of the classification of different blood vessels provided in an embodiment of the present application;

[0042] Figure 4 is a flow chart of a method for quantitative analysis of image information provided by another embodiment of the present application;

[0043] Figure 5 is a flow chart of a method for quantitative analysis of image information provided by a preferred embodiment of the present application;

[0044] Figure 6 It is a structural block diagram of an image information quantitative analysis device provided in one embodiment of the present application.

[0045] In the figure: 102, processor; 104, memory; 106, transmission device; 108, input and output device; 10, acquisition module; 20, identification module; 30, evaluation module. DETAILED DESCRIPTION

[0046] In order to more clearly understand the purpose, technical solutions and advantages of the present application, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0047] Unless otherwise defined, the technical terms or scientific terms involved in this application shall have the general meaning understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the", "these" and the like in this application do not represent quantitative restrictions, and they can be singular or plural. The terms "include", "comprise", "have" and any variants thereof involved in this application are intended to cover non-exclusive inclusions; for example, a process, method and system, product or device comprising a series of steps or modules (units) is not limited to the listed steps or modules (units), but may include unlisted steps or modules (units), or may include other steps or modules (units) inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether directly or indirectly. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, "A and / or B" can mean: A exists alone, A and B exist at the same time, and B exists alone. Usually, the character " / " indicates that the objects associated with each other are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0048] The method embodiment provided in this embodiment can be executed in a terminal, a computer or a similar computing device. For example, running on a terminal, Figure 1 FIG. 1 is a hardware structure diagram of a terminal of the method for quantitative analysis of image information of this embodiment. Figure 1 As shown, the terminal may include one or more ( Figure 1 Only one is shown in the figure) processor 102 and memory 104 for storing data, wherein processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA. The above terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is for illustration only and does not limit the structure of the above terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0049] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the image information quantitative analysis method in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0050] The transmission device 106 is used to receive or send data via a network. The above network includes a wireless network provided by the communication provider of the terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.

[0051] In this embodiment, a method for quantitative analysis of image information is provided. Figure 2 is a flow chart of the image information quantitative analysis method of this embodiment. Figure 2 As shown, the process includes the following steps:

[0052] Step S210, acquiring a first target image of the target part and a second target image of the target part;

[0053] Step S220, identifying a plurality of first target blood vessels corresponding to the target part in the first target image, and a plurality of second target blood vessels corresponding to the target part in the second target image;

[0054] Step S230 , comparing the first quantitative information corresponding to each first target blood vessel with the second quantitative information corresponding to each second target blood vessel to obtain a corresponding embolism comparison result.

[0055] Specifically, a first target image and a second target image of the target part are obtained. The first target image and the second target image are usually images at different times, and may be target images before and after the embolization operation, target images at different time points in the same embolization operation, or two target images selected from different embolization operations. For example, the first target image of the target part is acquired before the embolization operation is performed, and the second target image of the target part is acquired after the embolization operation is performed. In addition, the target image in this embodiment may be an angiography image, a cone beam computed tomography (CBCT) enhanced image, a computed tomography (CT) enhanced image, a micro-computed tomography (microCT) enhanced image, a magnetic resonance imaging (MRI) enhanced image, etc., and the image modalities of the first target image and the second target image may be the same or different, which is not limited here. The first target image and the second target image are both key frames selected from a continuous sequence of target images, and the image completely and clearly contains all the blood supply vessels in the target part to provide comprehensive vascular information, and the vascular foreground and background areas in the image are clearly distinguished, which is helpful for subsequent vascular segmentation.

[0056] Determine the region of interest in the first target image and the second target image, the region of interest is the region where the blood supply vessels in the target part are located, for example, in the case of embolization of tumor blood vessels, the region of interest is usually the region where the blood supply vessels in the tumor are distributed. Among them, the region of interest in the target image can be selected by automatic recognition by algorithm or manual annotation, and the algorithm used to automatically identify the region of interest includes but is not limited to edge detection, threshold segmentation and corresponding machine learning algorithm. Use multi-scale blood vessel segmentation algorithm or threshold-based blood vessel segmentation algorithm to extract blood vessels from the region of interest in the first target image and the second target image, respectively, to obtain multiple first target blood vessels corresponding to the target part in the first target image, and multiple second target blood vessels corresponding to the target part in the second target image. The target blood vessel refers to the blood supply vessel of the target part in the embolization operation, and the actual state of the first target blood vessel and the second target blood vessel depends on the application scenario. For example, in the case of embolization of tumor blood vessels, the target blood vessel is each blood supply vessel within the tumor range. If the first target image and the second target image are the target images before and after the embolization operation, the first target blood vessel and the second target blood vessel are the blood supply vessels before and after the embolization, respectively.

[0057] Further, feature extraction is performed on each first target blood vessel and each second target blood vessel to obtain the vascular features of each first target blood vessel and each second target blood vessel, and first quantitative information corresponding to each first target blood vessel is calculated based on the vascular features of each first target blood vessel, and second quantitative information corresponding to each second target blood vessel is calculated based on the vascular features of each second target blood vessel. The quantitative information is data information used to describe the vascular features.

[0058] The above-mentioned vascular characteristics include but are not limited to the vascular centerline and vascular diameter. Accordingly, the calculated quantitative information can be vascular length information, vascular distribution density, tumor blood supply, and vascular status information such as blood flow velocity and blood flow. Among them, vascular length information refers to the total length of the target blood vessel, and can also refer to the total length of the blood vessels in each category when the blood vessels are divided into multiple categories according to the size of the vascular diameter; vascular distribution density is used to indicate the density of blood supply vessels in the current given area, that is, the number of blood vessels per unit area in the current given area; tumor blood supply refers to the length of blood vessels per unit area of ​​the tumor when embolization is performed on the tumor blood vessels, and different tumor blood supply conditions can be divided into rich blood supply and poor blood supply. Rich blood supply refers to the rich blood supply of the tumor tissue, which is manifested as dense blood vessels and increased blood flow, while poor blood supply refers to the relatively poor blood supply of the tumor tissue, which is manifested as sparse blood vessels and less blood flow.

[0059] The first quantitative information is compared with the second quantitative information, and the state change information between the first target blood vessel and the second target blood vessel is determined according to the comparison result. Then, based on the state change information, the embolization effect corresponding to the embolization operation is evaluated. The embolization effect can be the blockage ratio of the target blood vessel to measure whether the expected effect is achieved. For example, it is evaluated that the blockage of the target blood vessel reaches 80%.

[0060] The following is an explanation of the process of obtaining state change information based on different quantitative information analysis. In the case where the quantitative information is the blood vessel length information, taking the classification of blood vessels into two categories of large blood vessels and small blood vessels as an example, the blood vessel diameter threshold for blood vessel classification is set to 1000 microns, that is, Figure 3 As shown, blood vessels with a diameter greater than or equal to 1000 microns are large blood vessels ( Figure 3 The blood vessels with a diameter less than 1000 microns are small blood vessels ( Figure 3 The green blood vessels in the middle) were extracted before and after embolization to obtain Figure 3 The blood vessels before embolization shown in (a) and Figure 3For the embolized blood vessels shown in (b), a first total length of the large blood vessels and a second total length of the small blood vessels in each first target blood vessel are calculated based on the blood vessel characteristics, and a third total length of the large blood vessels and a fourth total length of the small blood vessels in each second target blood vessel are calculated based on the blood vessel characteristics. The first total length is compared with the third total length, and the second total length is compared with the fourth total length, respectively, to obtain state change information of the large blood vessels and the small blood vessels before and after embolization. The specific calculation formula is as follows:

[0061] a=(T1-T3) / T1 (1)

[0062] b=(T2-T4) / T2 (2)

[0063] In formula (1) and formula (2), a represents the state change information of the large blood vessels before and after embolization; b represents the state change information of the small blood vessels before and after embolization; T1 represents the first total length of the large blood vessels in each first target blood vessel; T2 represents the second total length of the small blood vessels in each first target blood vessel; T3 represents the third total length of the large blood vessels in each second target blood vessel; T4 represents the fourth total length of the small blood vessels in each second target blood vessel.

[0064] In addition, when the quantitative information is the blood vessel distribution density, the blood vessel distribution density corresponding to each first target blood vessel and the blood vessel distribution density corresponding to each second target blood vessel are calculated, and the change in the blood vessel distribution density before and after embolization is used as the state change information between the first target blood vessel and the second target blood vessel; when the quantitative information is the tumor blood supply, the tumor blood supply corresponding to each first target blood vessel and the tumor blood supply corresponding to each second target blood vessel are calculated, and the change information of the tumor blood supply before and after embolization is used as the state change information between the first target blood vessel and the second target blood vessel.

[0065] Among them, when the quantitative information corresponding to the target blood vessel includes multiple different information, such as blood vessel length information and blood vessel distribution density, the state change information corresponding to each quantitative information is analyzed and obtained, and each state change information can be weighted to accurately output the state change of the blood vessel. When the information categories included in the first quantitative information and the second quantitative information are different, the same category information in the first quantitative information and the second quantitative information are extracted and compared accordingly to obtain the state change information of the blood vessel. For example, when the first quantitative information includes blood vessel length information and blood vessel distribution density, and the second quantitative information includes blood vessel length information, the blood vessel length information in the first quantitative information is compared with the blood vessel length information in the second quantitative information to obtain the state change of the blood vessel.

[0066] It should be noted that this embodiment is applicable to embolization operations in situations such as embolization treatment of tumors and malformed blood vessels. In order to timely evaluate the embolization effect and help formulate subsequent plans, the embolization operation can be performed in multiple stages. Target images are collected for each stage of the embolization operation, and the changes in the quantitative information of the blood vessels before and after the embolization are calculated using the target images obtained in each stage. The embolization situation is evaluated based on the changes in the quantitative information of the blood vessels, thereby preventing incomplete vascular embolization from failing to achieve the expected effect, and at the same time avoiding the situation where excessive embolism causes damage to some tissues or organs. In addition, this embodiment is also applicable to image comparison in different embolization operations, such as using different embolization materials or embolization methods (such as microsphere embolization, liquid embolization, etc.) to perform embolization. By comparing the embolization conditions in different embolization images, the embolization effects of different embolization materials or embolization methods are analyzed to facilitate the selection of a better embolization operation.

[0067] The embolization effect is an important factor affecting the patient's prognosis. In the existing technology, the embolization of tumor vessels is usually qualitatively evaluated based on empirical information with reference to the collected angiography images. However, due to the influence of personal subjective factors, this method cannot accurately evaluate the embolization situation.

[0068] Compared with the prior art, the present application obtains a first target image of the target part and a second target image of the target part; identifies multiple first target blood vessels corresponding to the target part in the first target image and multiple second target blood vessels corresponding to the target part in the second target image; compares the first quantitative information corresponding to each first target blood vessel with the second quantitative information corresponding to each second target blood vessel to obtain the corresponding embolism comparison result. Based on this, quantitative calculation is performed on the vascular feature information in different embolization images to obtain the change of vascular quantitative information between different embolization images, and the embolism situation is compared based on the change of vascular quantitative information, which solves the problem of being unable to accurately evaluate the embolism situation and achieves accurate evaluation of the embolism situation.

[0069] In some of the embodiments, Figure 4 As shown, step S230 of comparing the first quantitative information corresponding to each first target blood vessel with the second quantitative information corresponding to each second target blood vessel to obtain a corresponding embolism comparison result includes the following steps:

[0070] Step S231, determining first quantitative information corresponding to each first target blood vessel, and second quantitative information corresponding to each second target blood vessel;

[0071] Step S232, comparing the first quantitative information with the second quantitative information, and determining state change information between each first target blood vessel and each second target blood vessel according to the comparison result;

[0072] Step S233: determining the corresponding embolism situation comparison result based on the state change information.

[0073] Specifically, the vascular characteristics of each first target blood vessel are extracted, and each first target blood vessel is quantitatively calculated based on the vascular characteristics to obtain first quantitative information corresponding to each first target blood vessel. At the same time, the vascular characteristics of each second target blood vessel are extracted, and each second target blood vessel is quantitatively calculated based on the vascular characteristics to obtain second quantitative information corresponding to each second target blood vessel.

[0074] The quantitative information of blood vessels includes, but is not limited to, blood vessel length information, blood vessel distribution density, and tumor blood supply. Blood vessel length information refers to the total length of the target blood vessel, or it can refer to the total length of blood vessels in each category when the blood vessels are divided into multiple categories according to the size of the blood vessel diameter; blood vessel distribution density is used to indicate the density of blood vessels in the current given area, that is, the number of blood vessels per unit area in the current given area; tumor blood supply refers to the length of blood vessels per unit area of ​​the tumor when embolization is performed on the tumor blood vessels.

[0075] Further, the first quantitative information is compared with the second quantitative information to obtain the state change information between the first target blood vessel and the second target blood vessel. For example, when the first quantitative information and the second quantitative information include blood vessel length information, the total length of the large blood vessels and the total length of the small blood vessels in each first target blood vessel are calculated, and the total length of the large blood vessels and the total length of the small blood vessels in each second target blood vessel are calculated, and the total length of the large blood vessels before and after embolization is respectively compared, and the total length of the small blood vessels before and after embolization is respectively compared, or when the first quantitative information and the second quantitative information both include blood vessel distribution density and tumor blood supply, the blood vessel distribution density before and after embolization is compared, and the change information of the blood vessel distribution density before and after embolization is calculated, and the tumor blood supply before and after embolization is compared, and the change information of the tumor blood supply before and after embolization is calculated, and the change information corresponding to the two quantitative information is weighted to accurately output the state change information of the blood vessel.

[0076] Among them, the blood vessel length before embolization is subtracted from the blood vessel length after embolization to obtain the blood vessel length difference, and the ratio of the blood vessel length difference to the blood vessel length before embolization is used to characterize the degree of embolism of the tumor blood supply vessels in the change of blood vessel length characteristics. Similarly, the blood vessel distribution density before embolization is subtracted from the blood vessel distribution density after embolization to obtain the density difference, and the ratio of the density difference to the blood vessel distribution before embolization is used to characterize the degree of embolism of the tumor blood supply vessels in the change of blood vessel distribution density characteristics. The larger the ratio, the more complete the embolism, and the tumor blood supply vessels are completely embolized, and the smaller the ratio, the more unembolized blood vessels there are. It should be noted that the evaluation of the embolization effect for other quantitative information is similar to the above evaluation method, which will not be repeated here.

[0077] Through this embodiment, the first quantitative information corresponding to each first target blood vessel and the second quantitative information corresponding to each second target blood vessel are determined, and the first quantitative information is compared with the second quantitative information. According to the comparison result, the state change information between the first target blood vessel and the second target blood vessel is determined, and then based on the state change information, the corresponding embolism situation comparison result is determined, so that the embolism situation is evaluated according to the change of the blood vessel quantitative information, thereby improving the evaluation accuracy.

[0078] In some embodiments, determining the first quantitative information corresponding to each first target blood vessel and the second quantitative information corresponding to each second target blood vessel in step S231 includes the following steps:

[0079] Extracting features of each first target blood vessel and each second target blood vessel respectively to obtain blood vessel features of each first target blood vessel and blood vessel features of each second target blood vessel;

[0080] Determining first quantitative information corresponding to each first target blood vessel based on the blood vessel characteristics of each first target blood vessel;

[0081] Based on the blood vessel characteristics of each second target blood vessel, second quantitative information corresponding to each second target blood vessel is determined.

[0082] Specifically, feature extraction is performed on each first target blood vessel and each second target blood vessel to extract the blood vessel features of each first target blood vessel and the blood vessel features of each second target blood vessel. For example, by skeletonizing the target blood vessels, blood vessel-related features such as the blood vessel centerline, blood vessel diameter, blood vessel bifurcation point, and endpoint are obtained.

[0083] Furthermore, based on the vascular characteristics of each first target blood vessel, first quantitative information corresponding to each first target blood vessel is calculated, and based on the vascular characteristics of each second target blood vessel, second quantitative information corresponding to each second target blood vessel is calculated. The vascular quantitative information includes but is not limited to vascular length information, vascular distribution density, and tumor blood supply.

[0084] Among them, the vascular centerline provides an accurate trajectory of the vascular path. By calculating the length of the vascular centerline, the actual length of the blood vessel can be accurately measured. Based on the vascular centerline and the vascular diameter, the length of the blood vessel can be calculated. At the same time, the vascular centerline helps to identify different vascular branches. By analyzing the bifurcation points and branching conditions of the vascular centerline, the number of blood vessels can be accurately counted, the number of blood vessels per unit area in the current given area can be calculated, and the vascular distribution density can be obtained. In the case of embolization of tumor blood vessels, the length of blood vessels per unit area of ​​the tumor can be calculated to obtain the blood supply of the tumor.

[0085] Through this embodiment, feature extraction is performed on each first target blood vessel and each second target blood vessel respectively to obtain the blood vessel feature of each first target blood vessel and the blood vessel feature of each second target blood vessel. Based on the blood vessel feature of each first target blood vessel, the first quantitative information corresponding to each first target blood vessel is determined, and based on the blood vessel feature of each second target blood vessel, the second quantitative information corresponding to each second target blood vessel is determined, thereby achieving accurate calculation of the blood vessel quantitative information.

[0086] In some embodiments, the step S232 of comparing the first quantitative information with the second quantitative information and determining the state change information between each first target blood vessel and each second target blood vessel according to the comparison result includes the following steps:

[0087] Classifying each first target blood vessel into a plurality of categories, and classifying each second target blood vessel into a plurality of categories;

[0088] Traversing each category, comparing the first quantitative information of each first target blood vessel with the second quantitative information of each second target blood vessel in the same category, and obtaining a comparison result corresponding to each category;

[0089] According to each comparison result, state change information between each first target blood vessel and each second target blood vessel is determined.

[0090] Specifically, each first target blood vessel is divided into a plurality of categories, and each second target blood vessel is divided into a plurality of categories, according to blood vessel-related features such as blood vessel diameter, blood vessel distribution location, etc. For example, the actual blood vessel diameter of each target blood vessel is compared with a preset blood vessel diameter threshold, and the target blood vessel is classified into a corresponding category according to the size relationship between the actual blood vessel diameter and the blood vessel diameter threshold. The blood vessel categories include large blood vessels, medium blood vessels, and small blood vessels, etc. Target blood vessels with actual blood vessel diameters greater than or equal to the blood vessel diameter threshold belong to large blood vessels, and target blood vessels with actual blood vessel diameters less than the blood vessel diameter threshold belong to small blood vessels. It should be noted that this embodiment does not limit the granularity of blood vessel classification, and classification can also be performed according to the specific numerical range of blood vessel diameters, such as classifying target blood vessels with diameters of 1000 to 2000 microns into one category.

[0091] Furthermore, for each category, the first quantitative information of each first target blood vessel and the second quantitative information of each second target blood vessel in the category are counted, and the first quantitative information of each first target blood vessel is compared with the second quantitative information of each second target blood vessel to obtain the blood vessel state change corresponding to each category, and based on the blood vessel state change under each category, the state change information between each first target blood vessel and each second target blood vessel is comprehensively calculated.

[0092] Exemplarily, the vessel diameter threshold for vessel classification is set to 1000 microns, then the vessels with a diameter greater than or equal to 1000 microns are large vessels, and the vessels with a diameter less than 1000 microns are small vessels. The vessels before and after embolism are extracted to obtain a plurality of first target vessels in the target image before embolism and a plurality of second target vessels in the target image after embolism. The total length of the large vessels and the total length of the small vessels in each first target vessel are calculated based on the vessel characteristics, and the total length of the large vessels and the total length of the small vessels in each second target vessel are calculated at the same time. The total lengths of the large vessels before and after embolism are respectively compared, and the total lengths of the small vessels before and after embolism are respectively compared, so as to obtain the state changes of the large vessels and the small vessels before and after embolism, and perform weighted calculation on the state changes of the large vessels and the small vessels, and output the final state change information.

[0093] Through this embodiment, each first target blood vessel is divided into a plurality of categories, and each second target blood vessel is divided into a plurality of categories; each category is traversed, and the first quantitative information of each first target blood vessel in the same category is compared with the second quantitative information of each second target blood vessel to obtain a comparison result corresponding to each category; based on each comparison result, the state change information between each first target blood vessel and each second target blood vessel is determined, so as to evaluate the embolization effect by using the length information of blood vessels with different diameters, and improve the evaluation accuracy by classification comparison.

[0094] In some of the embodiments, determining the corresponding embolism comparison result based on the state change information includes the following steps:

[0095] Determine a ratio of the state change information to the first quantitative information; the state change information is the difference between the first quantitative information and the second quantitative information;

[0096] The ratio was used as the comparison result of embolism situation.

[0097] Specifically, the state change information between each first target blood vessel and each second target blood vessel is obtained. In this embodiment, the state change information is the difference between the first quantitative information and the second quantitative information. The ratio of the state change information to the first quantitative information is calculated, and the calculated ratio is output as the embolization situation comparison result. The larger the ratio, the more complete the embolization, and the tumor blood supply blood vessel is completely embolized. The smaller the ratio, the more unembolized blood vessels there are.

[0098] Exemplarily, the length of the blood vessel before embolization is subtracted from the length of the blood vessel after embolization to obtain the difference in blood vessel length, and the ratio of the difference in blood vessel length to the length of the blood vessel before embolization is used to characterize the degree of embolism of the blood vessels supplying the tumor in the change of blood vessel length characteristics. Similarly, the blood vessel distribution density before embolization is subtracted from the blood vessel distribution density after embolization to obtain the density difference, and the ratio of the density difference to the blood vessel distribution before embolization is used to characterize the degree of embolism of the blood vessels supplying the tumor in the change of blood vessel distribution density characteristics. It should be noted that the evaluation of the embolization effect for other quantitative information is similar to the above evaluation method and will not be repeated here.

[0099] Through this embodiment, the ratio of the state change information to the first quantitative information is determined. The state change information is the difference between the first quantitative information and the second quantitative information. The ratio is used as the embolism situation comparison result. Based on the state change information obtained by comparing the target image, the corresponding embolism situation is accurately evaluated.

[0100] In some embodiments, the first target image and the second target image are angiography images; identifying a plurality of first target blood vessels corresponding to the target part in the first target image and a plurality of second target blood vessels corresponding to the target part in the second target image comprises the following steps:

[0101] Performing subtraction processing on the first target image and the second target image respectively to obtain a first subtraction image corresponding to the first target image and a second subtraction image corresponding to the second target image;

[0102] A plurality of first target blood vessels corresponding to the target part in the first subtraction image and a plurality of second target blood vessels corresponding to the target part in the second subtraction image are identified.

[0103] Specifically, an original scanned image of the target site before contrast agent injection is obtained, and the original scanned image and the first target image are subtracted to obtain a first subtracted image corresponding to the first target image. At the same time, the original scanned image and the second target image are subtracted to obtain a second subtracted image corresponding to the second target image.

[0104] Furthermore, the region of interest in the target image is determined by automatic recognition by an algorithm or manual labeling, and blood vessels are extracted from the region of interest in the first target image and the second target image respectively by a multi-scale blood vessel segmentation algorithm or a threshold-based blood vessel segmentation algorithm, so as to obtain a plurality of first target blood vessels corresponding to the target part in the first target image and a plurality of second target blood vessels corresponding to the target part in the second target image.

[0105] Feature extraction is performed on each first target blood vessel and the second target blood vessel respectively to obtain the vascular features of each first target blood vessel and the second target blood vessel. Based on the vascular features of each first target blood vessel, the first quantitative information corresponding to each first target blood vessel is calculated, and based on the vascular features of each second target blood vessel, the second quantitative information corresponding to each second target blood vessel is calculated. Wherein, the vascular features include but are not limited to the vascular centerline and the vascular diameter. Accordingly, the calculated quantitative information may be vascular length information, vascular distribution density, tumor blood supply, etc. The vascular length information refers to the total length of the target blood vessel, and may also refer to the total length of the blood vessels in each category when the blood vessels are divided into multiple categories according to the size of the vascular diameter; the vascular distribution density is used to indicate the density of the blood supply vessels in the current given area, that is, the number of blood vessels per unit area in the current given area; the tumor blood supply refers to the length of the blood vessels per unit area of ​​the tumor when the tumor blood vessels are embolized.

[0106] The first quantitative information is compared with the second quantitative information, and the state change information between the first target blood vessel and the second target blood vessel is determined according to the comparison result. Then, based on the state change information, the embolization effect corresponding to the embolization operation is evaluated. The embolization effect can be the blockage ratio of the target blood vessel.

[0107] It should be noted that, in this embodiment, the first subtraction image and the second subtraction image are applicable to all the above-mentioned image processing methods and vascular feature processing methods for the first target image and the second target image, including vascular extraction for the target image, vascular feature extraction, vascular quantitative information calculation, embolization effect evaluation based on quantitative information, etc., which will not be repeated here.

[0108] Through this embodiment, the first target image and the second target image are subtracted respectively to obtain a first subtracted image corresponding to the first target image and a second subtracted image corresponding to the second target image, and multiple first target blood vessels corresponding to the target part in the first subtracted image and multiple second target blood vessels corresponding to the target part in the second subtracted image are identified, so that the subtracted image can be used to help identify and analyze the target blood vessels in the image, which is helpful for subsequent accurate evaluation of the embolization effect.

[0109] In some of the embodiments, before performing subtraction processing on the first target image and the second target image to obtain a first subtracted image corresponding to the first target image and a second subtracted image corresponding to the second target image, the following steps are also included:

[0110] Acquire the original scan image of the target site before contrast agent injection;

[0111] Based on the original scanned image, the first target image and the second target image are respectively registered.

[0112] Specifically, an original scanned image of the target site before contrast agent injection is acquired, a first target image is registered based on the original scanned image, and a second target image is registered based on the original scanned image. The first target image and the second target image after the registration are used as input images for subtraction processing to reduce respiratory artifacts in the image, improve the clarity of the target image, and help improve the quality of subsequent subtraction images.

[0113] Among them, the registration processing methods include rigid registration, non-rigid registration and registration algorithms based on deep learning, etc. The corresponding registration method can be selected according to the actual application scenario. For example, when there is a large deformation of tissue or organ in the contrast image, non-rigid registration is the preferred registration method.

[0114] Through this embodiment, the original scanned image of the target part before contrast agent injection is obtained, and based on the original scanned image, the first target image and the second target image are respectively registered, so as to effectively eliminate the influence of breathing artifacts and improve the accuracy of blood vessel recognition.

[0115] The present embodiment is described and illustrated below through preferred embodiments.

[0116] Figure 5 is a flow chart of the method for quantitative analysis of image information of the preferred embodiment. Figure 5 As shown, the image information quantitative analysis method includes the following steps:

[0117] Step S510, acquiring a first angiography image of the target site before the embolization operation and a second angiography image of the target site after the embolization operation;

[0118] Step S520, extracting blood vessels from the region of interest in the first angiography image using a multi-scale blood vessel segmentation algorithm to obtain a plurality of first target blood vessels corresponding to the target part in the first angiography image;

[0119] Step S530, extracting blood vessels from the region of interest in the second angiography image using a multi-scale blood vessel segmentation algorithm to obtain a plurality of second target blood vessels corresponding to the target part in the second angiography image;

[0120] Step S540, skeletonizing each first target blood vessel and each second target blood vessel respectively to obtain a blood vessel feature of each first target blood vessel and a blood vessel feature of each second target blood vessel;

[0121] Step S550, determining first quantitative information corresponding to each first target blood vessel based on the blood vessel characteristics of each first target blood vessel, and determining second quantitative information corresponding to each second target blood vessel based on the blood vessel characteristics of each second target blood vessel;

[0122] Step S560, comparing the first quantitative information corresponding to each first target blood vessel with the second quantitative information corresponding to each second target blood vessel, and evaluating the embolization effect corresponding to the embolization operation according to the comparison result; the quantitative information is data information used to describe blood vessel characteristics.

[0123] Through this embodiment, a first angiography image of the target site before the embolization operation and a second angiography image of the target site after the embolization operation are obtained, and a blood vessel is extracted from a region of interest in the first angiography image by a multi-scale blood vessel segmentation algorithm to obtain a plurality of first target blood vessels corresponding to the target site in the first angiography image, and a blood vessel is extracted from a region of interest in the second angiography image by a multi-scale blood vessel segmentation algorithm to obtain a plurality of second target blood vessels corresponding to the target site in the second angiography image.

[0124] Furthermore, each first target vessel and each second target vessel are skeletonized respectively to obtain the vessel characteristics of each first target vessel and the vessel characteristics of each second target vessel. Based on the vessel characteristics of each first target vessel, the first quantitative information corresponding to each first target vessel is determined, and based on the vessel characteristics of each second target vessel, the second quantitative information corresponding to each second target vessel is determined. The first quantitative information corresponding to each first target vessel is compared with the second quantitative information corresponding to each second target vessel, and the embolization effect corresponding to the embolization operation is evaluated based on the comparison result. The quantitative information is data information used to describe the vessel characteristics, which solves the problem of being unable to accurately evaluate the embolism situation and realizes accurate evaluation of the embolism situation.

[0125] It should be noted that the steps shown in the above process or the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0126] In this embodiment, an image information quantitative analysis device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. The terms "module", "unit", "subunit", etc. used below can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0127] Figure 6 is a structural block diagram of the image information quantitative analysis device of this embodiment, such as Figure 6 As shown, the device comprises:

[0128] In a second aspect, in this embodiment, a device for quantitative analysis of image information is provided, the device comprising: an acquisition module 10, a recognition module 20 and an evaluation module 30;

[0129] An acquisition module 10, used to acquire a first target image of a target part and a second target image of the target part;

[0130] an identification module 20, configured to identify a plurality of first target blood vessels corresponding to the target part in the first target image, and a plurality of second target blood vessels corresponding to the target part in the second target image;

[0131] The evaluation module 30 is used to compare the first quantitative information corresponding to each first target blood vessel with the second quantitative information corresponding to each second target blood vessel to obtain a corresponding embolism comparison result.

[0132] Through the device provided in this embodiment, a first target image of the target part and a second target image of the target part are obtained; multiple first target blood vessels corresponding to the target part in the first target image and multiple second target blood vessels corresponding to the target part in the second target image are identified; first quantitative information corresponding to each first target blood vessel is compared with second quantitative information corresponding to each second target blood vessel to obtain corresponding embolism situation comparison results, thereby solving the problem of being unable to accurately evaluate the embolism situation and achieving accurate evaluation of the embolism situation.

[0133] In some of the embodiments, the evaluation module 30 is further used to determine first quantitative information corresponding to each first target blood vessel, and second quantitative information corresponding to each second target blood vessel; compare the first quantitative information with the second quantitative information, and determine state change information between each first target blood vessel and each second target blood vessel based on the comparison result; and determine the corresponding embolism situation comparison result based on the state change information.

[0134] In some of the embodiments, the evaluation module 30 is further used to perform feature extraction on each first target blood vessel and each second target blood vessel respectively to obtain the vascular characteristics of each first target blood vessel and the vascular characteristics of each second target blood vessel; determine the first quantitative information corresponding to each first target blood vessel based on the vascular characteristics of each first target blood vessel; and determine the second quantitative information corresponding to each second target blood vessel based on the vascular characteristics of each second target blood vessel.

[0135] In some of the embodiments, the evaluation module 30 is further used to classify each first target blood vessel into a plurality of categories based on a preset blood vessel diameter threshold, and to classify each second target blood vessel into a plurality of categories; traverse each category, compare the length information of each first target blood vessel with the length information of each second target blood vessel in the same category, and obtain a comparison result corresponding to each category; and determine the state change information between each first target blood vessel and each second target blood vessel according to each comparison result.

[0136] In some of the embodiments, the evaluation module 30 is further used to determine the ratio of the state change information to the first quantitative information; the state change information is the difference between the first quantitative information and the second quantitative information; and the ratio is used as the embolism comparison result.

[0137] In some of these embodiments, Figure 6 On the basis of, the device also includes a subtraction module, which is used to perform subtraction processing on the first target image and the second target image respectively to obtain a first subtraction image corresponding to the first target image and a second subtraction image corresponding to the second target image; identify multiple first target blood vessels corresponding to the target part in the first subtraction image, and multiple second target blood vessels corresponding to the target part in the second subtraction image.

[0138] In some of these embodiments, Figure 6 On the basis of, the device also includes a registration module for acquiring an original scan image of the target part before injection of contrast agent; based on the original scan image, the first target image and the second target image are registered respectively.

[0139] It should be noted that the above modules can be functional modules or program modules, and can be implemented by software or hardware. For modules implemented by hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0140] In this embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0141] Optionally, the computer device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0142] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0143] S1, acquiring a first target image of a target part and a second target image of the target part;

[0144] S2, identifying a plurality of first target blood vessels corresponding to the target part in the first target image, and a plurality of second target blood vessels corresponding to the target part in the second target image;

[0145] S3, comparing the first quantitative information corresponding to each first target blood vessel with the second quantitative information corresponding to each second target blood vessel to obtain a corresponding embolism comparison result.

[0146] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and will not be repeated in this embodiment.

[0147] In addition, in combination with the image information quantitative analysis method provided in the above embodiments, a storage medium can also be provided in this embodiment to implement the image information quantitative analysis method. The storage medium stores a computer program; when the computer program is executed by a processor, any one of the image information quantitative analysis methods in the above embodiments is implemented.

[0148] It should be understood that the specific embodiments described herein are only used to explain the application, rather than to limit it. Based on the embodiments provided in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the protection scope of this application.

[0149] Obviously, the drawings are only some examples or embodiments of the present application. For ordinary technicians in the field, the present application can also be applied to other similar situations based on these drawings without creative work. In addition, it is understandable that although the work done in this development process may be complicated and lengthy, for ordinary technicians in the field, certain changes in design, manufacturing or production based on the technical content disclosed in this application are only conventional technical means and should not be regarded as insufficient content disclosed in this application.

[0150] The term "embodiment" in this application refers to a specific feature, structure or characteristic described in conjunction with the embodiment that can be included in at least one embodiment of the present application. The appearance of this phrase in various locations in the specification does not necessarily mean the same embodiment, nor does it mean that it is mutually exclusive with other embodiments and is independent or optional. It is clearly or implicitly understood by those of ordinary skill in the art that the embodiments described in this application can be combined with other embodiments without conflict.

[0151] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of patent protection. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the scope of protection of the present application. Therefore, the scope of protection of the present application shall be subject to the attached claims.

Claims

1. A method for quantitative analysis of image information, characterized in that: The method comprises: Acquire a first target image of a target part, and a second target image of the target part; identifying a plurality of first target blood vessels corresponding to the target part in the first target image, and a plurality of second target blood vessels corresponding to the target part in the second target image; The first quantitative information corresponding to each of the first target blood vessels is compared with the second quantitative information corresponding to each of the second target blood vessels to obtain a corresponding embolism situation comparison result.

2. The image information quantitative analysis method according to claim 1, characterized in that: The step of comparing the first quantitative information corresponding to each of the first target blood vessels with the second quantitative information corresponding to each of the second target blood vessels to obtain a corresponding embolism comparison result includes: Determining first quantitative information corresponding to each of the first target blood vessels, and second quantitative information corresponding to each of the second target blood vessels; Comparing the first quantitative information with the second quantitative information accordingly, and determining state change information between each of the first target blood vessels and each of the second target blood vessels according to the comparison result; Based on the state change information, a corresponding embolism situation comparison result is determined.

3. The image information quantitative analysis method according to claim 2, characterized in that: The determining of the first quantitative information corresponding to each of the first target blood vessels and the second quantitative information corresponding to each of the second target blood vessels includes: Extracting features of each of the first target blood vessels and each of the second target blood vessels respectively to obtain blood vessel features of each of the first target blood vessels and blood vessel features of each of the second target blood vessels; determining, based on the vascular characteristics of each of the first target blood vessels, the first quantitative information corresponding to each of the first target blood vessels; Based on the blood vessel characteristics of each second target blood vessel, the second quantitative information corresponding to each second target blood vessel is determined.

4. The image information quantitative analysis method according to claim 2, characterized in that: The step of comparing the first quantitative information with the second quantitative information and determining the state change information between each of the first target blood vessels and each of the second target blood vessels according to the comparison result includes: Classifying each of the first target blood vessels into a plurality of categories, and classifying each of the second target blood vessels into a plurality of categories; Traversing each of the categories, comparing the first quantitative information of each of the first target blood vessels with the second quantitative information of each of the second target blood vessels in the same category, to obtain a comparison result corresponding to each of the categories; According to each of the comparison results, state change information between each of the first target blood vessels and each of the second target blood vessels is determined.

5. The image information quantitative analysis method according to claim 2, characterized in that: The determining of the corresponding embolism situation comparison result based on the state change information includes: Determine a ratio of the state change information to the first quantitative information; the state change information is a difference between the first quantitative information and the second quantitative information; The ratio is used as the comparison result of the embolism situation.

6. The image information quantitative analysis method according to claim 1, characterized in that: The first target image and the second target image are angiography images; the identifying a plurality of first target blood vessels corresponding to the target part in the first target image, and a plurality of second target blood vessels corresponding to the target part in the second target image, comprises: Performing subtraction processing on the first target image and the second target image respectively to obtain a first subtracted image corresponding to the first target image and a second subtracted image corresponding to the second target image; A plurality of first target blood vessels corresponding to the target site in the first subtracted image and a plurality of second target blood vessels corresponding to the target site in the second subtracted image are identified.

7. The method for quantitative analysis of image information according to claim 6, characterized in that: Before performing subtraction processing on the first target image and the second target image to obtain a first subtracted image corresponding to the first target image and a second subtracted image corresponding to the second target image, the method further includes: acquiring an original scan image of the target site before contrast agent injection; Based on the original scanned image, the first target image and the second target image are respectively registered.

8. An image information quantitative analysis device, characterized in that: The device comprises: an acquisition module, an identification module and an evaluation module; The acquisition module is used to acquire a first target image of the target part and a second target image of the target part; The recognition module is used to recognize a plurality of first target blood vessels corresponding to the target part in the first target image, and a plurality of second target blood vessels corresponding to the target part in the second target image; The evaluation module is used to compare the first quantitative information corresponding to each of the first target blood vessels with the second quantitative information corresponding to each of the second target blood vessels to obtain a corresponding embolism situation comparison result.

9. A computer device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps of the image information quantitative analysis method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the image information quantitative analysis method according to any one of claims 1 to 7 are implemented.

Images