Method and device for quantitative analysis of brain metastatic tumor and storage medium

Through the combination of multimodal nuclear magnetic image registration and deep learning model, accurate segmentation and quantitative analysis of brain metastases are achieved, and the shortcomings of single-modal imaging and single-study examination results in the existing technology are solved, and brain metastases are improved the accuracy of treatment efficacy assessment and recurrence monitoring.

CN118982530APending Publication Date: 2024-11-19XUANWU HOSPITAL OF CAPITAL UNIV OF MEDICAL SCI
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411090885.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-09
Publication Date
2024-11-19

AI Technical Summary

Technical Problem

In the treatment and postoperative tracking of brain metastases, quantitative analysis of changes in brain metastases cannot be achieved in the prior art, and the automated identification and segmentation results are inaccurate, mainly because they only rely on single-modal nuclear magnetic images and single-study results.

Method used

After multimodal nuclear magnetic imaging registration, combined with the whole brain and brain metastases segmentation module, the Unet, FPN or PSPNet model was used for segmentation, and the brain metastases information was extracted, and the quantitative analysis results of multiple postoperative examinations were compared. , achieve more accurate brain metastases and quantitative analysis.

Benefits of technology

It improves the accuracy and efficiency of brain metastases segmentation, provides more comprehensive feature information through multimodal imaging, reduces false positives, obtains more accurate brain metastases information, and supports more accurate treatment effect evaluation and recurrence monitoring.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118982530A_ABST
    Figure CN118982530A_ABST
Patent Text Reader

Abstract

The invention discloses a method and equipment for quantitatively analyzing brain metastatic tumor and a storage medium. The method comprises the following steps: acquiring nuclear magnetic images of a plurality of modalities of a brain, and registering the nuclear magnetic images of the plurality of modalities; based on the registered nuclear magnetic images of the multiple modalities, performing brain metastatic tumor segmentation by using a segmentation model to obtain a brain metastatic tumor segmentation result; extracting brain metastasis tumor information according to the brain metastasis tumor segmentation result; and comparing the brain metastasis tumor information with quantitative analysis results of multiple postoperative examinations to quantitatively analyze the brain metastasis tumor. By means of the scheme, the accuracy and efficiency of brain metastatic tumor segmentation and quantitative analysis can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application generally relates to the technical field of brain metastasis analysis. More specifically, the present application relates to a method, device and computer-readable storage medium for quantitatively analyzing brain metastasis. Background Art

[0002] Currently, in the treatment and postoperative follow-up of brain metastases, doctors usually need to refer to multimodal MRI data (such as T1 mode and T2 mode) to identify brain metastases, manually find the lesion area, and outline the lesion. Then, compare it with the preoperative MRI image to determine the treatment effect and the possibility of recurrence. However, outlining is time-consuming and is usually not done again during postoperative follow-up. Therefore, traditional methods often cannot quantitatively analyze changes in the lesion area.

[0003] Currently, there are methods that use neural networks to automatically identify and segment brain metastases. However, current methods only target single-modality MRI images and only analyze brain metastases based on a single examination result, resulting in poor segmentation results for brain metastases and inaccurate final quantitative analysis results.

[0004] In view of this, there is an urgent need to provide a solution for quantitative analysis of brain metastases in order to improve the accuracy and efficiency of brain metastasis segmentation and quantitative analysis. Summary of the invention

[0005] In order to at least solve one or more of the above-mentioned technical problems, the present application proposes a scheme for quantitatively analyzing brain metastases in multiple aspects.

[0006] In a first aspect, the present application provides a method for quantitatively analyzing brain metastases, comprising: acquiring multiple modalities of nuclear magnetic resonance images of the brain, and registering the multiple modalities of nuclear magnetic resonance images; performing brain metastasis segmentation using a segmentation model based on the registered multiple modalities of nuclear magnetic resonance images to obtain a brain metastasis segmentation result; extracting brain metastasis information based on the brain metastasis segmentation result; and comparing the brain metastasis information with the quantitative analysis results of multiple postoperative examinations to quantitatively analyze the brain metastasis.

[0007] In some embodiments, the multiple modalities of nuclear magnetic images include at least T1 modality nuclear magnetic images and T2 modality nuclear magnetic images.

[0008] In other embodiments, the segmentation model includes a whole-brain segmentation module and a brain metastasis segmentation module, and based on the registered MRI images of multiple modalities, using the segmentation model to perform brain metastasis segmentation to obtain a brain metastasis segmentation result includes: based on the registered MRI images of multiple modalities, using the whole-brain segmentation module to perform whole-brain segmentation to obtain a whole-brain image after registration of each modality; and using the brain metastasis segmentation module to perform brain metastasis segmentation on the whole-brain image after registration of each modality to obtain a brain metastasis segmentation result.

[0009] In some other embodiments, based on the registered MRI images of multiple modalities, using the whole-brain segmentation module to perform whole-brain segmentation to obtain the registered whole-brain images of each modality includes: based on the registered MRI images of multiple modalities, using the whole-brain segmentation module to perform whole-brain segmentation to obtain a whole-brain segmentation label; and obtaining the registered whole-brain images of each modality according to the whole-brain segmentation label.

[0010] In some other embodiments, using the brain metastasis segmentation module to perform brain metastasis segmentation on the whole brain image after the modalities are registered to obtain a brain metastasis segmentation result includes: using the brain metastasis segmentation module to perform brain metastasis segmentation on the whole brain image after the modalities are registered to obtain a brain metastasis segmentation label; and obtaining a brain metastasis segmentation result based on the brain metastasis segmentation label.

[0011] In some other embodiments, the whole brain segmentation module and the brain metastasis segmentation module include a Unet model, a FPN model or a PSPNet model.

[0012] In some other embodiments, the brain metastasis information includes at least the number of brain metastases and / or the volume of brain metastases, and the quantitative analysis results of multiple postoperative examinations are obtained based on quantitative analysis of multiple modalities of magnetic resonance imaging acquired during multiple preoperative or postoperative examinations.

[0013] In some other embodiments, the brain metastasis information is compared with the quantitative analysis results of multiple postoperative examinations to quantitatively analyze the brain metastasis, including: determining whether there is a target brain metastasis based on the quantitative analysis results of the multiple postoperative examinations of the brain metastasis information; and calculating the target brain metastasis information based on whether there is a target brain metastasis or determining whether there is new brain metastasis information to quantitatively analyze the brain metastasis.

[0014] In a second aspect, the present application provides a device for quantitatively analyzing brain metastases, comprising: a processor; and a memory on which computer instructions for quantitatively analyzing brain metastases are stored, and when the computer instructions are executed by the processor, multiple embodiments of the aforementioned first aspect are implemented.

[0015] In a third aspect, the present application provides a computer-readable storage medium having stored thereon computer program instructions for quantitatively analyzing brain metastases, wherein when the computer program instructions are executed by one or more processors, multiple embodiments of the aforementioned first aspect are implemented.

[0016] Through the scheme for quantitative analysis of brain metastases provided above, the embodiment of the present application obtains the brain metastasis segmentation result by performing brain metastasis segmentation after registering the nuclear magnetic resonance images of multiple modalities. Then, the brain metastasis information is extracted from the brain metastasis segmentation result, and the brain metastasis is quantitatively analyzed by comparing it with the quantitative analysis results of multiple postoperative examinations. Based on this, the embodiment of the present application can combine the nuclear magnetic resonance images of multiple modalities to provide more comprehensive feature information, so that the segmentation result of brain metastases is more accurate, and by comparing the analysis results of multiple postoperative examinations, more accurate brain metastasis information is obtained, thereby improving the accuracy of quantitative analysis of brain metastases. Furthermore, the embodiment of the present application is also based on the registered whole brain image as the input of brain metastasis segmentation, avoiding false positives outside the whole brain, thereby improving the accuracy and efficiency of brain metastasis segmentation. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present application will become easy to understand. In the accompanying drawings, several embodiments of the present application are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0018] Figure 1 is an exemplary flowchart showing a method for quantitatively analyzing brain metastases according to an embodiment of the present application;

[0019] Figure 2 is an exemplary flowchart showing an overall process for quantitatively analyzing brain metastases according to an embodiment of the present application;

[0020] Figure 3 is an exemplary schematic diagram showing a brain metastasis segmentation result segmented in T1 mode according to an embodiment of the present application;

[0021] Figure 4 is an exemplary schematic diagram showing a quantitative analysis of T1 modality before and after treatment according to an embodiment of the present application;

[0022] Figure 5 is an exemplary structural block diagram showing an apparatus for quantitatively analyzing brain metastases according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0024] It should be understood that the terms "include" and "comprising" used in the specification and claims of the present application indicate the presence of described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or collections thereof.

[0025] It should also be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in this application specification and claims, unless the context clearly indicates otherwise, the singular forms of "a", "an" and "the" are intended to include plural forms. It should also be further understood that the term "and / or" used in this application specification and claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

[0026] As used in this specification and claims, the term "if" may be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" may be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0027] The specific implementation of the present application is described in detail below with reference to the accompanying drawings.

[0028] Figure 1 FIG. 1 is an exemplary flowchart of a method 100 for quantitatively analyzing brain metastases according to an embodiment of the present application. Figure 1As shown in, at step S101, multiple modal nuclear magnetic images of the brain are collected, and the multiple modal nuclear magnetic images are registered. In some embodiments, multiple modal nuclear magnetic images of the brain can be collected by, for example, a magnetic resonance device. The aforementioned multiple modal nuclear magnetic images may include, but are not limited to, nuclear magnetic images of T1 modality and nuclear magnetic images of T2 modality. In particular, the aforementioned nuclear magnetic images of T1 modality and nuclear magnetic images of T2 modality may be enhanced nuclear magnetic images of T1 modality and enhanced nuclear magnetic images of T2 modality. Among them, the enhanced nuclear magnetic images of T1 modality can provide active brain metastasis areas, and the enhanced nuclear magnetic images of T2 modality can provide strong images of nuclear magnetic to edema. Thus, more comprehensive image information can be obtained by combining multiple modal nuclear magnetic images. In addition, in some embodiments, for example, T1 contrast modality (i.e., T1C) and fluid attenuated inversion recovery modality (i.e., FLAIR) may also be included, and the present application does not impose any restrictions in this regard.

[0029] Based on the collected MRI images of multiple modalities of the brain, the MRI images of multiple modalities are first aligned. Specifically, by calculating the transformation relationship between the multiple modal images, the pixel points on each modality maintain spatial consistency. In some implementation scenarios, the aforementioned transformation relationship includes, for example, translation, rotation, scaling, or nonlinear transformation. In some embodiments, alignment can be achieved based on regions (e.g., whole brain regions) or features (e.g., edges or corners of the whole brain, etc.) on the MRI images of each modality.

[0030] Next, at step S102, based on the registered MRI images of multiple modalities, a segmentation model is used to perform brain metastasis segmentation to obtain a brain metastasis segmentation result. In some embodiments, the aforementioned segmentation model may include a whole brain segmentation module and a brain metastasis segmentation module. In obtaining the brain metastasis segmentation result, the whole brain segmentation module may be used to perform whole brain segmentation based on the registered MRI images of multiple modalities to obtain a whole brain image registered by each modality, and the brain metastasis segmentation module is used to perform brain metastasis segmentation on the whole brain image registered by each modality to obtain a brain metastasis segmentation result.

[0031] Specifically, in some embodiments, a whole-brain segmentation module can be used to perform whole-brain segmentation based on the nuclear magnetic images of multiple modalities after registration to obtain a whole-brain segmentation label, and then obtain the whole-brain image after registration of each modality according to the whole-brain segmentation label. More specifically, in some embodiments, the target modality nuclear magnetic image with the largest imaging area is selected from the nuclear magnetic images of multiple modalities after registration, and the target modality nuclear magnetic image is subjected to whole-brain segmentation using the whole-brain segmentation module to obtain a whole-brain segmentation label. Further, the whole-brain segmentation label is matched with the nuclear magnetic images of each modality to extract the whole-brain image after registration of each modality. In some implementation scenarios, the aforementioned whole-brain segmentation module may include but is not limited to a Unet model, an FPN model or a PSPNet model, and the present application does not impose any restrictions in this regard.

[0032] That is, the embodiment of the present application uses the modality image with the largest imaging area as the target modality image, inputs it into the whole brain segmentation module, performs whole brain segmentation via the whole brain segmentation module to obtain the whole brain label, and matches the whole brain label to other modality images. As an example, assuming that the imaging area is the largest in the nuclear magnetic image of the T1 modality, the nuclear magnetic image of the T1 modality is input into the whole brain segmentation module for whole brain segmentation to obtain the whole brain label (i.e., the whole brain foreground area or the whole brain area). Then, the whole brain label is matched to the nuclear magnetic image of the T2 modality, so as to obtain the whole brain image after the T1 modality and the T2 modality are registered. Similarly, if the imaging area is the largest in the nuclear magnetic image of the T2 modality, the whole brain label after the nuclear magnetic image of the T2 modality is segmented is matched to the nuclear magnetic image of the T1 modality, and the whole brain image after the T1 modality and the T2 modality are registered is obtained. Based on this, it is possible to delete the area outside the imaging area and only retain the whole brain image, avoid the false positives outside the whole brain image, thereby improving the accuracy of subsequent brain metastasis segmentation. It can be understood that the matching in the embodiment of the present application is also image registration, and thus the matching process can also be achieved through methods such as regions or features.

[0033] After obtaining the whole-brain image after the above-mentioned modal registration, the brain metastasis segmentation module is used to perform brain metastasis segmentation on the whole-brain image after each modality registration to obtain the brain metastasis segmentation result. In some embodiments, the brain metastasis segmentation module can be used to perform brain metastasis segmentation on the whole-brain image after each modality registration to obtain a brain metastasis segmentation label, and the brain metastasis segmentation result is obtained according to the brain metastasis segmentation label. Specifically, in some embodiments, the metastasis segmentation label is reverse matched with the nuclear magnetic resonance images of multiple modalities to obtain the brain metastasis segmentation result. In some implementation scenarios, the aforementioned brain metastasis segmentation module may include but is not limited to a Unet model, an FPN model or a PSPNet model, and the present application does not impose any restrictions in this regard.

[0034] That is, the embodiment of the present application first obtains brain metastasis segmentation labels (i.e., brain metastasis regions) by performing brain metastasis segmentation on the whole brain image, and then matches the brain metastasis segmentation labels to the original MRI images of multiple modalities to obtain the final brain metastasis segmentation results. Similarly, the reverse matching, i.e., image registration, can be achieved through methods such as regions or features.

[0035] Further, at step S103, brain metastasis information is extracted according to the brain metastasis segmentation result, and at step S104, the brain metastasis information is compared with the quantitative analysis results of multiple postoperative examinations to quantitatively analyze brain metastases. In some embodiments, the aforementioned brain metastasis information may include at least the number of brain metastases and / or the volume of brain metastases, and the aforementioned quantitative analysis results of multiple postoperative examinations are obtained based on the quantitative analysis of multiple modalities of nuclear magnetic images collected before or after the operation. Specifically, in some embodiments, the quantitative analysis results of multiple postoperative examinations of brain metastasis information are used to determine whether there is a target brain metastasis, and then the target brain metastasis information is calculated based on whether there is a target brain metastasis or whether there is a new brain metastasis information to quantitatively analyze the brain metastasis. For example, if the corresponding brain metastasis is found in the quantitative analysis results of multiple postoperative examinations, the change in the volume of the brain metastasis is calculated. If the corresponding brain metastasis is not found in the quantitative analysis results of multiple postoperative examinations, the treatment effect or the presence of a new brain metastasis can be determined based on the time relationship of the multiple examinations, and finally a report is generated and provided to the doctor and the patient.

[0036] In combination with the above description, it can be seen that the embodiment of the present application performs whole-brain segmentation after registration of multiple modal nuclear magnetic images, obtains a whole-brain image after registration of each modality, and provides more comprehensive feature information in combination with multiple modal nuclear magnetic images. Next, brain metastasis information is extracted from the brain metastasis segmentation result, and compared with the quantitative analysis results of multiple postoperative examinations to quantitatively analyze brain metastases, and compared by combining the analysis results of multiple postoperative examinations to make the segmentation results of brain metastases more accurate, and obtain more accurate brain metastasis information, thereby improving the accuracy of quantitative analysis of brain metastases. In addition, the embodiment of the present application also deletes areas outside the whole brain image to avoid false positives outside the whole brain, and improves the accuracy and efficiency of brain metastasis segmentation.

[0037] Figure 2 FIG. 1 is an exemplary flowchart showing the overall process for quantitatively analyzing brain metastases according to an embodiment of the present application. It should be understood that Figure 2 is the above Figure 1 A specific implementation of method 100, so the above Figure 1 The description also applies to Figure 2 .

[0038] like Figure 2 As shown in, at step S201, the nuclear magnetic images of the T1 modality and the nuclear magnetic images of the T2 modality of the brain are collected, and the nuclear magnetic images of the T1 modality and the nuclear magnetic images of the T2 modality are aligned. In some embodiments, the alignment can be achieved based on the regions or features on the nuclear magnetic images of the T1 modality and the T2 modality. Then, at step S202, the whole brain segmentation module is used to perform whole brain segmentation to obtain the whole brain image after each modality is aligned. According to the foregoing description, it can be known that the target modality image with the largest imaging area can be first selected from the nuclear magnetic images of the T1 modality and the nuclear magnetic images of the T2 modality after alignment. As an example, assuming that the imaging area on the nuclear magnetic image of the T1 modality is the largest, the nuclear magnetic image of the T1 modality is input into the whole brain segmentation module for whole brain segmentation to obtain a whole brain segmentation label. In some implementation scenarios, the aforementioned whole brain segmentation module can be, for example, a Unet model, an FPN model, or a PSPNet model. Based on the obtained whole-brain segmentation labels, the whole-brain segmentation labels are matched to the MRI images of other modalities (such as T2 modality) to obtain the whole-brain images after registration of each modality.

[0039] Further, at step S203, the brain metastasis segmentation module is used to perform brain metastasis segmentation on the whole brain image after each modality registration to obtain a brain metastasis segmentation result. As described above, the whole brain image after each modality registration can be input into the brain metastasis segmentation module for brain metastasis segmentation to obtain a brain metastasis segmentation label. In some implementation scenarios, the aforementioned brain metastasis segmentation module may include but is not limited to a Unet model, an FPN model, or a PSPNet model. The brain metastasis segmentation label is reversely matched to the nuclear magnetic resonance images of multiple modalities to obtain a brain metastasis segmentation result.

[0040] According to the obtained brain metastasis segmentation results, at step S204, brain metastasis information is extracted according to the brain metastasis segmentation results. In some embodiments, the brain metastasis information may be, for example, the number or volume of brain metastases. In addition, at step S205, multiple modal nuclear magnetic images collected by multiple examinations before or after surgery are obtained, and at step S206, the quantitative analysis results of multiple examinations after surgery are obtained. Finally, at step S207, the brain metastasis information is compared with the quantitative analysis results of multiple examinations after surgery to quantitatively analyze brain metastases. For example, the target brain metastasis is found according to the quantitative analysis results of multiple examinations after surgery of the brain metastasis information, and if it exists, the change in the volume of the brain metastasis is calculated; if it does not exist, the treatment effect or whether there is a new brain metastasis is determined, and finally a report is generated and provided to doctors and patients.

[0041] Figure 3 FIG. 1 is an exemplary schematic diagram showing the brain metastasis segmentation result under T1 mode according to an embodiment of the present application. Figure 3As shown in , the corresponding segmented brain metastasis segmentation results on the axial, sagittal, and coronal planes of the T1 modality are shown from left to right. According to the foregoing, brain metastasis segmentation can be performed by inputting the whole brain image segmented by the T1 modality into the brain metastasis segmentation module to obtain a brain metastasis segmentation label. Then, the brain metastasis segmentation label is reversely matched to the nuclear magnetic resonance image of the T1 modality, and the segmented brain metastasis segmentation result can be obtained. Through the solution of the embodiment of the present application, an accurate brain metastasis segmentation result can be obtained.

[0042] Figure 4 FIG. 2 is an exemplary schematic diagram showing the quantitative analysis of T1 modality before and after treatment according to an embodiment of the present application. Figure 4 As shown in Figure (a), the corresponding axial, sagittal, and coronal magnetic resonance images of the T1 mode before treatment are shown from left to right. Figure 4 As shown in Figure (b), the corresponding MRI images of the T1 modality after treatment are shown from left to right in the axial, sagittal, and coronal planes. As mentioned above, the whole brain image segmented by the T1 modality can be input into the brain metastasis segmentation module to perform brain metastasis segmentation to obtain a brain metastasis segmentation label. Then, the brain metastasis segmentation label is reversely matched to the T1 modality MRI image to obtain the segmented brain metastasis segmentation result (e.g. Figure 4 Then, the number or volume of brain metastases can be extracted, and the corresponding brain metastases can be found from the quantitative analysis results of multiple postoperative examinations. If they exist, the change in the volume of the brain metastases is calculated. The volume change can provide an effective and accurate treatment plan for the follow-up, so as to better treat brain metastases, for example Figure 4 Showing disappearance of brain metastases after treatment.

[0043] Figure 5 is an exemplary structural block diagram of a device 500 for quantitatively analyzing brain metastases according to an embodiment of the present application. It is understood that the device 500 may include the apparatus of the embodiment of the present application, and the device implementing the solution of the present application may be a single device (such as a computing device) or a multifunctional device including various peripheral devices.

[0044] like Figure 5As shown in , the device of the present application may also include a central processing unit or central processing unit ("CPU") 511, which may be a general-purpose CPU, a dedicated CPU, or other information processing and program execution unit. Further, the device 500 may also include a large-capacity memory 512 and a read-only memory ("ROM") 513, wherein the large-capacity memory 512 may be configured to store various types of data, including various nuclear magnetic images with multiple modalities, whole brain images after registration of each modality, brain metastasis segmentation results, brain metastasis information, quantitative analysis results, algorithm data, intermediate results, and various programs required to run the device 500. ROM 513 may be configured to store data and instructions required for power-on self-test of the device 500, initialization of each functional module in the system, basic input / output drivers of the system, and booting the operating system.

[0045] Optionally, the device 500 may also include other hardware platforms or components, such as the tensor processing unit ("TPU") 514, graphics processing unit ("GPU") 515, field programmable gate array ("FPGA") 516, and machine learning unit ("MLU") 517 shown. It is understood that although a variety of hardware platforms or components are shown in the device 500, they are merely exemplary and not restrictive, and those skilled in the art may add or remove corresponding hardware according to actual needs. For example, the device 500 may only include a CPU, related storage devices, and interface devices to implement the method for quantitatively analyzing brain metastases of the present application.

[0046] In some embodiments, in order to facilitate the transmission and interaction of data with an external network, the device 500 of the present application also includes a communication interface 518, so that it can be connected to a local area network / wireless local area network ("LAN / WLAN") 505 through the communication interface 518, and then connected to a local server 506 or connected to the Internet ("Internet") 507 through the LAN / WLAN. Alternatively or additionally, the device 500 of the present application can also be directly connected to the Internet or a cellular network through the communication interface 518 based on wireless communication technology, such as wireless communication technology based on the third generation ("3G"), the fourth generation ("4G") or the fifth generation ("5G") of the third generation ("3G"), the fourth generation ("4G") or the fifth generation ("5G") of the third generation ("3G") of the third generation ("4G") of the fourth generation ("4G") of the fourth generation ("5G") of the fifth generation ("5G") of the third generation ("3G") of the fourth generation ("4G") of the fourth generation ("4G") of the fourth generation ("5G") of the fifth generation ("5G") of the third generation ("3G") of the fourth generation ("4G") of the fourth generation ("4G") of the fourth generation ("4G") of the fifth generation ("5G") of the fifth generation ("5G") of the third generation ("3G") of the third generation ("3G") of the fourth generation ("4G") of the fourth generation ("4G") of the fourth generation ("4G") of the fourth generation ("4G") of the fifth generation ("5 ...

[0047] The peripheral devices of the device 500 may include a display device 502, an input device 503, and a data transmission interface 504. In one embodiment, the display device 502 may include, for example, one or more speakers and / or one or more visual displays, which are configured to perform voice prompts and / or image video display for quantitative analysis of brain metastases of the present application. The input device 503 may include other input buttons or controls such as a keyboard, a mouse, a microphone, a gesture capture camera, etc., which are configured to receive input and / or user instructions of audio data. The data transmission interface 504 may include, for example, a serial interface, a parallel interface or a universal serial bus interface ("USB"), a small computer system interface ("SCSI"), a serial ATA, a FireWire ("FireWire"), a PCI Express, and a high-definition multimedia interface ("HDMI"), etc., which are configured for data transmission and interaction with other devices or systems. According to the scheme of the present application, the data transmission interface 504 can receive nuclear magnetic images of various modalities collected from the MRI device, and transmit nuclear magnetic images of various modalities or various other types of data or results to the device 500.

[0048] The CPU 511, mass storage 512, ROM 513, TPU 514, GPU 515, FPGA 516, MLU 517 and communication interface 518 of the device 500 of the present application can be interconnected through a bus 519, and data interaction with peripheral devices can be achieved through the bus. In one embodiment, through the bus 519, the CPU 511 can control other hardware components in the device 500 and its peripheral devices.

[0049] Combination of the above Figure 5 The device for quantitative analysis of brain metastases that can be used to perform the present application is described. It should be understood that the device structure or architecture here is only exemplary, and the implementation method and implementation entity of the present application are not limited thereto, but can be changed without departing from the spirit of the present application.

[0050] According to the above description in combination with the accompanying drawings, those skilled in the art can also understand that the embodiments of the present application can also be implemented by software programs. Therefore, the present application also provides a computer-readable storage medium, on which computer-readable instructions for quantitatively analyzing brain metastases are stored. When the computer-readable instructions are executed by one or more processors, they can be used to implement the present application in combination with the accompanying drawings. Figure 1 A method for quantitative analysis of brain metastases is described.

[0051] It should be noted that although the operations of the method of the present application are described in a specific order in the accompanying drawings, this does not require or imply that the operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. On the contrary, the steps depicted in the flow chart can be performed in a different order. Additionally or alternatively, some steps can be omitted, multiple steps can be combined into one step, and / or one step can be decomposed into multiple steps.

[0052] It should be understood that when the terms "first", "second", "third" and "fourth" are used in the claims, the specification and the drawings of the present application, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the specification and claims of the present application indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their collections.

[0053] It should also be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in this application specification and claims, unless the context clearly indicates otherwise, the singular forms of "a", "an" and "the" are intended to include plural forms. It should also be further understood that the term "and / or" used in this application specification and claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

[0054] Although the implementation methods of the present application are as above, the contents described are only examples adopted to facilitate the understanding of the present application, and are not intended to limit the scope and application scenarios of the present application. Any technician in the technical field described in the present application can make any modifications and changes in the form and details of the implementation without departing from the spirit and scope disclosed in the present application, but the scope of patent protection of the present application shall still be subject to the scope defined in the attached claims.

[0055] In addition, the collection and acquisition of various data in this application complies with relevant laws and regulations and is authorized by the data provider. Any organization or individual that needs to obtain external data must obtain authorization in accordance with the law and ensure data security. It is not allowed to illegally collect, use, process, or transmit unauthorized or unprotected data, or to illegally buy, sell, provide, or disclose unauthorized or unprotected data.

Claims

1. A method for quantitatively analyzing brain metastases, comprising: Acquiring multiple modal nuclear magnetic resonance images of the brain, and registering the multiple modal nuclear magnetic resonance images; Based on the registered multiple modal MRI images, a segmentation model is used to segment brain metastases to obtain brain metastasis segmentation results; Extracting brain metastasis information according to the brain metastasis segmentation result; as well as The brain metastasis information is compared with the quantitative analysis results of multiple postoperative examinations to quantitatively analyze the brain metastasis. 2 . The method according to claim 1 , wherein the multiple modalities of nuclear magnetic images include at least T1 modality nuclear magnetic images and T2 modality nuclear magnetic images.

3. The method according to claim 1, wherein the segmentation model comprises a whole brain segmentation module and a brain metastasis segmentation module, and based on the registered multiple modalities of nuclear magnetic resonance images, using the segmentation model to perform brain metastasis segmentation to obtain a brain metastasis segmentation result comprises: Based on the registered MRI images of multiple modalities, the whole brain segmentation module is used to perform whole brain segmentation to obtain the registered whole brain images of each modality; as well as The brain metastasis segmentation module is used to perform brain metastasis segmentation on the whole brain image after the modality registration to obtain a brain metastasis segmentation result.

4. The method according to claim 3, wherein based on the registered MRI images of multiple modalities, using the whole brain segmentation module to perform whole brain segmentation to obtain the registered whole brain images of each modality comprises: Based on the registered MRI images of multiple modalities, the whole brain segmentation module is used to perform whole brain segmentation to obtain a whole brain segmentation label; as well as The whole-brain image after registration of each modality is obtained according to the whole-brain segmentation label.

5. The method according to claim 3, wherein using the brain metastasis segmentation module to perform brain metastasis segmentation on the whole brain image after the modality registration to obtain the brain metastasis segmentation result comprises: Using the brain metastasis segmentation module to perform brain metastasis segmentation on the whole brain image after the registration of each modality to obtain a brain metastasis segmentation label; as well as A brain metastasis segmentation result is obtained according to the brain metastasis segmentation label.

6. The method according to claim 3, wherein the whole brain segmentation module and the brain metastasis segmentation module comprise a Unet model, a FPN model or a PSPNet model.

7. The method according to claim 1, wherein the brain metastasis information includes at least the number and / or volume of brain metastases, and the quantitative analysis results of multiple postoperative examinations are obtained based on quantitative analysis of multiple modalities of nuclear magnetic resonance images collected during multiple preoperative or postoperative examinations.

8. The method according to claim 1 or 7, wherein comparing the brain metastasis information with quantitative analysis results of multiple postoperative examinations to quantitatively analyze the brain metastasis comprises: Determining whether a target brain metastasis exists according to the quantitative analysis results of the brain metastasis information during multiple examinations after the operation; as well as The target brain metastasis information is calculated based on whether the target brain metastasis exists or whether new brain metastasis information exists, so as to quantitatively analyze the brain metastasis.

9. A device for quantitative analysis of brain metastases, comprising: processor; as well as A memory having computer instructions for quantitatively analyzing brain metastases stored thereon, wherein when the computer instructions are executed by a processor, the method according to any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium having stored thereon computer program instructions for quantitatively analyzing brain metastases, wherein when the computer program instructions are executed by one or more processors, the method according to any one of claims 1 to 8 is implemented.