Genetic mutation types and treatment options for patients with cerebral cavernous malformations, non-invasive assessment and screening system

Abstract

The present disclosure relates to a system for identifying the gene mutation type of a cerebral cavernous malformation (CCM) patient, and a system for determining a treatment plan for a cerebral cavernous malformation patient. The system provided by the present disclosure can determine the gene mutation type of a cerebral cavernous malformation patient based on a head computed tomography (CT) image and / or a magnetic resonance imaging (MRI) of the cerebral cavernous malformation patient, and therefore, the present disclosure provides a non-invasive method for determining the corresponding gene mutation type of a CCM patient, enriches the diagnosis method of CCM, and can provide a strong basis for the rationalization and targeted treatment of CCM.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of medical treatment, in particular, to a system for identifying a gene mutation type of a cerebral cavernous malformation patient, and a system for determining a treatment plan of a cerebral cavernous malformation patient. BACKGROUND

[0002] Cerebral cavernous malformation (CCM) is a vascular dysplasia disease characterized by dilated venous vessels and capillaries, with an incidence of about 0.16% to 0.5%. CCM often causes symptoms such as epilepsy, hemorrhagic stroke, headache, or focal neurological deficits, which seriously threatens the life safety of patients. CCM can be caused by gene mutations, for example, CCM1 / KRIT1, CCM2 / MGC4607, and CCM3 / PDCD10 CCM gene family mutations can all cause CCM lesions.

[0003] In the treatment of CCM, the corresponding gene mutation type is first determined, and a suitable treatment method is adopted according to the gene mutation type, which can effectively improve the treatment effect. In related technologies, when the gene mutation type corresponding to CCM is determined, an invasive surgical method is usually used to obtain a lesion sample, and then the lesion sample is analyzed for the gene mutation type.

[0004] However, the intracranial invasive surgical method is difficult, and the intracranial surgery can easily worsen the short-term disability score of the patient, increase the risk of symptomatic intracerebral hemorrhage and new focal neurological deficits. Therefore, there is an urgent need for a method for non-invasively determining the gene mutation type corresponding to CCM. SUMMARY

[0005] The purpose of the present disclosure is to provide a system for identifying the gene mutation type of a cerebral cavernous malformation patient, and a system for determining the treatment plan of a cerebral cavernous malformation patient.

[0006] To achieve the above-mentioned purpose, the present disclosure provides a system for identifying the gene mutation type of a cerebral cavernous malformation patient, which comprises an image input device, a computing device and an output device;

[0007] The image input device is used to input an imaging examination image of the head of a cerebral cavernous malformation patient;

[0008] The computing device comprises a memory and a processor, the memory stores a computer program, and the processor is configured to execute the computer program stored in the memory to realize the following discrimination:

[0009] Judging the lesion characteristics of the cerebral cavernous malformation corresponding to the imaging examination image input by the image input device;

[0010] if the cerebral cavernous angioma corresponding to the image of the imaging examination is characterized by punctate multifocal lesions, it is determined that the patient with the cerebral cavernous angioma has a CCM germ cell mutation;

[0011] if the cerebral cavernous angioma corresponding to the image of the imaging examination is characterized by popcorn lesions, it is determined that the patient with the cerebral cavernous angioma has a MAP3K3 c.1323C>G type gene mutation;

[0012] The output device is used to output the determination result of the computing device.

[0013] Optionally, after determining that the patient with the cerebral cavernous angioma has a MAP3K3 c.1323C>G type gene mutation, the processor is further used to:

[0014] determine that the patient with the cerebral cavernous angioma does not have a CCM1 / 2 / 3 type gene mutation.

[0015] Optionally, the memory further stores feature data of cerebral cavernous angioma, and the lesion characteristics of the cerebral cavernous angioma corresponding to the image of the imaging examination input by the image input device include:

[0016] comparing the image of the imaging examination with the feature data of the cerebral cavernous angioma to obtain a comparison result;

[0017] determining the lesion characteristics of the cerebral cavernous angioma corresponding to the image of the imaging examination according to the comparison result.

[0018] Optionally, the feature data of the cerebral cavernous angioma includes a cerebral cavernous angioma image library, the cerebral cavernous angioma image library contains preset images, and the preset images include type I images, type II images, type III images and type IV images, wherein the type I images are characterized by subacute hemorrhage, the type II images are characterized by popcorn lesions, the type III images are characterized by chronic hemorrhage, and the type IV images are characterized by punctate multifocal lesions.

[0019] The comparison of the image of the imaging examination with the feature data of the cerebral cavernous angioma to obtain a comparison result includes:

[0020] performing image matching on the image of the imaging examination and the preset images in the cerebral cavernous angioma image library to obtain an image type corresponding to the image of the imaging examination.

[0021] The determination of the lesion characteristics of the cerebral cavernous angioma corresponding to the image of the imaging examination according to the comparison result includes:

[0022] if the image classification corresponding to the imaging examination image is type II, it is determined that the cerebral cavernous malformation corresponding to the imaging examination image is characterized by popcorn-like lesions;

[0023] if the image classification corresponding to the imaging examination image is type IV, it is determined that the cerebral cavernous malformation corresponding to the imaging examination image is characterized by punctate multifocal lesions.

[0024] Optionally, the imaging examination image includes a magnetic resonance image and / or a CT image.

[0025] The system further comprises an image acquisition device; preferably, the image acquisition device is a magnetic resonance imaging device and / or a CT scanning device.

[0026] The present disclosure also provides a system for determining a treatment plan for a patient with cerebral cavernous malformation, which comprises an image input device, a computing device and an output device;

[0027] The image input device is used to input an imaging examination image of the head of the patient with cerebral cavernous malformation;

[0028] The computing device comprises a memory and a processor, the memory stores a computer program, and the processor is configured to execute the computer program stored in the memory to realize the following discrimination:

[0029] determine the lesion characteristics of the cerebral cavernous malformation corresponding to the imaging examination image input by the image input device;

[0030] if the cerebral cavernous malformation corresponding to the imaging examination image is characterized by punctate multifocal lesions, the treatment plan for the patient with cerebral cavernous malformation includes a treatment plan targeting CCM gene germ cell mutations;

[0031] if the cerebral cavernous malformation corresponding to the imaging examination image is characterized by popcorn-like lesions, the treatment plan for the patient with cerebral cavernous malformation includes a treatment plan targeting MAP3K3 c.1323C>G mutations or MAPK downstream pathways;

[0032] The output device is used to output the discrimination result of the computing device.

[0033] Optionally, after determining that the treatment plan for the patient with cerebral cavernous malformation includes a treatment plan targeting MAP3K3 c.1323C>G mutations or MAPK downstream pathways, the processor is further configured to:

[0034] determine that the treatment plan for the patient with cerebral cavernous malformation does not include a treatment plan targeting CCM1 / 2 / 3 mutations.

[0035] Optionally, the memory further stores feature data of cerebral cavernous malformation, and the determining of the lesion feature of the cerebral cavernous malformation corresponding to the imageology examination image input by the image input device comprises:

[0036] comparing the imageology examination image with the feature data of the cerebral cavernous malformation to obtain a comparison result;

[0037] determining the lesion feature of the cerebral cavernous malformation corresponding to the imageology examination image according to the comparison result.

[0038] Optionally, the feature data of the cerebral cavernous malformation comprises a cerebral cavernous malformation image library, and the cerebral cavernous malformation image library contains preset images, and the preset images comprise type I images, type II images, type III images and type IV images, wherein the type I images are characterized by subacute hemorrhage, the type II images are characterized by popcorn-like lesions, the type III images are characterized by chronic hemorrhage, and the type IV images are characterized by punctate multifocal lesions.

[0039] The comparing the imageology examination image with the feature data of the cerebral cavernous malformation to obtain a comparison result comprises:

[0040] performing image matching on the imageology examination image and the preset images in the cerebral cavernous malformation image library to obtain an image type corresponding to the imageology examination image.

[0041] The determining the lesion feature of the cerebral cavernous malformation corresponding to the imageology examination image according to the comparison result comprises:

[0042] if the image type corresponding to the imageology examination image is type II, then it is determined that the cerebral cavernous malformation corresponding to the imageology examination image is characterized by popcorn-like lesions;

[0043] if the image type corresponding to the imageology examination image is type IV, then it is determined that the cerebral cavernous malformation corresponding to the imageology examination image is characterized by punctate multifocal lesions.

[0044] Optionally, the imageology examination image comprises a magnetic resonance image and / or a CT image.

[0045] The system further comprises an image acquisition device; preferably, the image acquisition device is a magnetic resonance imaging device and / or a CT scanning device.

[0046] Through the technical solution, the system provided by the present disclosure can determine the gene mutation type of the brain cavernous hemangioma patient based on the imageology examination image of the brain cavernous hemangioma of the brain cavernous hemangioma patient, and therefore, the present disclosure provides a non-invasive method for determining the corresponding gene mutation type of the CCM patient, enriches the diagnosis method of CCM, and can provide a strong basis for the rationalization and targeted treatment of CCM.

[0047] Other features and advantages of the present disclosure will be described in detail in the following detailed description section. BRIEF DESCRIPTION OF DRAWINGS

[0048] The accompanying drawings are included to provide a further understanding of the present disclosure and constitute a part of the specification, and are used together with the following detailed description to explain the present disclosure, but do not constitute a limitation on the present disclosure. In the drawings:

[0049] Figure 1 is a schematic diagram of somatic and germline mutations of 38 discovery samples in the embodiment of the present disclosure;

[0050] Figure 2 is a magnetic resonance image corresponding to four CCM lesion subtypes in the embodiment of the present disclosure;

[0051] Figure 3 is a schematic diagram of the clinical subtype and mutation characteristics of CCMs in the discovery sample in the embodiment of the present disclosure, Z and Z-N represent Zabramski and Zabramski-Nikoubashman respectively, and the P value is calculated by Fisher's exact test;

[0052] Figure 4 is a schematic diagram of a two-step decision tree model for predicting MAP3K3 c.1323C>G mutations based on radiological evaluation in the embodiment of the present disclosure;

[0053] Figure 5 is a receiver operating characteristic curve diagram of the model performance in the discovery sample (n=38) and the verification sample (n=56) in the embodiment of the present disclosure;

[0054] Figure 6 is a schematic diagram of a two-step decision tree model for predicting CCM gene germline mutations based on radiological evaluation in the embodiment of the present disclosure;

[0055] Figure 7 is a receiver operating characteristic curve diagram of the performance of the two-step decision tree model for CCM gene germline mutations in the embodiment of the present disclosure. DETAILED DESCRIPTION

[0056] The specific embodiments of the present disclosure are described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only used to illustrate and explain the present disclosure, and are not used to limit the present disclosure.

[0057] The first aspect of the present disclosure provides a system for identifying the gene mutation type of a cerebral cavernous malformation patient, the system comprising an image input device, a computing device and an output device; the image input device is used to input the imaging examination image of the head of the cerebral cavernous malformation patient; the computing device comprises a memory and a processor, the memory stores a computer program, and the processor is configured to execute the computer program stored in the memory to realize the following discrimination: judging the lesion characteristics of the cerebral cavernous malformation corresponding to the imaging examination image input by the image input device; if the cerebral cavernous malformation corresponding to the imaging examination image is characterized by punctate multifocal lesions, it is determined that the cerebral cavernous malformation patient has CCM gene germ cell mutation; if the cerebral cavernous malformation corresponding to the imaging examination image is characterized by popcorn lesions, it is determined that the cerebral cavernous malformation patient has MAP3K3 c.1323C>G type gene mutation; the output device is used to output the discrimination result of the computing device.

[0058] In addition, the present inventors have found that if the imaging examination image corresponds to a cerebral cavernous malformation characterized by subacute hemorrhage, it indicates that the cerebral cavernous malformation patient may have CCM gene somatic cell mutation.

[0059] In the present disclosure, the system provided by the present disclosure can determine the gene mutation type of the cerebral cavernous malformation patient based on the imaging examination image of the cerebral cavernous malformation of the cerebral cavernous malformation patient, and therefore the present disclosure provides a non-invasive method for determining the gene mutation type corresponding to CCM, at least partially enriches the diagnosis method of CCM, and can provide a strong basis for the rationalization and targeted treatment of CCM.

[0060] The MAP3K3 c.1323C>G mutation can activate the CCM1 / 2 / 3 inhibited ERK5 signal, can activate the ERK1 / 2, JNK and p38 pathways by inducing the enhanced kinase activity of MEKK3, and specifically, the expression of PDGFRb (MIM: 173410), FGF1 (MIM: 131220), FGFR2 (MIM: 176943), GPER1 (MIM: 601805), MT3 (MIM: 139255), NDRG4 (MIM: 614463) and TREM2 (MIM: 605086) in the endothelial cells of the MAP3K3 c.1323C>G mutation is up-regulated, indicating that ERK1 and ERK2 are activated.

[0061] Furthermore, after determining that the patient with cavernous malformation has a MAP3K3 c.1323C>G type gene mutation, the processor can also be used to: determine that the patient with cavernous malformation does not have a CCM1 / 2 / 3 type gene mutation.

[0062] To reveal the genetic landscape of CCM, deep whole-exome sequencing (WES) was performed on fresh frozen surgical specimens and corresponding peripheral blood samples from 38 patients in the discovery cohort. Using MUTracer, four germline mutations affecting the CCM1 and CCM3 genes, as well as 16 non-synonymous somatic mutations, were identified, located in CCM1, CCM2, MAP3K3 (MIM:602539), PIK3CA (MIM:171834), and MAP2K7 (MIM:6030142), respectively. Figure 1 As shown.

[0063] Depend on Figure 1 It can be seen that, under statistically consistent conditions (P=0.04), among the 38 patients in the cohort, 12 patients with CCM1 / 2 / 3 mutations (D29, D06, D13, D36, D32, D14, D21, D17, D19, D27, D18, D31) did not have the MAP3K3 c.1323C>G mutation, while 9 patients with the MAP3K3 c.1323C>G mutation (D24, D16, D12, D09, D22, D04, D33, D28, D03) did not have the CCM1 / 2 / 3 mutation. This indicates that the MAP3K3c.1323C>G mutation and the CCM1 / 2 / 3 mutation cannot coexist in patients; they are mutually exclusive.

[0064] According to this disclosure, the memory may also store feature data of cavernous malformations. When the computing device determines the pathological features of the cavernous malformation corresponding to the imaging examination image input by the image input device, it can compare the imaging examination image with the feature data of the cavernous malformation to obtain a comparison result. Then, based on the comparison result, it can determine the pathological features of the cavernous malformation corresponding to the imaging examination image.

[0065] According to this disclosure, the characteristic data of the cavernous malformation can vary within a certain range. For example, the characteristic data of the cavernous malformation may include a cavernous malformation image library, which may contain preset images. The preset images may include type I images, type II images, type III images, and type IV images. Among them, the type I images are characterized by subacute hemorrhage, the type II images are characterized by popcorn-like lesions, the type III images are characterized by chronic hemorrhage, and the type IV images are characterized by punctate multifocal lesions.

[0066] Specifically, according to the Zabramski classification, based on imaging examination images, the CCM lesions of the above patients can be divided into four subtypes: Type I is characterized by subacute hemorrhage, Type II by popcorn-like lesions, Type III by chronic hemorrhage, and Type IV by punctate multifocal lesions. Among these, for example... Figure 2 As shown, in MRI images, type I appears as a high signal on T1- and T2-weighted imaging, type II appears as a typical mulberry-like lesion on T1- and T2-weighted imaging, type III appears as a small punctate lesion on T1- and T2-weighted imaging, and type IV appears as multiple punctate lesions on susceptibility-weighted imaging sequences. In CT images, type I appears as a high-density hemorrhage; type II generally shows poor or no contrast enhancement, but calcifications can sometimes be seen on CT images; types III and IV are generally not visible on CT.

[0067] The preset images can be, for example, historical diagnostic imaging images corresponding to different lesion characteristics, or standard images simulated by machine learning from historical diagnostic imaging images. Each subtype may have only one preset image or multiple preset images.

[0068] Furthermore, comparing the imaging examination image with the feature data of the cavernous malformation to obtain the comparison result may include: performing image matching between the imaging examination image and a preset image in the cavernous malformation image database to obtain the image classification corresponding to the imaging examination image.

[0069] Specifically, the method for matching imaging examination images with preset images in the image library can be a conventional image matching algorithm and / or image similarity comparison algorithm in the field, such as the mean absolute difference algorithm (MAD), the sum of absolute errors algorithm (SAD), the sum of squared errors algorithm (SSD), the mean sum of squared errors algorithm (MSD), the normalized product correlation algorithm (NCC), the sequential similarity detection algorithm (SSDA), the Hadamard transform algorithm (SATD), and other algorithms.

[0070] Further, the determining the lesion feature of the brain cavernous hemangioma corresponding to the imageology examination image according to the comparison result can comprise: if the imageology examination image corresponds to the image classification of type II, determining that the brain cavernous hemangioma corresponding to the imageology examination image is characterized by popcorn-like lesion; and if the imageology examination image corresponds to the image classification of type IV, determining that the brain cavernous hemangioma corresponding to the imageology examination image is characterized by punctate multifocal lesion.

[0071] Optionally, the imageology examination image comprises a magnetic resonance image and / or a CT image; and the system can further comprise an image acquisition device; preferably, the image acquisition device can be a magnetic resonance imaging device and / or a CT scanning device. The image acquisition device can be connected to the image input device correspondingly, and can transmit the imageology examination image acquired thereby to the image input device.

[0072] The second aspect of the present disclosure provides a system for determining a treatment scheme for a patient with brain cavernous hemangioma, which comprises an image input device, a computing device and an output device; the image input device is used for inputting an imageology examination image of the head of the patient with brain cavernous hemangioma; the computing device comprises a memory and a processor, the memory stores a computer program, and the processor is configured to execute the computer program stored in the memory to realize the following discrimination: judging the lesion feature of the brain cavernous hemangioma corresponding to the imageology examination image input by the image input device; if the brain cavernous hemangioma corresponding to the imageology examination image is characterized by punctate multifocal lesion, determining that the treatment scheme for the patient with brain cavernous hemangioma comprises a treatment scheme targeting CCM gene germ cell mutation; if the brain cavernous hemangioma corresponding to the imageology examination image is characterized by popcorn-like lesion, determining that the treatment scheme for the patient with brain cavernous hemangioma comprises a treatment scheme targeting MAP3K3 c.1323C>G mutation or MAPK downstream pathway; and the output device is used for outputting the discrimination result of the computing device.

[0073] In the present disclosure, specifically, since the MAP3K3 c.1323C>G mutation can activate the MAPK downstream pathway, when it is determined that the brain cavernous hemangioma corresponding to the magnetic resonance image is characterized by popcorn-like lesion, it can be determined that the patient to be tested has MAP3K3 c.1323C>G gene mutation, and further, it can be determined that the treatment scheme for the patient to be tested comprises a treatment scheme targeting MAP3K3 c.1323C>G mutation or MAPK downstream pathway.

[0074] Further, after determining that the treatment scheme for the patient with the cerebral cavernous malformation includes a treatment scheme targeting the MAP3K3 c.1323C>G mutation or a MAPK downstream pathway, the processor is further configured to determine that the treatment scheme for the patient with the cerebral cavernous malformation does not include a treatment scheme targeting the CCM1 / 2 / 3 mutation.

[0075] Optionally, the memory further stores characteristic data of the cerebral cavernous malformation, and the determining of the lesion characteristics of the cerebral cavernous malformation corresponding to the imaging examination image input by the image input device comprises: comparing the imaging examination image with the characteristic data of the cerebral cavernous malformation to obtain a comparison result; and determining the lesion characteristics of the cerebral cavernous malformation corresponding to the imaging examination image according to the comparison result.

[0076] Optionally, the characteristic data of the cerebral cavernous malformation comprises a cerebral cavernous malformation image library, and the cerebral cavernous malformation image library contains preset images, the preset images comprising type I images, type II images, type III images, and type IV images, wherein the type I images are characterized by subacute hemorrhage, the type II images are characterized by popcorn-like lesions, the type III images are characterized by chronic hemorrhage, and the type IV images are characterized by punctate multifocal lesions.

[0077] Further, the comparing of the imaging examination image with the characteristic data of the cerebral cavernous malformation to obtain a comparison result can comprise: performing image matching of the imaging examination image with the preset images in the cerebral cavernous malformation image library to obtain an image classification corresponding to the imaging examination image.

[0078] Further, the determining of the lesion characteristics of the cerebral cavernous malformation corresponding to the imaging examination image according to the comparison result comprises: if the image classification corresponding to the imaging examination image is type II, determining that the cerebral cavernous malformation corresponding to the imaging examination image is characterized by popcorn-like lesions; and if the image classification corresponding to the imaging examination image is type IV, determining that the cerebral cavernous malformation corresponding to the imaging examination image is characterized by punctate multifocal lesions.

[0079] Optionally, the imaging examination image comprises a magnetic resonance image and / or a CT image; and the system can further comprise an image acquisition device; preferably, the image acquisition device is a magnetic resonance imaging device and / or a CT scanning device.

[0080] The present disclosure will be further described by way of examples, but the present disclosure is not limited in any way by the examples. The raw materials, reagents, instruments and equipment involved in the examples of the present disclosure can be obtained by purchase, unless otherwise specified.

[0081] Example 1

[0082] This example is used to illustrate that the MAP3K3 c.1323C>G gene mutation exists in patients with cerebral cavernous malformations characterized by popcorn-like lesions.

[0083] Based on the magnetic resonance images of 38 CCM patients, the CCM lesion types of the above-mentioned patients are classified into four subtypes according to the Zabramski classification method: Type I is characterized by subacute hemorrhage, Type II is characterized by popcorn-like lesions, Type III is characterized by chronic hemorrhage, and Type IV is characterized by punctate multifocal lesions. After classification, among the 38 CCM patients, 25 cases are Type I CCM lesions, 7 cases are Type II CCM lesions, 0 cases are Type III CCM lesions, and 6 cases are Type IV CCM lesions, as shown in Table 1. The magnetic resonance images corresponding to the above-mentioned four CCM lesion subtypes are shown in Figure 1. Figure 3 Figure 2

[0084] Using the operation in accordance with the standard of medical ethics committee, the CCM lesion tissue medical waste obtained after surgical treatment of the above-mentioned 38 CCM patients is collected, classified according to the CCM lesion subtype, and frozen for preservation as a discovery sample. Each patient whose sample is collected has obtained the consent of himself / herself and his / her treatment expert before the sample is collected, and has written proof materials.

[0085] The discovery samples of the above-mentioned four subtypes are detected by droplet digital polymerase chain reaction (ddPCR), and the detection results are shown in Table 2. The detection results (P<0.001) show that the MAP3K3 c.1323C>G gene mutation exists in 2 / 25 cases of Type I, 7 / 7 cases of Type II, and 0 / 6 cases of Type IV. Statistical regularity shows that the MAP3K3 c.1323C>G gene mutation exists in patients with magnetic resonance images showing Type II. Figure 3

[0086] Example 2

[0087] This example is used to verify that the cerebral cavernous malformation patients with the MAP3K3 c.1323C>G gene mutation are patients with popcorn-like lesion characteristics.

[0088] Using the operation in accordance with the standard of medical ethics committee, the CCM lesion tissue medical waste obtained after surgical treatment of 56 CCM patients is collected as a verification sample. Each patient whose sample is collected has obtained the consent of himself / herself and his / her treatment expert before the sample is collected, and has written proof materials.

[0089] ​​​The sequencing results of the digital polymerase chain reaction on the above-mentioned found samples show that the MAP3K3 c.1323C>G gene mutation exists in 25 verification samples, and the MAP3K3 c.1323C>G gene mutation does not exist in the remaining verification samples.

[0090] The magnetic resonance detection is performed on the patients corresponding to the above-mentioned 25 verification samples with the MAP3K3 c.1323C>G gene mutation, and the subtypes of each patient are determined based on the obtained magnetic resonance images. The detection results show that 4 of them are type I, 17 are type II, and 4 are type III. It can be seen that the gene mutation detection results are basically consistent with the magnetic resonance detection results, and the deviation conforms to the statistical law, which indicates that the system of the present disclosure can accurately identify the patients with the MAP3K3 c.1323C>G gene mutation according to the magnetic resonance images of the CCM patients.

[0091] Example 3

[0092] The found samples (38 patients) in Example 1 and the verification samples (56 patients) in Example 2 are taken as experimental samples (94 patients) together, and the subtype classification is performed based on the magnetic resonance images. Among them, 52 are type I, 26 are type II, 5 are type III, and 11 are type IV.

[0093] The droplet digital polymerase chain reaction (ddPCR) detection is performed respectively, and the detection results show that the MAP3K3 c.1323C>G gene mutation exists in 6 / 52 cases of type I (0.12), 24 / 26 cases of type II (0.92), 0 / 11 cases of type IV (0), and 4 / 5 cases of type III (0.80).

[0094] Based on the above detection results, a two-step decision tree model for inferring the MAP3K3 c.1323C>G gene mutation based on radiological evaluation is provided, as shown in Figure 4 wherein the numbers at each node represent the probability of the occurrence of the MAP3K3 c.1323C>G gene mutation. The area under the receiver operating characteristic curve (AUC ROC) of the above-mentioned model is 0.97 and 0.92 respectively in the found samples and the verification samples, as shown in Figure 5 which indicates that the system of the present disclosure has high credibility.

[0095] Based on the above detection results, a two-step decision tree model for inferring the CCM gene germ cell mutation based on radiological evaluation is provided, as shown in Figure 6 wherein the numbers at each node represent the probability of the occurrence of the CCM gene germ cell mutation. The area under the receiver operating characteristic curve (AUC ROC) of the above-mentioned model is 0.85, as shown in Figure 7As shown, it is illustrated that the system of the present disclosure has high credibility.

[0096] The preferred embodiments of the present disclosure are described in detail above with reference to the drawings, but the present disclosure is not limited to the specific details of the above-described embodiments. Within the technical concept of the present disclosure, various simple modifications can be made to the technical solutions of the present disclosure, and these simple modifications all belong to the protection scope of the present disclosure.

[0097] In addition, it should be noted that each specific technical feature described in the above specific embodiments can be combined in any appropriate manner without contradiction. In order to avoid unnecessary repetition, various possible combinations are not described again in the present disclosure.

[0098] In addition, various different embodiments of the present disclosure can also be combined in any manner, as long as they do not deviate from the idea of the present disclosure, and they should also be considered as disclosed by the present disclosure.

Claims

1. A system for identifying gene mutation types in patients with cavernous malformation, characterized in that, The system comprises an image input device, a computing device and an output device; The image input device is used for inputting the imageological examination image of the head of the patient with cerebral cavernous angioma; the imageological examination image comprises a magnetic resonance image; The computing device comprises a memory and a processor, the memory stores a computer program, the memory also stores feature data of cerebral cavernous angioma, and the processor is configured to execute the computer program stored in the memory to realize the following discrimination: determine the lesion characteristics of the cerebral cavernous angioma corresponding to the imageological examination image input by the image input device, comprising: comparing the imageological examination image with the feature data of the cerebral cavernous angioma to obtain a comparison result; determine the lesion characteristics of the cerebral cavernous angioma corresponding to the imageological examination image according to the comparison result; if the cerebral cavernous angioma corresponding to the imageological examination image is characterized by point-like multifocal lesions, it is determined that the patient with cerebral cavernous angioma has CCM germ cell mutation; if the imaging examination image corresponds to a brain cavernous hemangioma characterized by popcorn lesions, it is determined that the brain cavernous hemangioma patient has MAP3K3 c. a 1323C>G type gene mutation; determining that the patient with the brain cavernous angioma has MAP3K3 c.1323C>G (p.Ile441Met) type gene mutation, the processor is further configured to: determining that the patient with the cerebral cavernous malformation does not have CCM1 / 2 / 3 a mutation in the CCM2 gene; The output device is used for outputting the discrimination result of the computing device; The feature data of the cerebral cavernous angioma comprises a cerebral cavernous angioma image library, the cerebral cavernous angioma image library contains preset images, the preset images include type I image, type II image, type III image and type IV image, wherein the type I image is characterized by subacute hemorrhage, the type II image is characterized by popcorn-like lesions, the type III image is characterized by chronic hemorrhage, and the type IV image is characterized by point-like multifocal lesions; comparing the imageological examination image with the feature data of the cerebral cavernous angioma to obtain a comparison result, comprising: image matching the imageological examination image with the preset images in the cerebral cavernous angioma image library to obtain the image typing corresponding to the imageological examination image; determine the lesion characteristics of the cerebral cavernous angioma corresponding to the imageological examination image according to the comparison result, comprising: if the image typing corresponding to the imageological examination image is type II, it is determined that the cerebral cavernous angioma corresponding to the imageological examination image is characterized by popcorn-like lesions; if the image typing corresponding to the imageological examination image is type IV, it is determined that the cerebral cavernous angioma corresponding to the imageological examination image is characterized by point-like multifocal lesions.

2. The system of claim 1, wherein, The system further comprises an image acquisition device; the image acquisition device is a magnetic resonance imaging device.

3. A system for determining a treatment plan for a patient with cavernous malformation, characterized in that, The system comprises an image input device, a computing device and an output device; The image input device is used for inputting the imageological examination image of the head of the patient with cerebral cavernous angioma; the imageological examination image comprises a magnetic resonance image; The computing device comprises a memory and a processor, the memory stores a computer program, the memory also stores feature data of cerebral cavernous angioma, and the processor is configured to execute the computer program stored in the memory to realize the following discrimination: Judging the lesion characteristics of the brain cavernous hemangioma corresponding to the image input by the image input device, comprising: Comparing the image with the feature data of the brain cavernous hemangioma to obtain a comparison result; According to the comparison result, the lesion characteristics of the brain cavernous hemangioma corresponding to the image are determined; If the brain cavernous hemangioma corresponding to the image is characterized by point-like multifocal lesions, the treatment scheme of the patient with brain cavernous hemangioma includes a treatment scheme targeting CCM gene germ cell mutation; if the imaging examination image corresponds to a brain cavernous hemangioma characterized by popcorn lesions, determining that the treatment scheme of the brain cavernous hemangioma patient includes targeted MAP3K3 c. a 1323C>G mutation or a treatment scheme of a MAPK downstream pathway; determining that the treatment regimen for the patient with the cerebral cavernous malformation comprises targeting MAP3K3 c. the processor is further configured to determine that the treatment regimen for the patient with the cerebral cavernous malformation comprises targeting c. the processor is further configured to determine that the treatment regimen for the patient with the cerebral cavernous malformation comprises targeting determining that the treatment regimen for the patient with the cerebral cavernous malformation does not include targeting CCM1 / 2 / 3 a mutated treatment regimen; The output device is used to output the discrimination result of the computing device; The feature data of the brain cavernous hemangioma includes a brain cavernous hemangioma image library, which contains preset images, including type I images, type II images, type III images and type IV images, wherein the type I images are characterized by subacute hemorrhage, the type II images are characterized by popcorn-like lesions, the type III images are characterized by chronic hemorrhage, and the type IV images are characterized by point-like multifocal lesions. The comparison of the image with the feature data of the brain cavernous hemangioma to obtain a comparison result comprises: Image matching of the image with the preset images in the brain cavernous hemangioma image library to obtain the image typing corresponding to the image; According to the comparison result, the lesion characteristics of the brain cavernous hemangioma corresponding to the image are determined, comprising: If the image typing corresponding to the image is type II, it is determined that the brain cavernous hemangioma corresponding to the image is characterized by popcorn-like lesions; If the image typing corresponding to the image is type IV, it is determined that the brain cavernous hemangioma corresponding to the image is characterized by point-like multifocal lesions.

4. The system of claim 3, wherein, The system further comprises an image acquisition device; the image acquisition device is a magnetic resonance imaging device.

Images