29 results about "T2 weighted" patented technology

The invention discloses an MRI (Magnetic Resonance Imaging) image registration generation method based on a Cycle consistency framework, which comprises the following steps of: inputting a T1 weighted image into an image generation network to obtain a T2 weighted image, inputting the T2 weighted image generated by the image generation network and an original T2 weighted image into an image registration network to obtain an aligned T2 weighted image, and outputting the aligned T2 weighted image to a Cycle consistency framework; and inputting the aligned T2 weighted image into an image generation network to obtain a T1 weighted image, and inputting the T1 weighted image generated by the image generation network and the original T1 weighted image into an image registration network to obtain an aligned T1 weighted image. According to the invention, the defects in the prior art can be improved, and the generation quality of the MRI image is improved.

The invention discloses an automatic hepatic fibrosis staging method and system based on deep learning, and the method comprises the following steps: S1, obtaining T1WI and T2WI original image data of a patient, carrying out the data preprocessing and liver segmentation of the original image data, and obtaining a T1 weighted image data set and a T2 weighted image data set; s2, a DMF-Vheat hepatic fibrosis staging model is constructed, the staging model adopts a double-sequence classification architecture and comprises a T1 branch network, a T2 branch network and a fusion network, and a heat conduction operator layer and a mixed attention module are adopted to extract and process complementary information of T1WI and T2WI sequences; s3, putting the T1 weighted image data set and the T2 weighted image data set into the staging model for training, and optimizing the staging model; and S4, outputting a hepatic fibrosis staging result through the staging model. According to the method, complementary information of T1WI and T2WI is fully utilized through the multi-mode deep learning network, and the accuracy and practicability of hepatic fibrosis staging are remarkably improved.

The present disclosure relates to a lumbar vertebra lesion identification method, device, medium and electronic equipment, wherein the method comprises: determining a lumbar vertebra image of a user, the lumbar vertebra image being a T2 weighted magnetic resonance image; inputting the lumbar vertebra image into a target detection model to obtain a lesion category of the lumbar vertebra of the user, wherein the target detection model comprises a down-sampling layer and a pooling layer, the down-sampling layer is used to extract feature data of the lumbar vertebra image, and the pooling layer is used to classify the feature data to obtain the lumbar vertebra lesion category of the user. Compared with the way of judging the lumbar vertebra lesion by artificial judgment and identifying the lumbar vertebra lesion by machine learning method in the related art, the error of identifying the lumbar vertebra lesion type can be reduced, and thus the accuracy of identifying the lumbar vertebra lesion can be improved.

The invention discloses a neurodegenerative change assessment method and device based on nerve melanin MRI, and relates to the technical field of medical imaging and neuroscience assessment, and the method comprises the steps: obtaining MRI image data of a to-be-assessed individual; the MRI image data comprises multi-sequence MRI image data including three-dimensional T1 weighted imaging, two-dimensional T2 weighted imaging and magnetization transfer imaging; preprocessing the MRI image data to obtain preprocessed MRI image data; extracting a region of interest from the preprocessed MRI image data to obtain the region of interest; performing MRI signal feature analysis on the region of interest to obtain MRI signal features; and inputting the MRI signal features into a neurodegenerative change evaluation model, and outputting a neurodegenerative change evaluation result of the individual to be evaluated. According to the application, the non-invasive and accurate evaluation of the neurodegenerative change can be realized by using the unique signal characteristics of the nerve melanin in MRI imaging.

The invention relates to a method and a device for automatically identifying benign and malignant kidney cystic lesions based on magnetic resonance images. The method comprises the following steps: S1, preprocessing and standardizing a T2 weighted image, a diffusion weighted image, an apparent diffusion coefficient image, a T1 weighted image, a skin medullary phase image, a parenchyma phase image and an excretion phase image; s2, respectively training automatic segmentation models corresponding to different images in a targeted manner, and predicting a focus by using the automatic segmentation models; s3, extracting morphological features, first-order features and textural features of the lesions from all the lesions, wherein the morphological features, the first-order features and the textural features comprise features of capsule walls, partitions and nodules of the lesions; screening the extracted features, and constructing a classification model by using the features with good robustness; and S4, preprocessing and standardizing the image of the current patient, respectively inputting the image into each corresponding automatic segmentation model, and operating the segmentation model and the classification model to realize benign and malignant recognition based on image recognition. According to the invention, integrated and automatic benign and malignant accurate diagnosis of kidney cystic lesions is realized.

The invention relates to the technical field of medical image analysis and molecular diagnosis. The invention discloses a multi-mode prognosis evaluation method for local advanced cervical cancer. The method comprises the following steps: acquiring a magnetic resonance T2 weighted image and a tumor tissue sample of the same patient before treatment; based on the magnetic resonance T2 weighted image, a first risk score is output through a deep learning prognosis prediction model, and first risk layering is completed; screening prognosis related key protein combinations based on proteomics expression data of tumor tissue samples to complete second risk stratification or clustering typing; and fusing the first risk layering result and the second risk layering / clustering typing result to generate a comprehensive multi-mode prognostic risk assessment report. According to the method, the MRI image and the proteomics data are fused through the full-automatic deep learning model, non-invasive prognosis evaluation of cervical cancer is realized, high-risk / low-risk patients can be accurately distinguished without manual sketching, individualized treatment decision is supported, and the clinical transformation value is remarkably improved.

The invention relates to the technical field of biomedical nanomaterials, and particularly discloses a chemiluminescence afterglow nanoprobe based on magnetic regulation and control as well as a preparation method and application of the chemiluminescence afterglow nanoprobe. The nanoprobe takes zinc-doped ferroferric oxide (ZnFe2O4, ZF) magnetic nanoparticles with enzyme-like catalytic activity as an inner core, a chemiluminescent molecule QM-CF with a singlet oxygen response characteristic is wrapped, and the nanoprobe is formed by packaging an amphiphilic material DSPE-PEG-2000. According to the nanoprobe, under the action of an alternating magnetic field, a ZF core can be catalyzed to generate singlet oxygen, so that QM-CF molecules are efficiently activated to generate chemical afterglow luminescence with extremely high intensity and long half-life period; and meanwhile, the ZF kernel endows excellent T2 weighted magnetic resonance imaging capability and magnetocaloric effect. According to the invention, remote and controllable activation and enhancement of chemical afterglow luminescence through an external magnetic field are realized, a multi-mode imaging function integrating magnetic resonance imaging, magnetic afterglow optical imaging and thermal imaging is successfully integrated, and a novel tool is provided for precise diagnosis and imaging guide treatment of solid tumors.

The invention relates to the technical field of medical treatment of cesarean section scar pregnancy evaluation and treatment, in particular to a combined evaluation method and system for cesarean section scar pregnancy. According to the method, serum beta-hCG examination, ultrasonic examination and nuclear magnetic examination are completed within 24 hours before an operation, the blood flow type around a gestational sac is measured through ultrasonic, and the blood flow type around the gestational sac is measured; the size of a gestational sac, the size of a gestational sac in a diverticulum and the thickness of a cesarean delivery scar are measured on the T2 weighted sagittal view image through nuclear magnetism, a comprehensive score is preset according to 0-2 scores by combining a serum beta-hCG result (the total score is 10), and surgical treatment is guided according to the score; according to the method, evaluation is accurate and sufficient, operation is easy, convenient and rapid, damage is small, predicted AUC values for operation failure, serious bleeding and continuous existence of lesions are 0.922, 0.955 and 0.862 respectively, applicability and traceability are high, and clinical treatment risks can be effectively guided to be reduced.

The invention discloses a small kidney tumor preoperative diagnosis method, system, medium and device based on MRI, and belongs to the field of medical imaging diagnos.The method comprises the steps that clinical feature data and original MR I image data of a patient to be diagnosed and MRI interpretation feature data obtained through interpretation based on the original MRI image data under the blind method condition are obtained; performing tumor region segmentation in the original MRI image data to generate tumor three-dimensional volume-of-interest data; extracting a radiomics feature set from a non-fat suppression T2 weighted imaging sequence and a contrast enhancement T1 weighted imaging sequence in the original MRI image data based on the tumor three-dimensional volume-of-interest data, and performing weighted fusion calculation on each feature in the radiomics feature set to obtain a radiomics score; and inputting the clinical feature data, the MR I interpretation feature data and the radiomics score into a preset composite diagnosis model for diagnosis, and outputting a diagnosis result. By implementing the method, the accuracy of benign and malignant identification before the small kidney tumor operation can be improved.

The application provides a medical image cross-modality generation method based on double-contrast frequency domain decomposition and adaptive diffusion, which comprises the following steps: acquiring MRI samples and preprocessing, constructing a k-space decomposition and enhancement process, constructing a k-space double-flow adaptive degradation network, and constructing a k-space double-flow adaptive prediction network. Through data enhancement technology and an adaptive Gaussian filter set, different frequency components are separated and enhanced, common edge features are highlighted, and the quality of generated information is improved. By using a residual noise diffusion model, high-resolution images with rich details and high diversity are generated while maintaining smooth areas and large-scale structures of images. By introducing anatomical structure consistency constraints and multi-modality fusion optimization strategies, the complementary information of T1 and T2 weighted MRI is fully utilized, and the generation effect and visual authenticity of the medical image cross-modality generation in a complex scene are significantly improved.

The application discloses an infant brain T2 weighted magnetic resonance imaging optimization method based on a fast spin echo sequence. First, T1, T2 and PD quantitative imaging of the infant brain from 0 to 24 months old is collected to obtain T1, T2 and PD values of the infant brain white matter and gray matter regions, and according to the relationship characteristics of the infant brain white matter T2 value and the gray matter T2 value, the infant is divided into different month groups. Then, based on the 3D T2 weighted imaging of the variable flip angle fast spin echo sequence, the signal intensity of the infant brain white matter and gray matter under different refocusing flip angle chains is calculated through an extended phase graph algorithm, and the best flip angle chain design scheme of each group is determined with the maximum white matter / gray matter contrast as the target. The application fills the blank of the infant brain T2 weighted imaging optimization, formulates the best flip angle chain optimization scheme of different month groups, and thus significantly improves the contrast of the infant brain T2 weighted imaging.

The invention relates to the technical field of magnetic resonance imaging, and discloses a thin-layer oblique coronal focusing view diffusion weighted imaging method of a magnetic resonance system, which comprises the following steps of: extracting a three-dimensional space walking path of a target bile duct based on magnetic resonance pancreaticobiliary duct water imaging and a cross section T2 weighted image, performing optimal plane fitting, and determining a personalized oblique coronal scanning plane; in the plane, diffusion weighted imaging is carried out by adopting a small visual field set according to bile duct projection, a layer thickness not higher than 3.0 mm and a low b value not higher than 100 seconds / square millimeters and a high b value not lower than 800 seconds / square millimeters, and echo time is set to a minimum value allowed by a system. Through cooperation of personalized plane positioning, thin-layer high-b-value imaging and intelligent quality control, the problems that conventional magnetic resonance imaging is incomplete in display of an extrahepatic cholangiocarcinoma lesion anatomical structure, low in signal-to-noise ratio, multiple in motion artifacts and difficult to accurately evaluate the longitudinal infiltration range of a tumor are solved.

The invention relates to a lumbar vertebra lesion recognition method and device, a medium and electronic equipment, and the method comprises the steps: determining a lumbar vertebra image of a user, and the lumbar vertebra image is a T2 weighted nuclear magnetic resonance image; the lumbar vertebra image is input into a target detection model, the lesion category of the lumbar vertebra of the user is obtained, the target detection model comprises a down-sampling layer and a pooling layer, the down-sampling layer is used for extracting feature data of the lumbar vertebra image, the pooling layer is used for carrying out classification processing on the feature data, and the pooling layer is used for obtaining the lesion category of the lumbar vertebra of the user; and obtaining the lumbar vertebra lesion category of the user. Compared with a mode of manually judging the lumbar vertebra lesion and identifying the lumbar vertebra lesion through a machine learning method in the prior art, the method can reduce errors of identifying the type of the lumbar vertebra lesion, and can improve the accuracy of identifying the lumbar vertebra lesion.

The invention provides a Douglas fossa occlusion prediction method based on multi-mode MRI (Magnetic Resonance Imaging) feature fusion. The method comprises the following steps: collecting multi-modal 3D MRI data of a patient, wherein the multi-modal 3D MRI data comprises pelvic cavity 3D T1 weighted and T2 weighted MRI image data; the method comprises the following steps of: firstly, carrying out multi-modal MRI (Magnetic Resonance Imaging), preprocessing the multi-modal MRI to realize image registration, mapping the multi-modal MRI to the same space, and secondly, realizing local contrast enhancement and marginal definition optimization of the MRI image through adaptive histogram equalization; secondly, designing a parallel-based double-branch 3D-Mama network to extract long-term spatial dependence and continuous features of the weighted MRI images T1 and T2; a 3D channel and space double attention fusion module is further designed, and multi-mode MRI feature deep fusion and adaptive feature selection are achieved; and finally, mapping the learned multi-modal MRI fusion features to a classification space by using a multi-layer perceptron, and carrying out POD occlusion classification prediction.

The invention provides a medical image processing method and system, computer equipment and a storage medium, and belongs to the field of image processing.The medical image processing method comprises the steps that T1 weighted imaging and T2 weighted imaging in brain and neck medical images are collected, multi-scale feature extraction is conducted on the T1 weighted imaging and the T2 weighted imaging, and brain and neck region features are obtained; generating a first target image according to the brain and neck region features; generating a second target image from the first target image based on a dense connection mechanism; optimizing a signal of a focus area in the second target image through a focus perception loss function fused with the focus automatic segmentation result to obtain an optimized target image; and synthesizing a cross-modal brain target image and a cross-modal neck target image according to the first target image, the second target image and the optimized target image. According to the method, the problem of key sequence deletion in multiple sclerosis diagnosis is solved, the retention rate of small focuses is increased, and reliable technical support is provided for MS early screening.

The application provides a renal artery image registration method and device, electronic equipment and storage medium, and relates to the technical field of image processing. The method comprises: processing a magnetic resonance T2 weighted coronal sequence to determine a key frame image containing a spine structure; splicing at least two frames of images in a digital subtraction angiography sequence to generate a reference image containing a spine panorama; back-projecting head-to-foot direction coordinates of a target slice center in a patient coordinate system in magnetic resonance angiography to a corresponding pixel row in the key frame image to obtain first pixel coordinates; calculating a physical displacement corresponding to the first pixel coordinates from a starting pixel coordinate; calculating a pixel displacement corresponding to the physical displacement in the reference image, and determining a positioning result of a renal artery entrance in the reference image based on the pixel displacement and a mapping point of the starting pixel coordinate in the reference image. Through the method provided by the application, the amount of contrast agent and related risks are effectively reduced.

The invention relates to a local anesthesia dosage control system based on CFD (Computational Fluid Dynamics) and PC-MRI (Personal Computer-Magnetic Resonance Imaging) coupling and a working method thereof, and the system comprises an information collection unit which is used for collecting physical examination and medical evaluation information of a patient; the geometric unit is used for acquiring a T2 weighted MRI image sequence; the calculation model unit is used for determining the range of a lumbar, thoracic and vertebral segment calculation domain; a measurement unit for phase encoding using PC-MRI; the cerebrospinal fluid dynamic unit is used for acquiring an initial flow field of cerebrospinal fluid flow of the spinal canal of the patient; the dosage selection unit is used for selecting the injection dosage of the local anesthetic; the intrathecal administration calculation unit is used for establishing coupling analysis to obtain a local anesthetic concentration value of a blocking plane; and the dose evaluation unit is used for quantitatively evaluating the concentration value of the local anesthetic. The system is beneficial for improving the accuracy and safety of local anesthesia medication.

The invention discloses a magnetic resonance imaging sequence trajectory rewinding compensation method and device, a medium and a product, and relates to the technical field of magnetic resonance imaging, and the method comprises the steps: collecting the actual gradient waveforms of three gradient axes in a set time period after an excitation radio frequency pulse is applied to a water model in a magnetic resonance scanner in the current repetition time; setting ideal gradient waveforms of three gradient axes in a set time period; any gradient axis is determined as a current axis; determining the residual gradient time moment of the current axis based on the actual gradient waveform and the ideal gradient waveform of the current axis in the set time period, and determining the waveform parameter of the current axis of the rewinding compensation gradient pulse; and applying a component of the rewinding compensation gradient pulse on the current axis to the current axis based on the residual gradient time moment of the current axis and the waveform parameter of the current axis of the rewinding compensation gradient pulse at the end moment of the phase disturbing gradient so as to realize the rewinding compensation of the magnetic resonance imaging sequence trajectory. According to the invention, the problems of quantitative deviation and image blurring of T2 weighted imaging are solved.

The invention discloses a virtual magnetic resonance imaging system, which belongs to the technical field of magnetic resonance imaging, and comprises a layer thickness selection module, an interlayer interference module, an excitation angle module, an excitation frequency module, a TR dynamic adjustment module and a TE dynamic adjustment module. The thin layer thickness improves the layer selection direction resolution, and the thick layer thickness improves the signal-to-noise ratio; interlayer cross interference can be reduced by controlling the interlayer spacing, useless signal superposition is avoided, and the signal-to-noise ratio is further improved by combining with increase of the layer thickness; the adaptive excitation angle can optimize the energy consumption and the relaxation time, the energy demand is reduced at a small angle, and the relaxation time is shortened; the signal-to-noise ratio can be quantitatively improved by adjusting the excitation frequency, and the one-time excitation frequency and the signal-to-noise ratio are improved by two times; the signal strength can be guaranteed and the time waste can be avoided by dynamically adjusting the TR; tE is selected for focusing T2 weight, organization difference display and a basic signal-to-noise ratio are considered, and the image quality and the imaging efficiency are integrally optimized.

The invention relates to a noninvasive assessment method for radiation cognitive function impairment, and the method comprises the following steps: S100, obtaining a nuclear magnetic resonance image, and carrying out the standardization of the nuclear magnetic resonance image, and the nuclear magnetic resonance image comprises a T2 weighted image and a BOLD image; s200, after second-order analysis, parameter estimation and multiple comparison are carried out on the standardized T2 weighted image and the BOLD image, data with morphological differences are obtained through data processing, and a T2 weighted structure image and a BOLD functional image are obtained; s300, carrying out VBM analysis based on the T2 weighted structure image, and extracting a gray matter volume value of the differential brain region; s400, performing FC analysis based on the BOLD functional image; and S500, constructing a VBM-FC correlation analysis framework, and forming a joint index and integrated evaluation model.

The invention relates to the technical field of intelligent medicine, in particular to a Crohn disease intestinal fibrosis condition early warning method based on large model driving, which comprises the following steps: acquiring an intestinal MRI image sequence of a Crohn disease patient; inputting the intestinal MRI image sequence into a pre-trained intestinal structure analysis large model, and positioning the position of an initial intestinal fibrosis region; determining whether the intestinal lumen stenosis degree of the patient with the Crohn disease reaches the standard or not based on the intestinal lumen stenosis progress index, and determining a feature comparison threshold value for adjusting the large model according to the difference value; determining whether the acute inflammation shielding effect of the patient with the Crohn disease is qualified or not based on the intestinal wall edema characterization parameters, and determining and adjusting the T2 weighted imaging modal weight of the large model according to the relative difference; and determining whether the fibrosis seepage channel smoothness of the patient with the Crohn disease is qualified or not based on the fibrosis seepage resistivity, and determining and adjusting the boundary loss weight of the large model according to the ratio. The early warning accuracy of the intestinal fibrosis condition of the Crohn's disease is improved.

The invention discloses a method for predicting and identifying a joint replacement postoperative infection type based on a preoperative MRI (Magnetic Resonance Imaging) image, which comprises the following steps that: the preoperative MRI image of a patient, which comprises a T1 weighted sequence and a T2 weighted sequence, is acquired, and the T1 weighted sequence and the T2 weighted sequence both comprise three view angle images of coronal view, sagittal view and transection view to form an independent six-channel input tensor; automatically segmenting a joint infection related structure in the MRI image by introducing an image segmentation model of an attention mechanism, enhancing the response to high-risk infection region features, and generating a pixel-level mask as a subsequently classified ROI (Region of Interest); and inputting the six-channel input tensor into a deep convolutional neural network, guiding feature focusing in combination with an infection risk area mask generated by the image segmentation model, extracting high-order semantic features of an infection risk area, and outputting a three-classification prediction result through a full connection layer. The three-classification prediction result comprises superficial infection, deep infection and non-infection. And outputting a three-classification prediction result.

The invention provides a renal artery image registration method and device, electronic equipment and a storage medium, and relates to the technical field of image processing.The method comprises the steps that a magnetic resonance T2 weighted coronal sequence is processed, and a key frame image containing a spine structure is determined; splicing at least two frames of images in the digital subtraction angiography sequence to generate a reference image containing a spine panorama; back-projecting a head and foot direction coordinate of a target slice center in magnetic resonance angiography under a patient coordinate system to a corresponding pixel row in the key frame image to obtain a first pixel coordinate; calculating to obtain a corresponding physical displacement from the starting point pixel coordinate to the first pixel coordinate; and calculating a pixel displacement corresponding to the physical displacement in the reference image, and determining a positioning result of the renal artery inlet in the reference image based on the pixel displacement and a mapping point of the starting point pixel coordinate in the reference image. According to the method provided by the invention, the dosage of the contrast agent and related risks are effectively reduced.

The invention discloses a senile dementia related multi-contrast brain structure magnetic resonance imaging analysis method which comprises the following steps: acquiring multi-contrast brain structure magnetic resonance imaging data including T1 weighted imaging, T2 weighted imaging, proton density weighted imaging PD, liquid attenuation inversion recovery FLAIR and magnetic sensitivity weighted imaging SWI; constructing a model for multi-contrast brain structure magnetic resonance imaging analysis, wherein the model comprises an image denoising module, an image registration module and an image segmentation module; inputting the acquired magnetic resonance imaging data into the trained model; in the first step, noise suppression images corresponding to all contrast ratios are output, in the second step, multi-modal image registration is carried out, contrast ratio alignment images of unified voxel grids are generated, and in the third step, a final segmentation probability graph and a corresponding tissue label are output. By using the system and the method, high-quality, automatic and clinically deployable nuclear magnetic resonance imaging (MRI) brain image analysis is realized. The method can be widely applied to the field of medical image processing.

The invention provides a medical image cross-modal generation method based on double-contrast frequency domain decomposition and adaptive diffusion. The method comprises the steps of obtaining and preprocessing an MRI sample, constructing a k-space decomposition and enhancement process, constructing a k-space double-flow adaptive degradation network, and constructing a k-space double-flow adaptive prediction network. Through a data enhancement technology and an adaptive Gaussian filter bank, targeted separation and enhancement of different frequency components are realized, common edge features are highlighted, and the quality of generated information is improved. A residual noise diffusion model is utilized to generate a high-resolution image with rich details and high diversity while keeping a smooth region and a large-scale structure of the image. An anatomical structure consistency constraint and multi-modal fusion optimization strategy is introduced, complementary information of T1 and T2 weighted MRI is fully utilized, and the generation effect and visual authenticity of medical image cross-modal generation in a complex scene are remarkably improved.

The invention discloses a functional magnetic resonance imaging noise reduction method and device, and relates to the technical field of magnetic resonance imaging.The method comprises the steps that a T2 weighted functional magnetic resonance image and a T2 * weighted functional magnetic resonance image of a brain are acquired through a plane echo sequence, the plane echo sequence comprises a first echo chain and a second echo chain, t2 weighted signals collected by the first echo chain correspond to T2 weighted functional magnetic resonance images, T2 * weighted signals collected by the second echo chain correspond to T2 * weighted functional magnetic resonance images, and the T2 weighted signals appear before the T2 * weighted signals; splitting the signal change of each pixel in the T2 * weighted functional magnetic resonance image into short echo time signal change and blood oxygen level dependent signal change; and removing the short echo time signal change as noise to obtain the blood oxygen level dependent signal change. According to the invention, accurate short echo time signals can be acquired, and efficient noise reduction can be realized.

The invention discloses a nano-drug for improving the radiofrequency ablation curative effect of liver cancer as well as a preparation method and application of the nano-drug. An MELK inhibitor OTS167 is entrapped by a pH-responsive silicon-based nano-carrier, the MELK inhibitor OTS167 and superparamagnetic iron oxide are jointly loaded in nano-particles, and the surface of the carrier is modified with annular RGD polypeptide through covalent linkage, so that targeted recognition of high-expression integrin alpha v beta 3 in tumor cells and neovascularization of the tumor cells is realized; therefore, the active enrichment capability of the nanoparticles in tumor tissues is enhanced. The SPIO is used as a magnetic resonance imaging core of the nanoparticles and endows the nanoparticles with good T2 weighted imaging capability, and real-time monitoring of in-vivo distribution of the nanoparticles is realized. The compound can trigger the selective release of OTS167 in an acidic microenvironment, enhance the local drug effect of tumors and reduce the extratarget toxicity. In a liver cancer mouse model, the nano-drug combined with RFA can significantly inhibit tumor growth and prolong survival, and shows a good application prospect.

The embodiment of the invention relates to a method and device for predicting an early Alzheimer's disease based on lymphatic-like system characteristics. The method comprises the following steps: collecting an original sample set, constructing a first segmentation model based on a 3D-UNet model, and constructing a first prediction model based on an MLP model; constructing a first data set and a second data set based on the original sample set; training a first segmentation model based on the first data set; training a first prediction model based on the second data set; after model training is finished, a brain DTI image and a brain 3D-T2 weighted image of a testee are received, left and right brain ALPS index analysis is carried out according to the brain DTI image based on the DTI-ALPS technology, semantic segmentation is carried out on the brain 3D-T2 weighted image based on a first segmentation model, and volume fraction analysis is carried out on gaps around blood vessels of four brain regions according to a segmentation result; and using a first prediction model to perform prediction according to the two types of analysis results. The method can improve the processing efficiency and the prediction accuracy.