53 results about "Hepatic tumours" patented technology

The invention discloses a liver tumor image real-time segmentation method and system based on a YOLO algorithm, and the method comprises the steps: obtaining CT images and MRI images, and calculating the contrast indexes and signal-to-noise ratio indexes of a plurality of CT images; preprocessing the CT image, and dynamically adjusting an image enhancement strategy; a residual attention module is added on the basis of the YOLOv8 network, a multi-scale mask branch is introduced, and an optimized YOLO-Med segmentation network is constructed; inputting the enhanced CT image into a segmentation network, and training the segmentation network in combination with a loss function; and when an MRI image is input, through a multi-modal feature fusion mechanism, features of the MRI image and the enhanced CT image are aligned and fused and then are input into the segmentation network, and the segmentation network outputs a pixel-level segmentation mask for real-time segmentation of the liver and the tumor. According to the invention, by fusing the density characteristic of CT and the soft tissue resolution capability of MRI, the small tumor (diameter lt; 5 mm).

The invention discloses a 2.5 D dual-scale wavelet SAM-GAN liver tumor target region segmentation method, which comprises the following steps: establishing a segmentation model which is composed of a preprocessing module, a generation module and a discrimination module; an original image enters the preprocessing module and is subjected to neighborhood slice feature aggregation and anatomical perception to generate a 2.5 D image, the 2.5 D image is optimized and enhanced in the generation module and then input into the judgment module, and the judgment module evaluates the authenticity of the image output by the generation module and provides feedback training for the generation module. According to the method, the defects in the prior art can be overcome, the feature extraction capability on the liver tumor data set is improved, and the training stability and the model generalization capability are enhanced.

The invention relates to the technical field of medical image processing and surgical navigation, in particular to a liver segmentation, modeling and surgical simulation system based on a cascade neural network and a multi-scale reconstruction technology. The multi-scale dynamic registration module is used for carrying out coarse segmentation and fine segmentation on liver and focus areas of the medical image and is used for non-rigid registration and respiratory motion compensation of the multi-modal medical image; the physical enhancement modeling engine is used for constructing a liver vessel tree three-dimensional model containing hemodynamic characteristics; the operation navigation and risk assessment module is used for performing real-time navigation and operation path planning in the operation; and the self-adaptive computing framework provides underlying computing resource support for the system. And high-precision segmentation: through a cascade recursive network and a boundary sensitive loss function, the liver tumor segmentation Dice coefficient reaches 94-96%, which is increased by 6-12% compared with the traditional method.

The present disclosure provides a liver tumor segmentation method based on multi-temporal fusion and dual attention mechanism, which relates to the field of graphics processing technology and can solve the problem of poor liver tumor segmentation accuracy in the prior art. The specific technical solution is as follows: making a training set and a test set, and taking the arterial phase and portal venous phase same-layer images obtained from the same scan of a case as a pair of images; designing a multi-temporal feature fusion mechanism to fuse the features of the two-phase images; adding a dual attention mechanism to improve the network's attention to liver tumor features; constructing a liver tumor segmentation network based on the above two mechanisms with U-Net as the backbone network; using the images in the training set to train the liver tumor segmentation network; inputting the test set image pairs into the trained network, and using a threshold method to process the network output to obtain the liver tumor segmentation result. The present invention is used for liver tumor segmentation of multi-temporal CT images.

The invention discloses a navigation system for a liver tumor resection operation, and aims to solve the problems that in the prior art, the accuracy of the liver tumor resection operation is insufficient, the risk in the operation is high, and the evaluation after the operation is incomplete. The system comprises a preoperative data acquisition module, a preoperative three-dimensional modeling module, an intraoperative positioning module, an operation navigation module, a risk prompt module and a postoperative data analysis module. Through preoperative CT or MRI image data acquisition, automatic segmentation and three-dimensional reconstruction of liver, tumor and blood vessels are carried out by using a deep learning algorithm, and a high-precision anatomical model is generated. During the operation, the position of the surgical instrument is obtained in real time by using an optical tracking or electromagnetic positioning technology, spatial precise alignment of the surgical instrument with a tumor and surrounding tissues is realized in combination with a model registration algorithm, and a surgical path is displayed through a real-time navigation interface. And the risk prompting module calculates an excision risk coefficient and prompts a doctor in real time based on the shortest distance between the tumor and the blood vessel, the relative distance between the instrument and the target area and the trajectory change.

The invention provides a numerical simulation method for large tumor treatment of single-needle multi-point microwave ablation, and belongs to the technical field of large liver tumor data simulation. The method comprises the following steps: establishing a finite element simulation model, and solving the finite element simulation model according to the interaction among an electromagnetic field, heat conduction and biological tissues to obtain a simulation result; constructing a single-needle multi-point microwave ablation numerical model; carrying out ablation simulation by utilizing the single-needle multi-point microwave ablation numerical model, outputting multi-point ablation result data, quantifying the size and form of a solidification area, and carrying out space overlapping analysis on a contour surface to obtain the characteristics of the solidification area; ablation simulation is carried out by setting parameter combinations of pull-back distances and ablation time of a plurality of antennas, and an optimal parameter combination is obtained by combining feature analysis of a solidification area, so that numerical simulation of large tumor treatment is completed; according to the invention, the problems of low ablation temperature, long simulation time and difficulty in accurate positioning of the antenna in the existing single-needle multi-point microwave ablation simulation method are solved.

The invention discloses a liver tumor diagnosis method based on a self-supervision and multi-phase contrast enhanced CT image. The method comprises the following steps: collecting and preprocessing a CT image of a liver tumor; training a target detection model by using the marked CT image; processing the preprocessed CT image by using the trained target detection model, obtaining a focus detection frame, performing cutting and data enhancement according to the focus detection frame, performing resampling, adding a real joint label to the focus detection frame, and constructing a second training set and a test set; constructing a classification diagnosis model based on multiphase data based on self-supervision and knowledge distillation, performing iterative training by using the second training set, and adjusting parameters according to a total loss function of the classification diagnosis model in the training process to obtain a final liver tumor classification diagnosis model; and inputting the CT image in the test set into the final liver tumor classification diagnosis model to obtain a diagnosis result. The precision, accuracy and efficiency of liver tumor diagnosis can be improved.

An existing liver tumor automatic segmentation method is insufficient in expression in small focus, low-contrast edge and long-range space dependence modeling, and consequently high false positive and boundary deficiency are caused. Pure CNN is limited by a receptive field, pure Mama easily loses local details, multi-level attention stacking significantly increases parameter quantity, and traditional side supervision differential correction is difficult to accurately focus an uncertain area. The invention provides an end-to-end network, parallel ResNet and Mamba dual-coding and direct reaching a decoder after AFF fusion at the same scale, bottom features are accessed to a multi-scale feature fusion module to complete deep semantic enhancement, and a decoding side forms a GARS module concentration boundary difficult-to-distinguish pixel by matching an MSCB-EUCB-LGAG lightweight chain with four-stage Gaussian attenuation residual self-correction. Clinical level, the method can significantly reduce leak detection of small tumors, reduce false positive, and maintain geometric integrity of edges.

The application discloses a liver tumor CT image segmentation device and system and a storage medium. The application reads a liver tumor CT image, pre-processes the liver tumor CT image to obtain a target liver tumor feature image, and segments the target liver tumor feature image through a preset liver tumor segmentation model based on compressed attention to obtain a liver tumor segmentation image. The liver tumor segmentation model based on compressed attention is embedded with a gradient centering optimizer, and the optimizer is used to standardize a weight space and an output feature space and improve the generalization performance of the model. Compared with the existing liver tumor segmentation image segmentation mode, the liver tumor segmentation model based on compressed attention embedded with the gradient centering optimizer can learn more representative features in a semantic segmentation task and obtain a liver tumor segmentation image with higher segmentation accuracy.

The invention relates to the technical field of image segmentation, in particular to an automatic real-time outline drawing system for a liver tumor ablation area based on an ultrasonic image. The method comprises the following steps: firstly, registering and aligning preoperative and intraoperative ultrasonic images, and eliminating displacement deviation caused by factors such as respiratory movement and probe shaking; further based on the essential difference between the ablation region and the surrounding normal liver tissue in ultrasonic echo expression, dynamic changes of region features are analyzed to obtain ablation feature parameters of each sub-region in the intraoperative ultrasonic image so as to evaluate the ablation state, and then the image is enhanced based on the ablation state so as to enhance the boundary definition, and finally the ablation state of the intraoperative ultrasonic image is evaluated. And the outline drawing accuracy of the outline of the liver tumor ablation area is improved.

The application provides an unsupervised liver tumor CT image segmentation method based on manual features, relates to the technical field of deep learning, and first collects normal liver CT images as a data set, and selects a tumor position in combination with clinical knowledge. A texture similar to real imaging is generated through three-dimensional simple noise binary mask, and histological features are used for morphological modeling. Then, the tumor texture is superimposed with the liver CT image at the selected position to synthesize a new liver tumor CT image. A segmentation model is trained by using the CT image with annotations, and the synthesized image is used for medical image segmentation. Finally, the segmentation results are evaluated by using the Dice coefficient, the Hausdorff distance, the standardized surface distance and the surface distance index. The application is helpful for artificially synthesizing tumor lesion images and generating voxel-level annotations, and provides a new perspective for solving the medical image annotation challenge and promoting liver tumor diagnosis and treatment.

This invention discloses a liver tumor segmentation method, system, and storage medium based on plain CT scans, belonging to the field of medical image processing technology. It addresses the problem of the lack of existing liver tumor segmentation methods that can both improve the clarity of liver tumor boundaries and preserve detailed information. The key technical points of this invention include: Step 1, acquiring plain CT scan data of the liver from liver tumor patients; Step 2, segmenting the plain CT images using a pre-trained segmentation model to obtain a liver region mask; the segmentation model is based on the UNet model, using PVT-V2 as the backbone network of the encoder, and the decoder adopts a cascaded upsampling path, fusing a residual denoising module, a gated attention module, a multi-scale feature fusion module, and a depth supervision mechanism in each stage; Step 3, further segmenting the liver region mask using the segmentation model to obtain a liver tumor mask; Step 4, extracting features and classifying the liver region mask using a classification model to obtain the benign or malignant tumor result.

The invention discloses an automatic liver tumor segmentation method based on a UNet model fused with an SENet attention mechanism. The method comprises the following steps that an encoder of the UNet model receives input image data; the method comprises the following steps: gradually extracting the features of an input image through an encoder of a UNet model, reducing the spatial resolution, enabling the encoder to specifically extract the features of the input image with higher resolution capability by using an SENet attention mechanism, and screening out effective representative image feature information; the bottom convolution block performs convolution processing on the image feature information output by the encoder and then inputs the image feature information into the decoder; and performing up-sampling operation through a decoder of the UNet model, and generating a segmentation result through a 1 * 1 convolution kernel. According to the method, the subject Unet model and the channel attention mechanism SENet are included, and the targeted recognition and prediction capability of the model on the tumor existence area can be effectively improved through the attention mechanism, so that the diagnosis accuracy and efficiency of a doctor are improved, and better diagnosis and treatment experience is brought to a patient.

Disclosed in the application are a Bifidobacterium longum probiotic combined with a qi-tonifying and blood-nourishing medicinal and edible homologous composition, a preparation method thereof and application thereof in regulating immunity, inhibiting tumor cell proliferation and reducing tumor-induced inflammation, including Bifidobacterium longum subsp. infantis NKU FB3-14 and the qi-tonifying and blood-nourishing medicinal and edible homologous composition; the qi-tonifying and blood-nourishing medicinal and edible homologous composition comprises, by weight, 5-30 parts of ginseng, 5-20 parts of longan arillus, 20-50 parts of astragalus root, 10-50 parts of polygonatum, 5-20 parts of poria cocos, 5-15 parts of mulberry, 5-20 parts of licorice, 10-30 parts of orange peel, 5-15 parts of citrus medica, 5-20 parts of double-petaled rose flower and 3-10 parts of hawthorn. The probiotic preparation and the medicinal and edible homologous material have a synergistic effect, and the ability to inhibit the proliferation level of liver tumor cells H22 in vitro is determined.

The invention relates to a liver tumor segmentation method and device based on adaptive context awareness fusion, and the method comprises the steps: S1, obtaining and preprocessing liver CT data, and dividing the data into a training set, a verification set and a test set according to a proportion; s2, constructing an ACAF-Net (Adaptive Context-Aware Fusion Network), and constructing a double-enhanced dynamic convolution module in the transmission and fusion of the double paths; s3, fusing the double-enhanced dynamic convolution and the double attention weight, and constructing a double-dimensional mixed attention module; s4, fusing the sub-region segmentation error and the dynamic quantization difficulty, and constructing a double-error dynamic balance loss; s5, fusing the double-enhanced dynamic convolution module, the double-dimensional mixed attention module and the double-error dynamic trade-off loss to construct an ACAF-Net model; and S6, completing model training, verification optimization and performance evaluation by using the experimental data set. By using the method, the problems of fuzzy liver tumor boundary, large scale difference and unbalanced segmentation error are effectively solved, the segmentation precision and robustness are remarkably improved, and the method is suitable for automatic segmentation of the CT image liver tumor.

The invention discloses a traditional Chinese medicine composition for treating metabolic dysfunction related steatohepatitis inflammatory cancer transformation. The traditional Chinese medicine composition is prepared from the following raw material medicines in parts by weight: 15-20 parts of fructus perillae, 12-18 parts of semen brassicae, 12-18 parts of semen raphani, 12-18 parts of radix astragali, 28-32 parts of herba scutellariae barbatae, 12-18 parts of rhizoma polygonati, 6-12 parts of gecko, 12-18 parts of radix polygoni multiflori and 4-8 parts of liquorice root. The traditional Chinese medicine composition disclosed by the invention can be used for inhibiting the transformation progress of mouse metabolic dysfunction related steatohepatitis cancer, reducing the number of liver tumors, reducing the maximum surface area of the tumors and reducing the mRNA (messenger ribonucleic acid) levels of related tumor markers Gpc3 and Ly6d. In addition, the lipid level of the mouse liver and serum can be remarkably reduced, the fatty degeneration degree of the mouse liver is improved, the ALT and AST levels of the serum are reduced, and liver injury is relieved. In addition, the invention further discloses medical application of the traditional Chinese medicine composition.

The application relates to a semi-supervised medical image segmentation method based on double-view complementary consistency, which only uses a small amount of labeled medical image data to mine potential feature information in a large amount of unlabeled data to improve the segmentation model performance, and comprises the following steps: a feature space distillation mechanism is used to extract and transfer multi-scale semantic features through a teacher-student model; a double-view fusion strategy is used to optimize pseudo labels and optimize the learning effect of the model on unlabeled data; and an uncertainty estimation method assisted by a pre-trained autoencoder is used to optimize the reliability and segmentation precision of the model. Experimental results on a left atrium (LA) and liver tumor segmentation (LiTS) dataset show that the method achieves good effects in terms of segmentation precision and model robustness.

The application discloses a multi-branch liver tumor segmentation method based on UNet, and comprises the following steps: first, a multi-branch liver tumor segmentation network based on UNet is constructed; then, a training sample set constructed by CT images in which liver tumors have been segmented in advance is used to perform deep learning training on the multi-branch liver tumor segmentation network based on UNet, so that a trained multi-branch liver tumor segmentation network based on UNet is obtained; finally, a CT image currently in need of liver tumor segmentation is sent to the trained multi-branch liver tumor segmentation network based on UNet, so that the CT image in which the liver tumor has been segmented is obtained. By strengthening the receptive field of the segmentation network feature map and fully utilizing the channel and spatial structure information, pixel-level details and spatial information can be better captured, so that the segmentation performance of the network on medical images is improved. Different from existing methods, the network architecture proposed in the application can capture fine details of local edges and global multi-scale information at the same time, so that spatial consistency is ensured.

The application relates to a preoperative and intraoperative liver point cloud data registration system and method, a terminal and a storage medium. The method comprises the following steps: extracting local mixed features of preoperative point cloud data and intraoperative point cloud data respectively; fusing the local mixed features to obtain global features of the preoperative point cloud and global features of the intraoperative point cloud; fusing the local mixed features of the preoperative point cloud, the global features of the preoperative point cloud and the global features of the intraoperative point cloud to obtain fusion features of the preoperative point cloud; similarly, fusion features of the intraoperative point cloud are obtained; fusing the fusion features of the preoperative point cloud and the fusion features of the intraoperative point cloud to obtain respective overlapping area masks and decoding features; obtaining a spatial transformation matrix of the preoperative point cloud and the intraoperative point cloud; and applying the spatial transformation matrix to the preoperative point cloud data to obtain a registration result of the preoperative point cloud data and the intraoperative point cloud data. The application can provide convenience for accurate positioning of liver tumors, shorten the operation time, and improve the accuracy and safety of the operation.

The application provides a liver tumor segmentation method, and belongs to the field of medical image segmentation. In view of the starting point of how to improve the global context feature extraction ability and how to efficiently combine with local information, two parallel encoders are used, wherein a VGG convolutional neural network branch is introduced to extract local features, and an axial decomposition self-attention branch is designed to extract global features, and then a shared residual fusion decoder is used to effectively integrate the information of the two branches. While reducing the model calculation complexity and reducing the training parameter amount, the application can significantly improve the segmentation effect of liver tumors and reduce the false segmentation or misclassification phenomenon.

This invention discloses a semantic segmentation method for liver tumor CT images based on VIT-CNN and frequency awareness, belonging to the fields of medical image processing and computer vision technology. The method first preprocesses the liver tumor CT images to eliminate interference and standardize their dimensions. Then, it constructs a VIT-CNN hybrid feature extraction architecture, capturing local detail features through CNN branches and global context features through VIT branches. A frequency-aware mechanism is introduced to enhance and adaptively fuse the two types of features in the frequency domain, highlighting effective features and suppressing interference. An improved U-Net segmentation head and a hybrid loss function are designed, the model is trained, and the CT images are segmented. Finally, the segmentation performance is evaluated using multiple metrics. This invention solves the problems of unbalanced global and local feature capture, weak anti-interference ability, and insufficient segmentation accuracy in existing methods, achieving accurate segmentation of liver tumor CT images and providing reliable support for clinical diagnosis and treatment planning.

The present invention discloses a method and system for segmenting liver and liver tumor data. Based on the Unet network model, a long-distance attention mechanism and a multi-feature fusion module are proposed, and a cross-layer attention mechanism is designed using the hierarchical structure of the network; the cross-layer attention mechanism and the multi-feature fusion module are embedded in the Unet network, and the ResCLA-MNet segmentation network model is constructed in combination with the residual structure; the LiTS liver and liver tumor public CT dataset is used for training, verification, and testing the segmentation performance of the network model; the 3DircaDb-01 liver and liver tumor CT dataset is used to test the generalization performance of the ResCLA-MNet network model to ensure that the network has a certain data migration applicability; the hospital abdominal liver and liver tumor CT dataset is collected, and the trained network model is used to practice on the dataset to verify the application effect of the network. Based on Unet, the present invention draws on the Unet network architecture, combines the advantages of the attention mechanism and multi-feature fusion, and improves the accuracy of the network model in segmenting the liver and liver tumor.

The invention relates to the technical field of medical instruments, in particular to a liver tumor microwave ablation operation auxiliary device. Comprising an operating bed, a supporting platform arranged on one side of the operating bed, a rotation driving mechanism arranged on the top of the supporting platform, a lifting adjusting mechanism arranged on the rotation driving mechanism and a lifting sliding seat arranged on the lifting adjusting mechanism. The flexible positioning part is arranged on the lifting sliding seat and extends to the position over the operating bed. Controllable pressure is applied to the chest and abdomen through the flexible positioning part, the breathing movement amplitude can be actively and physically limited, and compared with the mode of simply depending on breath holding of a patient, a more stable and more lasting operation environment is created, and the operation difficulty is reduced. After an operation is completed, the whole auxiliary device can be rotated away from the position over an operating bed through the rotation driving mechanism, transferring and carrying of a patient are not hindered at all, and the turnover efficiency of an operating room is improved.

The invention discloses a method for establishing a target immunity treatment effect evaluation model for a liver cancer patient, and the method specifically comprises the following steps: S1, obtaining an arterial phase MRI image of the HCC patient, and carrying out the preprocessing; s2, inputting the preprocessed MRI image into a 3D-Unet network model for training so as to construct an automatic liver tumor segmentation model; s3, inputting an MRI image of an HCC patient receiving target immunotherapy into the 3D-Unet network model to obtain a liver tumor area image, and inputting the liver tumor area image into the 3D-CNN model to learn image features; and S4, fusing the image features extracted from the MRI sequence data by the 3D-CNN model with the clinical features extracted by the Transform module, constructing a multi-modal network model, outputting a dichotomy result of the target immunotherapy effect, and obtaining a model for predicting or evaluating the target immunotherapy effect of the HCC patient. According to the method, automatic segmentation of the liver and tumor areas is realized through the two-stage 3D-Unet network model, the segmentation result is accurate and smooth, and the problems of errors and time consumption caused by manual sketching are effectively reduced.

The present invention discloses a method for liver tumor segmentation in CT sequence images based on deep learning. The method mainly comprises: (1) constructing a U-shaped 2D convolutional network based on dilated spatial pyramid convolution, and using the network to perform two-dimensional slice segmentation of CT sequence images from three viewing directions: sagittal, coronal, and transverse; (2) using a lightweight 3D convolutional network to fuse the segmentation results obtained from different viewing directions to obtain the probability that each pixel in the CT sequence belongs to the target and the three-dimensional segmentation results of the CT sequence liver tumor; (3) constructing a graph cut energy function based on the obtained probabilities and three-dimensional segmentation results to further optimize the segmentation results. By combining 2D and 3D convolutional networks and a graph cut algorithm, the present invention can effectively extract three-dimensional spatial information from CT sequences while using a lightweight network, thereby improving the accuracy of liver tumor segmentation.

The application discloses a liver tumor radiotherapy dose prediction method based on a diffusion model, and an embodiment thereof is: 1) data collection; 2) preprocessing; 3) constructing a dose prediction model; 4) constructing a loss function; 5) training the prediction model; and 6) dose prediction. The application introduces a beam field, thereby providing the dose prediction model with radiotherapy beam direction information and dose deposition information in a beam propagation process; in order to efficiently utilize input condition information, in a noise prediction network, a multi-branch encoder and a multi-condition aggregation module are designed to realize feature extraction and aggregation of different input condition information, and an asymmetric fusion module is designed to reduce information loss in the input condition information processing process. Compared with a traditional deep learning method, the application can generate more realistic dose prediction results, is helpful to improve the efficiency of radiotherapy plan design, and formulates a personalized treatment plan, and has great practical application value.

The invention relates to the technical field of medical image processing, and discloses a liver tumor segmentation method based on multi-scale feature fusion and mixed attention. The method comprises the following steps: acquiring abdomen contrast enhancement CT (Computed Tomography) volume data containing a liver region, carrying out preprocessing such as resampling, gray scale cutting and normalization on the volume data, and constructing a 2.5 D input image as required; the input image is sent into a liver tumor segmentation network adopting a U-shaped topology, the network comprises an encoder, a multi-layer feature alignment fusion module and a decoder, and a deformable mixed attention module is embedded in the decoding stage to enhance the attention to tiny tumors and complex boundary areas; and generating a liver and intrahepatic tumor segmentation result based on the probability graph output by the network. According to the method, the problem that feature semantics of different levels of an encoder are inconsistent is solved through multi-layer feature alignment fusion, and a mixed attention mechanism of channel attention, channel shuffling and deformable space attention and mixed loss of binary cross entropy, Dice and boundary Dice combination are combined; the segmentation precision of multi-scale, especially small-size tumors and fuzzy boundaries is effectively improved, false positive is reduced, and the method has good clinical application.

The application provides a liver tumor ablation robot system based on image and in-situ fluorescence fusion navigation. The system is applied to the field of medical robots and interventional treatment and comprises an image data analysis module, a tumor activity probability map is constructed and output based on patient functional image data; an intelligent ablation needle, in the ablation process, fluorescence signals of the tissue around the ablation focus are collected in-situ at the needle tip; a multi-degree-of-freedom collaborative mechanical arm, which is used for controlling the intelligent ablation needle to perform puncture and ablation operation; a fluorescence signal processing and real-time classification model, which is used for extracting fluorescence kinetic characteristics from the fluorescence signals and outputting tissue state classification results in real time; a navigation and control console, which is used for fusing the tumor activity probability map and the tissue state classification results to generate an augmented reality navigation interface and controlling the intelligent ablation needle to perform the time sequence of ablation and signal collection. Thus, the problems of difficult identification of active lesions, difficult dynamic tracking and lack of intraoperative feedback in a complex background are solved.

Provided are a targeted near-infrared fluorescent compound, a preparation method therefor, and use thereof, relating to the technical field of near-infrared fluorescent molecules. The targeted near-infrared fluorescent compound has a structure represented by formula I below. By using an organic total synthesis method, a S0456 near-infrared small molecule is modified on a COX-2 inhibitor to obtain the targeted near-infrared fluorescent compound represented by formula I. The targeted near-infrared fluorescent compound has a good active targeting effect when identifying COX-2-overexpressing liver tumors; moreover, the targeted near-infrared fluorescent compound retains the water solubility of a dye and specificity for tumor cells, and has the advantages of good water solubility, high fluorescence quantum yield, and the like.

The application discloses a liver tumor image segmentation method based on a CNN-Transformer hybrid architecture, and comprises the following steps: pre-processing a liver CT image to reduce the influence of image acquisition differences on a model; a multi-stage hybrid encoder effectively combines a convolutional neural network and a Transformer network, extracts local details, takes into account the dependency relationship between elements, and obtains multi-scale features; a feature enhancement decoder performs up-sampling through a convolutional neural network, realizes multi-scale feature fusion through an improved skip connection, and finally outputs a segmentation probability graph with a size of 512*512*3; and a post-processing module converts the segmentation probability graph into a segmentation result that can be directly used for surgery planning. The application constructs a powerful segmentation model that can grasp local details and understand global context, improves calculation efficiency, and reduces the consumption of computing power resources.