33 results about "Hepatic tumours" patented technology

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 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.

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 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 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 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.

The application discloses a liver tumor segmentation method fusing three kinds of attentions, which effectively fuses spatial attention, self-attention and edge fusion attention, and realizes accurate liver tumor segmentation. The method comprises the following steps: S1, preprocessing abdominal CT data, and dividing the data into a training set, a verification set and a test set in proportion; S2, combining double attention with convolution operation to construct double attention dynamic convolution; S3, fusing edge information and attention mechanism to construct an edge fusion attention module; S4, fusing edge supervision loss and segmentation loss to construct a multi-scale edge segmentation loss; S5, fusing double attention dynamic convolution, the edge fusion attention module and the multi-scale edge segmentation loss to construct a Triple Attention Fusion Network (TAF-Net) model; and S6, using an experimental data set to complete training, verification optimization and performance evaluation of the model. The application can adaptively adjust a convolution kernel and effectively capture edge features, effectively improves segmentation precision, and is suitable for automatic segmentation of liver tumors in CT images.

The invention provides a deep learning-based recurrence level prediction system after liver tumor ablation, and mainly solves the problems that after a doctor performs liver tumor ablation on a patient, whether recurrence occurs or not is difficult to predict, and the recurrence level evaluation is inaccurate. Firstly, the system performs feature extraction and analysis by using a 3D convolutional neural network by inputting a medical image after liver ablation and a given ablation range so as to judge whether a tumor relapses or not. If the prediction result is no relapse, ending the process; and if the prediction result is recurrence, further analyzing by using another 3D convolutional neural network model specially aiming at the recurrence level so as to determine the specific recurrence level (such as level 1, level 2 or level 3). According to the method based on deep learning, the accuracy of predicting the recurrence condition after liver tumor ablation can be improved, refined recurrence grading can be achieved, and scientific and reliable decision support is provided for clinicians.

The invention relates to the technical field of medical image processing, in particular to a liver tumor MRI (Magnetic Resonance Imaging) image segmentation method based on deep learning, which is characterized by comprising the following steps: S1, acquiring a liver tumor MRI image data set; s2, the liver tumor MRI image data set is preprocessed; s3, constructing a ZCP-UNet network comprising a plurality of functional modules on the basis of the UNet; and S4, inputting the preprocessed liver tumor MRI image data set into the ZCP-UNet network for training and reasoning so as to improve the segmentation precision of the liver tumor image by the ZCP-UNet network. The method has the advantages of high calculation efficiency, high segmentation precision and good robustness.

This invention discloses a handheld ultrasound video probe tracking method based on the MOUNT model, mainly addressing the poor probe tracking performance in existing technologies due to the lack of consideration for the thin probe shape, uneven motion between adjacent frames, and low probe visibility. The implementation scheme is as follows: acquiring an ultrasound video dataset of the liver tumor ablation process; constructing a handheld ultrasound video probe tracking network MOUNT; iteratively training the handheld ultrasound video probe tracking network MOUNT; testing the trained MOUNT network on a test set to obtain a set of predicted candidate results; performing post-processing operations to filter and optimize the predicted candidate results set to obtain the probe entry point and tip coordinates, thus completing probe tracking. This invention focuses on the unique characteristics of the handheld ultrasound video probe tracking task, effectively improving the accuracy of handheld ultrasound video probe tracking, and can be used for real-time probe tracking in liver tumor ablation surgery.

The invention discloses a construction method of a hepatocyte line with high albumin yield, a plasmid and a hepatocyte line. According to the invention, a human serum albumin gene and a YAP gene are inserted into a genome of HepG2 human liver tumor cells so as to obtain a liver cell line with high albumin yield; the nucleotide sequence of the human serum albumin gene is as shown in SEQ ID No: 1, and the nucleotide sequence of the YAP gene is as shown in SEQ ID No: 2. According to the HepcellPro-H cell line constructed by the invention, under a specific culture condition, the concentration of albumin in a cell culture supernatant detected by ELISA (Enzyme-Linked Immunosorbent Assay) is obviously increased compared with that of an unmodified wild type HepG2 cell, the production efficiency is obviously improved, the large-scale extraction period of albumin is shortened, and the potential tumorigenic risk of a viral vector is avoided.

The present application belongs to the technical field of medical image processing, and provides a double-needle conformal ablation planning method for liver cancer microwave ablation, which comprises the following steps: S1, performing ex vivo pig liver microwave ablation experiment and measuring the axial length of the ablation injury area; using a distance field with weights, obtaining a simulation model of the ablation injury area in the double-needle simultaneous ablation mode with different intervals; S2, scaling the target ablation area along the needle insertion direction; S3, clustering the scaled target ablation area into a plurality of unit blocks, and obtaining the closest paired double-unit blocks; S4, covering the unit blocks with the simulation model to obtain the needle arrangement planning scheme before ablation. The method can solve the problem of rapid conformal ablation needle arrangement of liver tumors in the double-needle ablation mode, and quickly calculate an ablation preoperative planning scheme for conformally covering the target ablation area, thereby providing an optimized preoperative planning reference scheme for liver tumor ablation.

The invention provides a liver tumor classification method based on ultrasonic multi-modal information, belongs to the field of liver tumor classification and recognition, and uses a convolutional neural network CNN and a long short-term memory network LSTM to construct a multi-modal shared diagnosis model for deep learning and recognition of liver tumors. The modal scores of all training samples of the multi-modal shared diagnosis model are calculated through a Grad-CAM method based on gradient. And parameter gradient adjustment is carried out by using an RMSprop optimization algorithm, so that the gradient change speed can be adaptively adjusted in the training process. Through a heuristic search method, the weight of each mode is calculated and dynamically adjusted, and different disease modes can be differentially treated during prediction. When actual medical data are tested, the method has good performance in liver tumor recognition, has high accuracy and is expected to be applied to actual medical diagnosis.

The application belongs to the field of traditional Chinese medicines, and particularly discloses application of a leech dredging collaterals preparation in preparation of an anti-tumor medicine. The leech dredging collaterals preparation is prepared from four raw medicinal materials of astragalus, ligusticum wallichii, leech and salvia miltiorrhiza, and has the effects of tonifying qi and activating blood and dredging qi and collaterals. Pharmacodynamic studies show that the leech dredging collaterals preparation has the effects of inhibiting growth of liver tumors and lung tumors, is safe and has a good effect, expands the clinical application range of the leech dredging collaterals preparation, and has a good popularization and application prospect.

The application discloses a kind of liver tumor automatic identification and measurement method based on CT image, belong to medical image processing technical field, including the following steps: first, after the image pre-processing of patient abdominal CT image, input into liver component decomposition network, obtain the liver component image I1-I4 after decomposition, then liver component image I1-I4 is input into liver tumor segmentation network, and the segmentation result of tumor is output;Finally, the segmentation result is input into tumor measurement and analysis module to analyze tumor, and the detailed information of tumor is calculated.Through the above mode, the application solves the problems of poor applicability and robustness of traditional methods, difficulty in guaranteeing the accuracy of results, lack of model interpretability and other problems.The application has strong applicability and robustness, high accuracy, and the model has interpretability.

The invention discloses a construction method of a liver cell line with high blood coagulation factor yield, a plasmid and a cell line. According to the invention, the F10 gene and the YAP gene are inserted into the genome of HepG2 human liver tumor cells to obtain the liver cell line with high blood coagulation factor yield; the nucleotide sequence of the F10 gene is as shown in SEQ ID No: 1, and the nucleotide sequence of the YAP gene is as shown in SEQ ID No: 2. According to the HepcellPro-F cell line constructed by the invention, under specific culture conditions, the concentration of the blood coagulation factors in cell culture supernatant detected by ELISA is obviously increased compared with that of unmodified wild type HepG2 cells, so that the production efficiency is obviously improved, the large-scale extraction period of the blood coagulation factors is shortened, and the potential tumorigenic risk of a viral vector is avoided.