30 results about "Tumor margin" patented technology

The invention relates to the technical field of image recognition, in particular to a urinary system CT image tumor benign and malignant identification method based on deep learning, which comprises the following steps: acquiring a urinary system CT image, constructing a map band sequence and extracting gray level distribution, identifying a heterogeneous edge and a texture mutation region, aggregating perturbation map blocks to form an abnormal structure, and identifying the benign and malignant tumors. And fusing multiple types of image layers to complete label integration, and generating a feature recognition image layer. According to the method, the extension recognition capability of the tumor edge external expansion region is enhanced by combining a graph band gray scale aggregation and sequence construction mode, the judgment precision of local heterogeneous change is improved by fusing gray scale kurtosis and migration analysis, and the texture disturbance trend is extracted based on direction vector included angle change. The block gray level fluctuation and gradient relationship supports abnormal structure aggregation identification, spatial coincidence and boundary difference combined screening realizes multi-feature region unified coverage, abnormal region expression definition and structure positioning accuracy are enhanced, and image layer consistency and identification stability are improved.

Apparatuses and methods for using augmented / mixed reality in surgical settings are provided, and, in particular, apparatuses and methods for intraoperative integration of augmented / mixed reality 3D models with near real-time pathology results. Real-time pathology results are generated using a machine learning analysis of biopsy pathology images in conjunction with a predictive model based on the patient's clinical and demographic data and radiographic imaging data. The apparatuses and methods can be used to provide more accurate intraoperative visualization, tracking, and determination of tumor margins to improve resection extent and any intraoperative or postoperative adjuvant therapy.

The application discloses a brain tumor infiltration degree prediction method, device, storage medium and equipment, and belongs to the technical field of medical image processing. The application innovatively takes tumor segmentation probability and fiber density features of a tumor edge region as infiltration analysis features, constructs a brain tumor infiltration degree prediction model, device, storage medium and equipment, and is used for predicting the infiltration degree of a brain tumor. Experiments show that the brain tumor infiltration degree predicted by the model has a relationship (P<0.05) with survival, and the survival time of the high-infiltration degree is obviously lower than that of the low-infiltration degree, which has important clinical significance.

The invention discloses a cross-modal lightweight colorectal tumor segmentation method and device, and aims to solve the problems that an existing medical image segmentation model depends on large-scale annotation data, small lesions and fuzzy boundaries are inaccurately recognized, the calculation complexity is high, clinical deployment is difficult, and the like. According to the method, on the basis of an improved U-shaped network architecture, adaptive histogram equalization and Gamma correction are introduced in a data preprocessing stage to enhance boundary information of a low-contrast CT image; the encoder captures a multi-level context by adopting a multi-scale convolution and cavity convolution fusion module, and strengthens tumor edge response in combination with a boundary attention module; and meanwhile, the calculation amount is reduced by introducing rapid spatial pyramid pooling. The decoder effectively recovers details and avoids artifacts through lightweight jump connection and bilinear interpolation up-sampling. The parameter quantity of the whole model is only about 4.25 M, the reasoning efficiency and the cross-equipment generalization ability are remarkably improved while the high segmentation precision is guaranteed, and the method is suitable for a resource-limited clinical environment.

Medical software tools platforms utilize a surgical display to provide access to specific medical software tools, such as medically-oriented applications or widgets, that can assist surgeons or surgical team in performing various procedures. In particular, an endoscopic camera may register the momentary rise in the optical signature reflected from a tissue surface and in turn transmit it to a medical image processing system which can also receive patient heart rate data and display relevant anomalies. Changes in various spectral components and the speed at which they change in relation to a source of stimulus (heartbeat, breathing, light source modulation, etc.) may indicate the arrival of blood, contrast agents or oxygen absorption. Combinations of these may indicate various states of differing disease or margins of tumors, and so forth. Also, changes in temperatures, physical dimensions, pressures, photoacoustic pressures and the rate of change may indicate tissue anomalies in comparison to historic values.

The invention provides a method for determining a tumor boundary based on a mechanical atlas, which comprises the following steps: characterizing the Young modulus of an in-vitro tumor tissue formed by rigid tumor cells, processing the data obtained by characterization, constructing the mechanical atlas, and determining the specific position of the tumor boundary by analyzing the Young modulus distribution curve of the tumor tissue. And finally, calculating the stiffness gradient by using the Young modulus data of each point, calculating the maximum stiffness gradient direction of the tumor edge perpendicular to the maximum stiffness gradient, calculating the maximum stiffness gradient of the tumor tissue edge area, assisting to obtain a predicted tumor boundary line, and further confirming the boundary of the glioblastoma. According to the method, the mechanical property distribution of in-vitro tumor tissues is represented through a micro-nano mechanical representation technology, the tumor boundary is determined by constructing a mechanical map, and the safe resection range can be determined to the maximum extent while a normal functional area is protected.

The invention relates to a multi-modal ultrasonic image-based knowledge graph construction method and device, and a storage medium, and the method comprises the steps: obtaining a tumor gray-scale ultrasonic image, obtaining a tumor edge image and a tumor internal image through target segmentation, respectively extracting corresponding multi-modal candidate image omics features, and carrying out the target segmentation; forming a sample set comprising a plurality of samples in combination with a tumor type corresponding to the tumor gray-scale ultrasonic image; performing synthetic minority oversampling processing on a sample set, performing Z scoring processing on each candidate radiomics feature in each sample, screening radiomics features with strong correlation through principal component analysis, and performing recursive feature elimination to obtain finally reserved radiomics features corresponding to each tumor type; and establishing a knowledge graph and / or a machine learning model based on the finally reserved radiomics features corresponding to each tumor type. The method has the advantages that the association between the tumor type and the selected iconography features is fully established, and the abundant information of the tumor edge is fully considered.

Devices, systems, and methods to generate a plan for an interstitial laser ablation procedure are disclosed. The systems may be configured as an interstitial optical mapping system including a catheter, an emitter optical fiber, an imaging optical fiber, a light source, and a processing unit. The emitter optical fiber and the imaging optical fiber are used to interstitially image a fluorescent dye associated with a tumor, including the tumor margin, at discrete imaging positions along a length of the catheter. The processor calculates a location of the fluorescent dye at each discrete position and creates an optical map representing the tumor. The optical map is used to generate an interstitial laser ablation plan that includes laser fiber pull-back positions.

A system for automated tumor margin determination in radiological images, comprising: an image acquisition interface configured to receive radiological image data from one or more imaging modalities; a preprocessing unit operationally coupled to the image acquisition interface and configured to perform intensity normalization, spatial resampling, and noise reduction on the received image data to generate standardized image inputs; a feature extraction unit comprising a plurality of convolutional layers arranged in a hierarchical structure and configured to extract spatial features of different orders of magnitude from the standardized image inputs;a transformer coding unit operationally coupled to the feature extraction unit and configured to generate context-sensitive feature representations by applying self-attention operations over spatial areas of the extracted features; a fusion unit operationally coupled to both the feature extraction unit and the transformer coding unit and configured to combine features derived from convolutions and context representations derived from transformers into a unified feature map; a decoding unit operationally coupled to the fusion unit and configured to generate a segmentation map corresponding to the tumor regions by incrementally increasing and reconstructing the spatial resolution; a boundary refinement unit configured to improve the delineation of tumor margins in the segmentation map;a processing unit that is operationally coupled with the preprocessing unit, the feature extraction unit, the transformer coding unit, the fusion unit, the decoding unit, and the boundary refinement unit, wherein the processing unit executes instructions stored in a memory unit to perform automated tumor boundary delineation; and a display interface configured to overlay the delineated tumor boundaries onto the radiological image data.

The invention provides a precursor compound capable of targeting FAP. The structure of the precursor compound is shown as a formula (I) or a formula (II). Based on the precursor compound, the invention further provides a bimodal FAP targeting probe which is a complex formed by the precursor compound as shown in the formula (I) or the formula (II) as a ligand and radionuclide. The radionuclide is a radionuclide capable of forming stable complexation with a DOTA group, preferably 68Ga. The invention also provides an application of the bimodal FAP targeting probe in preparation of a living body imaging agent. The bimodal FAP targeting probe disclosed by the invention can accurately describe the tumor edge, and has the potential of guiding intra-operative decision in future clinical application.

This application provides a method and system for image recognition and diagnosis of brain tumors in neurosurgery. First, the brain tumor image is preprocessed. The preprocessed brain tumor image is then decomposed into at least two feature component maps that complement each other in terms of structural and texture information. Next, each feature component map is sequentially subjected to a first-stage adaptive nonlocal mean filtering based on local statistical characteristics and a second-stage filtering based on structural correlation similarity measurement. The filtered feature component maps are then fused and reconstructed to obtain a feature-enhanced brain tumor image. This feature-enhanced brain tumor image is input into a pre-trained brain tumor recognition model, and the neurosurgical diagnosis results are obtained through the model. Using the scheme of this application, a two-stage adaptive filtering based on local scattering statistics and structural correlation measurement can be achieved, thereby enhancing tumor edge and texture features while suppressing ultrasound speckle, thus improving the accuracy of segmentation and diagnosis.

A method for automating margin measurement for mass removal that utilizes one or more machine learning models is disclosed. The one or more machine learning models may assist in identifying and segmenting each biopsy in an image, classifying the biopsy as a clear biopsy or an ambiguous biopsy, rotating the image of the biopsy to a proper orientation, and identifying and segmenting the skin and tumor found in the image of the biopsy. The method may then determine a lateral and deep margin value and display the values on the image.

The invention provides a double-net-bag cooperative percutaneous puncture integral tumor excision system. The double-net-bag cooperative percutaneous puncture integral tumor excision system comprises net bags, the puncture coaxial guide system is used for establishing a percutaneous working channel from the body surface to the tumor edge; a fixing anchor is arranged at the far end of the inner core fixing rod and is used for fixing tumor tissues; the double-net-bag cutting system comprises an outer net bag and an inner net bag; the outer net bag is made of a high-rigidity material and is used for firstly expanding to create a protected operation space in tissues around the tumor. The whole core cutting component is double-net-bag cooperative cutting, no circuit or sensor or hydraulic system is adopted, the production cost is extremely low, large-scale manufacturing is easy, operation is visual, the whole operation process only comprises several simple actions of pushing, rotating and pulling, the learning cost of doctors is low, the surgical operation intuition is well met, and popularization is easy.

A method for characterizing a tissue sample is disclosed, which includes placing at least one nanostructured sensor in contact with said tissue sample, wherein said nanostructured sensor includes at least one response characteristic exhibiting dependence on a refractive index of said tissue sample when said nanostructured sensor is in contact with said tissue sample; directing interrogating optical radiation at a plurality of frequencies to said nanostructured sensor; detecting, for each of said optical radiation frequencies, radiation redirected by or transmitted through said nanostructured sensor in response to said interrogating optical radiation; analyzing said detected redirected or transmitted radiation to determine said at least one response characteristic of said nanostructured sensor at each of said plurality of interrogating optical radiation frequencies; and determining at least one attribute of said tissue sample based on said determined at least one response characteristic at said interrogating optical radiation frequencies.

The application discloses a cross-modal lightweight colorectal tumor segmentation method and device, aiming at solving the problems of existing medical image segmentation models, such as dependence on large-scale labeled data, inaccurate identification of small lesions and fuzzy boundaries, and high computational complexity difficult to be clinically deployed. The method is based on an improved U-shaped network architecture, and adaptive histogram equalization and Gamma correction are introduced in the data preprocessing stage to enhance the boundary information of low-contrast CT images. The encoder adopts a multi-scale convolution and a hollow convolution fusion module to capture multi-level context, and combines a boundary attention module to strengthen the tumor edge response. At the same time, a fast spatial pyramid pooling is introduced to reduce the computational amount. The decoder recovers details and avoids artifacts through lightweight skip connection and bilinear interpolation up-sampling. The overall model parameter amount is only about 4.25M, which can ensure high segmentation accuracy, significantly improve inference efficiency and cross-device generalization ability, and is suitable for resource-constrained clinical environment.

This invention provides a hepatocellular carcinoma (HCC) image classification method based on interference quantification and pathological priors, belonging to the field of medical technology. The method includes: acquiring HCC tumor images and dividing them into multi-region segmentation data, including a tumor core region, a tumor edge transition region, and a distal cirrhotic background region; calculating an interference index based on the gray-level and texture-related features of the HCC tumor images; performing adaptive feature selection and graded specific correction using a pre-constructed graded correction parameter library to obtain a corrected anti-interference tumor feature set; constructing a regularized loss function containing pathological constraints based on predefined cirrhosis and case association rules; training a model based on the anti-interference tumor feature set; and outputting the HCC image classification result. This invention solves the problem of difficult HCC image classification due to the blurred background boundaries and mixed features of tumors in HCC tumor images caused by varying degrees of cirrhosis in patients, as well as the scarcity of HCC tumor subtype samples.

A multi-axis tumor excision marker system is configured to deposit markers along multiple axes radially about a tumor to define a boundary of margin tissue for excision. A catheter may deploy a marker extension that extends to a margin tissue boundary for depositing the marker. The marker extension may be a shape memory material that extends radially outward from catheter opening or may be directed radially outward by a guide head. The radiopaque marker may be a phase change marker, such as an adhesive that changes from a liquid to a solid. A marker may be a discrete marker and may have an extension portion that extends from an anchor portion. An envelopment marker has a plurality of marker extensions that each extend along an offset axis from each other. A spiral maker includes a maker extension that spirals around the margin boundary tissue.

Deep-ultraviolet scanning microscopy uses a first imaging apparatus arranged on a first side of a sample and a second imaging apparatus arranged on a second side of the sample. The first imaging apparatus includes a first ultraviolet light source to illuminate the first side of the sample and a first camera to receive light emitted from the first side of the sample. The second imaging apparatus includes a second ultraviolet light source to illuminate the second side of the sample and a second camera to receive light emitted from the second side of the sample. The first and second sides can be imaged in parallel, and can be sparsely sampled to increase imaging speed. A machine learning model can be used to generate images from the acquired signals. Signals can be detected from intrinsic sources (e.g., tryptophan) and extrinsic sources (e.g., propidium iodide and / or eosin Y) at the same time.

A method for automating margin measurement for mass removal that utilizes one or more machine learning models is disclosed. The one or more machine learning models may assist in identifying and segmenting each biopsy in an image, classifying the biopsy as a clear biopsy or an ambiguous biopsy, rotating the image of the biopsy to a proper orientation, and identifying and segmenting the skin and tumor found in the image of the biopsy. The method may then determine a lateral and deep margin value and display the values on the image.

The present application relates to the technical field of image processing, in particular to a tumor margin intelligent recognition method based on HCR amplified fluorescence image, which aims at the problem that signal diffusion caused by defocus and margin recognition difficulty in HCR amplified fluorescence image, through evaluating the defocus degree of the image, calculating the fitting degree of the signal spot diffusion radius and the theoretically estimated radius, and combining the neighborhood difference analysis to generate the signal density distribution map, and finally recognizing different types of margins based on the signal density size. The present application can distinguish low-quality signals caused by defocus from real tumor signals, significantly improving the accuracy and reliability of tumor margin recognition.

The invention discloses a liver / mitochondria dual-targeting carboxylesterase fluorescent probe as well as a preparation method and application thereof, and belongs to the technical field of medicines. The probe is a compound LDM-CA, has the liver and mitochondria dual-targeting characteristic, and shows high selectivity, sensitivity and strong binding affinity to CEs. In-vitro cell experiments show that the LDM-CA has excellent mitochondrial targeting ability in the HCC cells and specific fluorescence opening response to CEs in the cells, and can clearly distinguish the HCC cells from normal liver cells or non-liver cancer cells. In-vivo imaging of a mouse model shows that no matter in-tumor injection or intravenous injection, the LDM-CA can effectively visualize the HCC tumor and draw the edge of the tumor, has the prospect of serving as a powerful molecular tool for early HCC diagnosis and image-guided surgery, and also provides a valuable means for studying the action of mitochondrial CEs activity in HCC pathogenesis at the subcellular level.

The application relates to the field of intelligent medical treatment, in particular to a method, equipment and program product for predicting perineural invasion of infiltrative breast cancer. The method comprises the following steps: acquiring chest image data sets and labels of a breast cancer perineural invasion patient; inputting the chest image data sets and the labels into a classification model to be trained, the classification model comprising an encoding module, a parallel classification module, a region segmentation module and an edge segmentation module; inputting the chest image data sets and the labels into the encoding module to generate image features through feature encoding; inputting the image features into the classification module to generate an invasion classification result; inputting the image features into the region segmentation module to generate a tumor region mask; inputting the image features into the edge segmentation module to generate a tumor edge mask; repeatedly encoding, segmenting and classifying until a loss function is unchanged or a preset iteration number is reached; obtaining a classification model; and classifying perineural invasion of the infiltrative breast cancer through the classification model. The application has good clinical value.

The invention provides a CT image tumor accurate segmentation method and system, and relates to the technical field of image processing, and the method comprises the steps: determining an undetermined region where a tumor is located in a CT image through an image segmentation model; determining a boundary line, a central position, a neighbor reference pixel point and determination probability information of the to-be-determined area; correcting pixel points are selected from the adjacent reference pixel points, and a correcting area is obtained, so that the training image segmentation model is updated. According to the invention, after the to-be-determined region where the tumor in the CT image of each fault is located is obtained through the image segmentation model, the boundary line of the to-be-determined region can be mutually verified based on the adjacent pixel points on the boundary line and the pixel points of the adjacent fault; therefore, the pixel points which can better represent the tumor edge are screened out from the adjacent pixel points of the boundary line, and the area where the tumor is located is segmented more accurately.

The application relates to the technical field of image processors, and discloses a tumor incisal edge design method based on a skin local image. The method comprises the following steps: establishing a global space coordinate system associated with the skin of a patient; collecting a local image and a six-degree-of-freedom pose by using a handheld device integrated with a pose tracking function; projecting and fusing the image to a digital surface model in real time to generate a panoramic image; segmenting a tumor boundary by using a deep learning model, and generating a safe incisal edge path by outward expansion based on a geometric algorithm; and finally projecting the incisal edge to the skin surface in the form of structured light by using a built-in projection unit of the device. The application realizes high-precision and low-delay dynamic planning and visualized guidance of the tumor incisal edge, and improves the precision and efficiency of the operation.

A robotic surgical system is disclosed for AI-guided neoplasm resection using multimodal imaging and machine learning. The system comprises a robotic manipulator with sub-millimeter precision and intraoperative imaging modules, including hyperspectral imaging. A data acquisition module integrates preoperative imaging (CT, MRI, PET, ultrasound, X-ray) with real-time surgical data via an image fusion engine to form a co-registered anatomical model. An AI engine analyzes spectral and anatomical data to differentiate tissue types and updates a dynamic resection path. A control unit autonomously adjusts the robotic trajectory in real-time. A visualization interface overlays tumor margins and surgical guidance for enhanced precision. The system further includes surgeon feedback integration, fatigue monitoring, and adaptive learning through historical and live procedure data, supporting autonomous and semi-autonomous operation across diverse surgical applications.

The embodiment of the invention provides a tumor radiotherapy auxiliary imaging image enhancement method and system, and relates to the technical field of medical image processing, and the method comprises the steps: receiving to-be-processed medical image data; the local area of the medical image data is calculated and extracted to obtain a feature mark, and the feature mark comprises a gray level change trend, a texture pattern and frequency distribution; the feature mark is compared with a preset reference mode set, the category of the local area is determined, and the category of the local area comprises physiological motion artifacts, metal artifacts or tumor edges; according to the type of the local area, corresponding image processing operation is executed on the local area, processed medical image data are output, and the image processing operation comprises deformation correction, image reconstruction, equalization processing, moderate smoothing and moderate enhancement. According to the invention, the image quality of tumor radiotherapy auxiliary imaging and the identification degree of tumor boundaries can be improved.

The invention relates to an auxiliary device for taking out a skin endothelial cell tumor puncture specimen, and belongs to the technical field of medical equipment. The subcutaneous tumor fixing device comprises a positioning adjusting assembly arranged at the front end of the positioning adjusting assembly and used for fixing a subcutaneous tumor; the negative pressure assembly is arranged at the front end of the positioning adjusting assembly and used for assisting the positioning adjusting assembly to be fixed to the skin surface; the puncturing and sampling assembly is located at the rear end of the positioning and adjusting assembly and used for puncturing and sampling the subcutaneous tumor sample; the position adjusting assembly is located on the base and used for adjusting the distance between the puncture sampling assembly and the to-be-punctured part. The device clamps the tumor edge through cooperation of the adjusting ring and the fixing rod, the adsorption force generated by the negative pressure assembly enables the skin surface to keep fixed contact with the device, the position adjusting assembly drives the puncture sampling assembly to move to the target depth along the preset path, the problem of sampling deviation caused by unstable tumor fixation is effectively solved, the operation process is simplified, and the sampling efficiency is improved. And the puncture depth and the angle can be adjusted more accurately.

The invention discloses a malignant tumor operation boundary in-vivo non-invasive detection method, system and equipment, and belongs to the field of biomedical engineering.The method is based on a portable optical fiber Raman spectrum technology, representative spectrums are screened through Gaussian kernel density estimation, a pure reference member library combined with perturbation spectrums is constructed, and the reference member library is used for detecting the malignant tumor operation boundary in-vivo non-invasive detection. And analyzing the tumor edge mixed spectrum based on a nonlinear relaxation model, proposing a nonlinear weight matrix, dynamically adjusting the influence of a reference member cross term on spectrum reconstruction, allowing a pure spectrum matrix to change within a certain limit in an iteration process, and determining the tumor edge mixed spectrum by quantifying the spectrum contribution proportion of normal tissues and malignant tumor tissues. And the tissue property is judged according to a preset threshold value, so that the tumor boundary can be accurately judged in the operation. The method does not need tissue slicing or fluorescence labeling, has the advantages of being real-time, non-invasive, high in accuracy and the like, can effectively assist doctors in formulating personalized excision schemes, and reduces the postoperative recurrence risk.

This invention discloses a plasma electrode, an impedance measurement signal injection method, and a tumor edge recognition method, relating to the fields of electrosurgical instruments and biological tissue detection technology. To address the problems of traditional plasma surgery's inability to acquire tissue electrical properties in real-time and in situ, and its difficulty in accurately identifying tumor edges, this invention integrates two pairs of miniature measurement electrodes into the active electrode, with a ceramic-insulated microchannel on the back side; it uses multi-frequency signals superimposed at logarithmic frequency points of 1kHz to 5MHz, and injects them in parallel within 10ms after phase optimization using a genetic algorithm; it extracts the Cole relaxation frequency based on distributed relaxation time, and achieves rapid tumor edge recognition through offline pre-calculation and online processing. This invention achieves deep integration of ablation and sensing, enabling early determination of tissue type and improving the accuracy and safety of tumor resection.

The invention relates to the technical field of image processing, in particular to an intelligent tumor incision edge recognition method based on an HCR amplified fluorescence image, and aims to solve the problems of signal dispersion and difficulty in incision edge recognition caused by defocus in the HCR amplified fluorescence image by evaluating the defocus degree of the image and calculating the coincidence degree of the light spot diffusion radius of a signal point and a theoretical estimated radius. And combining neighborhood difference analysis to generate a signal density distribution diagram, and finally identifying different types of cutting edges based on the signal density. According to the method, the accuracy and the reliability of tumor incision edge identification can be remarkably improved by distinguishing low-quality signals generated due to defocusing from real tumor signals.