16 results about "Bone neoplasm" patented technology

The invention provides a bone tumor fine-grained classification model training and classification method and device, and the method comprises the steps: constructing a multi-modal positive sample containing global / local positive lateral X-ray images, lesion attributes and patient information, and removing a false negative part in combination with text semantic similarity to construct a high-quality negative sample; global / local image features are extracted through double image encoders, lesion attribute keywords are converted into'entity-translation-existence 'triples based on a medical knowledge base, and basic information of a patient and global / local semantic features of lesion attributes are extracted through a text encoder; infoNCE contrast loss is constructed for global images and global semantics based on contrast learning, global image-text feature alignment and local image-text feature alignment are realized in combination with a local mutual information loss and classification loss training model calculated based on a DV variational formula, medical term semantics are deeply combined, the training stability is improved, and the training efficiency is improved. The accuracy and robustness of bone tumor subtype classification are remarkably improved, and reliable support is provided for clinical precise diagnosis.

The invention relates to a bone tumor ablation target region identification and real-time updating method. The method comprises the following steps: processing a multi-modal medical image acquired before an operation, performing information trust empowerment on a bone tumor area according to an image source type, structural definition, bone tissue shielding degree and spatial distribution complexity, and dividing the bone tumor area into a core target area, a semi-trusted marginal area and a dispute area; in the intraoperative ablation process, an ablation temperature change path, power response distribution and navigation position information are continuously monitored, and when it is detected that temperature response is sparse, a needle tip is static and energy motivates discontinuous feature combination in a semi-credible marginal area or a dispute area, target area offset warning logic is triggered; according to the bone tumor target region identification mechanism based on the multi-modal medical image trust empowerment, multi-dimensional information factors such as the image source type, the structure definition, the bone tissue shielding degree and the spatial distribution complexity can be considered at the same time.

The invention discloses a bone tumor image enhancement method and system, and the method comprises the steps: 1, collecting a bone tumor pathological image, carrying out the fuzzy processing of the bone tumor pathological image, taking the bone tumor pathological image after the fuzzy processing as an input data set, and taking an original bone tumor pathological image as an output data set; 2, constructing an image super-resolution enhancement model, and training the image super-resolution enhancement model by using the input data set and the output data set until a loss function value of the image super-resolution enhancement model tends to converge; and step 3, acquiring a bone tumor pathological image needing to be enhanced in real time, inputting the trained image super-resolution enhancement model, and generating a bone tumor pathological image with image super-resolution enhancement, and the method solves the problem of image distortion of a tiny pathological tissue part in the pathological image caused by a conventional image super-resolution enhancement method.

The application discloses a kind of biphasic bioactive tissue repair scaffolds and preparation method, comprising the following steps: step 1: calcium phosphate ceramic powder is modified on surface, and the modified calcium phosphate ceramic powder is obtained;Step 2: the modified calcium phosphate ceramic powder, potassium sodium niobate piezoelectric ceramic powder, dispersing agent, photoinitiator, photosensitive resin are mixed evenly, and the light-cured resin slurry is obtained after ball milling;Step 3: according to the design, 3D printing model is constructed, and the light-cured resin slurry is printed according to 3D printing model, and the scaffold body can be obtained;Step 4: scaffold body is cleaned, and the required scaffold can be obtained after defatting sintering;The application can prepare biphasic bioactive tissue repair scaffold with good mechanical properties, efficient antitumor ability and better bone regeneration capacity, and provide technical support for the repair of bone tumor postoperative bone defect in clinic.

This utility model discloses a bipolar radiofrequency electrode for bone tumor surgery, which includes a cable assembly, a handle, a scalpel, and a scalpel head connected in sequence. The scalpel head includes a suction tube and an outer steel tube that is spaced and sleeved on the suction tube, with a water outlet channel formed between the suction tube and the outer steel tube. The scalpel head includes an insulating head fixed to the distal end of the outer steel tube. The insulating head is provided with a first strip electrode and a second strip electrode arranged side by side. The insulating head located at the first strip electrode and the second strip electrode has several suction holes, which are connected to the suction tube. Several water outlet holes connected to the water outlet channel are provided on both sides of the distal end of the outer steel tube. This solution uses radiofrequency electrodes to irrigate the incision after the resection of benign spinal tumors, which can accurately stop bleeding at soft tissue bleeding points, effectively reducing the amount of bleeding. Furthermore, by utilizing the circulating supply of physiological saline, the first strip electrode and the second strip electrode are effectively wrapped by physiological saline, thereby ensuring the plasma excitation efficiency.

The present invention discloses a bone tumor image enhancement method and system, comprising: step 1: acquiring a bone tumor pathology image, and performing fuzzy processing on the bone tumor pathology image, using the fuzzy processed bone tumor pathology image as an input data set, and using the original bone tumor pathology image as an output data set; step 2: constructing an image super-resolution enhancement model, and training the image super-resolution enhancement model using the input data set and the output data set until the loss function value of the image super-resolution enhancement model tends to converge; step 3: acquiring the bone tumor pathology image to be enhanced in real time, inputting the trained image super-resolution enhancement model, and generating a bone tumor pathology image with completed image super-resolution enhancement. The present invention solves the problem of image distortion of subtle pathological tissue parts in pathology images caused by conventional image super-resolution enhancement methods.

The invention discloses a preparation method for constructing a piezoelectric bone scaffold for bone tumor repair through 3D printing, and belongs to the field of biomedical materials. The method constructs a piezoelectric bone scaffold material for bone tumor treatment and repair through 3D printing, and specifically comprises the following steps: uniformly mixing barium titanate (BTO) and hydroxyapatite (HA) in a fixed volume ratio, printing a green body with a specific pore structure through light-cured resin, and then performing degreasing, sintering, polarization and post-treatment to prepare the BTO / HA piezoelectric composite bone scaffold. The piezoelectric composite bone scaffold prepared by the invention has an accurate shape highly matched with a bone defect part, can catalyze and generate reactive oxygen free radicals through a piezoelectric effect, realizes efficient in-situ inactivation of residual bone tumor cells, integrates two major functions of bone tumor treatment (piezoelectric anti-tumor) and bone defect repair (HA ossification promotion), and has a good application prospect. The treatment and repair effects are improved and the life quality of patients is improved.

The invention relates to a block chain communication method and system for bone tumor data security sharing, and particularly relates to the field of payment protocols and security transactions for business management, and the scheme realizes verification of the accuracy and foresight of node screening by constructing a dynamic evaluation system fusing node behavior prediction and mechanism situational trust, thereby improving the security of bone tumor data. The method greatly reduces verification delay, effectively avoids resource redundancy and waste based on an elastic verification scale mechanism of a trust state and a transaction risk, remarkably improves consensus efficiency, introduces real-time performance monitoring and double-loop feedback adjustment, enables the system to have a continuous self-optimization capability, can dynamically adapt to node behavior change and network fluctuation, and improves the reliability of the system. Therefore, efficient and reliable intelligent collaborative verification is achieved while high security of bone tumor data sharing transaction is guaranteed.

The invention discloses a bone tumor pathological tissue taking-out device with a cutting device, and relates to the field of medical instruments, the bone tumor pathological tissue taking-out device specifically comprises a box body, a protective box cover, a fixing assembly and a blade, and is characterized in that the protective box cover capable of horizontally moving is arranged above the box body, and an electromagnetic sliding rail and an L-shaped supporting plate are fixedly installed in the middle of the upper end of the box body; a sliding plate capable of moving front and back is arranged at the upper end of the electromagnetic sliding rail, a guide rail allowing a guide block to horizontally move is fixedly installed at the upper end of the sliding plate, a fixing assembly is fixed to the upper end of the guide block, and the front end of the guide block is in threaded connection with a fixing bolt used for positioning. The protective box cover is used for protecting sampling medical workers, splashing broken bones are blocked in the protective box cover while the medical workers are protected, the medical workers can pick up the broken bones subsequently, and due to the fact that the box cover adopts the tempered glass plate as the observation opening, a user can check the sampling state of the device without being affected.

This invention provides the application of exosomes derived from Sipunculus fangka in the preparation of anti-bone tumor drugs, relating to the field of biomedical technology. This invention verifies the effects of exosomes derived from Sipunculus fangka in vitro, finding that exosomes derived from Sipunculus fangka can inhibit the cell viability and proliferation of 143B cells, and can significantly inhibit the migration and invasion of 143B cells, exhibiting good anti-bone tumor effects and can be applied to the preparation of anti-bone tumor drugs.

The invention discloses an anatomical femoral prosthesis system which comprises a greater trochanter bone cortex shell with physiological muscle attachment points and an alloy femoral stem prosthesis, and a greater trochanter attachment part is arranged on the alloy femoral stem prosthesis; during use, the greater trochanter bone cortex shell is fixed on the greater trochanter attachment part; the system comprises a major trochanter bone cortical shell construction process which comprises the following steps: (1) a proximal femur resection unit cuts off a proximal femur part which contains bone tumors and is provided with a major trochanter from a femur; (2) the greater trochanter separation unit cuts and separates the greater trochanter from the cut proximal femur which contains the bone tumor and is provided with the greater trochanter; and the cancellous bone removing unit is used for removing cancellous bone tissues in the greater trochanter and retaining a complete greater trochanter bone cortex shell. According to the system, the greater trochanter bone cortex shell with a whole or partial muscle attachment function can be constructed, and then the greater trochanter attachment part on the alloy femoral stem prosthesis is fixed with the greater trochanter bone cortex shell, so that anatomical reconstruction is realized.

The invention discloses a bone tumor specimen sampling device, and relates to the technical field of biopsy sampling, the bone tumor specimen sampling device comprises a base plate, a sampler body and a sampling needle tube, the sampling needle tube is fixedly connected to the bottom of the sampler body, the top of the base plate is bonded with a limiting pad, and the outer side of the base plate is provided with a pressing assembly. The sampler body and the sampling needle tube are stably moved downwards through the lifting block, so that the sampling needle tube is firstly inserted into a hole in the leg of a patient when being stably and downwards inserted, and compared with the mode that a medical worker holds the sampler body by hand and inserts the sampling needle tube into the hole in the leg of the patient, the sampling needle tube is inserted into the hole in the leg of the patient; the medical sampling device can avoid puncture path deviation caused by small shaking of the hand when a medical worker holds the medical sampling device for operation, reduces injury risks of adjacent blood vessels and nerves, in addition, uniform rotation of the threaded rod can stabilize the puncture speed of the sampling needle tube, avoids the problem that the force is too large or too small in manual operation, ensures that the sampling tube can reach the preset depth, and improves the sampling efficiency. And repeated puncture steps are reduced.

The invention relates to the technical field of medical image processing, and discloses a bone tumor CT image segmentation method and system based on image processing. The method comprises the following steps: establishing a bone tumor CT image feature expression structure containing a plurality of image region units, a region connection relationship and attribute description, and updating the structure based on a real-time image data stream containing a CT imaging sequence, pixel intensity distribution and the like; key segmentation boundaries, low-efficiency segmentation regions and difficult segmentation points are identified through an image analysis algorithm, and an initial segmentation strategy group covering region merging, boundary optimization and processing sequence adjustment schemes is generated; receiving a user interaction instruction, judging a correction operation category, and adjusting the initial segmentation strategy group in real time; the adjusted strategy group is implemented, and the feature expression structure is updated according to execution effect feedback. The method can adapt to complex features of the bone tumor CT image, and the segmentation flexibility and pertinence are enhanced.

The invention relates to the technical field of puncture positioning, and discloses a bone tumor surgery puncture positioning device accurate in positioning and guiding, which comprises a torsional resistance adjusting mechanism and a puncture angle positioning mechanism, an annular hollow shell which is fixedly mounted on one side of the central rotating shaft and is filled with a buffer solution, a rotating ball head which is mounted in the center of the annular hollow shell and can rotate, and an annular elastic gas film which has a wrapping type clamping effect on the rotating ball head are arranged in the annular hollow shell. According to the bone tumor surgery puncture positioning device accurate in positioning and guiding, by means of the spherical hinge connection principle, a puncture needle can have the ability of adjusting the puncture angle, meanwhile, the device can adjust the torsion needed when a rotating ball head rotates according to needs, and therefore it is guaranteed that the puncture needle can have the accurate positioning angle, and meanwhile the puncture needle can be accurately positioned and guided. And the torque can be adjusted.

The invention discloses a bone tumor pathological specimen sampling adjustable fixator, and relates to the field of medical auxiliary instruments, the bone tumor pathological specimen sampling adjustable fixator specifically comprises a base, a lifting seat, an inclined seat, a positioning ring and a fixing assembly, and is characterized in that the base is used for fixing the device and an operation table, and stand columns are fixedly mounted on the two sides of the upper end of the base; lifting seats capable of longitudinally lifting are arranged above the stand columns on the two sides, and the opposite faces of the two lifting seats are rotationally connected with the same inclined seat through slewing bearings; the upper ends of the two sides of the inclined base are each fixedly provided with two supporting columns through corner connectors. A pathological specimen is fixed to the middle of the positioning ring through the multiple fixing assemblies, compared with a manual fixing mode, the safety is better, meanwhile, during sampling, the front and back sampling angles of cutting-in can be adjusted through rotation of the inclined base, the positioning ring is designed to be rotatable, and the sampling efficiency is improved. And the pathological specimen can be rotated and adjusted clockwise or anticlockwise as required.

The application provides a tumor image region extraction method and system based on a neighborhood pixel feature classifier, comprising: collecting a medical sample polarization image of a tumor to be identified; pre-processing the medical sample polarization image to obtain a pre-processed polarization image; calculating a Mueller matrix and derived polarization feature parameters of each pixel in the pre-processed polarization image; determining a neighborhood pixel feature classifier, screening non-boundary pixels in combination with the Mueller matrix and the derived polarization feature parameters, and performing interpolation processing on the non-boundary pixels to form a multi-dimensional feature matrix; using a multi-layer perception to perform neural network identification on the multi-dimensional feature matrix, adopting four-fold cross-validation of a probability result of the neighborhood pixel feature classifier, and determining a tumor identification result to be identified based on the probability result. The application solves the problem of insensitivity of a multi-layer perception to a tumor incisal edge by using a two-dimensional feature relationship of each pixel and surrounding pixels, and realizes automatic identification of a bone tumor region and a tumor incisal edge of a fresh sample polarization image.