23 results about "Marrow cell" patented technology

The invention belongs to the technical field of medical image processing, and provides a bone marrow cell WSI region-of-interest automatic analysis positioning method and system, and the method comprises the steps: obtaining a full glass slide bone marrow aspiration smear image (WSI); a pyramid network is adopted to zoom the full-glass-slide bone marrow aspiration smear image, and a low-resolution image is generated; designing a general area condition prompt strategy by combining bone marrow cytology medical priori knowledge, and calling a language model to construct text description of a bone marrow microparticle area for the low-resolution image; using a visual language model to align the text and the low-resolution image, and then adopting a feature visualization technology and based on gradient weighted channel selection to generate a semantic response graph; the dispersion degree of a semantic response region in the semantic response graph is calculated, and segmentation prompt information is generated by adopting a region perception and strategy self-adaption mechanism; and inputting segmentation prompt information and the low-resolution image into an SAM model, generating an ROI mask image through reasoning, and completing positioning of the bone marrow cell WSI region of interest.

Provided herein are compositions that include bone grinding and a tissue sample derived from intervertebral disc. The compositions may include or be used as therapeutics. For example, the compositions may be implanted into a subject's body, such as in a body part, organ, or tissue to cause a therapeutic effect in the subject. In some embodiments, the compositions may be used for cell therapy. In some embodiments, the compositions may be used to treat cancer. In some embodiments, cells, such as stem cells and / or bone marrow cells in the compositions of the present disclosure may be used to treat diseases such as cancer.

The invention belongs to the technical field of cell sampling, and particularly relates to a skull bone marrow cell sampling device which comprises a base, a sampling vessel is in contact with the middle of the upper end of the base, a supporting frame is fixedly connected to the upper end of the base, a supporting block is fixedly connected to the inner side wall of the supporting frame, and a clamping groove is formed in the surface of the supporting block. And the inner wall of the supporting block is connected with a screw rod through threads, and the upper end of the screw rod is fixedly connected with an extrusion disc. According to the scheme, through the arrangement of the rotating handle, the screw rod, the extrusion disc and other structures, the skull can be fixed for use, under the telescopic action of the hydraulic cylinder, the positions of the electric drill and the flushing needle can be vertically adjusted, then the skull is drilled and flushed for subsequent sampling use, and through the arrangement of the positioning holes, the positioning balls and other structures, the skull can be conveniently and rapidly used. The positions of the electric drill and the flushing needle can be transversely adjusted, and the drilling position can be adjusted for use, so that the flushing and sampling effects are improved.

In the field of gene therapy, a major hurdle is the design and identification of constructs and gene therapy vectors providing therapeutic effects while displaying satisfactory safety profiles. In the treatment of Diamond-Blackfan Anemia (DBA), therapies alleviating several crucial anemia symptoms, such as blood or bone marrow cellularity, hemoglobin levels, erythrocytes levels, or platelet levels, while showing satisfactory safety profiles remain a challenge. The present invention provides constructs encoding ribosomal protein genes involved in DBA, such as genes encoding RPS19, RPS17, RPS24, RPS10, RPL35a, RPL11, RPS26, and RPL5, vectors, methods, cells, and medical uses thereof, addressing these challenges and finding particular applications in the field of autologous cell therapy treatment of DBA. Further, the present invention provides a non-genotoxic conditioning protocol for preparing a subject prior to cell therapy treatment for DBA using construct of the present invention.

The invention specifically discloses a bone marrow blood cell target identification and counting method based on an improved single stage, and relates to the technical field of medical image processing. The method comprises the following steps: S1, image acquisition and data preparation; s2, constructing and preprocessing a data set, and dividing the preprocessed data set into a training set, a verification set and a test set; s3, constructing an initial model of an improved single-stage target recognition model; s4, training the initial model by using a training set and a verification set to obtain a bone marrow blood cell target recognition and counting model; and S5, identifying and positioning the bone marrow blood cells in the test set image by adopting a bone marrow blood cell target identification and counting model, outputting cell categories and target frame coordinates, and realizing counting according to the number of target frames. According to the method, the detection problem caused by large bone marrow cell scale change is solved, the classification precision is improved, and unification of high precision and high speed of bone marrow blood cell target identification and counting is realized.

The utility model relates to the field of bone marrow smear equipment, in particular to a rapid bone marrow cell smear device. The problems that an existing bone marrow smear is large in operation difficulty, and smear uniformity cannot be guaranteed are solved. Comprising a clamping cylinder, a spring and a pushing piece, the pushing piece is movably installed in the clamping cylinder, and one end of the pushing piece extends out of the clamping cylinder and is arranged between ox horn clamps of the clamping cylinder; and a plurality of springs are arranged between the other end of the push piece and the clamping cylinder. According to the device, the aim of quickly, conveniently and uniformly smearing bone marrow is fulfilled by adopting a mode that the clamping cylinder is matched with the movable push sheet and assisting the spring to uniformly exert force.

The application discloses a bone marrow cell recognition result merging and counting method and system based on a double-space ontology constraint model. The method acquires a single cell record set, loads a statistical rule model containing a fine-grained label space, a clinical statistical space, a merging relationship, a denominator caliber relationship, an abnormal isolation relationship and a rule version identifier, forms a conversion path constrained by the rule version identifier, after rule integrity verification, maps an original fine-grained category to a clinical statistical node, determines a denominator caliber type and divides a denominator set, and generates an independent abnormal statistical item record; generates a clinical statistical result data set according to the clinical statistical node, the denominator set and the independent abnormal statistical item, and forms a reversible traceable data set. The application can reduce statistical denominator mixing, retain abnormal morphological characteristics, support rule version traceability, model upgrade compatibility and artificial correction incremental recalculation.

The application discloses a kind of bone marrow cell few sample classification method, system and electronic equipment, method includes: obtaining bone marrow cell dataset, constructs few sample training set and test set establishes the multi-scale multi-modal few sample classification network model based on text multi-source generation selection;According to the few sample training set, the few sample classification network model is trained, and the trained bone marrow cell classification network model is obtained;The bone marrow cell image of test is input into the bone marrow cell classification network model, and the prediction class of bone marrow cell image is obtained, realizes the bone marrow cell image classification under the condition of few sample training.The present application selects histopathology pre-training model for bone marrow cell classification, and designs text multi-source generation selection module, standardizes the semantic description of each category of bone marrow cell, and further improves the few sample classification accuracy of bone marrow cell, which can be widely applied in the field of computer vision technology.

The application discloses a kind of based on improved single-stage marrow blood cell target identification and counting method, it is related to medical image processing technical field.The method steps are:S1, image acquisition and data preparation;S2, the construction and pre-processing of data set, and the data set after pre-processing is divided into training set, verification set and test set;S3, the initial model of improved single-stage target identification model is constructed;S4, the initial model is trained using training set and verification set, and marrow blood cell target identification and counting model is obtained;S5, marrow blood cell target identification and counting model is used to identify and locate marrow blood cell in test set image, output cell class and target frame coordinates, and counting is realized according to target frame number.The application solves the detection problem caused by the large scale variation of marrow cell, improves the classification precision, realizes the unification of high precision and high speed of marrow blood cell target identification and counting.

The invention discloses a bone marrow cell morphology identification method and system based on a cross-domain adaptive joint convolutional neural network, and relates to the technical field of computer-aided diagnosis, the method comprises the following steps: S1, obtaining bone marrow cell image data, and carrying out image segmentation through a dual-path mask optimization segmentation module to obtain a single cell segmentation image; s2, extracting and fusing pathological features of the single cell segmentation image through a four-dimensional feature fusion module to obtain a spatial fusion feature vector; s3, performing feature alignment on the spatial fusion feature vector through a cross-domain adaptive joint module to obtain an aligned domain invariant feature vector; and S4, outputting a cellular morphology recognition type from the multi-center feature distribution vector through a dynamic element classifier. According to the method, high-precision and high-robustness automatic recognition of the bone marrow cellular morphology in a high inter-domain difference environment is realized, and the method has a significant clinical application value.

The invention discloses a bone marrow cell pushing device, and relates to the technical field of cell pushing, the bone marrow cell pushing device comprises a placing plate, the side surface of the placing plate is provided with a bottom plate, the upper part of the bottom plate is movably connected with a first movable box, the upper part of the first movable box is slidably provided with a second movable box, and the end part of the second movable box is rotatably connected with a connecting rod; a pushing piece is detachably installed at the end, away from the second movable box, of the connecting rod, and a pushing assembly used for the pushing piece is arranged on the first movable box. The pushing assembly comprises a third rack slidably arranged on the first movable box, a sliding block slidably arranged on the inner side of the first movable box, a first gear rotationally connected with the inner side of the first movable box, and a first rack installed on the side face of the sliding block. According to the invention, by arranging the pushing assembly, the uniformity of the speed during pushing can be better controlled in a pressing manner, the speed change possibly occurring during direct pushing is avoided, the cells can be ensured to be uniformly distributed on the glass slide, and the condition of cell overlapping or gathering is avoided.

This utility model relates to a semi-automatic bone marrow cell morphology slide washing instrument, comprising: a washing chamber with multiple slots for holding slides; and a robotic arm equipped with a washing head for driving the washing head to move. By holding the slides in the slots and using the robotic arm to drive the washing head, the water flow and angle can be controlled, reducing cell detachment. The closed washing chamber design allows the operator to have zero contact with the staining solution, improving operational safety. Multiple slides can be processed at a time, increasing washing efficiency.

The invention relates to a cell detection technology, in particular to a bone marrow cell detection and recognition system which integrates a slice image acquisition module, an image classification module, a real-time detection module, a cell data analysis module and the like. According to the scheme, automatic analysis of cell density, completeness and staining quality is carried out on the bone marrow smear image through an image processing technology, target detection is carried out by introducing the YOLO model, accurate identification and counting of cells in the image with complete cell morphology and uniform staining are realized, an alarm is given out in time when the cell number exceeds the preset threshold value, and the accuracy of cell detection is improved. While the automation level of bone marrow cell detection is improved, the reliability of a detection result and the clinical application value are enhanced.

The invention discloses a bone marrow cell classification method, system and device based on semi-supervised domain adaptation and a medium, the method comprises the steps that a data set is acquired and processed, and the data set comprises a source domain data set and a target domain data set; establishing a domain adaptive classification network model based on high-frequency feature fusion and target domain distribution disturbance alignment, wherein the domain adaptive classification network model adopts Predamp; the system is based on a Guide skeleton and comprises a high-frequency feature fusion module and a target domain distribution disturbance alignment module. Training the domain adaptive classification network model by using the source domain data set and the target domain data set to obtain a trained domain adaptive classification network model; and inputting the bone marrow cell image of the target domain data set into the trained domain adaptive classification network model to obtain a prediction category of the bone marrow cell image so as to realize semi-supervised bone marrow cell image classification. According to the method, more accurate label propagation of the target domain can be improved, so that the bone marrow cell image classification accuracy of the target domain is improved.

The invention relates to the field of cell extraction, and particularly discloses an artificial intelligence-based bone marrow cell extraction device which comprises an outer tube and a separation assembly, a storage cylinder is arranged in the outer tube, the separation assembly comprises a storage tube arranged on the outer side of the outer tube, a first telescopic rod is arranged at the top end of the storage tube, and a first piston is connected to the bottom end of the first telescopic rod; the first piston is slidably clamped in the storage pipe, a connecting pipe is connected to the outer side of the first piston, the free end of the connecting pipe directly communicates with the bottom end of the outer pipe, and a control assembly is arranged at the joint of the connecting pipe and the outer pipe. The separation assembly arranged in the device can separate other assemblies entering the needle tip in the outer tube puncture process independently, so that the doping amount of other tissues in a bone marrow extract is reduced, the extraction efficiency of the device is improved, the needle tip is inserted into the bone marrow extraction position, the tissues flow into the storage tube, and the bone marrow extraction efficiency is improved. After flowing for a period of time, the first telescopic rod is driven to be shortened until resetting, the rotating plate pushes the tissue into the storage tube, and tissue separation is completed.

This invention describes new methods for the mobilization of human cells such as hematopoietic stem cells in bone marrow, and the subsequent collection of such cells from the peripheral blood of deceased donors. These methods produce quantities of hematopoietic stem cells that can be used in a multitude of possible applications without harming the deceased donor or the recovery of the deceased donor's organs for solid organ transplantation. The methods involve the administration of one or more mobilizing agents to mobilize bone marrow cells into the peripheral blood cells followed by the collection of cells via apheresis.

The application discloses a kind of bone marrow cell identification systems based on multi-modal enhancement, comprising: cell image segmentation module, for the improved SAM model for the segmentation of bone marrow cell microscope image data;The module combines SAM model and Adapter block;Label text modification module is used to convert traditional label text into coarse and fine-grained text feature representation;Multi-modal alignment module uses an improved PMC-CLIP model to align the coarse and fine-grained text features output by the label text modification module to the image-text.The coarse-grained + fine-grained text information prompt of the present application can effectively improve the recognition accuracy of species with few cell numbers and complex cell images, solve the problem of unbalanced cell species and difficult-to-distinguish complex images, and improve the recognition accuracy of the model.

The application discloses a kind of based on improved ResNet-50 network's bone marrow cell classification method, belong to the medical auxiliary diagnosis field of artificial intelligence.The method includes: by designing a new classification model of fusion multiscale feature, introduce PSA module to improve ResNet-50 network, introduce CSAB module to enhance the edge feature extraction capability to image, help model capture the local details and global structure information of bone marrow cell image;Introduce ACAM module to improve the attention of model to different categories of bone marrow cell key features;By training the improved ResNet-50 network, the optimal model obtained by training is classified.In improving classification efficiency while ensuring high accuracy, compared with other bone marrow cell classification models applied has better performance.

The utility model discloses a multifunctional culture shelf for a bone marrow chromosome culture medium, which belongs to the technical field of bone marrow chromosome culture, and is characterized by comprising a box body, upright posts are fixedly connected to four corners in the box body, and a plurality of placing components are movably connected between opposite sides of the upright posts on two sides; the rear side of the interior of the box body is fixedly connected with an adjusting assembly, the adjusting assembly comprises a main plate, and the front side of the main plate is fixedly connected with a plurality of ultraviolet germicidal lamps. The problems that the temperature of a culture environment is inconvenient to adjust, and too high or too low temperature possibly affects the activity of bone marrow cells and hinders normal replication and separation of chromosomes, so that culture failure or chromosome abnormality is finally caused, culture of bone marrow chromosomes is affected, and the practicability of the device is reduced are solved.

The utility model discloses a bone marrow cell transport tube, and belongs to the technical field of medical detection materials. The transport tube comprises a tube body and a tube cover tightly covering the tube body, and further comprises an auxiliary tube used for storing a culture medium of bone marrow cells, a containing cavity is formed in the pipe sleeve; the auxiliary pipe and the pipe body can be arranged in the containing cavity, and the inner side of the pipe sleeve is tightly attached to the outer side face of the pipe body and the outer side face of the auxiliary pipe. After being collected, the bone marrow cells need to be conveyed to a laboratory for detection, and cell activity needs to be kept; when the bone marrow cell culture tube is used, the auxiliary tube can be opened, and the culture medium is poured into the tube body, so that nutrient substances are provided for bone marrow cells, the activity and the survival rate of the bone marrow cells are kept, the loss of the cells is reduced, and later cell culture is also facilitated; the pipe sleeve can be used for containing the auxiliary pipe and the pipe body, and in the process that cells are conveyed to a laboratory after being collected, the protection effect can be achieved by means of the elasticity of the pipe sleeve and the soft material layer on the inner side, and the influence of external collision on bone marrow cells is relieved.

This application provides a method, system, device, medium, and program product for analyzing bone marrow metastases in neuroblastoma, relating to the fields of intelligent medical image analysis and artificial intelligence-assisted diagnosis. The application includes: obtaining digitized whole-slice images of bone marrow cells from bone marrow cytological smears and preprocessing these images; preprocessing the whole-slice images to obtain bone marrow cell image blocks; weighting the bone marrow cell image blocks to obtain bone marrow cell feature images; wherein, the weighting processing includes feature extraction from the bone marrow cell image blocks to obtain corresponding feature vectors, employing multi-instance learning to represent the feature vectors at the whole-slice level to obtain bone marrow cell feature images; and classifying the bone marrow cell feature images to obtain corresponding classification results. This application achieves effective fusion from local cytological features to whole-slice-level diagnostic results through a multi-instance learning aggregation module.

The invention relates to a bone marrow cell image sample generation method and device, computer equipment and a computer readable storage medium, and the method comprises the steps: obtaining a simulated background / red blood cell segmentation binary image randomly generated by a generative adversarial network, and inputting the simulated background / red blood cell segmentation binary image as a constraint condition into a conditional generative adversarial network; acquiring a simulated background / red blood cell RGB image generated by the conditional generative adversarial network; obtaining a simulated karyocyte probability distribution function generated by a variational auto-encoder; performing random sampling on an image corresponding to the simulated nucleated cell probability distribution function according to a preset number, and determining coordinate positions of nucleated cells in a bone marrow cell image sample to be generated; and pasting the nucleated cell cut image in the bone marrow cell smear image to the coordinate position corresponding to the simulated background / red blood cell RGB image to generate a bone marrow cell image sample, thereby effectively improving the bone marrow cell image sample generation efficiency.