144 results about "Imaging diagnosis" patented technology

The invention discloses a brain tumor image diagnosis large model pre-training method, diagnosis method and system, and the method comprises the steps: obtaining the image data of a brain tumor patient and a corresponding diagnosis text, and the image data comprises a plurality of sequences; constructing a visual unified model, carrying out complete sequence standard training and missing sequence distillation training on the visual unified model by utilizing the image data, learning unified visual representation of the image data of any sequence combination, and taking characteristics of the complete sequence image data as teacher characteristics in the missing sequence distillation training; the features of the missing sequence image data serve as student features, and distribution alignment of the student features and the teacher features in the feature space is restrained; constructing a visual language model, taking unified visual representation output by the trained visual unified model as input based on a multi-task target, and training the visual language model in combination with the diagnosis text; the trained model can effectively process the sequence missing condition, and the accuracy and robustness of diagnosis are improved.

The invention discloses a thyroid ultrasound image diagnosis method based on deep learning, and the method comprises the following steps: collecting a thyroid ultrasound original image set, and carrying out the preprocessing; performing focus segmentation on the standardized thyroid ultrasound image set; performing morphological constraint and boundary refinement; calculating the blood flow direction, blood flow velocity and blood flow power of each thyroid focus area and neighborhood; generating a preliminary fusion feature map based on a feature adaptive deep learning network, and fusing the preliminary fusion feature map with the thyroid focus blood flow feature vector set; obtaining a thyroid focus detection list through thyroid focus benign and malignant discrimination branches; and generating thyroid focus structured diagnosis data records based on the thyroid focus detection list, and writing the thyroid focus structured diagnosis data records into a computer-aided diagnosis system. According to the method, deep learning and multi-modal blood flow features are fused, intelligent diagnosis of the thyroid focus is achieved, and the method has the advantages of being high in precision, high in interference resistance and structured in result.

The invention discloses a medical analysis method and system based on a multi-modal large language model and chain reasoning, and belongs to the crossing field of artificial intelligence and medical image analysis. The method comprises the following steps: firstly, carrying out preprocessing and modal alignment on medical multi-modal data to obtain image visual features and text embedding vectors of the same vector spatial dimension; capturing visual evidence in a structured pathological feature form through a self-excitation mechanism; on the premise of visual evidence, a thinking chain text containing causal logic is generated through evidence anchoring chain type reasoning; and finally, performing vision and text dual consistency verification on the thinking chain text, and outputting an analysis conclusion according to a result, or triggering a negative feedback correction mechanism to regenerate the thinking chain text. According to the method, medical reasoning full-process logic visualization is realized, medical illusion is eliminated, the diagnosis accuracy of complex cases is improved, and the method is suitable for medical scenes such as medical visual questions and answers and image diagnosis report generation.

Systems and methods are provided herein for developing and deploying active-prompt-tuned, domain-specific image diagnosis and categorization applications. Processes of the present disclosure may control and provide for human-confirmable diagnostics from images, based on controlled instructions provided to vision-language models. The controlled instructions may be developed by systems provided herein, which generate system prompts and example prompt sets using active prompt tuning approaches.

The invention relates to the field of biomedicine, particularly provides a copper-based nano-enzyme as well as a preparation method and application thereof, and aims to solve the problems that in the prior art, clinical treatment on primary sclerosing cholangitis (PSC) is difficult in diagnosis and lacks of effective treatment drugs. The copper-based nano-enzyme comprises a nano-enzyme carrier and a copper-based nano-enzyme, wherein the nano-enzyme carrier is a two-dimensional nanosheet formed by copper ions, gallic acid and ursodesoxycholic acid through coordinate bonds; the probe molecule is a cyanine dye molecule connected to the surface of the nano-enzyme carrier through a covalent bond; wherein the fluorescence intensity of the copper-based nano enzyme is enhanced after the action of the alkaline phosphatase. The three functions of alkaline phosphatase responsive diagnosis, nano-enzyme catalytic treatment and ursodesoxycholic acid hepatic targeting are innovatively and synergistically integrated into one nano platform, the treatment function can be executed while specific imaging diagnosis is performed on diseases, and a new strategy is provided for diagnosis and treatment of diseases such as PSC.

The invention discloses a medical image privacy protection-oriented structure perception adaptive steganography method, which comprises the following steps of: in a training stage, generating a diagnosis related region mask based on a pre-trained IMIS-Net, extracting an embeddable suppression mask, and obtaining an initial embedding probability under the minimum distortion constraint; and the self-adaptive adjustment of structure perception is carried out on the pixel-level embedding probability in combination with a reinforcement learning normal form, so that the ROI is protected preferentially and a high-risk region is inhibited on the premise of meeting the set capacity, and the steganalysis resistance and perception quality are improved. And after the training is completed, in a reasoning stage, the masks and probabilities are firstly generated or quoted, then action probabilities are obtained through a trained strategy network, then probability consistency is mapped into STC cost, real embedding is completed by the STC, and a secret-containing medical image is obtained. According to the invention, on the premise that the availability of image diagnosis is not reduced, safe embedding and hidden transmission of sensitive information are realized.

The invention relates to the technical field of computer vision and industrial equipment fault diagnosis, in particular to a fault image diagnosis system for a remote controller of a bolter miner driven by a CMC chip. Comprising a data sensing module for synchronously acquiring a CMC chip internal logic state vector and a real-time observation image, and preprocessing to obtain target visual data; the generative reconstruction module maps the logic state vector to a high-dimensional space to generate an ideal feature map; the visual analysis module is used for extracting an observation feature map through a convolutional neural network, generating an interference distribution mask based on frequency domain texture statistics, and identifying an unstructured environmental noise region; the difference analysis module is used for calculating a semantic residual image by combining the ideal feature map, the observation feature map and the interference distribution mask, and generating an image difference analysis result; according to the method, ideal features are generated by using the internal logic state vector of the CMC, and the residual calculation of the coal dust noise area is shielded by the interference mask, so that the false alarm caused by the environmental noise is effectively eliminated, and the closed-loop verification that what you see is what you control is realized.

The invention provides a pneumonia CT image diagnosis model training method, diagnosis method and equipment, and the training method comprises the steps: inputting a 3D chest CT image into a multi-task deep learning model, enabling a shared encoder in the model to extract multi-scale feature data, and enabling a connection module and a decoder to obtain pneumonia focus region prediction result data according to the multi-scale feature data, the classification head obtains pneumonia diagnosis type prediction result data according to the multi-scale feature data; determining the joint loss of the model in the current iteration round and updating model parameters; and if the current multi-task deep learning model satisfies a training termination condition, outputting the current model as a pneumonia CT image diagnosis model. According to the method, the problems of low model feature utilization rate and low pneumonia diagnosis process efficiency caused by incapability of simultaneously completing focus segmentation and type classification due to task simplification of an existing pneumonia diagnosis model can be solved.

This invention relates to aggregation-induced emission probes with specific responses to tumor markers and their applications, belonging to the field of biochemistry. This invention utilizes molecular structure modulation to prepare a series of molecules possessing large Stokes shifts, resistance to photobleaching, near-infrared II (NIR-II) emission, and aggregation-induced emission properties. Different self-eliminating groups are attached to the dimethylamino group of the molecule via quaternization or to the pyridine group via pyridinium salting. By controlling the structure of these self-eliminating groups, activatable luminescent probes responding to different tumor markers can be constructed. These probes integrate deep NIR-II imaging, aggregation-point luminescence, large Stokes shifts, and marker-specific responses, providing a new approach for precise imaging diagnosis of tumors.

The invention discloses a preparation method and application of near-infrared fluorescent dye DOM-O for acute alcoholic liver injury detection. The specific chemical structural formula of the near-infrared fluorescent dye DOM-O is shown in the specification. The near-infrared fluorescent dye prepared by the invention has excellent fluorescence imaging performance, can realize specific fluorescence imaging diagnosis of the acute alcoholic liver injury, and provides an imaging dye with application prospect for early detection and clinical diagnosis of the acute alcoholic liver injury.

This invention provides a detachable, interchangeable imaging diagnostic device that allows for the use of various sizes of scopes, enabling easy image diagnosis of various affected areas. [Solution] The interchangeable imaging diagnostic device comprises a scope module including a fluoroscopy tube 110, a scope body 120 surrounding the rear of the fluoroscopy tube, an LED 130 providing light into the fluoroscopy tube, a heat sink 140, and an LED connection jack 150 protruding from the rear surface; a main body including a focus lens 210 for observing the condition of the affected area through the fluoroscopy tube, an adjustment lever 220 for magnifying or reducing the condition of the affected area as seen by the focus lens, a camera 230 for saving images of the body cavity, and an imaging trigger 240 for capturing images of the captured images. The main body has an LED power jack into which the LED connection jack is inserted and a coupling groove into which the rear end of the fluoroscopy tube is inserted, and is characterized by a structure that allows for the selection of scope modules with different fluoroscopy tube sizes and their detachable connection to the main body.

The application provides an ophthalmic image diagnosis method and system based on multi-modal imaging cooperation, and relates to the technical field of medical image diagnosis. First, the OCT, fundus camera and ultrasonic original image data of an ophthalmic examination object are acquired, and multi-modal dynamic correlation mapping results are obtained through dynamic correlation and trend correlation processing. Cross-modal lesion feature progressive mining and interactive verification are performed to obtain a cross-modal lesion correlation feature set. Multi-modal cooperative diagnosis reasoning and weight feedback optimization are used to generate an ophthalmic disease reasoning result containing disease types, lesion dynamic distribution and reasoning confidence. Finally, an ophthalmic diagnosis report with dynamic labeling and confidence explanation is generated. The application comprehensively utilizes the advantages of various image technologies to improve the accuracy of ophthalmic image diagnosis.

The application discloses a kind of based on CBCT image data evaluation implant stability classification model and the construction method and device thereof.First, through the Mobilenetv2-DeepLabV3+ network after training in cross-sectional image implant is segmented, then in combination with the knowledge of oral implantology and segmentation result corresponding implant around bone image is extracted on cross-sectional image, finally using the deep residual network Resnet-50 after training is completed classification, obtains implant stability evaluation result.Test evaluation, the model of the application has higher diagnostic performance, the time consumption of evaluation is short, accuracy is high (>90%), can be effectively used for implant stability evaluation.The classification model for evaluating implant stability of the application has important significance for better guiding further implant restoration treatment, and provides important reference for artificial intelligence used for image diagnosis.

The invention belongs to the technical field of biological medicine. More specifically, the invention provides the annular RNACircMAP2, and the sequence of the annular RNACircMAP2 is as shown in SEQ ID NO. 1 or SEQ ID NO. 2. The invention proves that CircMAP2 can be used as a novel biomarker for diagnosing acute ischemic stroke for the first time. Compared with a traditional imaging diagnosis method, the acute ischemic stroke can be diagnosed by detecting the expression level of the CircMAP2 in the plasma and the plasma exosome of the patient, the cerebral infarction area of the acute ischemic stroke can be speculated through the expression level of the CircMAP2, and the method has the advantages of being easy and convenient to operate, high in detection speed and low in cost; the system is especially suitable for popularization and use in primary medical institutions. The product for diagnosing acute ischemic stroke provided by the invention can quickly and accurately diagnose acute ischemic stroke, and has good clinical popularization prospect and application value.

The invention relates to the field of CT image diagnosis, in particular to a comparison device for CT image diagnosis, which comprises a base, an observation assembly arranged at the upper end of the base, a placement assembly arranged in the observation assembly, a fixing assembly arranged on the inner wall of the observation assembly, an irradiation assembly arranged at the upper end of the base, and a rotating groove arranged in the rotating groove. A rotating groove is formed in the upper surface of the base, a fixing ring is fixedly connected to the inner wall of the bottom of the rotating groove, a lantern ring is connected to the outer wall of the fixing ring in a sleeving mode, a rotating box is fixedly connected to the outer wall of the lantern ring in a sleeving mode, and openings are formed in the outer wall of the rotating box. Then a transparent inserting plate is pushed to move towards the interior of the rotating box, the transparent inserting plate drives a push rod to approach an L-shaped rod, the inclined face of the L-shaped rod pushes a push plate, the push plate pushes the push rod, the push rod pushes a clamping block to extrude the CT film to be attached to a baffle, then the CT film is fixed, and the CT film is prevented from sliding off.

The invention discloses a tumor specific signal analysis device and equipment for uncertain pulmonary nodules and a storage medium, and relates to the technical field of electrical digital data processing.The device constructs a LungTCR database containing lung cancer tissue enrichment type and blood enrichment type CDR3 sequences through TCR beta chain sequencing and IMGT database comparison, and the LungTCR database is used for analyzing the lung cancer tissue enrichment type and blood enrichment type CDR3 sequences. A basis is provided for tumor specific signal recognition; a Needleman-Wunsch algorithm and an editing distance threshold value are adopted for screening, so that high-precision sequence matching is realized; through quantification of lung cancer tissue scores, blood scores and mutation specificity scores, a TCR feature group with biological significance is formed; and finally, the TCRnodseek plus model trained by clinical and image features is combined, a reliable malignant probability prediction value can be output, the model AUC can reach 0.90 or above, and the model is obviously superior to traditional imaging diagnosis and tumor markers.

The application belongs to the field of medical instrument imaging diagnosis equipment quality detection, and particularly relates to a phantom and a method for coronal plane transmission detection of a three-dimensional ultrasonic imaging device. The phantom comprises: an upper panel, an acoustic window, a target group, and an aggregate formed by background ultrasonic tissue simulation material. The upper panel is located above the acoustic window, and the upper panel and the acoustic window form an inner cavity after being connected. The target group and the aggregate formed by the background ultrasonic tissue simulation material are located in the inner cavity. When the coronal plane transmission imaging performance is detected, the phantom is suspended in the imaging area of a hemispherical ultrasonic array, and a degassed water body is also contained in the imaging area. Each target in the target group extends along the vertical direction and is perpendicular to the coronal plane of the breast to be imaged. In this way, the convenience and accuracy of the coronal plane transmission imaging performance detection are improved, and the utility is good.

This invention discloses a cross-modal medical image segmentation method based on pathological anchoring. Using pathological priors as semantic anchors, this method integrates cross-scale collaboration and uncertainty perception in a closed-loop prompting refinement process. This achieves interpretable suppression and robust learning of cross-modal domain shifts, forming a closed-loop path from structure to semantics to noise control. Under strong cross-modal zero-sample settings such as multi-source ultrasound cross-domain segmentation and color dermoscopy, stable and consistent improvements are achieved, manifested in more precise boundaries, better calibration, and more robust generalization. This provides technical support for disease image diagnosis.

The invention discloses a radioactive diagnosis medicine for targeting OPN as well as a preparation method and application of the radioactive diagnosis medicine. The radioactive diagnosis medicine comprises linear polypeptide and radionuclide, wherein the linear polypeptide is composed of 20 L-type amino acids and one D-type amino acid, and the radionuclide marks the linear polypeptide through a bifunctional chelating agent; the sequence of the linear polypeptide is as shown in SEQ ID NO. 1. In vivo, radionuclides in the medicine are concentrated to an atherosclerotic vulnerable plaque part through the targeting effect of the amino acid linear polypeptide, and imaging diagnosis is carried out on the atherosclerotic vulnerable plaque by utilizing a positron emission computed tomography technology of nuclear medicine.

This invention discloses a two-stage method for generating brain vascular images and labels. First, labeled and unlabeled brain vascular images are processed separately to obtain training set 1 and training set 2. Then, a two-stage generative adversarial network (GAN) model for brain vascular image-label generation is constructed and trained using training set 1 and training set 2. Finally, N-dimensional noise is input into the trained model to obtain a complete brain vascular image. This invention utilizes a two-stage GAN model with pseudo-labels and real data input to generate brain vascular images and labels respectively. The generated brain vascular images have clearer voxels around the blood vessels and stronger connectivity of the vascular labels. Data augmentation applied to segmentation tasks can improve the accuracy of brain vascular structures segmented from brain vascular images, facilitating subsequent pathological image diagnosis. Simultaneously, the use of pseudo-labels alleviates the shortage of labeled medical image data.

This invention discloses a radioactive molecular probe for targeting CSPG4 / NG2, its preparation method, and its application. The radioactive molecular probe comprises the structure shown in Formula I or Formula II. The technical solution of this invention uses a radioactive molecular probe to specifically recognize CSPG4 / NG2 in vivo through the target polypeptide portion, thereby achieving specific nuclear medicine positron emission tomography (PET) or single-photon emission computed tomography (SPECT) imaging diagnosis of CSPG4 / NG2 positive tumors or CSPG4 / NG2 positive lesions, such as autoimmune diseases and cardiovascular and cerebrovascular diseases, thereby realizing early diagnosis and efficacy evaluation of malignant tumors.

The invention relates to a preparation process of near-infrared fluorescent powder, in particular to nickel-containing near-infrared fluorescent powder and a preparation method thereof, a certain amount of barium carbonate, gallium oxide, nickel oxide and isopropanol are taken to be prepared into turbid liquid, and the nickel-containing barium gallate-based near-infrared fluorescent powder is prepared through the steps of grinding, drying, grinding, pressing, heat treatment, cooling, grinding and the like. Under the excitation of 635 nm light, the fluorescent powder presents ultra-wide band near-infrared luminescence composed of 1050-1400 nm light emission derived from matrix defects and 1300-1800 nm light emission of Ni < 2 + > ions; the light-emitting diode light source is more suitable for compact special near-infrared fluorescent powder conversion light-emitting diode light source design for high-resolution deep biological tissue imaging diagnosis equipment. Similarly, due to no ionizing radiation ultra-wide band NIR-II region emission, the system can be used in various biological tissue situations such as fat, muscle, endothelium and the like, and then development of multipurpose imaging diagnostic analysis technologies and equipment which are suitable for family daily medical treatment and are friendly and safe to special groups such as children, pregnant women, old people and the like can be promoted.

The present application relates to the technical field of image processing, and more particularly to a pancreatic cancer and breast cancer early image diagnosis method based on multi-modal contrast learning, step 1: obtaining multiple time-phase multi-modal images of the pancreas and breast of a subject in a unified spatial reference system to form a basic data set; step 2: based on the basic data set, alternately encoding the lesion candidate area mask and the peripheral ring domain mask to obtain an encoded feature vector; step 3: aligning the organ identification as the key according to the time-phase block index, and filling in the encoded feature vector of the missing time-phase block according to the set rule; jointly determining the intra-organ results of the two organs according to the set priority, and outputting the overall result. The present application can improve the sensitivity and specificity of early lesion detection, and enhance the diagnostic robustness and clinical application value while maintaining interpretability and traceability.

The invention provides a battle wound ultrasonic image diagnosis system and method based on deep learning, and the method comprises the steps: carrying out the adaptive preprocessing of a to-be-processed battle wound ultrasonic image, and obtaining a preprocessed ultrasonic image; global context features of image textures and local high-frequency features of image edges are extracted from the preprocessed ultrasonic image, and then a semantic fusion feature map containing deep image semantic information is generated; determining feature correlation coefficients between different feature sub-regions in the semantic fusion feature map and a preset feature template based on a preset sliding window, and further determining a segmentation probability matrix when the preprocessed ultrasonic image is segmented; and performing regionalization segmentation on the preprocessed ultrasonic image according to the segmentation probability matrix to obtain a regionalization segmentation image corresponding to the war wound ultrasonic image. According to the technical scheme provided by the invention, precise regionalization segmentation can be performed on the war wound ultrasonic image under the structural heterogeneity and texture complexity of the war wound tissue.

The invention discloses a preparation method of a ferritin-based magnetic resonance nanoprobe targeting hepatic stellate cells, which comprises the following steps: S1, preparing an HEPES salt solution with the working concentration of 10 mmoL / L, and adjusting the pH value to 8.3 by using a NaOH solution; s2, potassium chloroplatinite powder is dissolved in the HEPES salt solution in the S1, a ferritin solution is added, then the mixture is placed on a magnetic stirrer to be stirred for 1 h at the room temperature, and standing is conducted for 5 h. According to the preparation method of the hepatostellate cell targeting ferritin-based magnetic resonance nanoprobe, the ferritin-based magnetic resonance nanoprobe is endowed with good MRI T1 imaging ability after loading of metal manganese ions and platinum, and non-specific recognition of a ferritin receptor in a liver is shielded by modifying excessive double-active ester polyethylene glycol; then, through mediation of the specific targeting molecule RGD peptide, the nanoprobe is efficiently delivered to the fibrosis liver, the interception effect of normal liver tissue is avoided, the imaging effect is greatly enhanced, and imaging diagnosis of mouse hepatic fibrosis can be achieved.

The invention discloses a composite insulator filth hydrophobicity imaging diagnosis system and method, and relates to the technical field of power equipment detection, and the method comprises the steps: receiving the operation environment data, geometric structure data, an infrared time sequence matrix and a multispectral feature matrix of a target insulator, generating a temperature response baseline of the target insulator, and carrying out the imaging diagnosis of the filth hydrophobicity of the target insulator; extracting a target area on the surface of the insulator according to the operating environment data and the geometric structure data, dividing the target area into a plurality of pixel sub-areas, extracting temperature change data of each pixel sub-area, screening out a first candidate area set in which microcracks possibly exist in combination with a temperature response baseline, and obtaining a second candidate area set in which microcracks possibly exist according to a multispectral feature matrix; screening the first candidate region set to obtain a second candidate region set; performing spatial connectivity analysis and time stability analysis on the second candidate region set, and determining a hydrophobicity failure region of the target insulator; the method has the beneficial effect that the detection accuracy of the tiny hydrophobicity failure area on the surface of the composite insulator in the high-altitude area can be improved.

The present application relates to the technical field of heart ultrasound image diagnosis, in particular to a heart ultrasound image diagnosis report automatic generation system, comprising an OMM data preprocessing unit, used for processing data and outputting to a high-frequency time domain feature extraction unit and a multi-dimensional space-time correlation unit; the high-frequency time domain feature extraction unit is used for outputting to a coupling control and state discrimination unit; the multi-dimensional space-time correlation unit is used for evaluating a spatial decoupling index and outputting to the coupling control and state discrimination unit; the coupling control and state discrimination unit is used for receiving a time domain instability score and the spatial decoupling index; generating a control signal; reversely sending to the high-frequency time domain feature extraction unit and the multi-dimensional space-time correlation unit; a random process modeling unit is used for generating a probabilistic diagnosis feature set; a diagnosis report generation unit is used for generating a diagnosis report; the present application solves the problem that high-frequency time event fidelity and multi-dimensional space-time correlation integrity cannot be considered simultaneously, and realizes reliable modeling of non-periodic data.

This application provides a method, apparatus, device, and storage medium for self-correction of a medical visual language model based on a dynamic experience base (DEKB), relating to the field of medical visual language processing technology. The method includes: when the initial diagnostic result of the medical visual language model for a current clinical case does not match the fact label, constructing the current case as a structured experience unit and storing it in a dynamic experience knowledge base; upon receiving a query, retrieving historical experience cases related to the new query from the dynamic experience knowledge base; using the historical experience cases as contextual prompts to guide the medical visual language model in chain-like thinking, generating a corrected reasoning result. By constructing an endogenous dynamic experience knowledge base, designing a deep attribution analysis mechanism, and employing a dual-threshold retrieval algorithm, this application enables DEKB to transform the model's historical errors into structured knowledge that can be used for future reference, significantly improving the robustness and generalization ability of medical model image diagnosis reasoning.

To provide an ultrasonic image diagnostic system for independently displaying an image displayed on the side of an ultrasonic diagnostic apparatus, an image displayed on the side of an information terminal and an image displayed on the side of the information terminal obtained by remotely instructing the apparatus.SOLUTION: An ultrasonic image diagnosis system (1) is an ultrasonic image diagnosis system in which an ultrasonic diagnostic device (2) having a display section for displaying a first ultrasonic image generated on the basis of first ultrasonic image data obtained by transmitting and receiving ultrasonic signals by using an ultrasonic probe, and an information terminal (3) having an input section and a display section for displaying image data transmitted from the ultrasonic diagnostic device (2) are connected by a network, and the ultrasonic image diagnosis system (1) is provided with a display mode including a synchronous display mode for synchronously displaying the displays of the display section of the ultrasonic diagnostic device (2) and the display section of the information terminal (3), and an independent display mode for displaying the first ultrasonic image on the display section of the ultrasonic diagnostic device (2) and displaying the second ultrasonic image on the display section of the information terminal (3).SELECTED DRAWING: Figure 1