35 results about "Retinal lesion" patented technology

The invention relates to the technical field of medical image processing, in particular to a spatial self-adaption and thermodynamic diagram guided retina image segmentation method, which comprises the following steps of: acquiring retina image data containing three-dimensional information and at least one focus, optimizing an existing SAM model, and constructing a segmentation model, the architecture of which comprises the steps of taking a visual Transform as a backbone and taking a thermodynamic diagram as a template; designing and introducing an image encoder of a spatial adaptive feature enhanced Transform block, a dual-stage mask decoder and a thermodynamic diagram guided mask self-attention module, adopting a training process of a joint loss function supervision model based on cross entropy loss and Dice loss, and inputting an image to be segmented into the model to obtain a segmentation result; the scheme has the advantages that the three-dimensional structure information of the retina image can be fully mined, the segmentation precision of different types of lesions is remarkably improved, the problem of class imbalance is relieved, and high-precision and high-efficiency segmentation of the retina lesions is realized.

The invention provides a quantitative detection method and system based on an ophthalmic retina OCT image. The method comprises the steps that a quantitative parameter matrix of a three-dimensional structure is constructed according to a reflection intensity distribution curve corresponding to a target OCT image, the reflection intensity distribution curve and blood vessel density data of an OCTA image, and each voxel in the quantitative parameter matrix comprises space coordinates and parameter dimensions; inputting the quantitative parameter matrix into a pre-trained joint model to detect a retina leakage bounding box through a YOLOv7 network in the joint model, and segmenting the retina leakage area through a U-Net network in the joint model to obtain bounding box coordinates and a segmentation mask of the retina leakage area; and determining quantitative information of the retina lesion area according to the bounding box coordinates and the segmentation mask of the retina permeation area and a mapping relation between a preset permeation area and the lesion area. According to the technical scheme provided by the invention, the YOLOv7 network and the U-Net network are combined to accurately detect and segment the retinopathy area, and quantitative analysis is realized.

The invention discloses a diabetic retinopathy image classification method based on a multi-feature fusion network model, and the method comprises the steps: S1, obtaining an initial fundus image data set, and constructing a sample training set based on the initial fundus image data set, a first enhanced image data set, and a second enhanced image data set; s2, constructing a retinopathy image classification model, and training the retinopathy image classification model based on the sample training set to obtain a trained retinopathy image classification model; the retinopathy image classification model comprises a first multi-feature fusion enhancement module, a second multi-feature fusion enhancement module, a third multi-feature fusion enhancement module, a fourth multi-feature fusion enhancement module and a classification module; the classification module performs classification based on the input data to obtain a retinopathy image classification result. By designing a plurality of multi-feature fusion enhancement modules and double attention modules, hierarchical fusion of lesion features is realized, the recognition precision of tiny lesions is improved, dynamic calibration of a lesion area feature map is realized, and finally, high-precision and robust DR automatic classification is realized.

The invention relates to the technical field of blood vessel image segmentation, and provides a fundus blood vessel image accurate segmentation method based on a U-Net model, aiming at solving the problem that the existing blood vessel segmentation method based on deep learning is difficult to effectively balance global context and local details. In order to solve the problem of inaccurate blood vessel structure segmentation caused by factors such as poor image quality and low contrast ratio, a method of combining a wavelet and a visual state space model and an adaptive dynamic fusion module is provided to improve the integrity of a slender blood vessel and the structural segmentation accuracy of a complex blood vessel network in a fundus blood vessel image. By integrating multiple efficient feature extraction mechanisms, accurate recognition of small blood vessels and the whole blood vessel structure is achieved, the accuracy and robustness of blood vessel segmentation in complex medical images are remarkably improved, and the method can be widely applied to analysis of eye blood vessels such as retinopathy and hypertensive fundus lesion and research of biomarkers related to the blood vessels.

The present application provides a retinal lesion segmentation method and device, electronic device and storage medium, which belong to the field of medical image processing technology. The method comprises the following steps: acquiring a retinal image, performing multi-stage encoding on the retinal image to obtain first-stage encoding features and second-stage encoding features, performing feature fusion on the first-stage encoding features and the second-stage encoding features to obtain target retinal encoding features, performing attention processing on the target retinal encoding features to obtain target retinal attention features, performing multi-stage decoding on the second-stage encoding features to obtain target stage decoding features, performing feature splicing on the target retinal attention features and the target stage decoding features from the channel dimension to obtain target retinal decoding features, performing lesion segmentation on the retinal image according to the target retinal decoding features, obtaining the retinal lesion category and retinal lesion location, and improving the accuracy of retinal lesion segmentation.

Injectable photoelectrohydrogel for repairing retinal photoreceptor damage and its preparation method and application, photoelectroactive spirulina and conductive polymer poly(3,4-ethylenedioxythiophene) (PEDOT) hydrogel are physically cross-linked to construct an injectable material with photoelectric response characteristics, and the function of damaged photoreceptor cells in the retina is repaired in situ. Sp as a biologically active component not only gives the material photoelectric signal conversion capability, but also can achieve local antioxidant stress function, PEDOT-based hydrogel forms a three-dimensional scaffold by physically wrapping Sp, which not only ensures the activity of algal cells but also has excellent charge and ion conduction performance. The hydrogel can be injected into the retina to construct a biomimetic electrochemical signal transmission interface, rebuild the signal transduction of damaged photoreceptor cells, and realize the in situ repair of retinal signal pathways and the partial recovery of visual function. This technology provides a new strategy for the curative treatment of retinal diseases such as blinding eye diseases, and has the advantages of minimally invasive intervention, excellent biocompatibility and customizable treatment area.

The application discloses a kind of premature infant retinopathy typical lesion automatic segmentation method, comprising the following steps: S1, collect ROP image, exclude unqualified image therein, and after the qualified ROP image is labeled, it is used as ROP lesion segmentation dataset, and dataset is divided into training set, verification set and test set;S2, construct deep neural network model;S3, after the training set is preprocessed, the training set is used to train the deep neural network model, calculate loss, optimize network parameters, and obtain the optimal model after several iterations;S4, the optimal model is tested using test set, and the segmentation performance evaluation index of the model on test set is obtained.Compared with the prior art, the method can better distinguish between background and four lesion structures, reduce the misjudgment rate, achieve automatic pixel-level segmentation of ROP fundus image lesions, and ultimately improve the network segmentation performance.

This invention discloses a method for establishing a mouse model of outer retinal tubular structures, which is obtained by specifically knocking out the Lss gene in the mouse retina. This invention utilizes CRISPR / Cas9 gene editing technology to construct a mouse model of outer retinal tubular structures by specifically knocking out the Lss gene in the retina. The mouse model of outer retinal tubular structures constructed by this method is similar to the clinical phenotype of this type of retinal disease, providing a relatively ideal experimental animal model for studying the developmental regulation of the mammalian retina and the pathogenesis of retinal degeneration.

The invention provides a retina photosensitive neuronal lesion zebrafish model and a construction method thereof, and relates to the technical field of gene engineering. Wherein the sgRNA comprises a guide sequence which can specifically recognize and be combined with a nucleotide sequence shown as SEQ ID NO.4 in an elovl2 gene. The high specificity of the sgRNA ensures the precise targeted modification of the elovl2 gene, and obviously reduces the off-target risk. The genetic background of the constructed zebrafish model is clear, and the retinopathy phenotype can be reliably attributed to the lovl2 gene mutation, so that a stable biological tool which is highly similar to human diseases is provided for related disease research and drug screening.

The present application relates to the technical field of medical image processing, in particular to a kind of space adaptive and heat map guided retinal image segmentation method, comprising: obtaining the retinal image data containing three-dimensional information and at least one focus, optimizing existing SAM model, construct a segmentation model, its architecture contains with visual Transformer as backbone, and design is introduced space adaptive feature enhancement Transformer block image encoder, two-stage mask decoder and heat map guided mask self-attention module, using the combined loss function based on cross-entropy loss and Dice loss composition supervises the training process of model, the image to be segmented is input into model to obtain segmentation result;The advantages of the scheme are that the three-dimensional structure information of retinal image can be fully tapped, the segmentation accuracy of different types of lesions can be significantly improved, and the problem of class imbalance can be alleviated, and high-precision and efficient segmentation of retinal lesions is realized.

The present application belongs to the technical field of diabetic retinopathy lesion detection, and particularly relates to a diabetic retinopathy lesion detection method based on adaptive multi-label recognition, which comprises: acquiring multi-phase image data of FFA images of a patient; using a "16-tile input" method to combine and splice each group of 10 time-series FFA images; building a D-LAM model composed of a class-adaptive mapping module, a label-specific decoding module and a smooth focus loss function; using the processed FFA image data set to train and verify the model, and finally realizing automatic recognition of different types of lesions on the test set. The method significantly improves the recognition ability of micro-lesions such as microangioma, effectively handles the complex semantic correlation between multi-labels, and effectively assists doctors in identifying diabetic retinopathy, thereby improving the recognition efficiency and accuracy of diabetic retinal lesions.

The present disclosure relates to chimeric molecules which are fusion proteins comprising two components: an Ang-2 binding peptide linked to either a VEGF antibody or a VEGF receptor-Fc fusion protein. The Ang2 peptide, VEGF antibody, and VEGF receptor-Fc fusion proteins are each defined below with reference to percent identity to a reference sequence. The chimeric molecule is a fusion protein, dual antagonist of Ang2 and VEGF for treatment of cancers, proliferative retinopathies, neovascular glaucoma, macular edema, AMD, and rheumatoid arthritis.

The invention discloses lactobacillus reuteri LR1349 and application thereof in improving eye injury induced by blue light, and belongs to the technical field of microorganisms. The lactobacillus reuteri LR1349 disclosed by the invention is preserved in the German Microorganism and Cell Culture Collection Center (DSMZ), and the preservation number is DSM 35135. The lactobacillus reuteri LR1349 provided by the invention can effectively improve the reduction of visual acuity, retinal dysfunction and retinopathy caused by blue light irradiation. Therefore, the lactobacillus reuteri LR1349 disclosed by the invention can be used for preparing medicines, foods or food additives for improving eye injury induced by blue light or relieving visual fatigue.

The invention belongs to the technical field of biomedical instruments, and particularly relates to a device for detecting and intervening fundus retinopathy, which comprises an external energy transmitting device and a multifunctional integrated flexible corneal contact lens, and is characterized in that energy is provided for a biological light adjusting unit in the multifunctional integrated flexible corneal contact lens through the external energy transmitting device; according to the multifunctional integrated flexible corneal contact lens, the LED patch is integrated, and non-invasive intervention and treatment on the retina are achieved through the biological light adjusting technology. The receiving coil and the ERG electrode adopt a parting paper-cut structural design, so that the tensile property of the ERG electrode and the overall flexibility and structural consistency of the device are improved. The closed-loop management of'detection-treatment 'of retinal diseases is successfully realized, the device has more excellent histocompatibility, wearing comfort and large-scale production feasibility, and an innovative solution is provided for diagnosis and treatment of fundus diseases.

The present invention is directed vectors comprising a FCBR1-F0.4 promotor or an IRBP-GRK1 promotor and a nucleic acid sequence encoding a ciliary protein, or fragment or variant thereof. In particular, the invention relates to a method of treatment and prevention of retinal ciliopathies, such as retinitis pigmentosa 28.

Methods, systems, and devices to improve the assessment of visual function and overcoming limitations of current methods to identify the visual function that potentially could be reached by a given eye. Multiple eye tests including visual stimuli plus optical measurement components, and methods to combine the results, identify and quantify sources of decreased vision resulting from optical sources, such as a lens and cornea as distinguished from retinal sources. By identifying potentially correctable optical sources of decreased vision, and overcoming physiological limitations such as size of the eye's pupil, the visual benefits of treatment such as by cataract or corneal surgery are distinguished from retinal pathology that requires medical intervention. The devices and methods provide metrics that include an expected value of the visual function and sources of variability including both optical and neural components, to guide treatment and improve clinical trials.

The invention provides a retinopathy detection method fusing multi-focus segmentation and comparative learning, and designs a two-stage network by closely fusing focus segmentation and grading tasks. In the lesion segmentation task of the first stage, an improved MCA-UNet network is provided, the feature extraction capability is optimized by introducing a semi-wavelet collaborative attention module, and high-precision lesion spatial feature support is provided for the subsequent grading task. In the DR grading task of the second stage, a double-branch prototype comparison learning model is constructed, and a feature learning branch strengthens intra-class compactness and inter-class separability by constructing a class prototype, so that the problem of class imbalance ubiquitous in a DR data set is effectively relieved.

The application discloses a kind of based on MEA-Net network's modeling method of multi-expert system, the application includes data pre-processing, cutting and proportionally distributing production image data and label data set;In order to improve fundus retinal lesion classification accuracy, the application designs Multi-Expert attention Net network model.Input module is preliminary extracted to data, replaceable expert network module is responsible for the depth analysis of feature, and voting module is strengthened by separating channel adjacent module on channel space to feature, and output weight realizes expert voting, finally, classification result is obtained by output module.The application can use the picture information of optical coherence tomography, can analyze and extract the characteristics of the four types of macular edema degeneration performances of OCT image PED, SRF, IRF, HRF, and lay the foundation for subsequent retinal disease classification and analysis to improve efficiency.

The application discloses a diabetic nephropathy patient retinopathy image classification method based on artificial intelligence, relates to the technical field of medical images, and comprises the following steps: collecting retinal images and carrying out denoising and contrast adjustment to generate standardized images; using a generative adversarial network guided by medical prior knowledge, combining microaneurysm morphology and hemorrhage area texture features to perform feature constraint, generating retinal images with enhanced pathological features, and constructing an amplified training data set; training a deep convolutional neural network based on the data set, using a multi-scale feature extraction layer to identify microaneurysm and hemorrhage lesions, and outputting preliminary classification results; combining clinical physician feedback to construct a reinforcement learning environment, dynamically adjusting classification decision thresholds and optimizing lesion classification parameters. The method disclosed by the application adopts cross-modal correlation analysis, fuses retinal lesion features and biochemical time series data, and improves the accurate classification ability of diabetic retinopathy images.

Methods, systems, and devices to improve the assessment of visual function and overcoming limitations of current methods to identify the visual function that potentially could be reached by a given eye. Multiple eye tests including visual stimuli plus optical measurement components, and methods to combine the results, identify and quantify sources of decreased vision resulting from optical sources, such as a lens and cornea as distinguished from retinal sources. By identifying potentially correctable optical sources of decreased vision, and overcoming physiological limitations such as size of the eye's pupil, the visual benefits of treatment such as by cataract or corneal surgery are distinguished from retinal pathology that requires medical intervention. The devices and methods provide metrics that include an expected value of the visual function and sources of variability including both optical and neural components, to guide treatment and improve clinical trials.

The application discloses a diabetic retinopathy feature classification method, system, device and medium, wherein the method comprises: acquiring a diabetic retinal lesion image; inputting the lesion image into a preset channel attention network and a preset spatial attention network respectively to obtain a first feature map output by the channel attention network and a second feature map output by the spatial attention network; fusing the first feature map and the second feature map to obtain a third feature map; inputting the third feature map into a capsule network to obtain an output result of the capsule network; and inputting the output result into a preset classifier to obtain a classification result of the lesion image output by the classifier. The application can improve the accuracy and classification efficiency of diabetic retinal lesion image classification, and better cope with the problems caused by large differences between diabetic retinal lesion images and large amounts of diabetic retinal lesion image data.

The present application relates to the field of medical imaging technology, and particularly relates to a method for detecting retinal lesion hard exudate clusters under OCT imaging, which comprises the following steps: generating an Enface front projection image by establishing a three-dimensional coordinate system, and performing polar coordinate grid division to establish a mapping relationship between three-dimensional coordinate voxels and polar coordinate grids; on the Enface front projection image, extracting a suspected hard exudate grid according to the highlight aggregation feature; backtracking the vertical columnar region of the suspected hard exudate grid, taking the front highlight reflection focus and the rear acoustic shadow attenuation of the hard exudate in the Bscan section sequence as specific criteria to obtain real hard exudate clusters; quantifying each index of the real hard exudate clusters, and outputting a detection report of the real hard exudate clusters; the present application can quickly and accurately lock the real hard exudate clusters, and further provide a quantitative basis for long-term dynamic monitoring of fundus diseases.

The invention relates to an injectable photoelectric hydrogel for repairing retina photosensitive function damage and a preparation method and application thereof, and the injectable photoelectric hydrogel is characterized in that photoelectric active spirulina and a conductive polymer poly (3, 4-ethylenedioxythiophene) (PEDOT) hydrogel are physically crosslinked to construct an injectable material with a photoelectric response characteristic, and functional repair of retina damaged photosensitive cells is realized in situ. Sp is used as a bioactive component, the material is endowed with photoelectric signal conversion capacity, the local anti-oxidative stress function can be achieved, PEDOT-based hydrogel physically coats Sp to form a three-dimensional support, algae cell activity is guaranteed, and excellent charge and ion conduction performance is achieved. The hydrogel can be injected into the retina to construct a bionic electrochemical signal transmission interface, signal transduction of damaged photoreceptor cells is reconstructed, and in-situ repair of a retina signal channel and partial recovery of a visual function are achieved. The technology provides a new strategy for curative treatment of blinding eye diseases such as retinopathy, and has the advantages of minimally invasive intervention, excellent biocompatibility, customizable treatment area and the like.

The invention provides nano-particles of SPHK1 coated by a macrophage membrane and application of the nano-particles in experimental autoimmune uveitis, and relates to the technical field of new drug development. The preparation method comprises the following steps: loading SPHK1 expression plasmids driven by a TBG promoter by using a polylactic acid-glycolic acid copolymer (PLGA) as a nano-carrier, and then coating the SPHK1 expression plasmids with a macrophage membrane stimulated by lipopolysaccharide to prepare LPS-MM / PLGA-mSPHK1. According to the invention, LPS-MM / PLGA-mSPHK1 can be recruited to a retinopathy site, so that accumulation of the LPS-MM / PLGA-mSPHK1 in the retinopathy site is increased, the gene intervention effect is enhanced, the efficient uveitis lesion site targeting function is realized, retinal injury and inflammatory response can be relieved, retinal barrier injury is prevented, and good biological safety is achieved.

The invention discloses a multi-label retinopathy image classification method based on semantic feature iteration enhancement, and the method has the following beneficial effects: a model can carefully capture the local features of a lesion region through a multi-stage feature extraction strategy, and carries out combined enhancement in combination with the overall representation of a retina object; besides, an iteration enhancement mechanism is introduced into the model, semantic expression of a lesion area is gradually enhanced in multiple iteration processes, effective modeling of a retina overall structure is kept, and therefore the classification effect of the multi-label retina images is improved. Through the above mode, the method effectively combines the local features of the lesion area of the retina image and the global features of the overall structure of the retina through the multi-stage feature extraction strategy and the iteration enhancement mechanism, and gradually optimizes the positioning precision of the lesion area, thereby extracting more accurate lesion information, and improving the accuracy of the lesion information. And the characterization capability of the model on complex lesion features is improved.

The present application relates to the technical field of image processing, in particular to a retinal lesion segmentation method based on mixed supervision learning, which utilizes limited full-annotation images and more point-annotation images for retinal multi-class lesion segmentation; the mixed supervision network model adopts a parameter decoupling strategy to optimize the teacher network, and in the conventional training round, the student network updates the parameters of the teacher network based on the full-annotation images and the point-annotation images; in the specific training round, the current teacher network parameters are copied to the auxiliary optimization network, the auxiliary optimization network updates the parameters of the auxiliary optimization network based on the full-annotation images, and the updated parameters are copied back to the teacher network, so that the supervised fine-tuning of the teacher network is completed; based on the parameter decoupling strategy to optimize the teacher network, the pixel-level annotation information is fully utilized, and the strong dependency between the teacher network and the student network is relieved to a certain extent, so that the performance of the average teacher network in retinal lesion segmentation is effectively improved.

The invention relates to the technical field of computer vision, and discloses an automatic image focus identification method based on ophthalmology detection, the method comprises the steps of setting an image quality control module, setting a disease course tracking module and setting a focus decoupling module, when multi-mode fundus image comprehensive analysis is carried out, cross-device image registration standard parameters are formulated, and the cross-device image registration standard parameters are formulated; layered recognition standards are set according to different focus types, normalization of various retinopathy detection is guaranteed, meanwhile, multi-source imaging data are aligned and fused on a retina layer, the problem of interlayer registration deviation between optical coherence tomography and fundus photography can be found in real time, and the accuracy and accuracy of retinopathy detection are improved. According to the method, accurate space positioning of focus such as diabetes mellitus macular oedema is guaranteed, focus measurement errors caused by equipment differences are effectively reduced, the reliability of quantitative analysis is improved, when abnormal evolution of the focus is detected, the diagnosis threshold value can be dynamically adjusted according to the standard disease course database, and the clinical guidance value of follow-up visit monitoring results is guaranteed.

The present application belongs to the field of biotechnology, and discloses sgRNA targeting Ush2a gene and a method for knocking out Ush2a gene of Macaca fascicularis. The method mainly establishes a target sequence for mRNA of Ush2a gene of Macaca fascicularis and synthesizes corresponding sgRNA, then constructs a knockout vector, mixes sgRNA and Cas9 mRNA, and injects them into an embryo of Macaca fascicularis to obtain an embryo of Macaca fascicularis with Ush2a gene knocked out, and then obtains a Macaca fascicularis with USH2A gene knocked out through embryo transplantation. The present application can effectively realize gene knockout of Ush2a gene on the embryo of Macaca fascicularis and offspring Macaca fascicularis through knockout effect detection and identification, and provides a new and effective method for establishing an animal model of non-human primate retinal lesion and genetic deafness.

The invention relates to a retinopathy segmentation method, device and system based on a threshold channel regulation mechanism, and the method comprises the steps: collecting a preset number of color fundus images of diabetic retinopathy of different patients, carrying out the preprocessing, and generating a corresponding multi-valued mask image containing a focus condition; constructing a RetinaSAM large model, and introducing a threshold channel regulation and control mechanism into the model; dividing a training set and a test set based on the preprocessed color eye fundus image and the corresponding multi-valued mask image, and then performing model training and testing; and inputting a to-be-diagnosed color eye fundus image into the large model to obtain a focus segmentation result. According to the method, the large model introducing the threshold channel regulation and control mechanism is constructed, and the database containing different types of lesion information is used for model training and testing, so that the recognition capability of the model on small lesion, weak features and complex lesion areas is improved, and the model segmentation precision is improved.