645 results about "Automated segmentation" patented technology

The invention discloses an automatic segmentation method and device for a focus area in an ultrasonic image, a medium and a product, and relates to the field of intelligent medical treatment. The method comprises the following steps: firstly, acquiring an original ultrasonic image shot at a lesion part of a patient and preprocessing the original ultrasonic image, then labeling the preprocessed ultrasonic image, and storing the labeled image and the ultrasonic image in a one-to-one correspondence manner to form a sample data set; performing coarse segmentation on a foreground and a background in the ultrasonic image through an automatic threshold segmentation method to obtain a binary mask of the foreground as a coarse mask; the rough mask is converted into multi-mode cue word information; training an improved SAM large model by using the sample data set and the multi-modal cue word information, and using the improved SAM large model as a focus region segmentation model after training is completed; the to-be-segmented ultrasonic image and the cue word information thereof are obtained and input into the lesion region segmentation model, so that the lesion region can be automatically segmented, and the efficiency, accuracy and intelligent level of segmentation of the lesion region in the ultrasonic image are remarkably improved.

The invention discloses an IG-MambaUNet image segmentation model, a model training method and an application method thereof, the IG-MambaUNet image segmentation model comprises an encoder and a decoder which are symmetrically arranged in parallel, the encoder comprises three first encoding modules and a second encoding module, the three first encoding modules are sequentially connected from top to bottom, the second encoding module is connected with the first encoding module on the bottommost layer, and the third encoding module is connected with the second encoding module on the bottommost layer. The input end of the first coding module on the topmost layer is connected with a first convolution and maximum pooling operation module, the first coding module is formed by coupling an IG-Mama module and a Patch Merging module, the second coding module comprises an IG-Mama module, the IG-Mama module comprises a local feature extraction module, a global feature extraction module and a gating attention module, and the global feature extraction module comprises a local feature extraction module, a global feature extraction module and a gating attention module. The decoder comprises a second coding module and a first coding module which are sequentially connected from bottom to top, and the output end of the first decoding module on the topmost layer is connected with a second convolution and maximum pooling operation module. According to the scheme, fine segmentation is realized, and the method can be suitable for automatic cell body segmentation of histological dyed ganglion images with complex textures and fine structures.

The invention discloses a cervical cancer close-range radiotherapy high-risk target area sketching method fused with a multi-modal image. The method comprises the following steps of collecting an MRI image scanned before radiotherapy and a CT image during radiotherapy of a cervical cancer close-range radiotherapy patient and annotation data of the MRI image and the CT image; the method comprises the following steps: preprocessing an MRI image scanned before radiotherapy and a CT image during radiotherapy, and converting annotation data into a three-dimensional tag image; on the basis of the preprocessed MRI image, the preprocessed CT image and the three-dimensional label image of the preprocessed MRI image, the preprocessed CT image and the three-dimensional label image of the preprocessed MRI image, registration of the MRI image and the CT image is conducted through a pre-constructed registration neural network model, feature extraction and fusion are conducted on the registered MRI image and the registered CT image through a pre-constructed high-risk target area automatic segmentation neural network model of a multi-scale cross-modal attention mechanism, and the high-risk target area automatic segmentation neural network model of the multi-scale cross-modal attention mechanism is obtained. Automatic delineation of a cervical cancer close-range radiotherapy high-risk target area is realized; according to the method, automatic segmentation of HR-CTV in close-range radiotherapy of cervical cancer is realized, high efficiency, accuracy and generalizability are realized, and intelligent support can be provided for clinical work.

The invention relates to the technical field of medical image processing, and particularly discloses a medical image segmentation method with adaptive receptive field and feature correction, which comprises the following steps: (1) acquiring an original medical image and a segmentation label thereof, and constructing a training and testing data set; (2) carrying out size normalization and enhancement processing on the image; (3) establishing an improved U-shaped encoder-decoder segmentation network, introducing an adaptive branch mixed shape convolution module in a shallow layer, and improving edge and texture feature modeling capability by adopting a multi-branch banded convolution and channel attention mechanism; (4) a residual directional feature interaction module is introduced into a deep layer, a spatial dependency relationship is modeled through an information interaction structure in the horizontal and vertical directions, and the direction sensing ability of the heterostructure is enhanced; and (5) completing network training and reasoning, and outputting a segmentation result. The method gives consideration to the calculation efficiency and the segmentation precision, and is suitable for the automatic segmentation task of various types of medical images with complex structures.

The invention discloses a brain tumor area automatic segmentation method and system based on deep learning, and belongs to the technical field of image segmentation, and the method comprises the following steps: obtaining a disclosed brain tumor segmentation data set, and constructing a multi-modal brain tumor medical image database; performing data preprocessing on the multi-mode brain tumor medical image database; dividing the preprocessed multi-modal brain tumor medical image database into a training set, a verification set and a test set in proportion; a deep learning model LG-FPN-TransBTS based on the improved TransBTS is designed, and the deep learning model LG-FPN-TransBTS is designed; and training, evaluating and applying the model. The system comprises a data preprocessing module, a data set division and secondary processing module, a deep learning model construction module, a model training and optimization module and a model evaluation and application module. According to the method, the precision and robustness of brain tumor image segmentation are remarkably improved.

The invention provides an aorta morphological characteristic automatic measurement and clinical aid decision-making method and system based on artificial intelligence, and is suitable for three-dimensional medical image analysis of aorta and main branches thereof. The method comprises the steps of image data acquisition and preprocessing, vascular structure automatic segmentation, center line extraction and key point positioning, multi-parameter automatic measurement, risk assessment and clinical aid decision making, data standardization output and system feedback optimization. The corresponding system comprises an image acquisition and processing module, a segmentation module, a center line extraction module, a parameter measurement module, an auxiliary decision-making module, a data output module and a verification optimization module. Through a deep learning model and a morphological calculation means, efficient recognition and quantitative analysis of a vascular structure are realized, and individualized risk suggestions and surgical plans are output based on a statistics and machine learning model. According to the method, the automation, standardization and intelligence levels of blood vessel analysis are improved, and the clinical auxiliary decision-making capability under complex cases is enhanced.

The invention relates to the technical field of image segmentation, in particular to an automatic segmentation method and system for an echocardiogram of the department of cardiology, and the method comprises the following steps: based on image data of the echocardiogram, extracting gray level distribution, edge feature and texture feature information, analyzing gray level change amplitude, screening gray level change abnormal regions, and recognizing connectivity features. According to the method, the segmentation accuracy is effectively improved by extracting image gray, edge and texture features and identifying abnormal regions, noise and artifact interference are reduced by optimizing low connectivity regions, and the segmentation accuracy is improved. A problem area is analyzed and positioned in combination with multi-frame gray level change, a segmentation result is adjusted, the processing stability and consistency are enhanced, meanwhile, an optimized alarm node is output based on a frequency trend, more accurate and stable heart image analysis is supported, and the clinical application practicability is improved.

The invention discloses a urinary calculus CT image automatic segmentation method based on deep learning, particularly relates to the technical field of medical image processing, and is used for solving the problem of low geometric fidelity of a segmentation result caused by hardening artifacts when an existing deep learning segmentation method is used for processing a high-density urinary calculus CT image. The method comprises the following steps: acquiring a urinary calculus CT image, performing initial segmentation by using a deep learning model to generate an initial calculus segmentation region, evaluating texture heterogeneity degree and identifying a hardening artifact risk region by analyzing feature value distribution of a structure tensor field, and positioning an artifact-causing source point based on a CT imaging projection geometric principle by reversely tracing a spatial position relation. According to the method, boundary distortion features are identified by analyzing CT value profile curve form distortion features and local boundary curvature singularity features, geometric correction is performed on corresponding boundaries in an initial stone segmentation region according to the boundary distortion features, a final stone segmentation region is obtained, and the geometric accuracy and reliability of a segmentation result are effectively improved.

The invention discloses an abdominal multi-organ CT image automatic segmentation method based on deep learning. The method comprises the following steps: establishing a training sample set; constructing an improved encoder; an improved decoder is constructed; a PCE-TransUNet segmentation network model is established, and the PCE-TransUNet segmentation network model is Training the PCE-TransUNet segmentation network model by using the training set, and optimizing by using a joint loss function of cross entropy loss and Dice loss to obtain a trained PCE-TransUNet model; and inputting the test set into the trained PCE-TransUNet model, and outputting a segmented image by the PCE-TransUNet model. According to the method, partial convolution and an efficient channel attention mechanism are introduced, the ability of the model to extract image details is enhanced, the problem that feature extraction is insufficient in a traditional method is solved, and especially when small organs and complex boundaries are processed, the segmentation precision is remarkably improved.

The invention relates to an abdominal CT multi-organ segmentation method based on a LoRA vertical domain MedSAM large model. The method comprises the following steps: step 1, preprocessing an abdominal CT image supervised learning data set; step 2, constructing a feature selection network; step 3, constructing a LoRA layer; step 4, performing interlayer context reasoning by using a mixed prompt strategy to realize abdomen CT automatic segmentation; the method has the advantages that through multi-feature information fusion, dynamic context prompting and self-adaptive LoRA fine tuning, the precision and robustness of the MedSAM large model in the abdomen multi-organ CT segmentation task are improved, multi-feature information can comprehensively represent organ features, context information can be effectively utilized through dynamic context prompting, and the accuracy and robustness of the multi-organ CT segmentation task are improved. Limited training data can be effectively utilized by self-adaptive LoRA fine tuning; according to an image encoder based on a MedSAM large model, a learnable LoRA layer is added to each Transform layer so as to achieve efficient parameter training, and for a mask decoder of the MedSAM large model, the LoRA layers are also added to a self-attention layer and a cross-attention layer at the same time.

The invention discloses a swallowing function evaluation method and system based on tongue motion nuclear magnetic image registration, and belongs to the technical field of medical image processing. The system comprises a time sequence nuclear magnetic image reading module, a tongue body dynamic mask generation module, a tongue body dynamic image extraction module, a dynamic tongue body sequence registration module and a patient swallowing recovery evaluation module. Through an automatic segmentation and image registration technology, the system can accurately extract tongue motion displacement and calculate a local displacement vector, and evaluate the swallowing function recovery condition of a tongue cancer postoperative patient. The method comprises the steps of image reading, image screening, data set making, model training and tongue swallowing recovery evaluation, and the system can identify a tongue motion abnormal mode and provide an objective and quantitative evaluation result. According to the method, the accuracy and efficiency of tongue motion feature analysis are remarkably improved, and the method has a wide clinical application prospect.

The invention discloses a tumor image segmentation method and system of a multi-scale feature fusion network based on boundary enhancement, and relates to the technical field of image segmentation, and the method comprises the steps: obtaining a to-be-segmented tumor image; constructing a tumor image segmentation model based on a pyramid visual converter PVTv2 backbone network; training the tumor image segmentation model through the to-be-segmented tumor image and the known tumor image to obtain an optimal tumor image segmentation model; and acquiring a real-time to-be-segmented tumor image and inputting the real-time to-be-segmented tumor image into the optimal tumor image segmentation model to obtain a tumor image segmentation result. Aiming at the endoscope image segmentation of the kidney tumor, the kidney tumor in the endoscope image is efficiently, stably and automatically segmented through the boundary-enhanced multi-scale feature fusion network, clinical doctors are helped to provide accurate tumor area positioning in endoscopy and surgical operations, and compared with the most advanced method, the method has the advantages that the accuracy is high, and the efficiency is high. According to the method, better segmentation capability and stronger generalization capability are obtained.

The invention discloses a mandibular neural tube automatic segmentation method based on multi-view guidance, and relates to the technical field of oral medical treatment. Comprising the following steps: collecting original oral cavity CBCT image data, and performing preprocessing; sending the preprocessed image data into a mandible segmentation network, and segmenting a mandible region containing a mandible neural tube; a contrast enhancement technology is adopted for the segmented mandible area; projecting the processed mandible image along three orthogonal tangent planes of a coronal plane, a sagittal plane and a cross section; performing key point detection on the mandibular neural tubes on the three projection planes by using the trained key point detection network to obtain shape information of the mandibular neural tubes; and the features are combined with texture direction features to be input into a three-dimensional CBCT mandibular neural tube segmentation network, and accurate 3D segmentation is carried out. Two-dimensional missing space information is avoided, and mandibular neural tube segmentation is more complete and accurate.

According to various examples of the present disclosure, there is provided a machine learning image segmentation model for automatically identifying and segmenting structural features of a vessel tree from image frames. The model comprises a 3D encoder and 2D decoder, the 3D encoder and 2D decoder connected by at least one interlinked convolution node and a plurality of temporal extraction nodes therebetween. The model is configured to identify and segment structural features of a vessel tree from the plurality of image frames, by the model being configured to: receive a plurality of image frames as an input to the 3D encoder; provide an output of the 3D encoder as an input to the plurality of temporal extraction nodes to extract temporal information; generate, by the plurality of temporal extraction nodes, a 2D temporal output based on the extracted temporal information; provide the generated 2D temporal output to the at least one interlinked 2D convolution node and 2D decoder; generate, at the 2D decoder, a combined temporal output based on an output of the at least one interlinked 2D convolution node and at least one temporal extraction node, wherein the combined temporal output represents a predicted segmentation of the vessel; and generate an output representative of the segmented structural features of the vessel tree based on the predicted segmentation.

The invention belongs to the technical field of image recognition, and discloses a pelvic medical image automatic segmentation model based on global-local feature optimization. According to the model, an efficient non-local attention mechanism and a double attention mechanism are combined, global anatomical structure understanding and local fracture feature extraction are collaboratively optimized, and a three-level optimization strategy is adopted to achieve collaboration of anatomical constraint and pathological response. Specifically, the efficient non-local attention mechanism can enhance the global perception ability of the model and help the model to better understand a complex pelvic anatomical structure; and the double attention mechanism is helpful for the model to pay attention to details of a local area, such as changes of a fracture edge and a lesion area, so that the segmentation precision is improved. Meanwhile, according to the scheme, a mixed loss function combining label distribution perception loss and a surface supervision strategy is provided, the segmentation precision of an edge region is optimized through a guide network, the probability of missing detection and misjudgment is reduced, and then the robustness of the model in a complex pathological state is enhanced.

The invention belongs to the technical field of quality detection, and discloses an industrial visual identification method and system based on deep learning. The method comprises the following steps: constructing a high-quality welding image sequence through multi-angle image acquisition, multi-scale noise reduction optimization and welding spot feature enhancement processing; adopting adaptive feature extraction and cross-scale feature fusion technologies to generate a fusion welding feature tensor; the attention mechanism enhancement and automatic segmentation technology is utilized to realize accurate extraction of a welding spot area and microdefect enhancement identification; combining historical welding quality evaluation data to perform dynamic characteristic correlation analysis, and constructing a quality evaluation model; establishing a welding quality diagnosis strategy through multi-dimensional defect type identification and self-adaptive quality grade evaluation; and finally, dynamic quality prediction and real-time monitoring of the welding spot defects are realized. Accurate evaluation and real-time monitoring of the welding quality are achieved, and the quality cost and the rework rate are effectively reduced.

The invention provides a cervical cancer MRI image automatic segmentation method based on multi-modal fusion, and the method comprises the following steps: S1, obtaining tumor segmentation mask images of three modals T1c, T2 and DWI of a cervical cancer MRI image through an automatic prompt segmentation method, and carrying out the cross-modal attention interaction of a task token and an output token, dynamic alignment of medical image features and segmentation tasks is achieved, and segmentation mask images of all modes are generated in combination with sparse and dense prompts; and S2, performing registration and feature extraction on the segmentation mask images of the three modes to obtain a structured medical description of the segmentation mask image of each mode, and performing fusion processing on the structured medical descriptions by using a large language model to obtain a tumor segmentation mask image after multi-mode fusion. According to the method, the segmentation mask image of the MRI multi-mode image is fused by introducing the large language model, and the fused tumor segmentation mask image is finally obtained by combining the segmentation characteristics of different modes, so that the segmentation precision of the MRI image is greatly improved.

The invention provides a medical image automatic segmentation method and device based on a variational hybrid expert model, and relates to the technical field of medical image processing. The method comprises the following steps: acquiring a three-dimensional medical image, and inputting the three-dimensional medical image into a U-Net encoder for multi-level convolution, down-sampling feature extraction and adaptive dictionary enhancement operation to generate each level of enhanced feature map; inputting the enhanced feature map of the last level into a variational hybrid expert module to perform shared feature extraction, and outputting and fusing with dynamic routing selection results of a plurality of expert models to generate fused features; inputting the fused features and the enhanced feature map of the last level into a U-Net decoder for up-sampling operation, and splicing the output of up-sampling and the enhanced feature map of the current level step by step to recover the spatial resolution of the image to obtain decoded fused features; and inputting the decoding fusion feature into a single-channel convolutional layer, and outputting a segmentation result. According to the method, the accuracy and robustness of medical image segmentation and the adaptive capacity to the multi-modal medical image are effectively improved.

The invention provides a breast cancer recurrence risk prediction method, system and device based on an ultrasonic image, and relates to the field of intelligent medical treatment, the method uses a deep convolutional neural network to perform deep network feature extraction on a breast ultrasonic image, and uses a deep learning semantic segmentation algorithm to perform accurate positioning and automatic segmentation on a breast tumor region of interest, thereby improving the accuracy of breast cancer recurrence risk prediction. Meanwhile, habitat analysis is carried out on the ultrasonic images to extract tumor heterogeneity features, multi-level and multi-mode features such as deep learning features, radiomics features and habitat analysis features are fused, a breast cancer recurrence risk prediction model is constructed, breast cancer recurrence risk prediction is carried out, and a breast cancer recurrence risk assessment result is output. And a quantitative basis is provided for clinical treatment decisions. The accuracy and robustness of recurrence risk prediction are remarkably improved through multi-feature fusion, and standardization and objectification of breast cancer prognosis evaluation are achieved. In addition, the method further has the advantages of being easy and convenient to operate, low in cost, noninvasive, nonradiative, good in repeatability and the like.

The invention discloses a meniscus injury prediction method and system based on a neural network, and the method comprises the steps: obtaining a knee MRI image, carrying out the automatic segmentation of the knee MRI image based on a convolutional neural network, extracting a plurality of image features based on the segmented image, and obtaining a meniscus injury prediction result. And constructing a meniscus damage prediction model based on the SNN network model, and carrying out model training and verification. The meniscus injury diagnosis accuracy and diagnosis efficiency are improved, future injury risk prediction is achieved, valuable prediction information is provided for clinicians, prevention and treatment schemes are helped to be formulated, meanwhile, radiomics feature and load structure feature heat maps and a mixed attention mechanism are introduced, the clinical interpretability is enhanced, and the diagnosis accuracy and efficiency of meniscus injury are improved. And a full-automatic diagnosis process is realized.

The invention relates to the technical field of concrete structure damage detection, in particular to a post-fire RC structure burst damage three-dimensional segmentation method, which comprises the following steps: firstly, determining the type and three-dimensional characteristics of post-fire RC structure member surface concrete burst damage, and constructing a corresponding three-dimensional point cloud data set for network training and verification; and then based on a KP-FCNN network structure, a KPConv layer is improved and optimized, so that the detection and segmentation precision is improved, the model size is reduced, the reasoning time is remarkably shortened, the optimal segmentation precision of 82.3% is achieved under the working conditions of different damage degrees, automatic damage segmentation of the burst damage of the concrete structure after the fire disaster is realized, and the automatic damage segmentation of the burst damage of the concrete structure after the fire disaster is realized. And technical support is provided for subsequent damage three-dimensional quantification and deployment to an unmanned aerial vehicle system.

The invention relates to the technical field of computers, and discloses an automatic segmentation and intelligent plan generation method and device suitable for self-adaptive radiotherapy of prostate cancer. Comprising the following steps: acquiring medical image data of a treated object, clinical dose data of a target area and an organ at risk in a focus area of the treated object, and clinical treatment data of a preset priority level; performing automatic segmentation based on the medical image data to obtain target segmentation data; performing dose distribution prediction according to the target segmentation data to obtain initial dose distribution data, and performing iterative optimization on the initial dose distribution data by using clinical treatment data to obtain target dose distribution data of the treated object; and performing iterative optimization of a radiotherapy plan based on the target dose distribution data, and generating a target radiotherapy plan of the treated object. Therefore, on the basis of realizing accurate, efficient and automatic segmentation of the prostate cancer target region and the endangered organ, multi-round iterative optimization of dose distribution and the radiotherapy plan is carried out, and finally a high-quality target radiotherapy plan is obtained.

The invention discloses a handwritten element automatic segmentation and extraction method for a complex layout, relates to the technical field of handwritten element automatic segmentation and extraction, and aims to solve the technical problem that the recognition and separation precision of handwritten contents in a mixed image-text layout is insufficient. S201, a dynamic threshold segmentation algorithm is carried out; s202, context sensing connected domain analysis is carried out; s203, judging whether the elements are handwritten elements or not; s204, if the judgment result is yes, the handwriting region candidate is reserved; and S205, if not, filtering and eliminating. According to the method, the dynamic threshold segmentation algorithm and the context sensing connected domain analysis technology are cooperated, the segmentation threshold can be adaptively adjusted according to the pixel mean value and the standard deviation of the image local window through dynamic threshold segmentation, and the context sensing connected domain analysis is combined with the context information of the document to perform semantic analysis on the connected domain. The problem that the recognition and separation precision of the handwritten content in the mixed image-text layout is insufficient is solved.

The invention relates to the technical field of image segmentation, in particular to an anorectal focus automatic segmentation method based on deep learning, which comprises the following steps: acquiring an anorectal image pixel map, extracting contrast and direction offset to mark candidate focus points, screening overlapped marks to generate a focus activation mark map, and establishing a response map to generate a boundary response distribution map. And training the network to output a classification graph, and extracting a truncation path to complete image segmentation. According to the invention, through extracting the contrast value and the gradient amplitude of the local gray level co-occurrence matrix, accurate capturing of the spatial difference of the lesion area under a complex background is realized, through constructing a response map and direction consistency comparison mechanism and combining multi-dimensional features such as a direction gradient histogram and a structure tensor, the area discrimination capability and the edge classification precision are improved, and the accuracy of edge classification is improved. The texture stability is judged by means of anisotropic standard deviation, a fuzzy edge mask is set, truncation paths are screened in combination with a main direction vector included angle deviation trend, and continuity and stability of a boundary convergence position are ensured.

The invention relates to the technical field of crop monitoring, in particular to an automatic cell segmentation method for a crop remote sensing image based on geographic prior information. Comprising the steps that all images are determined to be in the same coordinate system through geographical registration, point cloud file conversion and ground specific point matching, and image registration is achieved; performing automatic segmentation or semi-automatic segmentation on the images determined in the same coordinate system to obtain a cell segmentation map of the multi-source crop remote sensing image; performing semi-automatic segmentation on an unplanted bare soil region and a region of crops with unknown growth vigor; aiming at a crop area with known growth vigor, carrying out batch full-automatic segmentation processing on the multi-source sensor image by adopting an improved Ground-SAM segmentation large model, and outputting a segmentation result; and carrying out optimization processing on the segmentation result, and finally outputting an optimized cell segmentation map of the multi-source crop remote sensing image. The method has the advantages of accurate registration, efficient segmentation, multi-sensor compatibility and automatic processing, and remote sensing monitoring is improved.

The invention provides an interactive pavement disease segmentation method based on a large model, and the method comprises the steps: constructing pavement disease segmentation models which comprise a disease detection network model, a disease initial segmentation network model and a disease segmentation large model, carrying out the offline training of the disease detection network model and the disease initial segmentation network model, and obtaining a disease segmentation model; performing fine adjustment on the disease segmentation large model; inputting the disease image into a pavement disease segmentation model, and detecting a disease area by using a disease detection network model based on a deep learning algorithm; based on a deep learning algorithm, performing disease initial segmentation on the disease areas by using the disease initial segmentation network model to obtain a disease initial segmentation result corresponding to each disease area, and automatically obtaining a disease positive prompt point and a disease negative prompt point; performing interactive correction on the automatically obtained disease positive prompt point and negative prompt point, and updating the positive prompt point, the negative prompt point and the frame; and based on the updated positive and negative prompt points and the frame, automatically segmenting the disease by using a disease segmentation large model to obtain a final segmentation mask.

The invention discloses a Crohn disease focus automatic segmentation and activity evaluation system based on deep learning, which belongs to the field of medical artificial intelligence and comprises a data preprocessing unit, a focus automatic segmentation unit, a radiomics feature extraction unit, a feature screening and dimension reduction unit and an activity classification unit. According to the method, an nnU-Net deep learning segmentation model is combined with image omics feature extraction, multi-stage feature screening and machine learning classification technologies, so that full-process automation from CTE image preprocessing, focus automatic segmentation, feature extraction and screening to activity classification is realized. The system can efficiently and accurately segment the focus of Crohn's disease, automatically assesses the disease activity based on the screened key radiomics characteristics, significantly improves the consistency, objectivity and efficiency of diagnosis, and is suitable for clinical auxiliary diagnosis and scientific research analysis.

The present invention provides a method for automatic segmentation of fundus blood vessels based on low-cost noise data, including: S1: screening the data set, obtaining retinal images and pixel-level blood vessel labels through publicly available data sets; S2: constructing a convolutional neural network to generate quantifiable noise data; S3: segmenting the data set to construct a training set and a test set, and at the same time retaining one clean image data in the training set and applying corresponding noise to other images; S4: setting a loss function and training parameters; S5: alternately inputting the clean image data and the noise data into the network, and updating the network parameters by using a reweighting function; S6: obtaining a retinal image and inputting it into the trained network model to output a segmentation result. The present invention realizes that only a small amount of clean data can correct the bias brought by incorrect noise to the deep model, and improves the accuracy of automatic segmentation of fundus blood vessels when facing low-cost noise data.

The invention discloses a semi-supervised medical image automatic segmentation method based on pseudo label optimization. The method comprises the following steps: step 1, preprocessing and dividing a data set; 2, constructing a semi-supervised training framework which comprises a pseudo label refining module, a triple loss module and a mutual correction framework; refining processing is carried out through an SLIC superpixel segmentation method and an information entropy voting mechanism; a triple loss function is controlled to be minimized; a mutual correction loss function is controlled to be minimized; step 3, constructing a supervision loss function based on the result of the supervision test; the total loss function convergence is controlled; and step 4, segmenting the verification set, and evaluating segmentation results based on two indexes of a Dice coefficient and an ASD average surface distance. According to the method, a semi-supervised training framework is constructed based on a pseudo-label refining module, a triple loss module and a mutual correction framework, the number of pseudo-labels is increased, the spatial consistency and accuracy of the pseudo-labels are improved, and the capture capability and segmentation precision of boundary information are optimized.

The objective of the invention is to provide a method for segmenting a colorectal cancer CT (Computed Tomography) image by introducing a 3DUNet network which separates heavy parameters and compresses an excitation structure (3D UNet with objective and auxiliary diagnosis) in order to solve the problem of diagnosis of colorectal cancer lesions by subjective factors, so that the objective and auxiliary diagnosis is realized, and the objective and auxiliary diagnosis can be realized, and the objective and auxiliary diagnosis can be realized, and therefore, the objective and auxiliary diagnosis can be realized, and the objective and auxiliary diagnosis can be realized, and the objective and auxiliary diagnosis can be realized, and the objective and auxiliary diagnosis can be realized, and the objective and auxiliary diagnosis can be realized. The invention provides a method for segmenting a colorectal cancer CT (Computed Tomography) image by introducing a 3D UNet network for separating heavy parameters and compressing an excitation structure. On the basis of a 3D UNet segmentation network, separation re-parameter convolution and a compression excitation structure are added into an encoder part, a decoder uses a transpose convolution mode to replace up-sampling and improve the resolution of a feature map, and the encoding-decoding part adopts jump connection for splicing; and constructing an automatic colorectal cancer focus segmentation system by using the optimized segmentation model, generating a focus segmentation result through data acquisition, data preprocessing, model reasoning and visualization processes, and assisting doctors in diagnosing focus boundaries.