320 results about "Automatic segmentation" patented technology

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 the cross technical field of computer vision and civil engineering, and discloses a deep learning-based bridge disease image segmentation method, which comprises the following steps of: establishing an image data set containing crack and spalling diseases and performing online enhancement; constructing a segmentation network model comprising a frequency dynamic convolution encoder branch, an edge enhancement Transform encoder branch, a gating cooperation unit, a decoder and a depth supervision module; training the model by using a weighted mixed loss function; and inputting the test set to obtain a final segmentation mask. Self-adaptive fusion of local texture features and global context information is realized through a dual-encoder architecture and a gating cooperation mechanism; a frequency dynamic convolution and edge enhancement module is utilized to enhance the anti-noise capability and micro-disease perception under a complex background; and in combination with a category weighting strategy, the problem of pixel category imbalance is effectively solved, and high-precision automatic segmentation of concrete bridge diseases is realized.

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 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 discloses a PET / CT head and neck tumor automatic segmentation method based on a fusion diffusion model, and the method comprises the steps: carrying out the preprocessing of input data, carrying out the extraction of exclusive features of a PET / CT image through CFE, carrying out the correction of the features through TAS through region / edge loss, carrying out the construction of a condition tensor through the corrected features and an original image, inputting DDPM, and carrying out the denoising of a condition, and generating a final segmentation result; according to the customized feature extraction, an exclusive extraction strategy is designed for PET metabolism and CT anatomical characteristics, the modal adaptation defect of a single encoder is made up, the pertinence and expressive power of cross-modal features are remarkably enhanced, task-oriented auxiliary supervision improves the segmentation precision through double constraints of region and edge loss, robustness is enhanced, and the segmentation efficiency is improved. A condition tensor is formed by cascading a PET / CT original image and customized features in an early channel to serve as diffusion trunk input, so that fine-grained clues are continuously transmitted in a fidelity manner in a diffusion link, small target information dilution and missing detection caused by late fusion are reduced, and the recall rate of small-size and weak-boundary lesions is increased.

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 invention relates to the technical field of digital medical treatment, and discloses a dental three-dimensional identification and model generation method based on CBCT and deep learning, and the method comprises the steps: carrying out the preprocessing of obtained CBCT image data; the preprocessed CBCT image data is segmented, and the segmentation step comprises the substeps that a tooth three-dimensional model, an alveolar bone three-dimensional model and a mandibular neural tube three-dimensional model are obtained by adopting a two-stage cascade deep learning network; based on the tooth three-dimensional model and the alveolar bone three-dimensional model, obtaining a periodontal membrane three-dimensional model through geometric and Boolean operation; a tooth root area in the tooth three-dimensional model is positioned, and a self-adaptive threshold method is adopted for CBCT image data corresponding to the tooth root area, and a root canal three-dimensional model is recognized and generated; based on at least one of the obtained three-dimensional models, a personalized clinical application model is generated, high-precision automatic segmentation of the dental complex anatomical structure is achieved, and a reliable digital model basis is provided for personalized precision medical treatment.

Disclosed is a computer-implemented method which encompasses registering a tracked imaging device such as a microscope having a known viewing direction and an atlas to a patient space so that a transformation can be established between the atlas space and the reference system for defining positions in images of an anatomical structure of the patient. Labels are associated with certain constituents of the images and are input into a learning algorithm such as a machine learning algorithm, for example a convolutional neural network, together with the medical images and an anatomical vector and for example also the atlas to train the learning algorithm for automatic segmentation of patient images generated with the tracked imaging device. The trained learning algorithm then allows for efficient segmentation and / or labelling of patient images without having to register the patient images to the atlas each time, thereby saving on computational effort.

The invention discloses an optic cup and optic disc segmentation method and system based on improved U-Net, and particularly relates to the technical field of medical image processing. The method includes: performing standardized preprocessing on an eye fundus image; the U-Net model is optimized and improved, and an improved model LFM-Net is obtained; the improved model LFM-Net comprises a multi-scale feature enhancement aggregation module and a trans-attention feature fusion module; the multi-scale feature enhancement aggregation module is used for capturing feature information of different scales, and the trans-attention feature fusion module is used for realizing fusion of features of an encoder and a decoder; and inputting the preprocessed eye fundus image data set into the improved model LFM-Net for training, and realizing automatic segmentation of an optic cup and an optic disk in the eye fundus image by using the trained model. According to the invention, by enhancing multi-scale feature expression and optimizing feature fusion efficiency, the problem of insufficient segmentation precision under complex conditions such as blurred optic cup and optic disc boundaries and irregular shapes is effectively solved.

The invention discloses a structured information extraction method and system based on a large language model, and the method comprises the following steps: carrying out the modular cue word design and adaptive loading, so as to guide the large language model to carry out the content generation according to the expected structure and logic; inputting text type identification and task routing to ensure that each type of information can be processed by adopting the most appropriate model prompt strategy; automatic segmentation and concurrent processing are carried out to ensure information integrity and processing efficiency; semantic completion and key information enhancement are carried out to carry out semantic completion on the entity information; performing structured format conversion and standard packaging to output a standardized format; and performing exception processing and full-process log recording to perform real-time tracking and backtracking on the state of each processing task. According to the method, the key information in the text can be automatically recognized, extracted and output in a structured mode, and the information processing efficiency and accuracy are improved.

The application discloses a kind of nnUNet zebra fish juvenile whole brain vascular system segmentation methods based on autonomous data set training, it is related to high-resolution imaging technology, image processing and medical image segmentation field, the method makes full use of zebra fish live transparency and fluorescent label advantage, obtains high-resolution whole brain three-dimensional vascular image data, and constructs high-quality segmentation truth value database by semi-automatic segmentation and artificial correction, training is carried out using nnU-Net deep learning model, realize the three-dimensional automatic segmentation of zebra fish brain vascular system signal.The application method significantly improves the degree of automation and precision of image segmentation, effectively solves the problems of low efficiency, high artificial dependence and poor repeatability of traditional brain vascular segmentation.The method is suitable for large-scale high-throughput data processing, can provide efficient, standardized image processing scheme for zebra fish brain vascular development mechanism and brain vascular disease model research, and has wide application prospect.

The invention provides an industrial material segmentation and size measurement method based on deep learning. The method comprises the following steps: acquiring a to-be-processed industrial material image; inputting the image into the trained segmentation network model, and outputting to obtain a pixel-level segmentation mask; the segmentation network model is a hybrid network based on a U-Net architecture, a pre-trained ResNet50 is adopted by an encoder of the segmentation network model, and a convolutional block attention module (CBAM) is fused in jump connection between the encoder and a decoder; transforming the pixel-level segmentation mask to an aerial view space by using a perspective transformation matrix obtained by pre-calibration to obtain a corrected mask; in the aerial view space, geometric features of the corrected mask are calculated, and the physical size of the material is obtained through conversion according to a preset proportional scale. The device has the beneficial effects that high-precision and automatic segmentation and size measurement of industrial materials can be realized.

The invention relates to the field of three-dimensional vision, in particular to a label-free three-dimensional point cloud segmentation method based on a visual large model, which comprises the following steps: acquiring three-dimensional point cloud data, and extracting a boundary point set according to the three-dimensional point cloud data in combination with curvature and normal vector to construct a target function; solving the objective function by using an optimization algorithm, selecting an optimal projection visual angle combination, and extracting two-dimensional features of all two-dimensional projection images and three-dimensional features of three-dimensional point cloud data by using a visual large model; performing consistency matching on the two-dimensional features and the three-dimensional features through a matching algorithm to obtain a plurality of matching results; acquiring a definition weight factor and a coverage rate weight factor to calculate an importance weight; fusing the two-dimensional features according to the weight factors to obtain overall fused two-dimensional features; and inversely mapping the integrally fused two-dimensional features to a three-dimensional space to realize three-dimensional point cloud unmarked segmentation. The three-dimensional point cloud segmentation method has the effect of realizing three-dimensional point cloud automatic segmentation without labels.

The invention discloses a pulmonary interstitial image analysis method and system based on clinical prior guidance feature fusion, and the method comprises the steps: obtaining chest CT images of a user at a plurality of time points and corresponding clinical data, and carrying out the data preprocessing and region segmentation; performing feature extraction on the automatically segmented chest CT image and the corresponding clinical data by using specific indexes; specific time points are coded into time embedding vectors, total image feature vectors are projected to the same dimension as the time embedding vectors through a linear layer, and time coding fusion is generated; the most relevant CT image follow-up visit time points are actively'inquired 'and'weighted' by using clinical risk factors, time sequence image feature fusion is carried out, and fusion features after weighted fusion are output; and carrying out progress probability calculation by using the fusion features, predicting the progress risk in the next one year according to the calculation result, and realizing dynamic time sequence feature selection driven by clinical priori knowledge.

The invention relates to a method, a device, equipment and a storage medium for automatically segmenting a vehicle journey to a return stroke, and the method comprises the steps: obtaining the journey data of a vehicle in a current journey process after the current journey of the vehicle is completed; according to position changes and time intervals of adjacent records in the travel data, parking point identification is carried out, and a parking point set is obtained; determining a stroke segmentation point according to a linear distance between a parking point in the parking point set and a starting point in the stroke data; segmenting the stroke data according to the stroke segmentation points to obtain a segmentation result; the segmentation result comprises a forward travel track and a return travel track; by acquiring the travel data of the vehicle after the current travel is completed, recognizing the parking point by combining the position change and time interval dual features, and recognizing the travel segmentation point based on the linear distance to realize travel segmentation, the problem that the traditional method depends on manual judgment and the segmentation deviation is caused by neglecting the actual parking behavior in the prior art is solved.

The invention discloses a real-time medical image segmentation method and system, and the method comprises the steps: carrying out the pre-training processing of a basic model in a self-supervised learning mode, and enabling the basic model to learn domain invariant features from inter-frame dependence based on the time series data input of a medical image sequence; the multi-scale feature knowledge of the basic model is migrated to the lightweight detection model through feature distillation operation, and the feature distillation operation is configured to be based on a feature alignment mechanism, and fine features are not lost during knowledge transfer; and automatically generating segmentation prompt information by using a lightweight detection model, inputting the prompt information as spatial guidance into a segmentation model, driving the segmentation model to output a pixel-level result, and constructing an end-to-end flow workflow without manual intervention. According to the invention, through organic combination of self-supervised pre-training, feature distillation and automatic prompt generation, end-to-end automatic segmentation is realized.

The invention relates to the technical field of medical image processing and three-dimensional reconstruction, and particularly discloses a reconstruction and analogue simulation method based on a cardiac image. The method comprises the following steps: firstly, preprocessing an input CT or MRI medical image, and automatically segmenting a heart multi-tissue structure by using an nnUNetv2 model, including a plurality of anatomical regions such as atrium, ventricle, myocardial tissue and blood pool; and then performing topology repair, smoothing processing and label resampling on the segmentation result to obtain a three-dimensional label body with a continuous structure and a complete boundary. And based on the optimized tag body, constructing a heart three-dimensional surface model by adopting a Marching Cubes algorithm, and generating a multi-material volume grid suitable for finite element analysis. According to an electrode position and a radio frequency parameter set by a user, a radio frequency ablation simulation model based on a Pennes biological heat conduction equation and an Arrhenius model is established, a temperature field and a tissue thermal damage range are calculated, and a simulation result is displayed in a three-dimensional mode in an overlapping mode. According to the method, the integrated process from medical image automatic segmentation to heart three-dimensional reconstruction and thermal simulation is realized, the segmentation precision, the modeling efficiency and the simulation reliability are improved, and the method can be applied to application scenes such as surgical planning, preoperative evaluation and medical teaching.

The invention relates to the technical field of medical image processing and deep learning crossing, and discloses a congenital heart disease whole heart segmentation method based on text guidance. According to the method, based on a U-Net architecture, a text-image alignment module is added between different levels of jump connections, and semantic information in report texts and CT image features are subjected to feature semantic alignment and fusion layer by layer; a multi-scale image feature fusion module is added between adjacent levels of the encoder, and the feature extraction capability of the encoder on each substructure is improved through mask adaptive fusion weight; a text-driven multi-level segmentation supervision module is added to a decoder part, and a segmentation result is guided and optimized by using semantic features, so that a constructed deep learning network effectively understands heterogeneity features of a congenital heart disease structure, and the structure distinguishing capability of a fuzzy boundary is enhanced; automatic segmentation of the congenital heart disease whole heart structure can be achieved, and effectiveness and accuracy of congenital heart disease whole heart segmentation are improved.

The invention discloses a gesture recognition method fusing continuous frame segmentation and spatial features. The gesture recognition method comprises the steps that three-dimensional coordinates of hand joint points are obtained through Mediape; performing dual normalization processing to eliminate size and position differences; extracting point cloud convex hull features, joint point distance features and specific triangularization area combination features; fusing a plurality of types of features and then training a Transform or GCN model; carrying out automatic segmentation on the continuous gesture sequence based on double cosine similarity thresholds; and inputting the segmented stable paragraphs into the model to realize real-time identification. The method provided by the invention has high precision and strong robustness in a complex scene, and is suitable for the fields of man-machine interaction, intelligent control and the like.

The invention belongs to the technical field of image processing, and particularly relates to a geological disaster risk area dynamic updating method based on slope unit automatic segmentation. Comprising the following steps: 1, acquiring digital elevation model raster data covering a target area and remote sensing image raster data spatially aligned with the digital elevation model raster data, and outputting slope unit vector data; 2, acquiring disaster-bearing body vector data, performing spatial superposition on the disaster-bearing body vector data and the slope unit vector data, and combining outer boundaries of slope units of all geological disaster risk areas to generate risk area vector boundary data; 3, generating new year risk area vector boundary data based on the new year data; and updating the risk area vector boundary data of the last year based on the risk area newly-added area and the risk area reduced area. According to the method, the slope unit division precision, the disaster-bearing body exposure description capability and the timeliness of risk area range updating are remarkably improved.

The embodiment of the invention discloses an automatic image segmentation method and device based on semantic segmentation and superpixel fusion, and the method comprises the steps: carrying out the image feature extraction of a target image, carrying out the semantic region division through a semantic segmentation module, and outputting a tongue region target image after region division; the method comprises the following steps: inputting a target image of a tongue region into a clustering engine for iterative calculation to obtain a super-pixel block set, setting a segmentation threshold value, performing pixel proportion calculation on the target image of the tongue region to determine a target affiliation category of the super-pixel block, and determining affiliation division of a tongue edge in the target image of the tongue region; according to the embodiment of the invention, semantic segmentation and pixel clustering are fused, an approximate tongue region is firstly positioned, and then the edge of the tongue is finely corrected, so that the edge blurring of pure semantic segmentation is avoided, and the semantic deviation of pure super-pixel segmentation is solved; meanwhile, a low segmentation threshold value is set to solve the under-segmentation problem of an edge fuzzy region, and the whole process is automatic without manual intervention.

The invention provides a driving skill evaluation system and method based on scene mode automatic segmentation, and relates to the technical field of driving skill evaluation, the system can automatically divide a complete driving process into typical working condition segments such as a curve and a straightway based on a high-precision map and an actual driving track, and the driving skill evaluation efficiency is improved. Targeted skill analysis in different scenes is supported; by calculating scores of multi-dimensional subdivision indexes such as speed basis, safety basis, operation intensity, vehicle dynamics, control precision and comfort, all aspects of driving behaviors are comprehensively reflected; more importantly, the system can dynamically adjust the weight of each index according to the evaluation purpose set by the user, so that the evaluation system has high configurability, personalized and objective skill evaluation for different driving targets is realized, and the scientificity, accuracy and practicability of the evaluation result are improved.

An existing liver tumor automatic segmentation method is insufficient in expression in small focus, low-contrast edge and long-range space dependence modeling, and consequently high false positive and boundary deficiency are caused. Pure CNN is limited by a receptive field, pure Mama easily loses local details, multi-level attention stacking significantly increases parameter quantity, and traditional side supervision differential correction is difficult to accurately focus an uncertain area. The invention provides an end-to-end network, parallel ResNet and Mamba dual-coding and direct reaching a decoder after AFF fusion at the same scale, bottom features are accessed to a multi-scale feature fusion module to complete deep semantic enhancement, and a decoding side forms a GARS module concentration boundary difficult-to-distinguish pixel by matching an MSCB-EUCB-LGAG lightweight chain with four-stage Gaussian attenuation residual self-correction. Clinical level, the method can significantly reduce leak detection of small tumors, reduce false positive, and maintain geometric integrity of edges.

The invention belongs to the technical field of computer vision, and discloses an unmanned aerial vehicle building outer wall crack adaptive segmentation method based on deep learning, which comprises the steps of collecting an outer wall image in a process that an unmanned aerial vehicle flies along a building facade, and synchronously obtaining space reference information corresponding to the outer wall image; based on the spatial reference information, establishing a spatial reference relationship corresponding to the building facade for the outer wall image; basic image correction processing is performed on the outer wall image, and self-adaptive adjustment is performed on the contrast ratio and noise suppression parameters of the outer wall image according to the surface material and texture feature difference of the outer wall; depth feature coding of crack analysis is executed according to the adjusted outer wall image, and in the coding process, crack structure sensing features containing prior information of a crack structure are formed through adaptive modeling of the slender shape, direction consistency and cross-regional continuity characteristics of the crack; the automatic segmentation and detection of the external wall crack with high precision, good continuity and spatial positioning are realized.

This invention discloses an automatic segmentation and scoring method and system for FDG PET-CT lesions in lymphoma, belonging to the field of medical image analysis technology. It aims to improve the segmentation accuracy of lymphoma lesions and the objectivity of the Deauville score. First, standardized uptake values ​​are calculated for FDG PET images, and lymph node morphological features are extracted from CT images based on multi-scale Hessian enhancement filtering to construct a dual-modality PET-CT image pair. Then, a dual-channel depth network is used to extract anatomical structural features and metabolic distribution features respectively. Cross-modal gating fusion is used to suppress physiological uptake interference, outputting preliminary lesion segmentation results. Next, three-dimensional connected component analysis is performed on the segmentation mask, and metabolic heterogeneity index is extracted by combining kurtosis and Haar wavelet multi-scale energy. A graph attention network is used to identify key lesions. Finally, the ratio of key lesions to standardized liver uptake values ​​is combined with the metabolic heterogeneity index to correct the Deauville score, achieving automation from lesion detection to treatment efficacy evaluation.

The application discloses a fiber bundle automatic segmentation and quantitative labeling method for white matter abnormalities of Parkinson's disease, and belongs to the technical field of medical image processing. The application solves the problem that the existing technology relies on manual delineation or traditional machine learning methods for white matter abnormality detection, and has the problems of low efficiency and strong subjectivity. By setting a first threshold value and a second threshold value, not only can the abnormal fiber bundle be identified, but also the required threshold range can be selected according to different research purposes and clinical needs, so that reliable judgment results can be provided in both diagnosis and early screening. If both threshold values are selected, the method can comprehensively judge each parameter of each fiber bundle, so as to more accurately identify the white matter abnormal fiber bundle of the Parkinson's disease patient, improve the accuracy of the fiber bundle labeling result of the white matter abnormalities of Parkinson's disease, realize the function of high-precision positioning of the white matter abnormal fiber bundle of Parkinson's disease, and provide stronger support for clinical diagnosis.

The invention discloses a small sample abdomen multi-organ image segmentation method based on a prototype network and cross attention. The method comprises the following steps: firstly, preprocessing an abdominal computed tomography (CT) image, and completing resampling and intensity normalization; dividing the preprocessed image into a support set and a query set, and constructing a small sample segmentation task; a support image and a query image are input into a deep learning network model, a cross attention module is introduced into a multi-layer structure of an encoder to explicitly model foreground, background and boundary regions, interaction and fusion among different level features are enhanced, and pixel-by-pixel matching and distinguishing of support prototype and query features are realized in combination with a double-branch contrast learning structure. According to the method, a cross attention mechanism is introduced into multiple layers of the encoder, the correlation and boundary expression ability between the features are effectively enhanced, the discrimination and robustness of the model under the small sample condition are further improved through a double-branch contrast learning structure, and therefore under the condition that labeling data is limited, the accuracy and robustness of the model are improved. And efficient and automatic segmentation of multiple organs of the abdomen is realized.