107 results about "Breast fluid" patented technology

The invention discloses a Mama-based spectrum dynamic fusion and double-attention enhancement medical image segmentation method, which comprises the following steps of: firstly, constructing a Mama integrated spectrum domain and attention pyramid module, fusing spectrum dynamic characteristics and a self-attention pooling mechanism, and performing frequency domain information compensation and local characteristic enhancement to obtain a spectrum dynamic fusion image; the spatial correlation loss caused by image blocking processing is relieved; secondly, designing a layered enhanced U-shaped architecture, deploying an MISAP module in a shallow layer of an encoder to capture multi-scale global context features, introducing a bipolar routing attention mechanism in a deep layer, and dynamically allocating sparse attention weights to focus a key pathological region; according to the method, the segmentation precision of complex edge textures and tiny lesions in medical images can be remarkably improved, and the Dice coefficient in breast tumor, polyp and abdominal organ segmentation tasks is averagely improved by 6.5%.

Disclosed is a system for detecting whether the breast cancer is benign or malignant based on multiple modalities, which comprises: an ultrasonomics model configured to extract breast tumor position information and breast tumor morphological features on the basis of an acquired grayscale breast ultrasound image, perform global interactive fusion on the breast tumor position information and breast tumor morphological feature information, and convert a Transformer encoder-based feature output into an output vector of the corresponding classification dimensions by means of a fully connected layer; a metabonomics model configured to obtain a metabolic fingerprint spectrogram and analyze the metabolic fingerprint spectrogram on the basis of a metabolic database and a predetermined significantly differential metabolite to obtain abnormal metabolic pathways, signal transduction pathways, and related biochemical reactions associated with breast cancer malignancy; and a detection module configured to perform joint modeling, based on the breast tumor position information, the breast tumor morphological features, and a peak value of the significantly differential metabolite of the breast cancer malignancy, to output a prediction result about whether the breast cancer is benign or malignant.

The invention discloses a breast ultrasound image processing method and device, a terminal, a storage medium and a computer program product, and the method comprises the steps: carrying out the data preprocessing of a breast ultrasound image sub-data set, obtaining a breast ultrasound image sample, and dividing the breast ultrasound image sample into a training set and a test set; the method comprises the following steps: constructing a segmentation network model by fusing an OfficientViT encoder, a symmetric U-Net decoder and a CBAM attention enhancement module, and designing a joint loss function; based on the joint loss function, training the segmentation network model by using the training set to obtain a segmentation network training model; and testing the segmentation network training model by using the test set, and optimizing the segmentation network training model according to a test result to obtain a breast tumor region segmentation model. According to the scheme, the breast tumor region segmentation model is set by fusing the codec, the CBAM attention enhancement module and the joint loss function, and the breast tumor region can be accurately segmented from the breast ultrasound image.

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 relates to the technical field of breast cancer detection based on multi-modal input, in particular to a breast cancer detection method and system based on multi-modal input. The method comprises the following steps: acquiring breast tumor original clinical data, including breast X-ray image data, medical history text data and clinical index data; preprocessing the obtained original clinical data of the breast tumor; performing feature extraction on the preprocessed breast tumor original clinical data; performing feature fusion on the extracted features to form a fusion feature vector; and performing breast cancer category classification by using the fusion feature vector. According to the application, the related information of the breast cancer is more comprehensively captured by fusing three types of multi-modal input data of the past medical history, the mammary gland X-ray and the clinical data of the patient. According to the multi-modal fusion method, the advantages of different types of data can be fully utilized, richer information is provided, and therefore the accuracy and reliability of detection are improved.

The invention relates to a breast tumor lesion part ultrasonic image segmentation method based on an SAM-VMama model. The method comprises the steps of obtaining a breast ultrasonic image set and performing preprocessing; the method comprises the following steps: constructing an SAM-VMama model, wherein the SAM-VMama model comprises a first encoder, a second encoder, a prompt encoder and a mask decoder; obtaining a trained model; obtaining a preprocessed breast ultrasound image to be segmented; and obtaining a segmentation result of the breast lesion tumor. According to the method, the local features are extracted through the first extraction, the global features are extracted through the second encoder, the interactive prompt information processed by the prompt encoder is combined, and the precise segmentation mask is generated through the mask decoder; the method not only retains the flexibility of SAM interactive segmentation, but also improves the long-sequence data processing capability and calculation efficiency through a Mamba structure, effectively adapts to the characteristics of uneven gray scale, multiple artifacts and the like of the ultrasonic image, and achieves the balance of high precision and high efficiency.

The invention relates to a multi-modal image fusion breast tumor diagnosis method and device, equipment and a medium. The method comprises the following steps: acquiring a multi-modal image of a subject, and performing spatial registration processing to obtain a multi-modal image group; the multi-modal image group comprises a molybdenum target image, a B ultrasonic image and an elastic ultrasonic image; performing modal sensitive feature extraction on each modal of the multi-modal image group to obtain molybdenum target image features, B ultrasonic image features and elastic ultrasonic image features; carrying out fusion processing on the molybdenum target image features, the B ultrasonic image features and the elastic ultrasonic image features to obtain global fusion features; performing breast tumor prediction according to the global fusion features to obtain a prediction result; the prediction result comprises the breast tumor focus existence probability and the breast tumor focus type. By adopting the method, cross-modal semantic alignment can be realized while original information of each modal is reserved, and the capability of discriminating a complex breast tumor focus is enhanced through fusion discrimination.

The invention belongs to the technical field of microbial fermentation, and particularly relates to a lactobacillus rhamnosus fermentation composition, a preparation method and application of the lactobacillus rhamnosus fermentation composition in the aspects of improving the tumor cell induced inflammation level and preventing and inhibiting breast tumors. The invention provides a lactobacillus rhamnosus fermentation composition. The lactobacillus rhamnosus fermentation composition is prepared from a raw material and lactobacillus rhamnosus NKU ML1-2, the raw materials comprise raspberry, poria cocos, cape jasmine, rehmannia, liquorice and orange peel. The lactobacillus rhamnosus fermentation composition has the effects of nourishing yin and clearing heat, soothing liver and regulating qi, and strengthening spleen and stomach. Results of embodiments show that the lactobacillus rhamnosus fermentation composition can prevent proliferation, invasion and migration of breast cancer tumor cells to a certain extent, and has an improvement effect on the level of inflammation induced by the tumor cells.

This invention relates to the field of optical imaging and detection technology, specifically providing a broadband snapshot-type polarization interferometry imaging detection system and method for breast tumors. A broadband light source illuminates a breast tumor tissue sample. The reflected signal light is collected and collimated by a pre-optical system, then sequentially passes through a first and a second ray shaping unit for two shearing and two polarization state transformations, resulting in two beams of linearly polarized light and two beams of circularly polarized light. These beams are imaged by an imaging lens to an area array detector to obtain a polarization interferogram, which is then demodulated to obtain all Stokes parameters of the breast tumor tissue sample. This invention achieves broadband snapshot imaging of breast tumors with all Stokes parameters without using an analyzer, doubling the light throughput compared to traditional polarization imaging instruments using analyzers. Furthermore, this invention has advantages such as compact structure, no moving parts, easy assembly and adjustment, and no need for image registration.

The invention provides a high-precision lightweight breast ultrasonic tumor detection method based on Improved-YOLOv8, and the method comprises the steps: obtaining a breast ultrasonic image, carrying out the preprocessing, and obtaining a preprocessed image; performing dynamic data enhancement to obtain an enhanced image; a fast network Faster Net and a self-adaptive wavelet down-sampling layer AWFD are introduced, a backbone network AWFD-Faster Net of an Improved-YOLOv8 network extracts features of an enhanced image, and then three image features are output to a fusion network Fusion; the fusion network Fusion carries out feature fusion on the input image features and then outputs three fusion features to the detection head network Head; the detection head network Head outputs an ultrasonic breast tumor detection result; the method has the advantages of short operation time, high calculation efficiency, high detection precision and the like, and meanwhile, the method is small in network parameter quantity and low in calculation complexity.

The invention discloses a mammary gland ultrasonic video tumor segmentation method and device based on spatial-temporal feature fusion, and aims to realize accurate mammary gland tumor segmentation. The method comprises the following steps: S1, preprocessing breast ultrasound video data, dividing the data into a training set, a verification set and a test set, and processing the data set into breast ultrasound continuous frames; s2, extracting initial features of the breast ultrasonic continuous frames through down-sampling; s3, constructing a Transform module, and extracting global features of the breast ultrasonic video data; s4, constructing a spatial feature extraction module, and extracting spatial features of the initial features; s5, constructing a time feature extraction module, and extracting time features of the initial features; s6, constructing a multi-scale feature fusion module, and performing feature fusion on the time features, the spatial features and the global features to obtain final features; and S7, performing up-sampling on the final features to obtain a breast tumor segmentation map. The method can effectively improve the segmentation precision of the breast tumor, and can be used for tumor segmentation of the breast ultrasonic video.

This invention discloses a medical image segmentation method based on inverse residual attention and multi-scale context. The method inputs the medical image to be segmented into an improved RAS-UNet segmentation network model. This model introduces an inverse residual attention module at the bottleneck feature of the deepest layer of the encoder, which suppresses background through an inverse weighting mechanism and enhances attention to blurred boundaries and weak response regions. Simultaneously, a hollow spatial pyramid pooling module is introduced into the decoding path, utilizing a parallel multi-branch structure to fuse multi-scale contextual information to adapt to lesions or anatomical structures of different sizes. Skip connections between the encoder and decoder achieve efficient fusion of detailed and semantic features. This invention can significantly improve the accuracy and boundary accuracy of segmenting medical targets such as polyps, breast tumors, and the hippocampus, providing a reliable tool for clinical auxiliary diagnosis.

This invention discloses a hydrogel for tumor treatment based on improving the tumor microenvironment to trigger gas therapy combined with chemotherapy, belonging to the field of biomedical technology. The hydrogel drug delivery system utilizes lipopolysaccharide (LPS) to induce local inflammatory stimulation, thereby altering the tumor microenvironment of breast cancer and promoting nitric oxide (NO) production. The NO donor arginine (L-Arg) and the chemotherapy drug doxorubicin (DOX) are transported using sodium alginate (ALG), achieving combined gas therapy and chemotherapy to inhibit breast tumor growth. The drug delivery system of this invention not only enhances the effect of chemotherapy but also simultaneously achieves precise drug delivery and reduces drug dosage. The preparation method of the drug delivery system of this invention is simple, safe, and without toxic side effects, showing promising application prospects in tumor treatment and possessing significant clinical value.

The application discloses a medical hollow tube positioning and marking device and belongs to the technical field of breast tumor marking. The device comprises a head, a fixing ring, an inner core, a hollow flexible tube and a needle cylinder. The fixing ring is fixed at intervals on the hollow flexible tube to form a long chain. The head is fixed at the head end of the long chain to form a marking body. The inner core penetrates into the hollow flexible tube to the head end to push the marking body to move in the needle cylinder. The front end of the needle cylinder is provided with a needle part. After puncture, the needle cylinder and the inner core are used to push the head outward and the marking body is pushed out and positioned. The marking body exposed outside is cut off. Multi-directional marking is used to form stereoscopic, linear and visual positioning. The marking body can be freely bent and is not easy to be cut off and displaced. The risk of infection or accidental injury caused by a traditional positioning steel wire is reduced. Breast cancer patients receiving neoadjuvant chemotherapy only need to be positioned and marked once and do not need to bear the secondary trauma of steel wire positioning again after traditional marking clamp marking.

The present invention discloses a breast tumor cutter, comprising a gripping sleeve, a rotating structure mounted at the rear end of the gripping sleeve, a grasping and cutting structure disposed within the gripping sleeve, the gripping sleeve comprising a sleeve and a movable sleeve, the rotating structure comprising a sleeve column and a rotating seat, and the grasping and cutting structure comprising a straight rod, a plurality of clamping rods, and a cover. The present invention utilizes the rotating structure and the grasping and cutting structure disposed within the gripping sleeve. After peeling back a breast flap and finding the tumor, the rotating seat can be rotated to cause the head end of the clamping rod to pull the cover, deforming the cover and placing it over the tumor. At this point, the grasping and cutting structure can be rotated to cause the cutting head at the head end of the clamping rod to cut along the edge of the tumor, achieving rapid cutting, a complete cutting surface, and a clear cutting edge.

The invention discloses a medical image segmentation method and system based on SAM fine tuning and automatic prompt generation, and belongs to the field of medical image processing, and the method comprises the steps: employing a pixel-level feature adapter to enhance the feature representation of a medical image, and then employing low-rank adaptation LoRA to carry out the efficient fine tuning of parameters of an SAM image encoder; secondly, an automatic bounding box generator based on a Transform decoder is designed, and a target bounding box is directly regressed from image features to serve as a space prompt; and finally, constructing a two-stage mask decoder, in the first stage, generating a coarse segmentation mask by using the frozen native SAM decoder in combination with the bounding box prompt, and in the second stage, inputting the coarse mask as an additional prompt into a trainable decoder for fine segmentation, and outputting a final result. According to the method, full-automatic and high-precision medical image segmentation is realized, and the segmentation performance on various medical images such as skin lesions, breast tumors and lung nodules is remarkably improved while the original architecture advantages of the SAM are reserved.

The invention relates to the field of target grading and classification, and discloses a breast tumor grading method and device based on an ultrasonic radio frequency signal and a medium, and the method comprises the steps: obtaining a breast tumor ultrasonic original echo signal; performing multi-mode feature extraction on the original echo signal to obtain a multi-mode feature; processing the multi-mode features by adopting a dynamic feature gating unit DFG to obtain enhanced multi-mode features; and inputting the enhanced multi-mode features into a gated multi-mode Transform unit GMT for processing, and obtaining a breast tumor grading result. According to the method, the five-classification precision of 3, 4A, 4B, 4C and 5 levels of (BI-RADS) can be improved, deployment is convenient, and the classification efficiency is improved.

This invention relates to a method for precise localization of breast tumors based on multi-level double-layer coding, comprising the following steps: acquisition of scattered microwave signals; signal processing and feature construction; multi-level data label coding based on a breast model containing the tumor target: each level contains double-layer coding, the first layer of coding is coarse-grained localization, and the second layer of coding is fine-grained localization; the localization interval of the initial level is determined based on the breast model containing the tumor target; given the constraints of the termination coding, the localization interval of the next level is determined based on the current level's localization interval after data label double-layer coding; model training and coding prediction output.

The invention provides a breast cancer ultrasonic image segmentation method and system, and relates to the technical field of image processing, and the method comprises the steps: obtaining an original breast ultrasonic image; performing data enhancement processing on the original breast ultrasound image; a breast tumor segmentation model is constructed, and the breast tumor segmentation model comprises an MGM encoder module, a multi-scale cross attention module, an edge feature refining module and an EMCAD decoder module which are connected in sequence; inputting the original breast ultrasound image after data enhancement processing into the breast tumor segmentation model, and training the breast tumor segmentation model; acquiring a real-time breast ultrasonic image; and inputting the real-time breast ultrasonic image into the trained breast tumor segmentation model, and outputting a final segmented image. The method depends on a multi-module collaborative architecture, fuses multi-scale semantic features, accurately refines tumor edges, and greatly improves tumor segmentation precision and edge positioning accuracy.

This invention discloses a medical image segmentation method based on enhanced attention. The method acquires a medical image, preprocesses it, and inputs it into an encoder to output a multi-scale feature map of the medical image. The encoder includes N cascaded multi-dimensional attention modules. Each multi-dimensional attention module extracts multi-scale features through dual-channel convolution and residual connections, and performs feature recalibration using an attention enhancement module. The output multi-scale feature map is then fused by a multi-scale dilated fusion attention module to obtain the feature map output by the encoder. The feature map output by the encoder is input to the decoder, where it is combined with high-resolution feature maps of the corresponding levels passed from the encoder via skip connections. Through progressive upsampling and feature fusion, a reconstructed feature map is obtained. The reconstructed feature map output by the decoder is used to generate a medical image segmentation mask through 1×1 convolution and a sigmoid activation function to complete the segmentation of diseased tissues. This invention significantly improves the boundary segmentation accuracy for knee joints, breast tumors, and skin lesions.

The application provides a breast cancer patient lymph node metastasis prediction model without clinical pathological characteristics, comprising the following steps: after three-dimensional reconstruction of two-dimensional lung enhanced CT films, an axillary lymph node atlas is established, all axillary lymph nodes in the atlas are selected as ROI regions, and more than 5 combined image features of each axillary lymph node are selected to distinguish whether breast cancer has axillary lymph node metastasis; and a logistic regression machine learning prediction model is used to construct the breast cancer patient axillary lymph node metastasis prediction model. The model established by the application can non-invasively predict whether breast cancer has axillary lymph node metastasis, the clinical pathological characteristics of the patient are not included in the model, and the image cutting in the model is not based on breast tumors, but based on axillary lymph nodes; the model is used to determine a suitable axillary treatment scheme, thereby avoiding unnecessary axillary surgery and complications, and helping to carry out more accurate surgery and adjuvant therapy mode of breast cancer.

The utility model relates to the technical field of treatment bed protection, in particular to an anti-toppling safety device for emergency evacuation of a breast tumor radiotherapy bed, which comprises a fixed block, a driving mechanism, a pushing mechanism and a protection mechanism, the fixed block is provided with the driving mechanism, the pushing mechanism and the protection mechanism, and the protection mechanism comprises a sliding part. A sliding piece slides on the fixed block, a limiting groove is formed in the sliding piece, a limiting piece is slidably connected to the interior of the sliding piece, a fixed piece sliding with the fixed block is fixedly connected to the limiting piece, an elastic piece is clamped between the limiting piece and the sliding piece, and a disconnecting groove is formed in the limiting piece; by means of the structure, it can be avoided that due to misoperation, the columns of the treatment bed are clamped, and overturning of the treatment bed is affected, the treatment bed can be smoothly overturned to the treatment device during overturning and cannot be blocked, and treatment is facilitated.

The invention discloses a mammary gland tissue characterization method and device, a medium and a product, and relates to the field of mammary gland tissue analys.The method comprises the steps that RF signals, envelope signals and B-mode signals corresponding to sections of a mammary gland cross section, a sagittal plane and a coronal plane are determined according to mammary gland three-dimensional data; generating a corresponding B-mode image according to the determined B-mode signal of each tangent plane; inputting the B mode images of all sections into an ROI detection model to obtain a tumor ROI region; the ROI detection model comprises a tumor B model edge detection model, a tracking module and an ROI generation module; based on the tumor ROI region, extracting RF signals, envelope signals and B-mode signals corresponding to the cross section, sagittal plane and coronal plane regions of interest from the mammary gland three-dimensional data; and inputting the extracted signal into a tumor tissue analysis model to obtain a tumor tissue characterization result. According to the invention, the searching efficiency and the positioning accuracy of the breast tumor can be improved, and the quantitative analysis of the tumor tissue characteristics is realized.

The application discloses a low-temperature freezing rotary cutting device and a rotary cutting system for breast tumor diagnosis. The outer tube outer layer and the outer tube inner layer are arranged on the fixing member, and a sampling groove is formed by the slot opening and the sealing structure. The inner tube and the inner cutting blade are arranged in the outer tube inner layer. The sealed cavity formed between the outer tube outer layer and the outer tube inner layer is divided into an expansion cavity and a backflow cavity. The air inlet structure is arranged to extend into the expansion cavity to output the refrigerant. The outer tube outer layer is provided with an insulating material layer to isolate the cold energy transmission. The tumor tissue is sucked into the sampling groove under negative pressure. The refrigerant is released into the expansion cavity through the air inlet structure to expand and cool. The cold energy is transmitted to the sampling groove through the outer tube inner layer to freeze the tumor tissue, so that the original biological elasticity is lost. Then, the tissue is rotary cut by the inner cutting blade on the inner tube, and the cutting efficiency and the sampling efficiency are improved.

Provided herein is a method for detecting a tumour that can be applied to cell-free samples, to cell-free detect circulating tumour DNA. The method utilizes detection of adjacent methylation signals within a single sequencing read as the basic positive tumour signal, thereby decreasing false positives. The method comprises extracting DNA from a cell-free sample obtained from a subject, bisulphite converting the DNA, amplifying regions methylated in cancer (CpG islands, CpG shores, and / or CpG shelves), generating sequencing reads, and detecting tumour signals. To increase sensitivity, biased primers designed based on bisulphite converted methylated sequences can be used. Target methylated regions can be selected from a pre-validated set according to the specific aim of the test. Absolute number, proportion, and / or distribution of tumour signals may be used for tumour detection or classification. The method is also useful in, predicting, prognosticating, and / or monitoring response to treatment, tumour load, relapse, cancer development, or risk.

The invention relates to the technical field of medical treatment, in particular to a preparation method of injectable BiOCl (at) CuOF127 (at) rGO thermosensitive hydrogel for superficial tumor treatment, which comprises the following steps: pretreating raw materials, preparing BiOCl nanosheets by a solvothermal method, washing and drying for later use; according to the manufacturing method of the injectable BiOCl (at) CuOF127 (at) rGO thermosensitive hydrogel for superficial tumor treatment, the injectable BiOCl (at) CuOF127 (at) rGO thermosensitive hydrogel is embedded into injectable, conductive and thermosensitive hydrogel composed of PluronicF127 (F127) and reduced graphene oxide (rGO), the injectable BiOCl (at) CuOF127 (at) rGO thermosensitive hydrogel is used for combined treatment of breast cancer, remarkable ROS outbreak and effective breast cancer cell ablation are induced through in-vitro and synergistic therapy, toxicity to normal cells is minimum, and the injectable BiOCl (at) CuOF127 (at) rGO thermosensitive hydrogel can be applied to in-vivo and in-vivo treatment of breast cancer. In-situ breast tumors treated with US + NIR show obvious fading, proliferation and angiogenesis reduction, apoptosis and immunogen cell death pathway activation and good biocompatibility, an accurate and minimally invasive strategy is established, piezoelectric catalysis and photo-thermal conversion are combined, and the in-situ breast tumors are used for effective breast cancer treatment.

The application relates to the technical field of nursing, in particular to a breast tumor postoperative nursing belt which comprises two protective belts, an inflation mechanism is arranged between the two protective belts, the lower edge of each protective belt is connected with an extension belt, the front surface of the extension belt is fixedly connected with a soft belt, the upper edge of the front surface of the soft belt is fixedly connected with a hard plate, a sliding opening is arranged in the front surface of the hard plate, a connecting seat is slidably connected to the inner side of the sliding opening, an elastic sheet is arranged at the rear end of the connecting seat, pulling mechanisms are arranged at the two sides of the front surface of the elastic sheet, and a binding mechanism is arranged at the side away from each other of the two protective belts. The drainage tube is led out from the rear of the elastic sheet, the problem that the drainage tube is squeezed can be avoided, the drainage is ensured, when the protective belt is inflated, the rear end of the elastic sheet is well limited, and the elastic sheet is prevented from being easily slid and displaced in the later use.

The invention discloses a breast ultrasound image segmentation method and device based on semantic perception, and the method comprises the steps: obtaining an ultrasound image of a patient, constructing a semantic perception breast tumor segmentation network of the ultrasound image, employing an encoder to capture the global structure information of the ultrasound image, employing a semantic perception block to extract low-level features from the global structure information, and carrying out the segmentation of a breast tumor. A plurality of decoders combine the global structure information with the low-level features to generate an optimized breast tumor segmentation result, and the decoders combine the global structure information extracted by the encoders with the low-level detail features acquired by the semantic perception module to finally generate an optimized segmentation result. An output result is ensured to have context accuracy and keep boundary accuracy, the network adopts an efficient U-shaped network architecture and fuses deep convolution and jump connection, different scale changes can be flexibly coped with, meanwhile, additional calculation overhead is avoided, and the method is suitable for large-scale application. Therefore, the effectiveness and robustness of breast tumor segmentation of the breast ultrasound image are improved.

The present invention belongs to, but is not limited to, the fields of medical imaging and artificial intelligence technology, and discloses a method and system for classifying benign and malignant breast tumors based on contrastive learning; in the pre-training stage, a self-supervised learning strategy based on contrastive learning is used, and by designing a comprehensive contrast loss function, the samples are finely divided in combination with the physiological information of the breast tumor, so that the model can effectively extract discriminative features from limited labeled data; a multi-view data enhancement method is used to enhance the diversity of the training set through image data at different angles, effectively improving the generalization ability of the model. In the fine-tuning classification stage, a three-branch network structure is used to process near-infrared images and time series images at different wavelengths respectively, and a feature fusion module is designed to fuse multiple signal information. This fine-tuning stage specifically targets the spatiotemporal signal characteristics in the optical image data set, enhancing the model's sensitivity to tumor characteristics, and is particularly outstanding in the detection of early small tumors.

The invention relates to the technical field of tumor prediction, in particular to a breast tumor growth trend prediction method and system based on big data, and the method comprises the following steps: obtaining a breast voxel sequence mark mutation region, carrying out the clustering recognition of an extension path, analyzing a density trend screening direction, positioning a diffusion hot spot region, and carrying out the modeling to generate a three-dimensional growth dynamic map. According to the method, through mutation point identification and multidirectional intersection analysis, the spatial identification capability of density variation of the mammary gland tissue is enhanced, a structural path with a stable growth trend is accurately extracted in combination with direction consistency clustering, a forward screening mechanism is introduced to perform density difference trend analysis, directivity expression in the direction of a path terminal is improved, and the accuracy of the density variation of the mammary gland tissue is improved. A diffusion hot spot area is positioned through direction included angle consistency calculation, the space focusing capacity of the diffusion trend is enhanced, a dynamic trend map is formed through three-dimensional track construction, visualization, continuity and resolution of the directional expansion trend of the breast tumor are enhanced, and prediction precision and space expression capacity are improved.