244 results about "Breast tumor" 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%.

The invention discloses an MRI medical image segmentation method and system based on deep learning, and the method comprises the steps: obtaining a mammary gland MRI image, carrying out the standardization processing of the mammary gland MRI image, and removing a non-region of interest to obtain a target MRI image; performing detail enhancement on the suspected lesion area to reconstruct an image to be preprocessed; performing noise reduction processing, contrast enhancement and edge enhancement preprocessing on the to-be-preprocessed image to generate three versions of input images, and inputting the three versions of input images into a pre-trained deep learning model as three channels to complete breast tumor identification; and carrying out image segmentation on the breast tumor region, and classifying segmented breast tumors. According to the MRI medical image segmentation method and system based on deep learning provided by the invention, accurate and efficient processing of the mammary gland MRI image is realized, efficient identification, accurate segmentation and accurate classification of the mammary gland tumor are realized, the accuracy and robustness of mammary gland tumor detection can be improved, and efficient and reliable auxiliary diagnosis is provided for clinic.

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 discloses a breast tumor benign and malignant identification system based on a double-branch attention distillation network, belongs to the field of medical image processing, and particularly relates to the breast tumor benign and malignant identification system based on the double-branch attention distillation network. The invention aims to solve the problem that the existing method based on deep learning is insufficient in feature extraction capability and cannot accurately focus a lesion area. The system comprises an ultrasonic image preprocessing main module used for preprocessing collected breast ultrasonic images, obtaining ultrasonic imaging areas, unifying the image size of the obtained ultrasonic imaging areas, obtaining preprocessed breast ultrasonic images, and taking the preprocessed breast ultrasonic images as a training set; the double-branch convolutional neural network main module is used for building a double-branch attention distillation network model; the model training main module is used for obtaining a trained double-branch attention distillation network model; and the model test main module is used for loading the trained double-branch attention distillation network model and classifying breast ultrasound images to be diagnosed.

The invention discloses a method and a system for visually identifying hemodynamic spatial-temporal heterogeneity in breast tumors, and belongs to the technical field of medical image acquisition and auxiliary detection. The method for visually recognizing the hemodynamic spatial-temporal heterogeneity in the breast tumor comprises the steps that S1, DCE-MRI images of breast benign and malignant tumors are obtained, and region-of-interest sketching is carried out; s2, carrying out TIC automatic classification and coding on each voxel in the tumor by adopting 19 types of TIC curves to obtain a TIC color coding graph; s3, calculating the TIC type and proportion of each focus, and extracting a TIC color coding map to reflect radiomics characteristics of tumor internal heterogeneity; s4, screening the image omics characteristics of the TIC color coding image, and establishing three models including 19 types of TIC curve fusion models; according to the method, the difference of hemodynamics time and space heterogeneity in the breast tumor of the patient can be visually judged and compared, and benign and malignant and biological behaviors of the tumor of the patient are judged.

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 discloses a breast tumor accurate segmentation method based on a space-time fusion network, which adopts the space-time fusion network fusing convolution, LSTM and PK feature fusion to capture space and time features at the same time so as to improve segmentation precision and enhance medical interpretability, and introduces LSTM into each layer of an encoder of the space-time fusion network to capture sequence dependence, so that the segmentation precision is improved. And the model can learn the mode in the whole dynamic enhancement process. In addition, parameters of the classic PK model are fused into network input and training processes, so that the medical interpretability of the model is improved. By comprehensively utilizing a deep learning framework of DCE-MRI spatio-temporal dynamic information and radiomics characteristics, high-precision segmentation of breast tumors is realized, and medically interpretable tumor characteristics are provided, so that doctors can make more accurate diagnosis and treatment plans based on segmentation results.

A breast tumor marker based on a serum protein, used for carrying out serum measurement on suspected breast tumor patients, and effectively distinguishing healthy people, breast nodule patients, and breast cancer patients. A serum protein spectrum classifier has, in an independent verification queue, an accuracy of 0.87, a precision of 0.93, a recall of 0.82, and an F1-score of 0.86. The area under the ROC curve for benign nodule patients is 0.96, the area under the ROC curve for breast cancer patients is 0.96, and the area under the ROC curve for healthy people is 0.96. The marker has high accuracy and good specificity, and has a good application prospect in clinical diagnosis of breast lesions.

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.

Described herein are gene signatures providing prognostic, diagnostic, treatment and molecular subtype classifications of cancers through genomic and epigenomic profiling, Methods and compositions for determining cancer and subtypes, including breast cancer are described and specific and sensitive detection of biomarkers of interest is provided. Such biomarkers are indicative of disease pathogenesis, which provides opportunity for selection of treatment, including treatment regimes directed at identifying candidates for responsiveness and overcoming resistance mechanisms.

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 relates to a breast tumor segmentation method based on a multi-modal ultrasonic image, which aims to solve the problems that artifacts and low-echo regions are easily wrongly recognized as tumors and the tumor boundary segmentation precision is low in the existing breast ultrasonic image segmentation technology, and comprises the following steps of: 1, acquiring a B-type ultrasonic image and a strain elastic image which are paired, and constructing a multi-modal breast ultrasonic image data set; 2, constructing a multi-modal image segmentation model algorithm based on feature correction alignment and boundary uncertainty enhancement; 3, training a multi-modal image segmentation model based on feature correction alignment and boundary uncertainty enhancement by adopting a five-fold cross validation mode, and storing model parameters with optimal performance; and 4, loading optimal model parameters, performing reasoning prediction on images in the verification set, calculating evaluation indexes on the verification set, and comparing the evaluation indexes with other current advanced algorithms. The method can effectively improve the segmentation precision of the breast tumor in the ultrasonic image, and improves the accuracy of network prediction. The invention belongs to the field of computer vision, deep learning and medical image segmentation.

The invention provides an accurate breast tumor segmentation method based on a multi-scale and multi-task fusion UNet model. The method comprises the following steps: (1) obtaining an original tumor medical image and a corresponding tumor region label, and adjusting the size of the original tumor medical image and the corresponding tumor region label; (2) performing Z-Score standardization and random rotation on the tumor image for image enhancement, and dividing a training set, a verification set and a test set according to a proportion of 7: 2: 1; (3) segmenting a target, namely a region of interest; (4) establishing an MTF-UNet model, wherein the MTF-UNet model comprises a multi-branch encoder, a branch self-attention network ADF module and a tumor element prediction auxiliary branch (EPB); (5) training an MTF-UNet model; and (6) adjusting hyper-parameters of the model to further optimize the performance of the model. According to the method, the segmentation of the small target can be enhanced, the generalization ability of the model is improved, the diversity and comprehensiveness of the fused features can still be kept, and the data demand is reduced on the premise that the segmentation performance is not reduced.

The invention belongs to but not limited to the technical field of medical images and artificial intelligence, and discloses a breast tumor benign and malignant classification method and system based on comparative learning. In the pre-training stage, a self-supervised learning strategy based on contrast learning is used, a comprehensive contrast loss function is designed, and in combination with physiological information of breast tumors, a sample is finely divided, so that the model effectively extracts discriminant features from limited annotation data; a multi-view data enhancement method is adopted, and the diversity of a training set is enhanced through image data at different angles, so that the generalization ability of the model is effectively improved. In the fine tuning classification stage, a three-branch network structure is adopted to respectively process near-infrared images and time sequence images under different wavelengths, and a feature fusion module is designed to fuse various kinds of signal information. The fine tuning stage enhances the sensitivity of the model to tumor characteristics especially aiming at the characteristics of space-time signals in an optical image data set, and especially has outstanding performance in early small tumor detection.

The invention provides a system for medical image processing, a medium and computer equipment. The system comprises an image preprocessing module, an image convolutional network module, a convolutional neural network module and a multi-modal feature fusion module. The image preprocessing module performs morphological operation on the tumor core area of the first image to obtain a second image; the graph convolutional network module outputs a first feature vector integrating information of a tumor core region and information of a peritumor neighborhood region; the convolutional neural network module performs convolution to extract deep features of the image to obtain a second feature vector; performing feature fusion on the first feature vector and the second feature vector to obtain a first output and a second output, and determining a final tumor identification result by the first output and the second output through a multi-layer perceptron. According to the system disclosed by the invention, the input breast ultrasonic image is subjected to image processing, and judgment is carried out based on related characteristics of a tumor core region and a peritumor neighborhood region, so that benign and malignant types of breast tumors are divided.

The invention relates to a method for extracting two tocopherol derivatives A and B from epimedium sagittatum and application of the two tocopherol derivatives A and B, which can effectively solve the problem of preparing the tocopherol derivatives A and B from the epimedium sagittatum and realizing the application of the tocopherol derivatives A and B in preparing anti-breast tumor drugs, and the method comprises the following steps: crushing the overground part of the epimedium sagittatum, carrying out reflux extraction with ethanol, carrying out reduced pressure recovery to obtain an extract, extracting, and carrying out chromatographic separation to obtain the two tocopherol derivatives A and B; and carrying out gradient elution, reduced-pressure recovery, thin-layer point plate detection, merging, purification, collection of fractions within retention time, and drying to obtain the product. The raw materials are rich, the preparation method is easy to operate, the obtained product is good in quality and good in use effect, the pharmaceutical composition can be effectively used for treating breast cancer, application in preparation of anti-breast cancer drugs is achieved, the medicinal value and commercial value of epimedium sagittatum are developed, and the pharmaceutical composition has remarkable economic and social benefits.

The present disclosure provides methods, systems, and devices for coregistering imaging data to form three-dimensional superimposed images of target such as a tumor or a surgical bed. A three-dimensional map can be generated by projecting infrared radiation at a target area, receiving reflected infrared radiation, and measuring depth of the target area. A three-dimensional white light image can be created from a captured two-dimensional white light image and the three-dimensional map. A three-dimensional fluorescence image can be created from a captured two-dimensional fluorescence image and the three-dimensional map. The three-dimensional white light image and the three-dimensional fluorescence image can be aligned using one or more fiducial markers to form a three-dimensional superimposed image. The superimposed image can be used to excise cancerous tissues, for example, breast tumors. Images can be in the form of videos.

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 provides an ultrasonic breast tumor image segmentation method based on hierarchical cross correlation learning. The method comprises the following steps: performing multi-stage feature extraction on an ultrasonic image; performing alignment and fusion processing on the multi-stage representation features of the ultrasonic image, and performing tumor boundary feature learning in combination with a residual structure; performing alignment and fusion processing on the multi-stage representation features of the ultrasonic image, and performing enhancement and learning by using a residual structure; and performing association modeling on the fused multi-scale tumor boundary features and the fused multi-scale tumor segmentation features by using a hierarchical cross attention mechanism, and performing decoding in combination with the enhanced tumor segmentation features to obtain a tumor segmentation prediction map. According to the invention, the boundary sensing fusion module is utilized to explicitly strengthen the sensing ability to the tumor boundary area in the feature learning process, so that the problems of fuzzy boundary and inaccurate positioning in the traditional method are significantly relieved, and the fineness and coherence of tumor contour extraction are improved.

The present invention discloses a terahertz image breast tumor detection method based on SAM and curriculum learning. In order to accurately locate and identify tumors from terahertz breast images, the present invention applies the visual basic model SAM to tumor detection and constructs a dual-branch tumor detection network, in which one branch uses the target detection model DETR to perform coarse-grained tumor detection on terahertz breast images and generate mixed prompts, including bounding boxes and categories, where the categories are used as text prompts, and then input them into the SAM branch for fine-grained tumor detection. In addition, the present invention adopts the idea of ​​curriculum learning and sends terahertz breast tumor image data sets from easy to difficult into the dual-branch tumor detection network in batches for training to obtain better detection results.

The invention discloses a postoperative rehabilitation management method for a breast tumor patient and related equipment. The method comprises the following steps: sending an exercise rehabilitation initialization instruction to a target patient under the condition that the intelligent wearable equipment monitors that the operative limb of the target patient is in a natural sagging state; under the condition that the target patient completes the exercise rehabilitation initialization instruction, positioning a shoulder joint on the operative limb side of the target patient based on a movement track collected by an intelligent wearable device; under the condition that the target patient carries out the operation limb movement rehabilitation, the operation limb movement pose of the target patient is predicted through the intelligent wearable device based on the obtained shoulder joint positioning of the target patient, so that movement rehabilitation management is carried out. The multiple problems that postoperative rehabilitation of breast tumors is a key link in continuous treatment, but at present, patient cognition is insufficient, medical resources are not evenly distributed, a rehabilitation path is not clear, and informatization support is insufficient can be solved.

The invention provides an ultrasonic breast tumor recognition method and device based on prior anatomical knowledge and a medium, and the method specifically comprises the steps: firstly segmenting an original breast ultrasonic image through a segmentation algorithm model, and carrying out the morphological processing of a segmentation result, thereby obtaining a breast region image; then performing channel synthesis on the original ultrasonic image and the breast region image to obtain a fused image, and finally performing breast tumor detection on the fused image by using the optimized target detection algorithm model. The interference of a non-tumor area can be greatly reduced through a prior knowledge mask image and original image fusion preprocessing mode, and the false positive rate of tumor recognition is reduced. Meanwhile, a target detection algorithm is improved by using large-scale convolution and programming gradient information, tumors of different scales and peripheral information can be better obtained, and the tumor detection effect is improved.

According to the breast cancer prediction model construction system based on the MRI image and the storage medium provided by the invention, the model for predicting the neoadjuvant chemotherapy pathological alleviation condition and prognosis of the breast cancer patient is constructed by combining the dynamic change of the blood vessel characteristics and the clinical pathological characteristics, so that the system has relatively high accuracy and clinical practicability, and is suitable for popularization and application. And making of an individualized adjuvant therapy scheme is facilitated. The method can early predict breast pathology remission and long-term prognosis, and can early and accurately predict neoadjuvant chemotherapy curative effect and long-term prognosis of breast cancer patients. The model predicts whether a patient can achieve complete relieving of breast pathology or not by analyzing changes of breast tumor blood vessel characteristics in the chemotherapy process and correlation with clinical factors, and further predicts the recurrence-free lifetime of the patient, so that a reference basis is provided for individualized treatment.

The invention relates to the field of deep learning, in particular to a three-dimensional breast ultrasound image semi-automatic segmentation method based on a fine-tuning large model, which comprises the following steps of: preprocessing acquired to-be-segmented three-dimensional breast ultrasound image data, and inputting an SAM-Med3D model fine-tuned based on a low-rank fine-tuning strategy to realize semi-automatic segmentation of a breast tumor, and a customization module MLoRA is embedded in each 3D attention block of the 3D image encoder of the SAM-Med3D model. According to the method, the customization module based on the low-rank fine tuning strategy is applied to the SAM-Med3D model, and a doctor is simulated to click an ABUS image lesion area, so that semi-automatic segmentation of the breast tumor is realized, the segmentation capability of the SAM-Med3D model for the three-dimensional ABUS image is effectively improved, and the segmentation efficiency of the SAM-Med3D model is improved. Therefore, the problems of lack of ABUS image training data, high training cost and semantic confusion of an existing medical image segmentation large model are solved.

The invention discloses a marker SKP1 for predicting the curative effect of breast cancer immunotherapy and application of the marker SKP1, and belongs to the technical field of tumors. Through bioinformatics analysis of gene expression of triple-negative breast cancer compared with other types of breast cancer, the gene SKP1 which is highly expressed in breast cancer and closely related to prognosis is screened out, the gene SKP1 can be used as a novel breast tumor molecular marker, and the high expression of the gene SKP1 predicts poor prognosis of tumor. The expression quantity of the SKP1 in the breast cancer is higher than that of para-carcinoma cells, and the SKP1 is related to immune cold tumors and is also in negative correlation with a biomarker of BrCa immunotherapy, so that a new target spot is provided for diagnosis, prediction and treatment of the breast cancer; the invention further discloses application of the marker SKP1 for predicting the breast cancer immunotherapy curative effect in preparation of a detection kit for identifying breast cancer cells and predicting breast cancer.

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.