41 results about "Mammary gland mass" patented technology

The invention provides a mammary gland mass image recognition method and device. The method comprises the steps that a mammary gland magnetic resonance image to be recognized is acquired; Inputting the mammary gland magnetic resonance image to be identified into a constructed mammary gland mass identification model to obtain a mass identification result in the mammary gland magnetic resonance image to be identified; Wherein the lump recognition model adopts a deep full convolutional neural network model; wherein the coding process of the deep full convolutional neural network model adopts a basic convolutional module in the U-shaped convolutional neural network model to perform feature extraction, and the decoding process of the deep full convolutional neural network model adopts dense connection to perform size unification on to-be-fused feature maps and then perform fusion. According to the embodiment of the invention, automatic recognition of the breast lumps is realized, and the recognition accuracy of the breast lumps is improved.

The invention relates to the technical field of Chinese medicaments, and in particular relates to a Chinese medicament for treating hyperplasia of mammary glands. The Chinese medicament consists of the following raw material drugs by weight: 10g of Chinese angelica, 12g of hemlock parsley, 12g of raw rehmannia, 12g of red peony root, 12g of white peony root, 10g of Chinese thorowax root, 12g of turmeric root-tuber, 10g of green tangerine peel, 10g of cowherb seed, 10g of tangerine leaf, 10g of cochinchnese asparagus root, 12g of trichosanthes kirilowii maxim, 10g of szechwan Chinaberry fruit, 10g of common burreed rhizome, 6g of poria, 10g of rhizome cyperi, 20g of dandelion. The Chinese medicament can eliminate breast mass and reinforce resistance, and has the advantages of convenience in taking, easy absorption, quick response, good curative effect and low price. Clinical application observation indicates that 75 patients are treated, and the effective rate is 94.7 percent.

The invention belongs to the technical field of image processing, and discloses a breast cancer image recognition method based on multi-stage multi-feature deep fusion, and the method comprises the steps: extracting the Gist, SIFT, HOG, LBP, VGG16, ResNet and DenseNet features of an image from multiple angles of shape, texture and deep learning; deeply mining cross-modal pathological semantics contained in different features; performing feature fusion through early fusion, middle fusion and post fusion; constructing a multi-stage multi-feature fusion model integrating early fusion, middle fusion and post fusion; and classifying, identifying and processing the breast lumps and outputting a processing result. According to the method, traditional features and deep learning features of mammography images are extracted, cross-modal pathological semantics among different features are deeply mined, and a multi-stage multi-feature fusion strategy is designed to complete breast cancer image recognition. Meanwhile, the dimensionality of the core features is compressed to improve the real-time efficiency of the diagnosis model.

An electric impedance scanning-projecting imaging method for early diagnosis of breast mass includes such steps as creating an equivalent model of the current field in breast tissue on the basis of electric field disturbing principle in uniform dielectric, applying the driving electric field to the electrode array on the surface of breast and upper extremities, detecting the current distubance caused by breast mass and the current distribution on electrode array, and expressing the 2D image of breast mass in grayscale mode.

The present invention relates to a Chinese medicine capsule preparation for curing hyperplasia of mammary glands with obvious and stable therapeutic effect. The Chinese medicine capsule preparation is made up by using 13 Chinese medicinal materials of bupleurun root, cyperus root, sargassum, kelp, frankincense and others through the processes of grinding, decocting, mixing, drying and capsulizing to obtain the finished product.

The invention discloses an X-ray breast mass image automatic classification method. According to the invention, an automatic classification network for the X-ray breast mass image is designed from theperspective of image processing; according to the network, firstly, two computing paths are used for carrying out convolution and downsampling operation on an X-ray breast mass image by using convolution kernels of different sizes, convolution feature maps of different scale types are extracted, the feature maps input by the two computing paths are superposed and fused, and feature information obtained after double computing paths are fused is obtained. Feature extraction is carried out on the fusion features by using a full convolutional network, and finally the extracted features are sent to a Softmax classification layer to classify the features, and a breast mass image classification result is obtained. A model is trained by using a membership-based objective function suitable for X-ray breast mass image classification, and a new objective function enhances the generalization ability of the model by increasing the membership degree of a breast mass sample and a category to which the breast mass sample belongs and reducing the membership degree of the breast mass sample and a non-category to which the breast mass sample belongs, so that the classification accuracy is improved.

The invention relates to a mammary gland lump image processing and classifying system which comprises a mammary gland X-ray machine used for shooting mammary gland X-ray photography images; an image preprocessing module used for preprocessing the mammary gland X-ray photography images; a breast area extraction module used for extracting breast area images in the preprocessed mammography images; and a lump detection and classification module used for carrying out lump position detection and benign and malignant classification on the breast area images by a DIoU-YOLOv3 target detection network.By implementing the mammary gland lump image processing and classifying system, the target detection network can be adopted to automatically detect and classify benign and malignant breast lumps, so that compared with manual film reading, speed is high, the efficiency is high, and accuracy rate is high.

The invention relates to an X-ray auxiliary diagnosis technology, and aims to provide a mammary gland lump segmentation method based on a cross attention mechanism. The method comprises the steps: making a data set; preprocessing a cross attention mechanism; constructing a deep convolutional neural network; adjusting the pre-training weight distribution of the image network data set; adjusting pre-training weight distribution by utilizing a data preprocessing result, and training a deep convolutional neural network; and reasoning the X-ray image to be detected by using the deep convolutional neural network. According to the method, the model is quickly trained by using the cross attention mechanism, and the network can select the lump features from the MLO position and the CC position through the cross attention mechanism so as to learn and adjust the cross attention weight value. Compared with the conventional method for judging the lump only from the CC position or the MLO position,the lump on the mammary gland X-ray image can be rapidly, efficiently and automatically segmented, the detection rate and accuracy of the lump in the mammary gland X-ray image are improved, and the method has higher practical application and popularization value.

The embodiment of the invention discloses a mammary gland molybdenum target image segmentation method and device, a terminal and a storage medium, and the mammary gland molybdenum target image segmentation method comprises the steps: obtaining a mammary gland molybdenum target image, and adjusting the contrast of the mammary gland molybdenum target image according to the pixel value of the mammarygland molybdenum target image; inputting the contrast-adjusted mammary gland molybdenum target image into a pre-trained image segmentation model, so as to output a pre-segmented image of the breast region according to the image segmentation model; and performing region filling and / or elimination processing on the pre-segmented image to obtain a target segmented image of the breast region. By adjusting the contrast of the mammary gland molybdenum target image, the difference between a background region and a foreground region (a breast region and a non-breast tissue region) can be highlighted;pre-segmentation of a breast region in the mammary gland molybdenum target image can be realized through a pre-trained image segmentation model; and by performing region filling and / or elimination processing on the pre-segmented image, the breast segmentation precision can be improved, and front-end display and subsequent breast lump and calcification research are facilitated.

The invention provides a mammary gland X-ray image automatic generation method based on a convolutional generative adversarial network, and the method comprises the following steps: 1, carrying out the preprocessing of an inputted original image, removing the redundant background in the image, and adjusting the proper size to enable the lump and mammary gland background of a lump region to be segmented; step 2, constructing a convolutional generative adversarial network model which comprises a generative network G, a discriminant network D and a pre-trained discriminant network D-pro; 3, pre-training the convolutional generative adversarial network, and storing trained model parameters as initialization parameters of the convolutional generative adversarial network; 4, generating an image;and step 5, fusing the breast lump image and the breast background generated in the step 4 based on medical features. According to the mammary gland X-ray image automatic generation method based on the convolutional generative adversarial network provided by the invention, lump images with different morphologies and sizes are generated by adopting a thought of firstly segmenting, then generatingand then fusing, and a multi-lump mammary gland image is generated based on the single-lump mammary gland images, so that data support is provided for research of a multi-lump mammary gland diagnosistechnology.

The invention discloses a breast lump benign and malignant judgment method and equipment. The method and the equipment relate to an image processing field, the method comprises the following steps: acquiring a mammography image; and pre-treating it, obtaining a mammography image to be detected; inputting the mammary gland X-ray photographic image to be detected into a target detection positioningnetwork for target detection positioning to obtain a mammary gland lump position, inputting the detected mammary gland X-ray photographic image of the mammary gland lump into a target classification network for shape prediction and edge prediction, and meanwhile obtaining a classification result of the corresponding breast cancer lump. The method is based on semantic description features corresponding to characterization features of breast lumps. Through the target classification network, benign and malignant judgment on the breast lumps in mammography is realized, and weighted fusion is performed on the probability scores of the attributes according to the target classification network to obtain a final breast lump benign and malignant judgment result, so that the judgment accuracy and the detection efficiency are improved.

The invention relates to a method and a device for judging whether a breast mass is benign or malignant. The method comprises the following steps of obtaining a plurality of first image characteristics of a to-be-detected breast mass; calculating characteristic distances between the first image characteristics and second image characteristics of sample images of the breast mass respectively; according to the number of the sample images with characteristic distances smaller than a first preset value, judging whether the breast mass is benign or malignant. According to the embodiment mode of the invention, the method and the device for judging whether the breast mass is benign or malignant are used for performing quantitative analysis on images of the to-be-detected breast mass, and extracting the mass images with characteristics similar to those of known benign or malignant masses, so that a predicted value of inquiring whether the mass is benign or malignant is provided for clinical reference.

The embodiment of the invention provides a mammary gland lesion detection method and device, and the method comprises the steps: building the corresponding relation between the image features of a mammary gland image and a mammary gland lesion region through the self-learning capability of an artificial neural network; obtaining current image features of the current mammary gland image; determining a current mammary gland lesion area corresponding to the current image feature according to the corresponding relation; and determining a current mammary gland lesion area corresponding to the current image feature, including determining the mammary gland lesion area corresponding to the image feature the same as the current image feature in the corresponding relationship as the current mammarygland lesion area. The method can improve the judgment accuracy of breast lesions, such as breast lumps, and improve the user experience effect.

The invention discloses a mammary gland puncture fixing device and a use method thereof in the field of puncture biopsy medical instruments. The mammary gland puncture fixing device comprises an ultrasonic high-frequency probe, a probe cable and an ultrasonic diagnostic apparatus, the ultrasonic high-frequency probe is placed in a positioning groove in the middle of a probe support, positioning splints are hinged to the front side and the rear side of the probe support, an elastic compression mechanism is arranged between the two positioning splints, an elastic protective pad is arranged at the bottom of one side of each positioning splint, the left side and the right side of the probe support are detachably connected with puncture guide modules, and at least four puncture needle guide grooves are formed in the puncture guide modules. The method includes the steps: disinfecting a mammary gland; fixing the mammary gland and the ultrasonic high-frequency probe by the positioning splints;finding out a puncture guide path after analysis of the ultrasonic diagnostic apparatus. The positional relationship of the ultrasonic high-frequency probe and a mammary gland mass can be positioned,stability of the probe is improved, and puncture needle inserting paths are more accurately selected.

The invention relates to the technical field of teaching appliances and particularly relates to a breast mass inspection teaching mold. The mold includes a model body, wherein a bottom surface of themodel body is provided with an elliptical groove, a through hole and a first rectangular groove, a wall of the elliptical groove is equipped with a cancer model, a wall of the through hole is equippedwith a mass model, the cancer model, the mass model and a surface of lobular hyperplasia model are respectively equipped with a pressure sensor, and a lower surface of a rubber cover is equipped withan air bag. The mold is advantaged in that through setting the pressure sensors, when medical staff contact the pressure sensors, sound is generated by the mold body, problems that a breast mass inspection teaching mold has the poor teaching effect and is not conductive to improvement of work experience of the medical staff are solved, moreover, the air bag is set, so a display screen is protected, and a problem of damage to the display screen on the breast mass inspection teaching mold due to bump is solved.

The invention relates to the technical field of pattern recognition, in particular to a classification prediction method and device based on data fusion and a storage medium. The method comprises thesteps: firstly marking collected sample data as a malignant sample or a benign sample, and constructing a sample data set through the marked sample data, and the sample data is breast lump cell nucleus data; preprocessing and normalizing the sample data set to obtain a normalized data set, and dividing the normalized data set into a training set and a test set; adopting a plurality of neural networks to train a normalized data set, and integrated three networks through an AdaBoost algorithm to generate an integrated classifier; and finally, obtaining test data in real time, and inputting the test data into the integrated classifier to obtain a diagnosis result. The invention further provides a classification prediction device and a storage medium correspondingly, and a classification prediction effect with high stability and accuracy for breast tumors can be obtained.

The invention belongs to the technical field of medical treatment, and particularly relates to a mammary gland image recognition method which comprises the following steps: acquiring a to-be-detectedmammary gland image, and detecting mammary glands by using a detection device, the detection method comprising mammary gland molybdenum target X-ray photography, B-ultrasonic, CT, MRI and nuclide imaging; and acquiring a lump image according to mammary gland development, inputting the lump image into a processing center, carrying out data analysis on a mammary gland lump, obtaining a typing resultto which the mammary gland lump belongs according to the lump in the image, and meanwhile, judging the mammary gland position corresponding to the mammary gland lump according to the mammary gland lump. A mammary gland image recognition device comprises a microprocessor, an image acquisition module, an analysis module, a display module and a communication module, and the microprocessor is in electrical input connection with a power module and the image acquisition module. The accuracy of mammary gland diagnosis is improved, the diagnosis efficiency is improved, and meanwhile the comprehensiveeffect of remote transmission of data is achieved.

The invention relates to the technical field of medical instruments, in particular to a guiding and positioning device for mammary gland puncture. The guiding and positioning device comprises a negative pressure cup body, an ultrasonic probe and a puncture needle body, the left side and the right side of the negative pressure cup body are fixedly connected with a first binding band and a second binding band respectively, and the surface of one side of the first binding band is sewn with a soft-face hook-and-loop fastener; the negative pressure suction cup can be bound to the body of a patient,the negative pressure suction cup is not prone to loosening or falling off, meanwhile, the puncture speed of the puncture needle can be regulated and controlled, convenience is brought to puncture operation of medical staff, and the problems that at present, in the breast lump diagnosis process, only the negative pressure suction cup is adopted for fixing, when the negative pressure suction cup leaks air, the negative pressure suction cup is loosened and even falls off, the puncture needle inclines or falls off, and when medical staff conduct puncture, once the medical staff exert too much force, the puncture needle is too high in speed, and then huge pain is brought to a patient can be solved.

Embodiments of the present application provide a method and device for detecting breast X-ray image masses, electronic equipment and a computer-readable storage medium, and solve the problem of low accuracy of a current method for detecting breast X-ray image masses. The method for detecting the breast X-ray image masses includes the following steps: inputting an axial breast X-ray image and a lateral oblique breast X-ray image into a mass detection model; determining coordinate data of a mass contour of the axial breast X-ray image and coordinate data of a mass contour of the lateral obliquebreast X-ray image; determining the coordinate of a center point of the axial breast mass and the coordinate of a center point of the lateral oblique breast mass; obtaining the coordinate of an axialnipple and the coordinate of a lateral oblique nipple; calculating the axial nipple and breast distance according to the coordinate of the center point of the axial breast mass and the coordinate of the axial nipple, and calculating the lateral oblique nipple and breast distance according to the coordinate of the center point of the lateral oblique breast mass and the coordinate of the lateral oblique nipple; and confirming that the axial breast X-ray image mass and the lateral oblique breast X-ray image mass are the same breast mass.

The invention provides a breast screening system based on infrared thermal imaging, which comprises an infrared thermal imager, a system host and a display, the infrared thermal imager is connected with the system host through a USB connecting line, the system host transmits an infrared image of the infrared thermal imager to the display for displaying, the breast screening system further comprises a shell, an examination space with an outlet is enclosed by the shell, a user enters a detection space for examination, an outlet of the detection space is provided with a shielding curtain, the shielding curtain is used for sealing the outlet, and the shell is further provided with an air conditioning system. According to the invention, the privacy during screening can be ensured, so that an examinee can perform screening in a relatively comfortable environment, the influence of factors such as temperature, wind speed and background can be overcome, the screening efficiency is improved, the accuracy is also improved, the breast can be preprocessed, tiny breast masses can be accurately screened, the screening accuracy is increased further. The breast screening system is reasonable in structural design, convenient and fast to use and high in practicability.

The invention provides a system for automatically segmenting, measuring and locating breast masses on MRI, including an AI scheduling module to extract header file information of a patient's DICOM image and search for a DCE sequence; a breast segmentation module to segment the bilateral breast glands of the DCE sequence , on the axial image, sagittal image and clock plane image of bilateral breast glands, respectively, divide the bilateral breast glands into multiple different partitions, and set a unique partition number for each partition; The intelligent detection module identifies all breast cancer foci in the DCE sequence, measures the three-dimensional diameter and volume of the cancer foci, and matches any two partition data of the three partition data of the axial, sagittal, and clock plane images. The location of cancer foci can be output; the structured report module outputs the volume, number, and location of cancer foci. The invention also discloses a method for automatically segmenting, measuring and locating breast masses on MRI. The invention can accurately locate the position and size of the cancer foci and improve the working efficiency of doctors.

The disclosure relates to a method and a device for detecting breast mass candidate regions. The method includes: extracting a maximum stable extremum region from an original image including a breast image, and forming a nested structure based on the extracted maximum stable extremum region; decomposing the nested structure to obtain multiple nested sequences and selecting a target nested sequence from the plurality of nested sequences according to the sequence length of each nested sequence, and converging the region corresponding to the target nested sequence into a breast mass candidate region. The method can identify breast masses of any shape.

The embodiment of the present invention discloses a segmentation method, device, terminal and storage medium of a mammogram image. The method includes: acquiring a mammogram image, and adjusting the contrast of the mammogram image according to the pixel values ​​of the mammogram image; Input the contrast-adjusted mammography image into the pre-trained image segmentation model to output the pre-segmented image of the breast region according to the image segmentation model; perform region filling and / or elimination processing on the pre-segmented image to obtain the target segmentation of the breast region image. By adjusting the contrast of the mammography image, the difference between the background area and the foreground area (breast area and non-breast tissue area) can be highlighted; the pre-segmentation of the breast area in the mammography image can be realized through the pre-trained image segmentation model; through Performing region filling and / or culling processing on pre-segmented images can improve the accuracy of breast segmentation, which is beneficial to front-end display and subsequent research on breast masses and calcifications.

The invention provides a multi-modal feature fusion Vnet-based breast mass segmentation method. The method comprises the following steps: S1, obtaining a breast magnetic resonance image and a data set of breast mass segmentation results manually marked by a doctor; s2, data preprocessing: dividing data in the data set; s3, constructing a network model based on multi-modal feature fusion Vnet; s4, training the network model in the step S3, and performing parameter adjustment to obtain a predicted breast lump segmentation result; and S5, comparing the predicted breast lump segmentation result obtained in the step S4 with the breast lump segmentation result manually marked by the doctor in the step S1 by using a set evaluation index and a loss function, and verifying the effectiveness of the segmentation method. The breast mass segmentation accuracy can be effectively improved, doctors are assisted in diagnosis and decision making, the burden of the doctors is relieved, and the method has high application value in breast mass auxiliary diagnosis, operation simulation and medical teaching.

The invention discloses a traditional Chinese medicine for treating various diseases. The traditional Chinese medicine is prepared from the following active pharmaceutical ingredient of, by weight, 30g of cottonrose hibiscus leaves, 50 g of Chinese violet, 50 g of dandelion, 30 g of caulis lonicerae, 50 g of selfheal, 50 g of peach blossom, 15 g of sappanwood, 10 g of caulis sinomenii, 10 g of Chinese actinidia root, 20 g of glechoma, 20 g of clarke boea, 8 g of mastix, 8 g of myrrh, 10 g of borneol and 1 g of musk. The traditional Chinese medicine for treating the various diseases has the effects of promoting blood circulation to remove blood stasis, softening hardness to remove stasis, cooling blood, detoxifying, diminishing inflammation, diminishing swelling and relieving pain, bettercurative effects on osteomyelitis, femoral head necrosis, lumbar and cervical spondylosis, traumatic bone setting, scrofula, hysteromyoma, mammary gland mass and suppurative infection, and has specialeffects on the suppurative infection and the traumatic injury bone setting.

The invention discloses a breast lump segmentation method based on deep learning. According to the scheme, a deep neural network is trained by training a manually labeled lump image. After a complete mammary gland image is input, the network can autonomously learn imaging features of the lumps, and an output result is an area which is identified as the lumps by the network, so that end-to-end mammary gland lump segmentation is realized. In order to improve the detection rate of the lumps, the invention discloses a novel weighted compound loss function.

An embodiment of the present invention provides a method and device for automatically detecting a breast mass, the method comprising: acquiring a breast image to be detected, and acquiring a candidate mass image from the breast image; the candidate mass image is a part of the breast image A sub-image: using the candidate mass image as an input of a pre-built mass recognition model to obtain a detection result of whether a mass appears in the breast position corresponding to the candidate mass image. The method can more accurately complete the segmentation of breast images to be detected, and at the same time use a neural network recognition model pre-built based on a large number of sample data to identify the segmented images and obtain breast masses. This method has strong adaptability and accurate detection Beneficial effect.

The invention discloses a breast mass positioning needle. The breast mass positioning needle comprises a needle sheath, wherein a puncture needle fixer is sleeved on the needle sheath; a tilted sharp end is arranged on the puncture needle fixer; a puncture needle is arranged in the needle sheath; a needle head is arranged at the end part of the puncture needle; barbs capable of being expanded and ejected in the radial direction of the puncture needle are arranged on the needle head; the three barbs are uniformly arranged around the puncture needle; and the puncture needle and the barbs are made of metal. The breast mass positioning needle has the following advantages: 1, the barbs are arranged at the head end of the puncture needle and can tightly grasp a breast mass after being released, so that the puncture needle is effectively prevented from being shifted and the breast mass can be stereoscopically and accurately positioned; the barbs capable of being expanded and ejected in the radial direction of the puncture needle are arranged on the needle head; and the barbs tightly grasp the breast mass after being ejected, so that the positioning needle is prevented from falling; 2, both the needle sheath and the puncture needle are provided with scale, so that the depth of the breast mass can be judged, thereby being favorable for operation; and 3, the puncture needle is easy to operate and simple to release.

The invention relates to an X-ray assisted diagnosis technology, and aims to provide a breast mass segmentation method based on a cross-attention mechanism. Including steps: making a data set; preprocessing with a cross-attention mechanism; constructing a deep convolutional neural network; adjusting the pre-training weight distribution of the image network dataset image network dataset; using the data preprocessing results to adjust the pre-training weight distribution, Train the deep convolutional neural network; use the deep convolutional neural network to infer the X-ray images to be detected. The present invention uses the cross-attention mechanism to quickly train the model, and the cross-attention mechanism enables the network to select tumor features from the two orientations of the MLO position and the CC position, and learn to adjust the weight value of the cross-attention. Compared with the traditional way of judging tumors only from CC or MLO positions, this invention can quickly and efficiently segment out tumors on mammograms, improve the detection rate and accuracy of tumors in mammograms, and has a high practical Application and promotion value.