40 results about "Palpable mass" patented technology

A system and a method are disclosed that forms a novel, synthetic, two-dimensional image of an anatomical region such as a breast. Two-dimensional regions of interest (ROIs) such as masses are extracted from three-dimensional medical image data, such as digital tomosynthesis reconstructed volumes. Using image processing technologies, the ROIs are then blended with two-dimensional image information of the anatomical region to form the synthetic, two-dimensional image. This arrangement and resulting image desirably improves the workflow of a physician reading medical image data, as the synthetic, two-dimensional image provides detail previously only seen by interrogating the three-dimensional medical image data.

A computer controlled apparatus for detecting breast tumors by mechanically palpating a breast in a full scan manner to detect small lumps or anomalies. The patient is positioned on a fully adjustable bed and oriented relative to the apparatus. A detection head mounted for movement in three dimensions is positioned above the bed. A palpation finger is brought into pressure contact with a sequence of small areas across the entire breast, palpating each area to measure tissue density. Concurrent with the palpation scan, a scan of breast color and temperature is conducted. A locator head positions the detector for the scan in a manner that assures repeatability during each of a series of periodic examinations. This system detects very small lumps and allows easy, accurate monitoring of suspicious areas over an extended time period. Several different embodiments of the detection head and location head are described.

Cone Beam Breast CT (CBBCT) is a three-dimensional breast imaging modality with high soft tissue contrast, high spatial resolution and no tissue overlap. CBBCT-based computer aided diagnosis (CBBCT-CAD) technology is a clinically useful tool for breast cancer detection and diagnosis that will help radiologists to make more efficient and accurate decisions. The CBBCT-CAD is able to: 1) use 3D algorithms for image artifact correction, mass and calcification detection and characterization, duct imaging and segmentation, vessel imaging and segmentation, and breast density measurement, 2) present composite information of the breast including mass and calcifications, duct structure, vascular structure and breast density to the radiologists to aid them in determining the probability of malignancy of a breast lesion.

A basic component of Computer-Aided Detection systems for digital mammography comprises generating candidate mass locations suitable for further analysis. A component is described that relies on filtering either the background image or the complementary foreground mammographic detail by a purely signal processing method on the one hand or a processing method based on a physical model on the other hand. The different steps of the signal processing approach consist of band-pass filtering the image by one or more band pass filters, multidimensional clustering, iso-contouring of the distance to centroid of the one or more filtered values, and finally candidate generation and segmentation by contour processing. The physics-based approach also filters the image to retrieve a fat-corrected image to model the background of the breast, and the resulting image is subjected to a blob detection filter to model the intensity bumps on the foreground component of the breast that are associated with mass candidates.

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.

A transducer is used to send an ultrasound pulse toward a stone and to receive ultrasound reflections from the stone. The recorded time between a pulse that is reflected from the proximal surface and a pulse that is reflected either from the distal surface of the stone or from a surface supporting the stone is used to calculate the stone size. The size of the stone is a function of the time between the two pulses and the speed of sound through the stone (or through the surrounding fluid if the second pulse was reflected by the surface supporting the stone). This technique is equally applicable to measure the size of other in vivo objects, including soft tissue masses, cysts, uterine fibroids, tumors, and polyps.

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 invention belongs to the technical field of medical image processing, and provides a breast cancer image information bottleneck multi-task classification and segmentation method and system. The method comprises the following steps: acquiring a plurality of breast images of contrast enhanced X-ray photography and corresponding benign and malignant categories and lump position pixel-level labels; performing preprocessing operation on each acquired breast image of the contrast enhanced X-ray photography; adopting a multi-task network to extract multi-task shared representation for each preprocessed mammary gland image; inputting the shared representation to a classification encoder to obtain an encoding tensor of an intermediate layer, and then sending the intermediate encoding tensor to an information bottleneck attribution module for feature compression and benign and malignant classification to obtain a classification task tensor; adapting the shared representation to a segmentation network to obtain a segmentation task tensor; and carrying out feature fusion on the classification task tensor and the segmentation task tensor to segment the focus.

The present invention proposes a method for semantic segmentation of lumps in breast mammography images based on deep residual networks. and the corresponding label images are divided into training samples and test samples; after preprocessing the training samples, a training data set is formed; a deep residual network is constructed, and the training data set is used to train the network to obtain a deep residual network training model; the preprocessing is to be After segmenting the mammography image mass, the deep residual network training model is used to perform binary classification and post-processing on the mammography image pixels to be segmented, and output the mass segmentation image to realize the semantic segmentation of the mammography image mass. The invention can effectively improve the automation and intelligence level of mammography image mass segmentation, and can be applied in technical fields such as assisting radiologists in medical diagnosis.

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 lump image segmentation method and system based on pruning U-Net + +, and relates to the technical field of ultrasonic image segmentation. The constructed pruning U-Net + + breast lump image segmentation model is based on a U-Net + + network, feature expressions of all branch U-Net are fused through jump connection, residual connection is introduced to replace dense connection in the U-Net + + method, and an obtained original breast ultrasound image is segmented through the model. According to the constructed pruning U-Net + + breast ultrasound image segmentation model, when the lumps in the breast ultrasound image are segmented, the model overfitting problem caused by the small data set problem of medical image data can be avoided, and the generalization ability of the ultrasound image breast lump segmentation model is improved; meanwhile, the scale of the model parameters is far smaller than that of the prior art, the complexity of the network model is reduced, the calculation time of network training can be shortened, the memory occupation of network training is reduced, and the model training efficiency is improved.

The invention discloses a simulation device for mammary gland rotary cutting needle or puncture needle training under ultrasound, and relates to interventional instruments such as rotary cutting needles and puncture needles, the simulation device comprises an outer skin, a filler, a simulation lump, a bottom plate and an anti-skid module, the outer skin is arranged on the upper surface of the bottom plate, the filler is arranged in the outer skin, the simulation lump is arranged in the filler, and anti-skid modules are symmetrically mounted on the lower surface of the bottom plate. According to the invention, the tissue texture can be simulated under the ultrasonic image, and under the observation of the ultrasonic image, the tumor implantation can realistically simulate the ultrasonic image of the breast benign mass. A rotary cutting needle or a puncture needle can be used for excision, no obvious needle passage or cavity is left in an ultrasonic image when the rotary cutting needle or the puncture needle is pulled out, the real simulation of training is improved, the hardness of the simulated lump is controlled to show a water-containing solid under ultrasound, and the simulated lump can be cut off by the rotary cutting needle or the puncture needle and pulled out through a negative pressure pipeline.

The invention discloses a breast cancer marking ruler and a marking technology, and relates to the technical field of breast cancer marking, in particular to a breast cancer marking ruler and a marking technology. The breast cancer marking ruler comprises a transverse measuring ruler, a surveying and mapping ruler arranged on the transverse measuring ruler and a groove clamping plate arranged on the surveying and mapping ruler, and the groove clamping plate is integrally fixed to the surveying and mapping ruler; a plurality of measuring scales are engraved on the transverse measuring scale and the surveying and mapping scale, two limiting mechanisms are further arranged on the transverse measuring scale, and supporting rods are arranged at the two ends of the transverse measuring scale. Compared with a guide wire positioning technology and a breast tissue positioning mark clamp technology which are most commonly used at the present stage, the application of the rectangular plane coordinate system breast cancer and cancerous swelling body surface marking method is innovation and supplement; especially for breast cancer which cannot be positioned by iconography examination after puncture biopsy and iconography negative breast cancer which achieves pathological complete remission or nearly pathological complete remission through new adjuvant therapy, the method is one of technologies capable of accurately positioning the primary lump position before an operation.

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 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 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.

Aiming at the fact that the existing breast lesion detection algorithm cannot well combine the information of bilateral breasts, cannot simultaneously meet the needs of identification and detection of multiple diseases including lumps and calcifications, and has a general effect on asymmetric dense glands, the present invention proposes A fully convolutional single-stage mammography lesion detection method with fusion of multi-image information. Use a non-anchor-based method for lesion detection, extract features of different scales from the original image, fuse the features of different scales, and fuse the information of different images, and finally directly predict whether a point on the feature map corresponds to a lesion and the specific location of the lesion.

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.

The invention provides a visual follow-up visit system and method based on breast ultrasonic scanning, and relates to the technical field of medical treatment. The system specifically comprises a datacollection module which is used for collecting and processing three-dimensional lump positioning images and obtaining current follow-up visit information of a patient so as to configure an identification code for the patient; a central storage module which is connected with the data collection module and is used for storing the three-dimensional lump positioning images and the follow-up visit information in a classified manner according to the identification code; and a data analysis module which is connected with the central storage module and used for extracting the three-dimensional lump positioning images and the follow-up visit information, carrying out alignment superposition on the three-dimensional lump positioning images according to the follow-up visit information to obtain superposed images, processing the superposed images to obtain lump change data and displaying the lump change data in real time. The system has the beneficial effects that through three-dimensional reconstruction of a mammary gland image, a doctor can master the illness state and conduct lump annotation positioning, and the three-dimensional lump positioning images of the patient with the same identification code can be extracted for multiple times, so that lump changes are visually reflected, and follow-up visit advises are checked and provided.