94 results about "Breast lesion" patented technology

The invention provides a multi-scale feature fusion ultrasonic image semantic segmentation method based on adversarial learning, and the method comprises the following steps: building a multi-scale feature fusion semantic segmentation network model, building an adversarial discrimination network model, carrying out the adversarial training and model parameter learning, and carrying out the automatic segmentation of a breast lesion. The method provided by the invention achieves the prediction of a pixel class through the multi-scale features of input images with different resolutions, improvesthe pixel class label prediction accuracy, employs expanding convolution for replacing partial pooling so as to improve the resolution of a segmented image, enables the segmented image generated by asegmentation network guided by an adversarial discrimination network not to be distinguished from a segmentation label, guarantees the good appearance and spatial continuity of the segmented image, and obtains a more precise high-resolution ultrasonic breast lesion segmented image.

A method and apparatus for automatically detecting breast tumors and lesions in images, including ultrasound, digital and analog mammograms, and MRI images, is provided. An image of a breast is acquired. The image is filtered and contrast of the image is enhanced. Intensity and texture classifiers are applied to each pixel in the image, the classifiers indicative of the probability of the pixel corresponding to a tumor. A seed point is identified within the image, and a region of interest is grown around the seed point. Directional gradients are calculated for each pixel of the image. Boundary points of the region of interest are identified. The boundary points are passed as inputs to a deformable model. The deformable model processes the boundary points to indicate the presence or absence of a tumor.

The invention provides a mammary gland lesion area detection method based on deep learning and transfer learning. The method comprises: preparation and amplification of a training set and a test set;according to lump position information marked by a doctor in the breast data set, extracting an available lump image and normalizing the size of the available lump image into a size of 100 * 100 pixels as a positive sample; according to the invention, the AlexNet network is used to train the parameter model of the classification model of the natural image on the ImageNet data set; training and transfer learning are carried out on a specific breast image data set, so that the binary classification problem of the convolutional neural network on a small-scale breast data set can be successfully solved, a lesion area in the breast image can be identified, and the prediction effect on the breast lesion is improved.

The invention relates generally to biopsy needle guidance which employs an x-ray / gamma image spatial co-registration methodology. A gamma camera is configured to mount on a biopsy needle gun platform to obtain a gamma image. More particular, the spatially co-registered x-ray and physiological images may be employed for needle guidance during biopsy. Moreover, functional images may be obtained from a gamma camera at various angles relative to a target site. Further, the invention also generally relates to a breast lesion localization method using opposed gamma camera images or dual opposed images. This dual head methodology may be used to compare the lesion signal in two opposed detector images and to calculate the Z coordinate (distance from one or both of the detectors) of the lesion.

A cryosurgical system using a low-pressure liquid nitrogen supply, which requires only 0.5 to 15 bar of pressure to provide adequate cooling power for treatment of typical breast lesions. The pressure may be provided by supplying lightly pressurized air into the dewar, by heating a small portion of the nitrogen in the dewar, or with a small low pressure pump.

The invention provides a method and a system for automatically analyzing a mammary gland ultrasonic image, identifying a mammary gland focus and then carrying out focus area contour extraction and parameter calculation. According to the invention, the convolutional neural network is used to construct the recognition classification recognition and segmentation extraction model, the breast lesion area in the video or image can be recognized, the lesion area contour can be automatically extracted, and the parameters of the lesion area can be calculated. According to the method and the system, theauxiliary diagnosis accuracy is remarkably improved, repeated operations of doctors are greatly reduced, and the robustness is good.

A series of ultrasound strain images of a breast lesion are acquired along with corresponding B-mode images using a real-time ultrasound strain imaging system and a free-hand technique. A visual assessment of the lesion is made by the sonographer after image acquisition. A conspicuity metric is calculated from the strain images based on the weighted sum of lesion contrast values in each strain image. The weighting of each lesion contrast value is based on observed characteristics of malignant lesions in a series of strain images. Diagnosis is made based on the visual assessment and the conspicuity metric

The invention provides a quantitative image evaluation system of breast lesions and an application method thereof. The quantitative image evaluation system adopts fractal technology and graphic analysis in tumor medical image analysis and tumor hazard rate evaluation, establishes and adopts a nonlinear data model for growth and diffusion of breast lesion cells. The nonlinear data model comprises morphological characteristic parameters of growth, diffusion and calcification of mammary tumor cells and clinical parameters as well. The quantitative image evaluation system of breast lesions of the invention adopts the nonlinear data model for growth and diffusion of breast lesion cells and comprises the morphological characteristic parameters of growth, diffusion and calcification of mammary tumor cells and the clinical parameters as well, calculates predictive values of benign and malignant breast lesions by mammography and predictive values of tumor cell classification; therefore, the quantitative image evaluation system can be widely used in mammography diagnosis and mammography screening.

The invention relates generally to biopsy needle guidance which employs an x-ray / gamma image spatial co-registration methodology. A gamma camera is configured to mount on a biopsy needle gun platform to obtain a gamma image. More particular, the spatially co-registered x-ray and physiological images may be employed for needle guidance during biopsy. Moreover, functional images may be obtained from a gamma camera at various angles relative to a target site. Further, the invention also generally relates to a breast lesion localization method using opposed gamma camera images or dual opposed images. This dual head methodology may be used to compare the lesion signal in two opposed detector images and to calculate the Z coordinate (distance from one or both of the detectors) of the lesion.

An automated method for determining a plurality of characteristics of a breast lesion is provided. The method comprises automatically identifying a region of interest in an image, the region of interest comprising the breast lesion, and preprocessing the region of interest to enhance a quality of the image. The method further comprises automatically segmenting the breast lesion in the region of interest and automatically measuring a plurality of measurements for determining the plurality of characteristics of the breast lesion. The breast lesion is automatically classified as benign or malignant based on the plurality of measurements.

The invention provides an MRI image-based axillary lymph gland metastasis prediction system and relates to the technical field of computer aided diagnosis. The system comprises an input module, an area-of-interest extraction module, a lump segmentation module, a sub-visualization module, a feature extraction module, a feature dimensionality reduction module, a classification and diagnosis module,and an output module. The input module receives a to-be-diagnosed mammary gland DCE-MR image sequence input by a user. The area-of-interest extraction module extracts an area of interest from the mammary gland DCE-MR image sequence. The lump segmentation module segments a lump in the area of interest. The sub-visualization module carries out the visual display on each segmented image and extractsthe edge of a focus. The feature extraction module extracts relevant feature values according to the lump information and transmits the relevant feature values to the feature dimensionality reductionmodule. The feature dimensionality reduction module carries out feature dimensionality reduction on an extracted feature set. The classification and diagnosis module inputs each lump feature value into a classifier. After that, the automatic classification and recognition is carried out by a computer for judging whether a lymph gland has already been transferred or not. The output module displaysa transfer prediction result and a transfer probability. According to the invention, the accurate segmentation of breast lesions can be realized. The accurate diagnosis of mammary axillary lymph glandmetastasis can be effectively assisted.

The invention provides an ultrasonic imaging system, a BI-RADS grading method and a model training method. The ultrasonic imaging system comprises an ultrasonic probe, a transmitting / receiving circuit, a processor performing feature map extraction on the breast ultrasound image based on one or more first feature map extractors to obtain one or more first feature maps about breast lesion features,the breast lesion features including BI-RADS features, performing feature map extraction on the breast ultrasound image based on a second feature map extractor to obtain a second feature map about BI-RADS grading, and classifying the first feature map and the second feature map based on a first classification model to obtain a BI-RADS classification result, and an output equipment used for outputting the BI-RADS grading result. The ultrasonic imaging system can eliminate the difference between the features, and can improve the accuracy of BI-RADS classification.

The invention provides a method for partitioning breast lesion. The method comprises steps as follows: coarse chest partition is performed on a magnetic resonance image on the basis of an oval model before a contrast medium is injected, and a first image is acquired; silhouette is performed after registration of magnetic resonance images obtained before and after the contrast medium is injected, and a silhouette image of the breast part is extracted from the acquired silhouette images on the basis of the first image; the silhouette image of each layer of breast parts is subjected to lesion detection, and a second image is acquired; and a three-dimensional communication area is found sequentially from the second image, self-adaptive region growing is performed on the silhouette image by taking the gravity center of each communication area as a seed point, and the magnetic resonance images are acquired after suspicious lesions of the breast are partitioned. The provided method for partitioning breast lesions can simply, effectively and automatically partition the suspicious lesions and can be widely applied to magnetic resonance imaging data by injecting various contrast media.

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.

The invention discloses a time intensity characteristic-based computer aided method for diagnosing benign and malignant breast lesions, comprising the following steps of: selecting an image sequence layer with suspicious lesions from a DCE(Dynamic Contrast-Enhanced)-MRI (Magnetic Resonance Imaging) image sequence set; carrying out denoising and filtering treatment on each image layer and acquiring a photographic subtraction sequence of the layer; determining a time intensity curve according to the photographic subtraction sequence of the layer; analyzing the characteristic of the time intensity curve and giving out a diagnosis result of the layer, namely a preliminary diagnosis result of the lesion; and fusing diagnosis results of the time intensity curves for different layers to give out a final lesion diagnosis result. According to the time intensity characteristic-based computer aided method disclosed by the invention, by comprehensively analyzing the characteristic of the time intensity curve on each layer, the accuracy of benign and malignant diagnosis of the lesions can be greatly improved for assisting clinical diagnosis for breast diseases and further the misdiagnosis rate is reduced.

The invention provides a breast lesion quantitative image evaluation (CAD) system and an application method thereof. The breast lesion quantitative image evaluation system adopts image data of a fractal technology, pattern analysis, and the like to extract an excavating mean and a mathematical modeling algorithm, combines clinical data to establish a breast lesion grown diffusion nonlinear data model and is applied to tumor medical image analysis and tumor disease risk evaluation. The nonlinear data model comprises the clinical parameters of breast tumor grown diffusion state characteristic parameters, calcific state characteristic parameters, breast surface characteristic limitation asymmetric compaction comparison, nipple retraction, pachyderma, structural distortion, and the like. The breast lesion quantitative image evaluation system has a full-graphical interface, can lead a molybdenum target, nuclear magnetism and ultrasonic image data in and is convenient and quick in operation(one-key operation). By the CAD system, a benign-malignant forecasting numerical value and a tumor classification forecasting value of breast molybdenum target piece (nuclear magnetism and ultrasonic) lesions can be calculated, and results of the benign-malignant forecasting numerical value and the tumor classification forecasting value can be applied to breast image auxiliary diagnosis and breast filming screening.

A cryosurgical system using a low-pressure liquid nitrogen supply, which requires only 0.5 to 1 bar of pressure to provide adequate cooling power for treatment of typical breast lesions. The pressure may be provided by supplying lightly pressurized air into the dewar, by heating a small portion of the nitrogen in the dewar, or with a small low pressure pump.

A method for selectively heating cancerous conditions of the breast including invasive ductal carcinoma and invasive glandular lobular carcinoma, and pre-cancerous conditions of the breast including ductal carcinoma in-situ, lobular carcinoma in-situ, and intraductal hyperplasia, as well as benign lesions (any localized pathological change in the breast tissue) such as fibroadenomas and cysts by irradiation of the breast tissue with adaptive phased array focused microwave energy is introduced. Microwave energy provides preferential heating of high-water content breast tissues such as carcinomas, fibroadenomas, and cysts compared to the surrounding lower-water content normal breast tissues. To focus the microwave energy in the breast, the patient's breast can be compressed and a single electric-field probe, inserted in the central portion of the breast, or two noninvasive electric-field probes on opposite sides of the breast skin, can be used to measure a feedback signal to adjust the microwave phase delivered to waveguide applicators on opposite sides of the compressed breast tissue. The initial microwave power delivered to the microwave applicators is set to a desired value that is known to produce a desired increase in temperature in breast tumors. Temperature feedback sensors are used to measure skin temperatures during treatment to adjust the microwave power delivered to the waveguide applicators to avoid overheating the skin. The microwave energy delivered to the waveguide applicators is monitored in real time during treatment, and the treatment is completed when a desired total microwave energy dose has been administered. By heating and destroying the breast lesion sufficiently, lesions can be reduced in size and surrounding normal breast tissues are spared so that surgical mastectomy can be replaced with surgical lumpectomy or the lesions can be completely destroyed so that surgical mastectomy or lumpectomy is avoided.

The invention discloses a double X-ray tube correction guide puncture mammary gland X-ray machine. The machine comprises a vertical shaft (11) and a pickup platform (10) which is connected with the vertical shaft (11) in a rotatable way; a cassette (7) is arranged in the pickup platform (10), a mammary gland compression device (6) is arranged above the pickup platform (10), the pickup platform (10) is provided with a puncture needle fixing frame assembly (9) which is provided with a puncture needle (4); a main pickup bulb tube (2) is fixedly connected with the pickup platform (10) through a support (12); a main pickup bulb tube (1) is positioned above the mammary gland compression device (6); and the guide puncture mammary gland X-ray machine also comprises an auxiliary pickup bulb tube (3) which is movably connected with the support (12) and is positioned above the mammary gland compression device (6). By adopting the guide puncture mammary gland X-ray machine, breast lesion tissues can be detected without errors.

The invention discloses a multiple stain reagent and a detection method for identifying a breast myoepithelial lesion. The multiple stain reagent comprises 20% of mouse anti-human CK8 / 18 immunohistochemical monoclonal antibody, 20% of ready-to-use calmodulin mouse anti-human monoclonal antibody, 20% of ready-to-use cytokeratin mouse anti-human monoclonal antibody, 20% of ready-to-use P63 protein mouse anti-human monoclonal antibody, and 20% of actin HHF-35 anti-human monoclonal antibody. When a breast myoepithelial cell is marked, the myoepithelial cell has strong specificity and sensibility, and different target antigens in the same target cell can be identified, so that a cell nucleus, a cell membrane and a cytoplasm can be stained synchronously, the reactivity and the sensibility of the myoepithelial cell are markedly improved, basic structures of a breast acinus and a catheter can be indicated more objectively, and a good assistance effect is exerted on the diagnosis of the breast lesion.

The embodiment of the invention provides a method and device for identifying breast image signs, and relates to the technical field of machine learning. The method comprises the steps that a breast image and the coordinates of lesions in the breast image are acquired; a region of interest (ROI) containing the lesions is determined from the breast image according to the coordinates of the lesions;the ROI is input into a first feature extraction module, and a feature image of a lesion image is determined; the feature image output by the feature extraction module is input into a classification module, and the signs of the breast lesions are determined.

The invention belongs to the technical field of medical diagnosis, and particularly discloses a triple-inspection comprehensive breast neoplasm diagnosis apparatus utilizing infrared thermography, guide pressure-sensitive palpation and an ultrasonic detector to perform local precise inspection and an inspection method utilizing the diagnosis apparatus. The diagnosis apparatus comprises a working platform, an infrared thermography acquisition device, a pressure-sensitive palpation detector and the ultrasonic detector are arranged on the working platform and all connected with a computer and an image display, and the pressure-sensitive palpation detector is used for performing accurate checking to find out whether neoplasms or abnormal deformations are formed in the breasts locally. The infrared thermography acquisition device, the pressure-sensitive palpation detector and the ultrasonic detector are connected with the computer through a digital interface. The diagnosis apparatus makes full use of advantages of infrared thermography, pressure-sensitive palpation and ultrasonography, and quickly and effectively makes a more accurate judgment whether local breast lesions structurally change or not.

The invention provides a mammary gland focus positioning method and device. The mammary gland focus positioning method splits the video sequences mainly based on mammary gland ultrasonic video sequence data, so as to process the video sequences into continuous image frame sequences, thus compared with a traditional ultrasonic image, increasing more information amount, and avoiding the condition that the sample is too good due to manual selection. Besides, the mammary gland focus positioning method adopts a deep learning method to train a model, so as to realize end-to-end positioning of test set data while the breast lesion area can be automatically detected, and then information of a subject is utilized to the maximum extent, and an effective auxiliary effect is provided for diagnosis ofdoctors, and the workload of the doctors is reduced.

The invention discloses a positioning method and a positioning system for a breast lesion puncture point. The positioning method comprises the following steps of: acquiring breast images shot at two different angles by a bulb tube of an X-ray digital mammography machine, and establishing a lesion projection light cone to generate a puncture guide body model. The maximum cross section is obtained by using a plane cross section guide body of a detector which is parallel with the X-ray digital mammography machine, and a point which is far away from the edge is picked on the maximum cross section to serve as the puncture point. The puncture point determined by the positioning method is located in a breast lesion, and is remote from the edge of the lesion, and more enough lesion tissues can be obtained when puncture biopsy is performed. Compared with other puncture point coordinate computing methods, the positioning method for the breast lesion puncture point has the advantages that puncture point computation is exquisite; the theory is perfect; the result accuracy is higher; the operation is simple; and the computing speed is high.

The present invention provides for means for linking breast lesion locations across imaging studies. In particular, a generic three-dimensional representation of the female breast is used. Automatic translation of the lesion location into standard clinical terminology and aligning the breast model with individual patient images is comprised. Moreover, a mechanism for linking image locations showing a lesion to a location in the breast model is presented. If desired, a region of interest can be calculated by a region of interest definition module that predicts a region of interest of a known lesion in terms of the breast model representation in a new imaging study.