1035 results about "Circumscribed lesion" patented technology

An exemplary system, method and computer-accessible medium for determining resultant information about a portion(s) of a tissue(s), can include, for example, receiving initial information which is based on a particular radiation that is returned from the portion(s), the particular radiation can be is based solely on an interaction between the portion(s) and a near-infrared radiation forwarded to the portion(s), and determining the resultant information about the portion(s) of the tissue(s) based on the initial information. The near-infrared radiation can be provided by a near-infrared light optical arrangement that can include a diffusely reflected near-infrared light arrangement. A depth of a lesion to be ablated can be determined by the near-infrared radiation based on the initial information. The initial information can include data corresponding to a reflectance spectrum(s) of the portion(s).

A method for using computer-aided diagnosis (CAD) for digital tomosynthesis mammograms (DTM) including retrieving a DTM image file having a plurality of DTM image slices; applying a three-dimensional gradient field analysis to the DTM image file to detect lesion candidates; identifying a volume of interest and locating its center at a location of high gradient convergence; segmenting the volume of interest by a three dimensional region growing method; extracting one or more three dimensional object characteristics from the object corresponding to the volume of interest, the three dimensional object characteristics being one of a morphological feature, a gray level feature, or a texture feature; and invoking a classifier to determine if the object corresponding to the volume of interest is a breast cancer lesion or normal breast tissue.

Lesion size or volume prediction shortly after the onset of an ablation procedure can inform or control the ablation procedure. The prediction and/or control is made without regard to an actual detected temperature in the vicinity of the ablation electrodes. As a consequence, the system has utility with irrigated catheter constructions and other situations in which local irrigation in the vicinity of an ablation site would otherwise interfere with a prediction or control scheme that solely relies upon temperature measurements.

The invention provides a method for detecting an X-ray mammary gland lesion image based on feature pyramid network under transfer learning. The method comprises the steps: 1, establishing a source domain data set and a target domain data set; 2, establishing a deformable convolution residual network layer by a deformable convolution and extended residual network module; 3, establishing a multi-scale feature extraction sub-network based on a feature pyramid structure through a feature map up-sampling and feature fusion method in combination with a deformable convolution residual network layer;4, establishing a deformable pooling sub-network sensitive to the focus position; 5, establishing a post-processing network layer to optimize a prediction result and a loss function; and 6, migratingthe training model to a small sample molybdenum target X-ray mammary gland focus detection task so as to improve the detection precision of the network model on the focus in the small sample image. According to the method, a transfer learning strategy is combined to realize focus image processing in a small sample medical image.

Methods for isolating polynucleotides encoding antibodies against lesional tissues are provided, wherein the methods comprise the steps of: (a) isolating a B cell(s) that infiltrates into a lesional tissue of interest; and (b) obtaining an antibody-encoding polynucleotide from the isolated B cell(s). The lesions may be a cancer tissue or such. Antibody genes can be obtained without depending on B cell cloning. Accordingly, it is also possible to obtain genes encoding human-derived antibodies which are difficult to clone. Genes that encode antibodies against cancer can be obtained using cancer tissues as the lesion.

The invention discloses a local ablation method for liver cancer. The local ablation method comprises the following steps: carrying out modular partition including the liver, the tumor focus, the blood vessel and the tissue around the liver in sequence on the preoperative image after registration, and carrying out puncture path planning and puncture thermal field planning; carrying out multi-modal image registration on the preoperative image and an intra-operative image, outputting the tumor focus of the preoperative image, and displaying the tumor focus on the intra-operative image in a fusion manner; and carrying out multi-modal image registration on the preoperative image and a postoperative image, outputting the tumor focus in the preoperative image, and displaying the tumor focus in the preoperative image on the postoperative image in a fusion manner, wherein the preoperative image and the postoperative image respectively comprise the CT image and/or MR image of the time sequence, and the intra-operative image comprises the CT image. According to the method, the image registration step is added in preoperative planning, the intra-operative locating and postoperative assessment, thus the scientific planning for the tumor thermal ablation before the operation, the visual and effective information display in treatment during the operation, and the scientific assessment for the curative effects and the treatment experience feedback after the operation are realized, so that the preoperative planning is guided.

The present invention, in one aspect, relates to a method for examining a target for tumors or lesions using what is referred to as “Early Increase in microvascular Blood Supply” (EIBS) that exists in tissues that are close to, but are not themselves, the abnormal tissue and in tissues that precede the development of such lesions or tumors. While the abnormal tissue can be a lesion or tumor, the abnormal tissue can also be tissue that precedes formation of a lesion or tumor, such as a precancerous adenoma, aberrant crypt foci, tissues that precede the development of dysplastic lesions that themselves do not yet exhibit dysplastic phenotype, and tissues in the vicinity of these lesions or pre-dysplastic tissues.

The invention relates to the technical field of medical equipment, and discloses a focus image recognition method and a focus image recognition system based on a deep learning model. The invention provides a new method and a new system for automatically identifying conditions of medical images by replacing doctors based on the deep learning model. Regarding acquired to-be-detected medical images,Segmentation of a smallest organ tissue image and image recognition of a corresponding organ tissue, prediction of a deep learning model and marking on a predication result are carried out. The invention can replace doctors find out underlying conditions of medical images and automatically mark lesion tissues on the medical images. Therefore, a reminder is given to doctors for timely diagnosis. Working intensity of the doctors can be reduced. Whether diseases occur or not can be timely diagnosed. The treatment opportunity of conditions is prevented from being delayed, and the discovery of early-stage diseases is particularly facilitated.

A method for detecting and analyzing candidate lesions in a magnetic resonance image of a breast. The method includes the steps of: accessing a plurality of temporal magnetic resonance images of the breast; identifying candidate lesions by performing a temporal pattern analysis of the plurality of images to produce temporal features based on an uptake phase and a washout phase; performing a morphological operation on the candidate lesions to produce morphological features; and classifying the candidate lesions using the morphological features and temporal features to produce classified candidate lesions.

An instrument for photodynamic therapy applies treatment light from a dye laser, white light, and ultraviolet fluorescence excitation light from an LED onto a lesion and surrounding areas in a time-multiplexed manner. The reflected white light is analyzed in a spectrometer to determine a correction for the dynamic optical spectral properties of the patient's tissue. Light emitted by fluorescence from the lesion and the surrounding areas is analyzed in another spectrometer, and the results are corrected in a computer, using the correction. An optical switch has been developed for the instrument, using a bistable solenoid and a sled.

A method, code and system for planning the treatment a lesion on or adjacent to the retina of an eye of a patient are disclosed. There is first established at least two beam paths along which x-radiation is to be directed at the retinal lesion. Based on the known spectral and intensity characteristics of the beam, a total treatment time for irradiation along each beam paths is determined. From the coordinates of the optic nerve in the aligned eye position, there is determined the extent and duration of eye movement away from the aligned patient-eye position in a direction that moves the patient's optic nerve toward the irradiation beam that will be allowed during treatment, while still maintaining the radiation dose at the patient optic nerve below a predetermined dose level.

The invention discloses a three-dimensional imaging method and system of an organ and a lesion based on a medical image. The method comprises the steps of (S1) obtaining thin layer scan images of an organ to be split, (S2) sketching the contour of a lesion/target area of an image, (S3) carrying out 3D modeling on the organ to be split comprising the lesion/target area, and (S4) carrying out multi-area splitting on a model of the organ to be split obtained by the 3D modeling. According to the method and the system, medical image segmentation is not only stay in the segmentation of a whole organ and an external non-organ part, each area of the organ is segmented further and the lesion/target area is segmented, the observation of possible diseased organs of a patient in a later period is facilitated, and the analysis of a lesion/target area (tumor) position is facilitated.

The invention discloses a training method for a lesion identification model. The training method comprises the following step of utilizing an obtained lesion image sample to train a Faster RCNN (Recurrent Neural Network) to obtain the lesion identification model. The invention also correspondingly provides a lesion image device based on the lesion identification model and a verification method for the lesion identification mode. The training method for the lesion identification model is designed on the basis of a deep learning concept, and the position and the type of a focus can be accurately judged when the model is used for carrying out lesion identification.

The embodiment of the invention provides a medical image processing method and device, electronic equipment and a computer storage medium. The method can comprise the steps of obtaining a to-be-processed 3D medical image; segmenting the 3D medical image into at least two adjacent image blocks; performing feature extraction on each image block to obtain a feature map of each image block; determining a prediction probability graph corresponding to each image block based on the respective feature graph of each image block; and based on the prediction probability graph of each image block, determining a detection result of a lesion area corresponding to each disease in the 3D medical image. Through the scheme of the invention, the detection result corresponding to the same disease in the 3D medical image can be accurately determined based on the image blocks and the relevance among the image blocks.

The invention discloses a pathological image processing method based on deep learning. The pathological image processing method comprises: obtaining a pathological image of a to-be-processed target object; partitioning the pathological image of the target object to be processed to obtain a partitioned image set; performing feature classification extraction processing on the block image set to obtain N first feature sets, N second feature sets and N third feature sets; generating a target fusion feature corresponding to the target object; and calling the pathological image analysis model to analyze and process the target fusion features so as to output a pathological analysis result of the to-be-processed target object. The invention further discloses a model training method. The pathological image can be directly utilized to predict the risk of lesion metastasis. Compared with a biological detection technology, the method is advantageous in that the time for waiting for a detection result can be shortened, the detection efficiency can be improved, errors caused by uncontrollable factors such as experimental errors and operation errors can be avoided, and then a more accurate detection result is provided.

The embodiment of the invention provides a pneumonia lesion segmentation method and device, and solves the problems of low accuracy and low efficiency of an existing pneumonia lesion segmentation mode. The pneumonia lesion segmentation method comprises the following steps: predicting a lesion area on medical image data of a positive level based on an image semantic segmentation model; counting thelesion area of each parallel layer, and calculating the lesion volume by combining the lesion area of each parallel layer, wherein the image semantic segmentation model is established through the following training steps: inputting all or part of marked sample data into a focus segmentation model to obtain a prediction result output by the focus segmentation model; based on a focus detection frame predicted by a focus detection model and a lung region predicted by a lung lobe lung segment segmentation model, screening out a low-level false positive region from a prediction result to obtain afalse label of sample data, and adding unmarked sample data; and rechecking the pseudo label, and marking the marked sample data to update the marked sample data.

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.