292 results about "Tumor region" patented technology

A method for brain tumor segmentation in multi-parametric 3D magnetic resonance (MR) images, comprising: determining, for each voxel in the multi-parametric 3D MR image sequence, a probability that the voxel is part of brain tumor; extracting multi-scale structure information of the image; generating multi-scale tumor probability map based on initial tumor probability at voxel level and multi-scale structure information; determining salient tumor region based on multi-scale tumor probability map; obtaining robust initial tumor and non-tumor label based on tumor probability map at voxel level and salient tumor region; and generating a segmented brain tumor image using graph based label information propagation. The present invention is capable of achieving statistical reliable, spatially compact, and robust tumor label initialization, which is helpful to the accurate and reliable tumor segmentation. And the label information propagation framework could partially alleviate the performance degradation caused by image inconsistency between images to be segmented and training images.

An ultrasound imaging diagnosis apparatus and a method for supporting safe and exact puncturing operation into a target region in a living body of a patient are provided. In the ultrasound imaging diagnosis apparatus, a regions setting unit sets a target tumor region for puncturing and blood vessel regions and organ region that are located near the tumor region based on the volume data acquired by 3-D scans on the object. To avoid insertions into the blood vessel regions and organ region, a puncturing needle position detecting unit detects the tip position and the inserting direction of the puncturing needle at just before and during insertion into the object. An expected inserting position calculating unit calculates an expected inserting position and an insertion error region to the tumor region based on the tip position data, inserting direction data and characteristic data of the puncturing needle. A puncturing navigation data generating unit generates a puncturing navigation data by composing the tumor region data, the organ region and blood vessel regions data, and the data relating to the expected inserting position and the insertion error region.

The invention provides an MRI (Magnetic Resonance Imaging) brain tumor localization and intratumoral segmentation method based on a deep cascaded convolution network, which comprises the steps of building a deep cascaded convolution network segmentation model; performing model training and parameter optimization; and carrying out fast localization and intratumoral segmentation on a multi-modal MRIbrain tumor. According to the MRI brain tumor localization and intratumoral segmentation method provided by the invention based on the deep cascaded convolution network, a deep cascaded hybrid neuralnetwork formed by a full convolution neural network and a classified convolution neural network is constructed, the segmentation process is divided into a complete tumor region localization phase andan intratumoral sub-region localization phase, and hierarchical MRI brain tumor fast and accurate localization and intratumoral sub-region segmentation are realized. Firstly, the complete tumor region is localized from an MRI image by adopting a full convolution network method, and then the complete tumor is further divided into an edema region, a non-enhanced tumor region, an enhanced tumor region and a necrosis region by adopting an image classification method, and accurate localization for the multi-modal MRI brain tumor and fast and accurate segmentation for the intratumoral sub-regions are realized.

The invention discloses a brain tumor segmentation network and segmentation method based on a U-Net network. The tail of a contraction path of the segmentation network is connected with a spatial pyramid pooling structure; hole convolution of different scales is introduced into a network jump connection part of the segmentation network; an Add operation and original input are adopted to form a residual block with hole convolution; a receptive field of shallow feature information in the contraction path is expanded; fusing with an expansion path of a corresponding stage is carried out. The segmentation method comprises the following steps: cutting and preprocessing a training data set, then constructing a brain tumor segmentation network DCU-Net based on a U-Net network, then inputting a preprocessed two-dimensional image into a segmentation model for feature learning and optimization, obtaining an optimal parameter model of the segmentation model, and finally inputting a to-be-segmented test data set image into the segmentation model for tumor region segmentation. According to the method, the problems of over-segmentation and under-segmentation in brain tumor segmentation can be effectively solved, and the brain tumor segmentation precision is improved.

The invention discloses a fully convolutional network based tumor segmentation method in allusion to a brain MRI image. A task of tumor segmentation is divided into two steps such as coarse segmentation and fine segmentation. The fully convolutional network based brain MRI tumor segmentation method comprises the steps of firstly training a coarse segmentation fully convolutional network model by using a preprocessed sample so as to be used for detecting a tumor region in an original image, and then taking the tumor region as a training sample to train a fine segmentation fully convolutional network so as to be used for performing fine segmentation on the internal structure of the tumor region. The result shows that the method has a good segmentation effect for a brain MRI tumor.

The present invention provides stem cells loaded with bi-functional magnetic nanoparticles (nanoparticle-loaded stem cells (NLSC)) that both: a) heat in an alternating magnetic field (AMF); and b) provide MRI contrast enhancement for MR-guided hyperthermia. The nanoparticles in the NLSC are non-toxic, and do not alter stem cell proliferation and differentiation, the nanoparticles do however, become heated in an alternating magnetic field, enabling therapeutic applications for cancer treatment. NLSC can deliver hyperthermia to hypoxic areas in tumors for sensitization of those areas to subsequent treatment, thus delivering therapy to the most treatment-resistant tumor regions. The heating of diseased tissue either results in direct cell killing or makes the tumor more susceptible to radio- and / or chemotherapy. The NLSC of the present invention can be used for MR image-guided hyperthermia in oncology, in stem cell research for cell tracking and heating, and for elimination of mis-injected stem cells.

Disclosed herein are radiation therapy systems and methods. These radiation therapy systems and methods are used for emission-guided radiation therapy, where gamma rays from markers or tracers that are localized to patient tumor regions are detected and used to direct radiation to the tumor. The radiation therapy systems described herein comprise a gantry comprising a rotatable ring coupled to a stationary frame via a rotating mechanism such that the rotatable ring rotates up to about 70 RPM, a radiation source (e.g., MV X-ray source) mounted on the rotatable ring, and one or more PET detectors mounted on the rotatable ring.

The invention discloses an image segmentation method and device, a diagnosis system and a storage medium. The image segmentation method comprises the steps of obtaining a tumor image; Carrying out tumor positioning on the obtained tumor image to obtain a candidate image for indicating the position of a full tumor region in the tumor image; Inputting the candidate image into a cascade segmentationnetwork constructed based on a machine learning model; And carrying out image segmentation on the whole tumor region in the candidate image by using a first-stage segmentation network in the cascade segmentation network as a starting point, and stepping to a last-stage segmentation network step by step to carry out image segmentation on an enhanced tumor core region to obtain a segmented image. Byadopting the image segmentation method and device, the diagnosis system and the storage medium provided by the invention, the problem of poor tumor image segmentation effect in the prior art is solved.

The subject disclosure presents systems and computer-implemented methods for providing reliable risk stratification for early-stage cancer patients by predicting a recurrence risk of the patient and to categorize the patient into a high or low risk group. A series of slides depicting serial sections of cancerous tissue are automatically analyzed by a digital pathology system, a score for the sections is calculated, and a Cox proportional hazards regression model is used to stratify the patient into a low or high risk group. The Cox proportional hazards regression model may be used to determine a whole-slide scoring algorithm based on training data comprising survival data for a plurality of patients and their respective tissue sections. The coefficients may differ based on different types of image analysis operations applied to either whole-tumor regions or specified regions within a slide.

A system for segmenting a target organ tumor from an image includes a background model builder, a foreground model builder and a tumor region locator. The background model builder uses an intensity distribution estimate of voxels in an organ region in an image to build a background model. The foreground model builder uses an intensity distribution estimate of voxels in a target organ tumor to build a first foreground model. The tumor region locator uses the background model and the first foreground model to segment the target organ tumor to obtain a first segmentation result.

The invention belongs to the field of image processing, and particularly relates to an automatic extraction method of regions of interest in three-dimensional breast full-volume images (ABVS). The method comprises the following steps: processing the continuous cross section two-dimensional images in three-dimensional ABVS images by using a maximum direction-based phase information method to obtain the candidate regions of interest on each cross section image; removing the unrelated regions according to the prior knowledge such as the continuity and position characteristic of breast tumor on the two-dimensional cross section images; obtaining the shape and texture features of the residual suspected tumor regions, inputting the shape and texture shapes to a two-valued logistic regression classifier to obtain the probability of each region becoming tumor and selecting the region with the maximum probability as the tumor region; obtaining the minimum ellipsoid comprising the region of interest according to the selected region to serve as the region of interest. The automatic extraction method provided by the invention can be used for realizing the automatic extraction of tumor regions of interest in the three-dimensional ABVS images, obtaining the correct positions of tumor, decreasing the workload of the manual operation and providing important reference to further tumor detection.

The invention discloses an automatic fast segmenting method of a tumor pathological image. The method comprises the following steps: firstly filtering a tumor original pathological image through the adoption of a Gaussian pyramid algorithm to respectively obtain pathological images with equal resolution, double resolution, fourfold resolution, eightfold resolution and 16-fold resolution; determining an initial region of interest containing the tumor on the equal resolution image through a RGB color model and morphological close operation; iteratively optimizing the initial regions of interest from the equal resolution to the fourfold resolution through the adoption of bhattacharyya distance; judging that the contribution of the RGB color model to the tumor region of interest has been reduced to zero when the bhattacharyya distance achieves a set threshold value; performing the self-adaptive high resolution selection of the deep precise segmentation through the adoption of a convergence exponent filtering algorithm, thereby further segmenting under the most suitable high resolution; and finally segmenting out a normal tissue and a tumor tissue in the tumor region of interest through the adoption of a bag of words model based on random projection. The method disclosed by the invention has the features of being accurate, fast and automatic.

The invention relates to segmenting blood vessels in perfusion MR images, more particularly, the invention relates to automated vessel removal in identified tumor regions prior to tumor grading. Pixels from a perfusion related map from dynamic contrast enhancement (DCE) MR images are clustered into arterial pixels and venous pixels by e.g. a k-means class cluster analysis. The analysis applies parameters representing the degree to which the tissue entirely consists of blood (such as relative blood volume (rBV), peak enhancement (ΔR2max) and / or post first-pass enhancement level (ΔR2p)) and parameters representing contrast arrival time at the tissue (such as first moment of the area (fmAUC) and / or contrast arrival time (T0)). The artery and venous pixels are used to form a vessel mask. The invention also relates to a computer aided diagnostic (CAD) system for tumor grading, comprising automated tumor segmentation, vessel segmentation, and tumor grading.

The embodiment of the invention provides a liver tumor segmentation method and device based on multi-stage CT image guidance, and the method comprises the steps: obtaining an abdomen CT image with enhanced contrast, inputting the abdomen CT image with enhanced contrast into a preset single-channel full convolutional neural network, and obtaining a liver region-of-interest image; inputting the liver region-of-interest image into a preset tumor segmentation network to obtain a tumor segmentation result corresponding to the contrast-enhanced abdominal CT image; wherein the tumor segmentation network is obtained by performing multi-channel fusion training according to liver region-of-interest image samples in different periods and image samples with tumor region marks corresponding to the abdominal CT image samples. According to the embodiment of the invention, the liver tumor CT images in different periods are effectively subjected to feature mining by adopting a multi-channel fusion training network, so that the trained network has higher segmentation precision and better robustness on liver tumors.

The invention discloses a thyroid tumor ultrasonic image recognition method and device, and the method comprises the steps: selecting a tumor region in a thyroid tumor ultrasonic image, extending a certain boundary scope and then performing cutting, carrying out the benign and malignant marking, and enabling the cut images to form a training set; training a selected CNN (Convolutional Neural Network) through the training set, and forming a thyroid tumor ultrasonic image recognition model; obtaining a to-be-recognized thyroid tumor ultrasonic image, selecting a tumor region and extending a certain boundary scope, and carrying out the benign and malignant recognition through the thyroid tumor ultrasonic image recognition model. The method and device are used for assisting a doctor to diagnose the benign and malignant thyroid tumors, obtain the accuracy of 90% or greater in the detection test of the benign and malignant thyroid tumors through the thyroid tumor ultrasonic image, and is ofgreat reference significance to the actual clinical diagnosis.

The invention discloses a pancreatic cancer tumor automatic identification system based on depth learning, belonging to the technical field of image identification. The system comprises a depth learning model, wherein the depth learning model comprises a feature extraction network, a region generation network and a fast R- CNN target detection network; The feature extraction network is used for abstracting the image features of pancreatic cancer tumors and generating a convolution feature map; The region generation network is used for sliding scanning all features existing in the convolution feature map, and selecting a plurality of candidate regions at each sliding window position, wherein the candidate regions are possible pancreatic cancer tumor regions; Fast R-CNN target detection network is used to classify and regress the convolution feature map and the generated candidate regions, and finally output the location and probability of the pancreatic cancer tumor region. The system of the invention can complete the tracking identification of the pathological tissue, reduce the manual operation, and has the advantages of high processing speed and high accuracy.

Provided herein is a breast ultrasound scanning and diagnosis aid system. The scanning aid system is capable of aiding positioning and tracking the scanned breast ultrasound images and suspicious tumor ultrasound images so that the doctor can be easily informed of the scanned positions of the breast ultrasound images and the suspicious tumor ultrasound images. The diagnosis aid system selects at least one representative, breast ultrasound images with tumor characteristics, segments a suspicious tumor region, and acquires a plurality of characteristic parameters in association with tumor tissues from the suspicious tumor region so as to provide a diagnostic suggestion. With the use of the present invention, the positions of suspicious tumors can be acquired from the positioning data of the breast ultrasound images, and tumor diagnosis accuracy can be improved by selecting an ultrasound image with tumor characteristics.

The invention relates to an image processing technology and particularly relates to an interactive liver tumor region segmentation method based on watershed transform and classification through a support vector machine. The method comprises the following steps: 1) performing segmentation pretreatment on a liver tumor region; 2) performing watershed transform on an image of the pretreated liver region which is obtained in the step 1) and dividing the image of the pretreated liver region into numerous reception basins; 3) calculating four-dimensional characteristic vectors of all the reception basins which are generated by the watershed transform, marking tumor and normal liver tissues in the image of the liver region in an interactive manner and adopting a support vector machine process to classify the reception basins in a characteristic space; and 4) adopting communicating region detection to eliminate a false positive tumor region generated by the classification, and applying morphological operation to fill voids and smoothen edges. The region class is classified, and user marks are further utilized for training parameters of a classifier, thereby effectively improving the segmentation speed and the precision. The method has important application value in the fields of liver surgical planning and the like.

The invention discloses a magnetic resonance imaging nanometer drug carrier, and a nanometer drug loading system and a preparation method thereof. The magnetic resonance imaging nanometer drug carrieris a triblock polymer nanoparticle, wherein the triblock polymer is PLGA-PEI-PEG, and has active groups on the surface, and the active groups comprise amino, hydroxyl and carboxyl. According to the present invention, the drug carrier can efficiently load a nuclear magnetic resonance imaging drug and an antitumor drug to make the antitumor drug specifically reach the tumor lesion site, such that the nuclear magnetic resonance positioning of the superparamagnetic ferroferric oxide nanoparticle at the tumor region can be achieved while the high-selectivity and low-toxicity treatment effect can be achieved, and the disadvantages of poor selectivity, strong toxic-side effect, easy drug-resistance generation and the like of the traditional cytotoxic drugs can be overcome; and the preparation method is simple and is easy to perform, the prepared triblock polymer nanoparticle can be stably stored in the aqueous solution so as to be easily stored, and various functional groups exist on the surface of the particle, such that the prepared triblock polymer nanoparticle can be easily subjected to surface modification or surface functionalization.

The invention belongs to the technical field of computer auxiliary diagnosis, and specifically relates to an identification method of primary central nervous system lymphoma and glioblastoma based on a sparse representation system. The method includes: segmenting T1 enhanced and T2 weighted MRI image tumor regions by employing an image segmentation method based on a convolutional neural network; then designing a dictionary learning and sparse representation method, and extracting texture characteristics of the tumor regions; selecting some characteristics with high stability and high resolution for tumor identification by employing an iterative sparse representation characteristic selection method in order to reduce the characteristic redundancy and improve the tumor identification efficiency; and finally establishing a combined sparse representation classification model containing two modals of T1 enhanced or T2 weighted based on the thought of eigenstate fusion in order to improve the tumor identification precision. According to the method, high tumor identification precision can be obtained, manual operation for extraction of identification parameters is avoided, the robustness is high, and the method can be applied to clinic identification of primary central nervous system lymphoma and glioblastoma.

Disclosed herein are radiation therapy systems and methods. These radiation therapy systems and methods are used for emission-guided radiation therapy, where gamma rays from markers or tracers that are localized to patient tumor regions are detected and used to direct radiation to the tumor. The radiation therapy systems described herein comprise a gantry comprising a rotatable ring coupled to a stationary frame via a rotating mechanism such that the rotatable ring rotates up to about 70 RPM, a radiation source (e.g., MV X-ray source) mounted on the rotatable ring, and one or more PET detectors mounted on the rotatable ring.

A tumor region is determined within a three dimensional medical image. A long axis and a short axis of the determined tumor region are designated. The lengths of the designated long axis and the designated short axis are measured. The measured lengths of the long axis and the short axis are displayed.

The invention relates to an image data expansion method for deep learning model training and learning, and belongs to the technical field of computer medical image calculation. The method comprises the following steps: firstly, judging a data type, and identifying CT or MRI image data; For the image data, judging whether an ROI (Region Of Interest) is defined or not, and selecting a correspondingmethod to complete the construction of an image data set in combination with the size of a tumor region; Training the image data set by adopting a basic image transformation method to obtain a preliminary training data set; And finally, carrying out data expansion on the preliminary training data set, carrying out deep training by adopting a network model, and finally, carrying out probability prediction. Based on artificial intelligence deep learning, a series of data expansion methods are applied to learning of deep model training in the field of medical image processing, the influence of medical image data heterogeneity on abnormal data is solved, computer-aided diagnosis is facilitated, and the diagnosis efficiency and accuracy are improved.

The invention discloses a preparation method and application of a drug-loaded magnetic composite nanometer material. The fat-soluble solution (or emulsion) of the surface lipophilic magnetic nanoparticles and the drug is added to the dichloromethane solution of polylactic acid / glycolic acid copolymer (PLGA), and the three are mixed with each other to form an oil phase system. The oil phase system is added dropwise to the aqueous solution in which the surfactant Pluronic F127 is dissolved to form an oil-in-water system, and then the drug-loaded magnetic composite nanomaterial is obtained under the action of ultrasound. The drug-loaded magnetic composite nanomaterial can concentrate the drug in the tumor area under the action of an in vitro magnetic field to achieve targeting; the coating of PLGA solves the problem of mutual self-aggregation of magnetic particles, and the slow release control of the drug solves the problem It has great toxicity and side effects in the body and can be quickly taken up by tumor cells, leading to apoptosis of tumor cells and reversing the multidrug resistance of tumor cells.

The invention discloses a tumor region image enhancement method and system based on an enhanced composite image, and relates to the field of medical image processing. The invention puts forwards a concept "enhanced composite image" for the first time, a ROI (Region Of Interest) which covers all tumor regions is independently subjected to noise reduction processing and enhancement processing in an original CT (Computed Tomography) or MR (Magnetic Resonance) image to obtain a noise reduction image and an enhancement image of the RIO, and the noise reduction image and the enhancement image are subjected to weight fusion to obtain the enhanced composite image. The RIO in the original CT or MR image can be enhanced, and different weighting factors in the enhanced composite image are selected to cause the surface and the fuzzy boundary of the tumor in the CT or MR image to become clear so as to bring convenience for doctors to observe the surface and the boundary of the tumor. A threshold value segmentation method is adopted on the enhanced composite image, and therefore, the tumor region can be precisely segmented.

An ultrasonic diagnostic apparatus (100) that decides a type of a tumor contained in a specimen includes: an image forming unit (103) that forms an ultrasonic image corresponding to an echo signal received from the specimen after administration of a contrast medium; a feature value calculating unit (106) that classifies each of a plurality of pixel regions contained in a tumor region including the tumor in the ultrasonic image into a low-luminance region, or a high-luminance region having higher luminance than the luminance of the low-luminance region, and calculates, based on a difference between a variance at a position of the low-luminance region and a variance at a position of the high-luminance region, a ring level indicating a degree of a ring shape of an image of the tumor region, the ring shape in which a luminance value of a central portion is lower than a luminance value of a peripheral portion surrounding the central portion; and a type deciding unit (107) that decides the type of the tumor based on the ring level.

An exemplary embodiment of the present invention provides a three-dimensional virtual liver surgery planning system including: a digital imaging and communications in medicine (DICOM) receiving module which receives an abdomen computer tomography (CT) volume data set from a picture archiving and communication system (PACS) server; a DICOM loading and noise removing module which loads the received abdomen CT volume data set and remove noises; a standard liver volume estimation module which estimates a standard liver volume (SLV) from the denoised abdomen CT volume data set; a liver extraction module which extracts a three-dimensional liver region; a vessel extraction module which extracts a three-dimensional vessel region including a portal vein, a hepatic artery, a hepatic vein, and an inferior vena cava (IVC); a tumor extraction module which extracts a three-dimensional tumor region; a liver segmentation module which divides the extracted three-dimensional liver region into several segments using landmarks which are selected by a user or a segmentation sphere; and a liver surgery planning module which makes a three-dimensional liver surgery plan using a resection surface, a liver segments, or the segmentation sphere.

The invention discloses a tumor region segmentation method and system for a liver CT image based on a cascaded full convolutional network. According to the method, automatic segmentation of a liver tumor region is realized by using a full convolutional network model. The method comprises the following steps: performing preprocessing operations such as filtering and sharpening enhancement on a CT image; training a cascade network by using the preprocessed CT data set; achieving liver region segmentation by using two stages of FCN networks and segmenting a tumor region from a liver region of interest. A first-stage FCN network uses a variable pooling method so that more liver features are reserved and liver segmentation precision is improved; and a second-stage FCN uses hole convolution replaces an original convolution layer and a pooling layer, so that the position information of the target can be reserved while a image is reduced and the feeling domain is increased. A large number of features do not need to be manually extracted, and the tumor region can be effectively and accurately segmented from the liver CT image.

The invention discloses a method based on a deep belief network to segment a brain tumor so as to be favorable for the auxiliary diagnosis of a patient brain tumor disease. The method comprises the following steps that: firstly, utilizing an adaptive filter and histogram equalization and brightness transformation to process an original image to reduce the noise of the original image and enhance an image contrast ratio; then, extracting image blocks from the processed image to generate a data set; utilizing the deep belief network to classify edema, necrosis and tumor regions in the integral brain tumor by the deep belief network to realize preliminary segmentation; and finally, utilizing fuzzy C-means clustering segmentation to carry out further accurate segmentation on the image to obtain an integral brain tumor segmentation result.

An anticancer pharmaceutical composition composed of pharmaceutic adjuvant and anti-metabolism medicine is disclosed. Wherein, the anti-metabolism medicine can effectively destroy DNA and / or protein synthesis and repairing function inside the tumor cell so as to inhibit the tumor cell growth, while the pharmaceutic adjuvant can mainly be biological compatible, degradable and absorbable macromolecule polymer, which can make the anti-metabolism drug to release slowly in the local tumor region in the degradation and absorption process, therefore it can both decrease considerably the whole body toxic reaction and sustain the local tumor effective drug level.