526 results about "Pulmonary nodule" patented technology

The invention relates to an automatic detection system for a pulmonary nodule in a chest CT (Computed Tomography) image. The system provides improvements for the problems of large calculated amount of computer aided software, inaccurate prediction and few prediction varieties. The improvement of the invention comprises the steps of acquiring a CT image; segmenting a pulmonary tissue; detecting a suspected nodular lesion area in the pulmonary tissue; classifying nidi based on a nidus classification model of deep learning; and outputting an image mark and a diagnosis report. The system has high nodule detection rate and relatively low false positive rate, acquires an accurate locating, quantitative and qualitative result of a nodular lesion and a prediction probability thereof. The end-to-end (from a CT machine end to a doctor end) nodular lesion screening is truly realized, the accuracy and operability demands of doctors are satisfied and the system has wide mar5ket application prospects.

A method and system for the automated detection and analysis of pulmonary nodules in computed tomographic scans which uses data from computed tomography (CT) scans taken at different times is described. The method and system includes processing CT lung images to identify structures in the images for one patient in each of a plurality of different studies and then relating the plurality of CT lung images taken from the patient in one CT study with a plurality of CT lung images taken from the same patient in at least one other different study to detect changes in structures within the CT images.

The invention discloses a CT image pulmonary nodule detection system based on 3D full-connection convolution neural network. The detection system comprises the following five steps: constructing a training set data; performing 3D convolution neural network classification network training; performing 3D convolution neural network segmentation network training; carrying out false-positive suppression in which the trained segmentation network and the false-positive are utilized to inhibit the network; and detecting the pulmonary nodule. The technical schemes of the invention can realize the full automatic detection without any human intervention. At the same time, the recall rate of pulmonary nodule detection can be increased effectively; the false-positive focus of infection is reduced considerably; and a pixel level positioning quantitative and qualitative result for the focus-of-infection area of the pulmonary nodule can be obtained.

Systems, methods, and devices for biopsying tissue, in particular lung nodules, with a flexible needle are described herein. Preferably, the flexible needle is able to articulate or bend so as to provide access to areas previously difficult or impossible to biopsy. Further embodiments provide for steering and navigating the flexible needle to a region to be biopsied.

The invention discloses a method for grading and managing detection of pulmonary nodes based on in-depth learning. The method for grading and managing detection of the pulmonary nodes based on in-depth learning is characterized by comprising the steps of S100, collecting a chest ultralow-dose-spiral CT thin slice image, sketching a lung area in the CT image, and labeling all pulmonary nodes in the lung area; S200, training a lung area segmentation network, a suspected pulmonary node detection network and a pulmonary node sifting grading network; S300, obtaining pulmonary node temporal sequences of all patients in an image set and grading information marks corresponding to the pulmonary node sequences to construct a pulmonary node management database; S400, training a lung cancer diagnosis network based on a three-dimensional convolutional neural network and a long-short-term memory network. According to the method for grading and managing detection of the pulmonary nodes based on in-depth learning, the lung area segmentation network, the suspected pulmonary node detection network, the pulmonary node sifting grading network and the lung cancer diagnosis network are trained based on in-depth learning, the pulmonary nodes are accurately detected, and through the combination of subsequent tracking and visiting, more accurate diagnosis information and clinic strategies are obtained.

A computer aided diagnostic system and automated method diagnose lung cancer through tracking of the growth rate of detected pulmonary nodules over time. The growth rate between first and second chest scans taken at first and second times is determined by segmenting out a nodule from its surrounding lung tissue and calculating the volume of the nodule only after the image data for lung tissue (which also includes image data for a nodule) has been segmented from the chest scans and the segmented lung tissue from the chest scans has been globally and locally aligned to compensate for positional variations in the chest scans as well as variations due to heartbeat and respiration during scanning. Segmentation may be performed using a segmentation technique that utilizes both intensity (color or grayscale) and spatial information, while registration may be performed using a registration technique that registers lung tissue represented in first and second data sets using both a global registration and a local registration to account for changes in a patient's orientation due in part to positional variances and variances due to heartbeat and / or respiration.

The invention discloses a generative adversarial network improved CT medical image pulmonary nodule detection method. The method includes: 1), acquiring a section of a pulmonary CT image; 2), separating according to image morphological properties to acquire a ROI pulmonary parenchyma area; 3), acquiring different suspected pulmonary nodule candidate sets according to a connected domain formed by abinarized image; 4), building a model of an assistant classifier generative adversarial network to generate positive samples overcome the circumstance that positive-negative sample number is unbalanced; 5), building a convolution neural network to classify suspected pulmonary nodule parts to acquire pulmonary nodule areas; 6), using a non-maximum suppression algorithm to acquire a final area of pulmonary nodule. By the method, efficient processing performance of a computer can be fully utilized, certain expandability is provided, and data processing efficiency is improved; through a convolution neural network algorithm, classifying accuracy is improved, CT image data processing performance is improved, and pulmonary nodule images can be built and analyzed more efficiently.

The invention provides a pulmonary nodule benignity and malignancy predicting method based on convolutional neural networks. The pulmonary nodule benignity and malignancy predicting method based on the convolutional neural networks comprises obtaining multi-scale pulmonary nodule image blocks from pulmonary nodule coordinates; according to the multi-scale pulmonary nodule image blocks, structuring the convolutional neural network corresponding to every multi-scale pulmonary nodule image block; according to a loss function, training the convolutional neural networks through the multi-scale pulmonary nodule image blocks; extracting low-dimensional features of pulmonary nodules through the trained convolutional neural networks; training a non-linear classifier through the low-dimensional features and predicting unknown pulmonary nodule image blocks. The pulmonary nodule benignity and malignancy predicting method based on the convolutional neural networks can accurately predict the benignity and malignancy of the unknown pulmonary nodule image blocks.

The invention relates to a deep model and shallow model decision fusion-based pulmonary nodule CT image automatic classification method. Deep convolutional neural network-based features and visual features describing pulmonary nodule textures and shapes are extracted. Three classifiers are trained for the three different features, and results of all the classifiers are subjected to weighted averaging to obtain a final classification result. Therefore, the innovation of a CT image-based pulmonary nodule classification method is realized.

An embodiment of the invention discloses an image identification method. The method comprises: obtaining a training image set, wherein the training image set comprises a pulmonary nodule region image and a non pulmonary nodule region image; constructing a deep convolutional neural network, and taking the pulmonary nodule region image carrying a pulmonary nodule identifier and the non pulmonary nodule region image carrying a non pulmonary nodule identifier as inputs for training the deep convolutional neural network; constructing a testing network according to the deep convolutional neural network obtained by training; and obtaining a suspected pulmonary nodule region image, and inputting the suspected pulmonary nodule region image into the testing network to obtain a judgment result of judgment whether a pulmonary nodule exists in the suspected pulmonary nodule region image or not, thereby realizing identification of the suspected pulmonary nodule region image. An embodiment of the invention furthermore discloses an image identification apparatus. According to the image identification method and apparatus, the identification accuracy of the suspected pulmonary nodule region image is improved.

A pulmonary nodule detection device and method based on a shape template matching and combining classifier comprises an input unit, a pulmonary parenchyma region processing unit, a ROI (region of interest) extraction unit, a coarse screening unit, a feature extraction unit and a secondary detection unit. The input unit is used for inputting pulmonary CT sectional sequence images in format DICOM; the pulmonary parenchyma region processing unit is used for segmenting pulmonary parenchyma regions from the CT sectional sequence images, repairing the segmented pulmonary parenchyma regions by the boundary encoding algorithm and reconstructing the pulmonary parenchyma regions by the surface rendering algorithm after the three-dimensional observation and repairing; the ROI extraction unit is used for setting a gray level threshold and extracting the ROI according to the repaired pulmonary parenchyma regions; the coarse screening unit is used for performing coarse screening on the ROI by the pulmonary nodule morphological feature design template matching algorithm and acquiring selective pulmonary nodule regions; the feature extraction unit is used for extracting various feature parameters as sample sets for the post detection according to selective nodule gray levels and morphological features; the secondary detection unit is used for performing secondary detection on the selective nodule regions through a vector machine classifier and acquiring the final detection result.

The present invention provides a unique profile of volatile organic compounds as breath biomarkers for lung cancer. The present invention further provides the diagnosis, prognosis and monitoring of lung cancer or predicting the response to an anti-cancer treatment through the detection of the unique profile of volatile organic compounds indicative of lung cancer at its various stages.

The invention discloses a pulmonary nodule automatic detection method and system based on a chest CT image; the method comprises the following steps: receiving a chest CT image, using a preset 3D convolution nerve network to carry out pulmonary nodule focus detection for the chest CT image, and outputting a detection result; receiving the CT image and the detection result, and loading the detection result with the corresponding chest CT image to form a fused file; obtaining the fused file and carrying out visualization treatment, providing browse auxiliary operations for users on the fused file with the visualization treatment, and providing a calculation and measuring function. The method and system can isolate lung areas, extract candidate pulmonary nodules and remove false positives, thus improving focus detection efficiency, and the false positive efficiency can reach 97.7%. the method can use visualization three dimensional forms to directly assist a doctor to determine the pulmonary nodule forms.

The invention belongs to the application field of computer analysis technology of medical image, and relates to a pulmonary nodule three-dimensional segmentation and feature extraction method and a system thereof based on chest CT. By adopting a level set method based on a three-dimensional space, pulmonary nodule is divided within a three-dimensional interest area, and the feature of the nodule can be extracted by combining the characteristics of a bounding curved surface and the interest area of the pulmonary nodule. The invention comprises a lung area segmentation module, a three-dimensional interest area extracting module, a pulmonary nodule three-dimensional segmentation module, a nodule feature extraction and quantification module and an output module. The invention fully utilizes the three-dimensional space information of HRCT image, thus reducing the interference of normal tissues around the nodule for segmentation and feature extraction, and improving the accuracy of feature extraction.

The invention discloses a system and a method of detecting a pulmonary nodule. The system comprises an image preprocessing module, a three-dimensional RPN network model and a three-dimensional capsulenetwork model, wherein the image preprocessing module is used for preprocessing an original three-dimensional CT image to acquire a standard CT image; the three-dimensional RPN network model is usedfor detecting a first candidate pulmonary nodule from the standard CT image outputted from the image preprocessing module; and the three-dimensional capsule network model is used for carrying out false positive pulmonary nodule screening on the first candidate pulmonary nodule outputted by the three-dimensional RPN network model to acquire a pulmonary nodule detection result. According to the technical scheme provided in the invention, while the false positive pulmonary nodule detection rate is ensured to be lower, a high recall ratio is ensured to be realized for the pulmonary nodule, and thedetection method is simple and the detection speed is quick.

The invention provides a CT image pulmonary nodule detection method and device, an apparatus, and a readable storage medium. The CT image pulmonary nodule detection method comprises the following step: acquiring a CT image to be detected, performing pixel segmentation processing on the CT image through a pre-stored three-dimensional convolution neural pixel segmentation network to obtain a probability map corresponding to the CT image, and marking the probability map with a connectivity domain to obtain a candidate nodule region; predicting the candidate nodule region by a plurality of modelscorresponding to different pre-stored three-dimensional convolution neural network classifiers, obtaining each probability prediction value corresponding to the candidate nodule region, and fusing theprobability prediction values to obtain a classification result of the candidate nodule region. The invention solves the technical problem of poor accuracy of automatic detection of lung nodules based on CT images.

The invention relates to a lung nodule detection method based on a three-dimensional convolution neural network, which adopts a network structure of a feature pyramid and an attention mechanism,. Themethod integrates features of low-level and high-resolution and high-level abstract features, and enables the network to concentrate attention on a target area. The method has the effects of using three-dimensional convolution neural network detection method, end-to-end detection of pulmonary nodules, and reducing the time overhead. Compared with the traditional methods, the method can improve therecall rate and average accuracy of nodule detection.

A method of detecting lung nodules in an anterior posterior x-ray radiograph comprising the steps of: generating candidate regions in image showing changes in contrast above a threshold level, and eliminating false positives by eliminating edges assignable to organs by: identifying edges; categorizing and eliminating rib edges; categorizing and eliminating lung tissue edges, and categorizing and eliminating blood vessels.

A CT image pulmonary nodule detection method based on a 3D residual convolutional neural network includes a training process and a testing process. The training process includes the following steps: S1, preprocessing an original image, resetting the voxel spacing to (1, 1, 1), and converting the voxel spacing into voxel coordinates; S2, capturing 3D positive and negative samples from a CT image; S3, setting a maximum and a minimum, and standardizing the sample data; S4, constructing a 3D convolutional neural network; S6, setting training hyper-parameters, and importing the training hyper-parameters to a data training model in the form of mini-batch; and S6, saving the model after the model is fully trained. The testing process includes a step S7: preprocessing test CTs, sampling the test CTs one by one in the form of sliders, importing the test CTs to the model for calculation, selecting samples with high confidence, and deleting repeated samples through a non-maximum suppression algorithm. The method is of high accuracy, and can be used to analyze whether there is a nodule in an image and the specific position of the nodule in the image.

The invention discloses a pulmonary nodule benignity and malignancy detection method based on feature-fusion convolutional neural network. According to the method, first a position area of a pulmonarynodule needs to be drawn in a lung CT image according to marking of an expert, then an area of interest of the pulmonary nodule is segmented according to the position information, and images having the same size and only containing the pulmonary nodule are obtained; next, HOG features and LBP features of the pulmonary nodule images are extracted to obtain corresponding visual feature maps; and then the pulmonary nodule images, LBP feature graph and HOG feature map are used as input of a convolutional neural network to carry out convolution operation, image features are further extracted, andfinally, the probability that the pulmonary nodule is benign or malignant is obtained through classification. In the process of feature extraction, since what LBP and HOG extract is local information,what the convolutional neural network extracts is global information, traditional features and convolutional neural network (CNN) features are fused to carry out a pulmonary nodule benignity and malignancy analysis, a higher accuracy rate can be obtained, and better robustness is achieved.

A method for the detection of target structures shown in digital medical images, the method of comprising: (1) generating a three dimensional (3D) volumetric data set of a patient region within which the target structure resides from a plurality of segmented medical image slices; (2) grouping contiguous structures that are depicted in the 3D volumetric data set to create corresponding grouped structure data sets; (3) assigning each grouped structure data set to one of a plurality of detection algorithms, each detection algorithm being configured to detect a different type of target structure; and (4) processing each grouped structure data set according to its assigned detection algorithm to thereby detect whether any target structures are present in the medical images. Preferably, the target structures are pulmonary nodules, and a specialized detection algorithm is applied to image data classified as a candidate for depicting perivascular nodules. To segment perivascular nodule candidates from surrounding vessels, the image data is preferably correlated with a plurality of 3D morphological filters.

The present invention relates to a method for automatically detecting and delineating the location of pulmonary nodules based on a convolutional classifier, including: (1) delineating and storing the positions of pulmonary nodules and suspected pulmonary nodules, marking and storing pulmonary nodules (2) check whether the stored information in step (1) is correct; (3) the position of the pulmonary nodule and the position of the suspected pulmonary nodule outlined in step (1) are the ROI area, Perform translation, scaling, rotation, compound rotation, and a combination of two or more of translation, scaling, rotation, and compound rotation, and use all the obtained operation results as a sample set; (4) input some samples in the sample set into the convolution The neural network classifier outputs the correct ROI area where the pulmonary nodule is located and the correct ROI area where the suspected pulmonary nodule is located. With the data set obtained by this method, the detection accuracy rate is increased by more than 5%, and the false positive is reduced by more than 0.4%.

The invention relates to the technical field of computer vision, and provides a pulmonary nodule image classification method when uncertain data is contained in a data set. The method comprises the following steps: firstly, collecting a pulmonary nodule CT image set, determining the category of the image through a majority voting principle by utilizing an expert voting method, and preprocessing toobtain a pulmonary nodule CT image data set; then, based on a knowledge distillation method, constructing a pulmonary nodule image classification model comprising a teacher model and a student model;next, obtaining a determined tag data set, training a teacher model on the determined tag data set, and calculating a soft tag on the pulmonary nodule CT image data set; then, training a student model on the data set combining the hard label and the soft label; and finally, inputting the preprocessed CT image to be classified into the trained lung nodule image classification model to obtain the category of the lung nodule image classification model. According to the method, the uncertain label data in the data set can be effectively utilized, the accuracy and efficiency of pulmonary nodule diagnosis are improved, and the usability and robustness are high.

The invention discloses a deep learning method-based automatic pulmonary nodule detection method. The method comprises the following steps of: a, preprocessing: acquiring CT files of a plurality of patients so as to form a data set, and making the CT file corresponding to each patient to a CT file comprising 100-600 slices, wherein a pixel separation distance of each slice is 1*1*1 mm, and the size of each slice is 512*512 pixel; b, lung area image extraction: carrying out pixel value binarization on the CT file of each patient on the basis of a Heinz unit value so as to obtain a mask map of alung area, and extracting a lung area image according to the mask map; c, pulmonary nodule detection: detecting a U-Net convolutional neural network to carrying out pulmonary nodule detection on thelung area image so as to obtain a U-Net training model; and d, false positive rate reduction: training a deep residual network to get rid of false positive points of pulmonary nodules in the U-Net training model so as to obtain a detection model, and carrying out automatic pulmonary nodule detection on the CT files of the patients by using the detection model. The method is high in automatic detection precision.

The invention discloses a supervoxel sequence lung image 3D pulmonary nodule segmentation method based on multimodal data. The method comprises the following steps: A) extracting sequence lung parenchyma images through superpixel segmentation and self-generating neuronal forest clustering; B) registering the sequence lung parenchyma images through PET / CT multimodal data based on mutual information; C) marking and extracting an accurate sequence pulmonary nodule region through a multi-scale variable circular template matching algorithm; and D) carrying out three-dimensional reconstruction on the sequence pulmonary nodule images through a supervoxel 3D region growth algorithm to obtain a final three-dimensional shape of pulmonary nodules. The method forms a 3D reconstruction area of the pulmonary nodules through the supervoxel 3D region growth algorithm, and can reflect dynamic relation between pulmonary lesions and surrounding tissues, so that features of shape, size and appearance of the pulmonary nodules as well as adhesion conditions of the pulmonary nodules with surrounding pleura or blood vessels can be known visually.

A computer aided diagnostic system and automated method diagnose lung cancer through modeling and analyzing the shape of pulmonary nodules. A model used in such analysis describes the shape of pulmonary nodules in terms of spherical harmonics required to delineate a unit sphere corresponding to the pulmonary nodule to a model of the pulmonary nodule.

The invention discloses a pulmonary nodule detection method and system based on a CT image. The detection method specifically comprises the following steps: (1) rapid positioning processing based on aUNet network: obtaining a mask of a suspected pulmonary nodule by using a model based on the UNet network; (2) target detection processing based on a DSSD network: processing an image block corresponding to the pulmonary nodule mask obtained in the step (1) by using a DSSD network-based model to obtain a pulmonary nodule detection result; And (3) false positive screening processing based on 3DCNN: screening the candidate nodules by using a 3DCNN-based model to remove the false positive nodules. Compared with the prior art, the whole process of the method for detecting the pulmonary nodules inthe CT image and the design of all functional modules are improved, ideal detection performance is achieved, that is, the method can be used for detecting various types of pulmonary nodules, and compared with the prior art, manual intervention on a detection result can be effectively reduced.

The invention discloses a pulmonary nodule edge rebuilding and partitioning method based on a computed tomography (CT) image. According to the pulmonary nodule edge rebuilding and partitioning method, the image is subjected to spatial transformation by using a transformation method which has a sparse representation ability on gradient characteristics; a high energy transformation coefficient is reserved through shrinkage of a transformation domain; the image is rebuilt through inverse transformation to realize strengthening of the gradient characteristics; and amplification of small signals of the gradient characteristics is realized through multistage strengthening of the signals, a pulmonary nodule edge is rebuilt, and important edge information is provided for subsequent partitioning. The pulmonary nodule edge rebuilding and partitioning method provides a clustering-based pulmonary nodule partitioning algorithm, does not have the process of a training classifier, has a self-training ability, and can be used for strengthening edge detection, overcoming partitioning difficulty caused by uneven gray levels, and eliminating influence by speckle noise. The pulmonary nodule edge rebuilding and partitioning method can also be used for establishing a CT image partitioning algorithm evaluation system and combining contours drawn manually by different clinical medical experts into optimum partitioning standards so that the partitioning algorithm can be compared systematically, and the effectiveness of the partitioning algorithm can be revealed.

The invention relates to a method for three-dimensionally segmenting an insubstantial pulmonary nodule based on a fuzzy membership model. The method comprises the following steps of: manually acquiring a region of interest, which includes the insubstantial pulmonary nodule, and performing subsequent processing in the region of interest; removing substantial parts which have larger gray values and comprise blood vessels, calcified points and the like by using threshold operation; establishing the fuzzy membership model of the insubstantial pulmonary nodule, calculating the membership, of each volume pixel, of the insubstantial pulmonary nodule according to the fuzzy membership model, and classifying the volume pixels based on the calculated membership by using a linear discriminant function; and for the insubstantial pulmonary nodule which is connected with the blood vessels, removing the blood vessels by using a Hessian matrix characteristic value, and thus obtaining a final segmentation result by using a three-dimensional connected region mark. Compared with other domestic and foreign methods for segmenting the insubstantial pulmonary nodule in recent years, the method for three-dimensionally segmenting the insubstantial pulmonary nodule based on the fuzzy membership model has the advantage that: the segmentation accuracy of the insubstantial pulmonary nodule is effectively improved.

A method of generating a pulmonary nodule image from a chest radiograph. The method includes the steps of: producing a map of a clear lung field; removing low frequency variation from the clear lung field to generate a level image; and performing at least one grayscale morphological operation on the level image to generate a nodule-bone image. Pulmonary nodules can be detected using the nodule-bone image by the further steps of: pulmonary nodules from a chest radiograph. The method includes the steps of: identifying candidate nodule locations in the nodule-bone image; segmenting a region around each candidate nodule location in the nodule-bone image; and using the features of the segmented region to determine if a candidate is a nodule.