521 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.

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.

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 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 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 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.

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.

The present invention is a multi-stage detection algorithm using a successive nodule candidate refinement approach. The detection algorithm involves four major steps. First, the lung region is segmented from a whole lung CT scan. This is followed by a hypothesis generation stage in which nodule candidate locations are identified from the lung region. In the third stage, nodule candidate sub-images pass through a streaking artifact removal process. The nodule candidates are then successively refined using a sequence of filters of increasing complexity. A first filter uses attachment area information to remove vessels and large vessel bifurcation points from the nodule candidate list. A second filter removes small bifurcation points. The invention also improves the consistency of nodule segmentations. This invention uses rigid-body registration, histogram-matching, and a rule-based adjustment system to remove missegmented voxels between two segmentations of the same nodule at different times.

The invention provides a pulmonary nodule benign and malignant prediction method and device, and the method comprises the steps: obtaining a chest flat-scanning thin-layer CT image, carrying out region-of-interest delineation of pulmonary nodules in the CT image layer by layer to acquire the clinical information and pathological information of a patient; extracting an image omics feature of the pulmonary nodule in the region-of-interest based on a PyRadio toolkit; screening the image omics features by using a plurality of feature selection algorithms; training a deep convolutional neural network model by using the CT image to acquire deep learning features, forming a multi-dimensional clinical feature vector in combination with clinical information of the patient, and splicing the deep learning features, the clinical features and the imaging omics features to obtain a multi-modal feature vector; and establishing a pulmonary nodule benign and malignant prediction model by using variousclassifier algorithms based on the multi-modal feature vector, and analyzing a prediction result by using the pathological information of the patient to obtain an optimal pulmonary nodule benign and malignant prediction model to perform benign and malignant prediction on the pulmonary nodule.