77 results about "Lung field" patented technology

A method of detecting a pleural plaque candidate from a medical image, which includes the steps of obtaining a medical image representing a subject, extracting a lung field area from the obtained medical image, comparing a contour of the extracted lung field with a comparison contour obtained by causing an active curve, having an initial shape in the lung field area and repeats deformation according to a certain deformation trend, to converge after repeating the deformation and detecting a depressed portion of the lung field, and determining the detected depressed portion as a first pleural plaque candidate.

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.

In consideration of the fact that a lung field varies in the density of sponge-like tissue depending on an individual or display region, an opacity curve which gives priority to a nodule candidate region or an extended nodule candidate region can be set by generating a histogram concerning a volume of interest which includes a foreground region, and using the statistical analysis result on the histogram as an objective index.

A system and computation method is disclosed that identifies radiation-induced lung injury after radiation therapy using 4D computed tomography (CT) scans. After deformable image registration, the method segments lung fields, extracts functional and textural features, and classifies lung tissues. The deformable registration locally aligns consecutive phases of the respiratory cycle using gradient descent minimization of the conventional dissimilarity metric. Then an adaptive shape prior, a first-order intensity model, and a second-order lung tissues homogeneity descriptor are integrated to segment the lung fields. In addition to common lung functionality features, such as ventilation and elasticity, specific regional textural features are estimated by modeling the segmented images as samples of a novel 7th-order contrast-offset-invariant Markov-Gibbs random field (MGRF). Finally, a tissue classifier is applied to distinguish between the injured and normal lung tissues.

Extracting a lung field area and a branch structure area from a three-dimensional medical image, dividing a branch structure local area representing a portion of the branch structure area into a plurality of branch structure local sub-areas and estimating a lung field local sub-area in the lung field area functionally associated with each divided branch structure local sub-area based on the branch structure area, obtaining a pulmonary evaluation value in each estimated lung field local sub-area, and displaying, in a morphological image representing morphology of at least a portion of the branch structure local area, the pulmonary evaluation value in each lung field local sub-area functionally associated with each branch structure local sub-area in the morphological image superimposed such that correspondence relationship between the pulmonary evaluation value and the branch structure local sub-area in the morphological image is visually recognizable.

N images in a respiratory cycle which are radiographed in year P are input, and binary lung field images are extracted from the respective front chest images. Lung field areas S and lung field heights are then calculated. In forming area and height variation waveforms, regions of the N input images are obtained and plotted. Each image is determined as an image belonging to the inspiration mode or expiration mode. The respective images are sorted and stored. Similar processing is performed for N images in a respiratory cycle which are radiographed in year P+1, and the resultant images are stored. Difference images are obtained from the basic images radiographed in year P+1 and the reference images radiographed in year P for each mode by image analysis, thereby extracting changes over time.

A method for clavicle suppression in a chest x-ray image. The method identifies the lung fields in the x-ray image and detects at least one portion of a clavicle ridge that lies outside the lung fields. Edges of a clavicle on each side of the detected clavicle ridge are detected, edge detection extended for the clavicle edges into the lung fields, and the clavicle defined within the x-ray image according to the edge detection. The clavicle is suppressed within the x-ray image to generate a clavicle-suppressed x-ray image and the clavicle-suppressed x-ray image is displayed, stored, or transmitted.

A radiographic image capturing apparatus captures consecutive radiographic images on the basis of the radiation intensity distribution transmitted through a subject, and extracts lung field parts from the captured consecutive radiographic images. A fluctuation condition is detected from the extracted lung field parts, and whether or not the respiratory condition of the subject is suited to radiograph a respiratory behavior is determined on the basis of the detected fluctuation condition.

According to one implementation, a thoracic diagnosis assistance information generation method includes the following. A dynamic state of a chest portion is captured to generate frame images. Air velocity is calculated by dividing a lung field region extracted from one frame region into small regions, corresponding the small regions among the frame images, and calculating a feature amount showing air velocity. Air velocity distribution is calculated by dividing the lung field region into block regions in a trunk axis direction, calculating a feature amount showing air velocity of each block region based on a feature amount showing the air velocity of the small regions in the divided block regions, and calculating a feature amount showing air velocity distribution of the lung field region based on the calculated feature amount showing the air velocity of each block region.

The invention discloses a chest radiography lung field segmentation model establishment based on multi-scale feature fusion and segmentation method. A segmentation model establishing method comprisesthe following steps: firstly, processing an X-ray chest radiograph; obtaining a preprocessed picture and a recoded mask picture, then constructing an X-ray chest radiography lung field segmentation network based on multi-scale convolution and a feature pyramid, and finally training the segmentation network by using the preprocessed picture as an input of the segmentation network and using the recoded mask picture as an output of the segmentation network to obtain a trained segmentation model; and based on the obtained segmentation model, preprocessing any to-be-processed X-ray chest radiograph, and inputting the preprocessed X-ray chest radiograph into the segmentation model to obtain a lung field segmentation result. According to the method, multi-resolution feature fusion is provided incombination with a feature pyramid theory, wherein the segmentation results with different resolutions can be fused, so that the segmentation effect is improved.

A dynamic analysis system includes an imaging device and an analysis device. The imaging device performs dynamic imaging by emitting radiation to a chest part of a human body, thereby obtaining a series of frame images showing a dynamic state of the chest part. The analysis device includes a controller. The controller (i) selects a first plurality of frame images to be analyzed from the series of frame images obtained by the imaging device, (ii) calculates, based on the first plurality of frame images, a ventilation amount index value that indicates an amount of ventilation of a lung field and a perfusion amount index value that indicates an amount of perfusion of the lung field, and (iii) calculates a ratio of the ventilation amount index value to the perfusion amount index value.

An image processing device includes an acquiring unit configured to acquire a medical video image obtained by imaging of lungs, a holding unit configured to hold a lung field motion model, the lung field motion model simulating lung field motion, and a processing unit configured to process the medical video image by using the lung field motion model.

The invention is able to provide physicians with information that facilitates understanding of the clinical features of lung field ventilation and is effective for diagnosis. In particular, diagnostic information is provided with which appropriate diagnoses can be made even by physicians with little practical experience in using stethoscopes. With the diagnostic console (3) of this thoracic diagnosis assistance system (100), the control unit (31) extracts lung field regions from each of the multiple image frames obtained by imaging the movements of the chest, divides the extracted lung field regions into a plurality of sub-regions, and correlates the various sub-regions between the multiple image frames. Thereafter, the multiple image frames corresponding to each sub-region are analyzed, characteristic inspiratory values and characteristic expiratory values are calculated for each sub-region, ratios of the calculated characteristic inspiratory values to characteristic expiratory values are calculated and histograms of the ratios thus calculated are generated. The generated histograms are displayed on the display unit (34).

The invention relates to a system and method for diagnosing lung disease by a computer. The diagnostic system comprises a first training unit, a second training unit, a segmentation unit, and an assessment unit, wherein the first training unit is used for generating an average lung shape model based on a plurality of first figure X-ray image samples; the second training unit is used for generating at least one lung area classifier model for classifying characteristics of the lung disease based on a plurality of second figure X-ray image samples; the segmentation unit is used for generating a lung field image through segmenting a to-be-diagnosed figure X-ray image and based on the average lung shape model; the assessment unit is used for comparing the lung area classifier model with the lung field image to analyze the characteristics of the lung disease in the to-be-diagnosed figure X-ray image.

A dynamic image processing apparatus includes: a hardware processor that: extracts a lung-field region from at least one of a plurality of frame images of a chest dynamic image obtained by radiographing a dynamic state of a chest of an examinee; sets a feature point in a position that moves according to a movement of a lung field due to respiration in the lung-field region extracted by the hardware processor; searches a frame image other than a frame image in which the feature point has been set for a corresponding point that corresponds to the feature point set by the hardware processor, and estimates a correspondence relationship of each pixel in the lung-field region among the plurality of frame images in accordance with a positional relationship between the feature point set by the hardware processor and the corresponding point searched for by the hardware processor.

Provided is a GUI-containing system that effectively utilizes kymographic images, integrates information to be used for diagnosis in a viewing system and allows accurate diagnosis even by physicians who have little experience with stethoscopes. With this diagnosis assistance system (100), a control unit (31) of a diagnostic console (3) extracts the lung field regions from the respective image frames of a plurality of image frames representing the movements of the chest, which have been transmitted from an imaging console (2); divides said extracted lung field regions into a plurality of sub-regions; correlates the divided sub-regions in the plurality of image frames with each other and analyses same; thereby calculating previously established characteristic quantities that represent the movement of the divided sub-regions. When the regions for display of analysis results are selected by the operating unit (33), the characteristic quantities for the selected sub-regions are displayed.

The invention belongs to the technical field of machine learning, and particularly relates to a lung medical image analysis method, device and system. The lung medical image analysis method comprises the steps of segmenting a lung field and a lung lesion area from an acquired lung medical image, calculating an ROI (Region of Interest) containing the lung field and the lung lesion area, and cutting an input picture for image recognition in the lung medical image according to the ROI. And inputting the input picture into a second-stage detection model, further extracting feature parameters, and obtaining a final lesion analysis result output by a preset semantic segmentation model. By means of the lung medical image analysis method, device and system, multiple lung lesions can be recognized and classified and judged at the same time, and the device is high in efficiency and accuracy of lung medical image analysis and has good application prospects.

The invention relates to an image processing technology, and discloses electronic equipment, a medium and a medical image index generation method and device. The method comprises the steps of judgingwhether a thoracic cavity image is abnormal or not by utilizing a classification network; when the thoracic cavity image is abnormal, obtaining a lung field segmentation index of the thoracic cavity image by utilizing the lung field segmentation sub-network; obtaining a heart segmentation index of the thoracic cavity image by utilizing the heart segmentation sub-network; utilizing the spine segmentation sub-network to obtain spine segmentation indexes of the thoracic cavity image; calculating a cardiothoracic ratio index according to the lung field segmentation index and the heart segmentationindex; obtaining lung field lesion segmentation indexes of the thoracic cavity image by utilizing the lung field lesion sub-network; and pushing the spine segmentation index, the cardiothoracic ratioindex and the lung field focus segmentation index to the user. The invention relates to the field of digital medical treatment. The electronic equipment, and the medical image index generation methodand device and the computer readable storage medium can be applied to medical image analysis. According to the invention, the medical index data in the medical image can be obtained.

The invention provides a lung image segmentation method and device and a training method of an image segmentation model, and the method comprises the steps: inputting lung image data into the image segmentation model, and obtaining segmented first image data; performing post-processing on the first image data based on a full-connection conditional random field model to obtain second image data; and obtaining a lung field segmentation image based on the second image data. According to the technical scheme, the lung field segmentation images with continuous and clear boundaries can be obtained.

The invention provides a sequential AI diagnosis model chest X-ray intelligent diagnosis system. The sequential AI diagnosis model chest X-ray intelligent diagnosis system comprises an image classification module for identifying a normal chest radiograph image in a DICOM image; the image quality judgment module extracts an orthotopic chest radiography image meeting a preset condition and defines the orthotopic chest radiography image as a qualified image; the postoperative and implanted object diagnosis module is used for detecting whether postoperative or implanted objects exist in the qualified images or not; the lung field segmentation diagnosis module is used for segmenting the lung field on a qualified image without an operation or an implant; the binary classification diagnosis module performs positive and abnormal diagnosis on the lung field; the AI scheme management module judges the operation sequence of each module, and sends the qualified images and the diagnosis data outputby the modules which are operated in advance to the modules which are operated in the later period according to preset configuration; the structured report module automatically generates a diagnosticimpression based on the diagnostic data of each module. The invention further discloses a chest X-ray intelligent diagnosis method of the sequential AI diagnosis model. According to the invention, the diagnosis accuracy is improved, and the examination cost is reduced.

Provided is a diagnostic support program that is possible to display a movement of an area whose shape changes for each respiratory element including all or part of expired air or inspired air.There are provided processing of acquiring a plurality of frame images from a database that stores images, processing of specifying of a cycle of a respiratory element including all or part of expired air or inspired air based on pixels in a specific area in each of the frame images, processing of detecting a lung field based on the cycle of the specified respiratory element, processing of dividing the detected lung field into a plurality of block areas and calculating a change in image in a block area in each of the frame images, processing of Fourier-transforming a change in image in each block area in each of the frame images, processing of extracting a spectrum in a fixed band including a spectrum corresponding to the cycle of the respiratory element, out of a spectrum obtained after the Fourier-transforming, processing of performing inverse Fourier transform on the spectrum extracted from the fixed band, and processing of displaying each of the images after performing the inverse Fourier transform, on a display.

The invention discloses a non-small cell lung cancer subtype classification system based on multi-view deep learning, which realizes classification of lung adenocarcinoma and lung squamous carcinoma based on a CT image, generates and displays image data of an examined part based on volume data generated by performing lung CT on an examined body, and obtains non-small cell lung cancer subtype classification result of the examined body. The non-small cell lung cancer pathological subtype classification system comprises an information acquisition module, a network module and a training module. According to the system, automatic lung field segmentation can be realized, interlayer information and three-dimensional information carried by a CT image are fully utilized by a multi-view model, an obtained classification model can be used as a tool for assisting a doctor through automatic feature extraction and classification training, and the system has the characteristics of high automation and high practicability.