255 results about "Imaging interpretation" patented technology

An automated three dimensional mapping and display system for a diagnostic ultrasound system is presented. According to the invention, ultrasound probe position registration is automated, the position of each pixel in the ultrasound image in reference to selected anatomical references is calculated, and specified information is stored on command. The system, during real time ultrasound scanning, enables the ultrasound probe position and orientation to be continuously displayed over a body or body part diagram, thereby facilitating scanning and images interpretation of stored information. The system can then record single or multiple ultrasound free hand two-dimensional (also “2D”) frames in a video sequence (clip) or cine loop wherein multiple 2D frames of one or more video sequences corresponding to a scanned volume can be reconstructed in three-dimensional (also “3D”) volume images corresponding to the scanned region, using known 3D reconstruction algorithms. In later examinations, the exact location and position of the transducer can be recreated along three dimensional or two dimensional axis points enabling known targets to be viewed from an exact, known position.

Digital image signal interpretation is the process of understanding the content of an image through the identification of significant objects or regions in the image and analysing their spatial arrangement. Traditionally the task of image interpretation required human analysis. This is expensive and time consuming, consequently considerable research has been directed towards constructing automated image interpretation systems. A method of interpreting a digital video signal is disclosed whereby the digital video signal has contextual data. The method comprising the steps of firstly, segmenting the digital video signal into one or more video segments, each segment having a corresponding portion of the contextual data. Secondly, analysing each video segment to provide a graph at one or more temporal instances in the respective video segment dependent upon the corresponding portion of the contextual data.

According to the medical image display apparatus of an aspect of the present invention, the display mode to provide multi-screen display of the plurality of slice images including the abnormal shadow region is determined based on the result of acquisition of the abnormal shadow region (three-dimensional information for the abnormal shadow region), which eliminates the necessity for users (doctors) to perform an operation to set a display mode, and enables display of the plurality of slice images including the abnormal shadow region efficiently in a display mode enabling easy image interpretation.

A method of classifying a digital image is disclosed. The method provides a region adjacency graph (310) representing the digital image and analyses the region adjacency graph (310) for predetermined patterns. For each identified pattern a classification of the digital image is selected. The region adjacency graph (310) is classified as one of a number of stereotypes.

The same subject can be accurately aligned for effective interpretation of two observation images representing a change in the subject and not adjacent to each other in three or more images arranged in temporal order of the change. The subject in one of the observation images is aligned to the subject in a transitional image adjacent to the observation image, and an aligned image is generated. The same procedure is repeated between the previous aligned image and a transitional image adjacent to the previous transitional image to generate another aligned image. A final aligned image is generated by aligning the subject in the observation image to the subject in a reference image. This procedure is carried out for the other observation image and a final aligned image is also generated by alignment to the reference image. A diagnostician compares the two final aligned images.

A link corresponding range is specified for any of strings arranged in an observation column in a medical report display screen. Then, a drag operation is input which specifies any of contents being displayed on a monitor. When a dragged display icon is dropped onto a link corresponding range displayed portion of a medical report creation screen to specify the string, address information on the content is acquired. The address information on the referenced content is then pasted to the string. At the same time, the string in the link corresponding range has its color changed and is underlined for identification. After the report has been completed, a file is saved and the series of operations are finished. Then, the file is transferred to, for example, an image interpretation report requester.

An image interpretation support system by which past image interpretation results on an examination as an object of follow-up observation can be easily grasped. The system has: a server for storing a report database accumulating difference information between past reports in association with the respective past reports; and an image interpretation report creating apparatus connected thereto. The apparatus includes: a follow-up observation examination determining unit for determining whether or not this examination is an object of follow-up observation; a report finding control unit for creating an image interpretation report at this time by generating an image interpretation report creation screen and entering information in the screen; a changed portion extracting unit for extracting a changed portion to generate difference information; and a report saving unit for storing the difference information in association with the report at this time and the past report in the report database.

There is provided a light-sensitive system responsive to light supplied by the system and less responsive to other light. The system includes a light source operable to supply time-modulated illumination, and a light sensor having greater response to the time-modulated illumination than to light from sources not so modulated. The invention may be embodied as a camera sensitive to supplied light and relatively insensitive to ambient light, and is useful in providing images for automated image interpretation. A method for photographing an object is also provided.

The number of similar case images to be displayed is changed according to the number of times and progress of imaging diagnosis. First examination judgment means is added to a medical image interpretation support system comprising storage means for storing image data sets obtained by imaging subjects, similar case image search means for extracting similar case image data sets having a characteristic similar to an interpretation target image from the image data sets, and display control means for controlling display of the interpretation target image and the similar case images. The display control means controls the display so as to display a larger number of the similar case images together with the interpretation target image in the case where the interpretation target image has been judged to be a first examination image than in the otherwise case.

A medical image interpretation system for displaying a medical image generated from a subject and for generating an interpretation report of the medical image, includes: a drawing section for drawing an annotation on an area of interest over the displayed medical image, the annotation being previously related to a text for interpretation report generation; and a report generating section for obtaining drawn position information and drawn size information of the annotation drawn by the drawing section, for obtaining region information of the medical image, and for generating the interpretation report of the medical image based on the obtained information and the text for interpretation report generation corresponding to the drawn annotation.

An image interpretation report creating apparatus for displaying a case in combination of an image interpretation report and a blood test result even if they are stored in different computers. The apparatus includes: a display unit for displaying an image interpretation report creation screen along with a blood test result; an input unit for specifying finding and a blood test result; a search key generating unit for generating search keys for searching an image interpretation report DB and a blood test result DB; a search processing unit for causing an image interpretation report server and an examination result server to obtain cases that match the search keys; a similarity degree determining unit for displaying the cases in an order of the degree of similarity; and an image interpretation report preservation unit for causing the image interpretation report server to store image interpretation report data.

A method for characterising texture or a texture-like region in an image includes the steps of obtaining saliency values (104) of an image or set of images and applying a threshold to the saliency values (108), to remove the less salient features. A three dimensional shape, for example a cuboid of a predefines size, is generated (210) and saliency space sampled by moving the cuboid across spatial dimensions of the saliency space. An estimation of z probablility density function of scales within that sample space is generated and texture or a texture-like region in the saliency space is characterised using the estimation. This provides a method by which texture can be classified within an image to aid image interpretation. In particular, the texture is classified independent of scale, orientation and illumination. The method is particularly useful for texture classification problems where: the scale is unknown, the scale may vary, or a general scene description is required.

The invention relates to a complex object automatic recognition method based on multi-category primitive self-learning, which comprises the steps of: a) establishing a representational set of multi-category object images; b) preprocessing images in a training set and respectively extracting point, linear and planar primitives; c) conducting concentrated matching calculation, screening and merging to the obtained numerous primitives in a confirmation image set, and respectively constructing point, linear and planar primitive dictionaries; and d) selecting a certain quantity of primitives from the dictionaries, using the primitives as a weak classifier after the primitives are mated and combined, and respectively training the strong classifiers of the three categories of primitives through self-learning; and e) combining the strong classifiers of the three categories of primitives in a probabilistic polling space to realize the accurate positioning, contour extraction and categorical recognition of multi-category complex objects. The method provided by the invention has the advantages that the intelligent level is high and the demands for the recognition and image interpretation of multi-category complex objects can be met.

When a series of present images have been taken at a follow-up examination of a patient, correspondence data is produced, showing correspondence between the respective present images and past images that were taken at past examinations of the same patient under similar condition. The correspondence data is stored in association with the present images. In a normal mode of an image interpretation making terminal, a designated one of the present images is displayed on a monitor. When a comparison mode is selected, such past images that correspond to the designated present image are retrieved from among those taken at the respective past examinations with reference to the correspondence data, so that the present image and the corresponding past images are displayed in turn or in parallel on the monitor.

The invention discloses an interpretation and evaluation method for a reservoir area engineering geological survey and particularly relates to a hierarchy interpretation method and a comprehensive evaluation method for reservoir area engineering geological survey and evaluation. According to the interpretation and evaluation method, the interpretation of bad geologic bodies of landslide, collapse, debris flow and the like can be achieved, the precision can meet a requirement of feasibility, and the comprehensive evaluation of engineering geological problems of reservoir leakage, reservoir bank stability, reservoir bank collapse, reservoir immersion, the debris flow and the like can be achieved. The steps of the interpretation and evaluation method includes firstly, establishing a geographic information system (GIS) data bank of a reservoir area engineering geology and a three-dimensional true color remote-sensing image visualization system; secondly, establishing remote-sensing interpretation marks of the bad geologic bodies of the landslide, the collapse, the debris flow and the like; thirdly, performing preliminary interpretation with geography interpretation as a priority; fourthly, performing outdoor verification by matching of image interpretation; fifthly, performing detailed comprehensive interpretation with three-dimensional interpretation as a priority; sixthly performing reservoir leakage comprehensive interpretation based on a GIS; seventhly, performing reservoir bank stability comprehensive interpretation based on the GIS; eighthly, performing reservoir bank collapse and reservoir immersion comprehensive interpretation based on the GIS; and ninthly, performing reservoir debris flow comprehensive interpretation based on the GIS.

Disclosed in this specification is a device configured to detect fractures in a bone by reflecting waves off of the bone. Certain parameters of the reflected wave are compared to a threshold condition. When the threshold condition is met, a first indication is generated. When the threshold condition is not met, a second indication is generated. This device allows detection of bone fractures without requiring that the user of the device be skilled in image interpretation (e.g. interpreting x-ray or ultrasound images).

In comparative image reading of projection images representing an observation target in two three-dimensional images of the same subject photographed at different times, alignment accuracy can be improved between the projection images and artifacts in subtraction images can be suppressed. In each of the three-dimensional images, pixels in a region specified by a cross section perpendicular to an observation direction and a thickness are projected, and the projection images are generated by repeating the procedure while moving a position of the cross section in the observation direction. Alignment processing and subtraction image generation is carried out between the corresponding projection images, and a superposed subtraction image is generated by superposing the generated subtraction images. Consequently, an effect of three-dimensional body movement of the subject at the time of photography can be suppressed than a projection image generated by projecting the entire observation target.

In embodiments, a medical image interpretation system has at least a medical image storing part, a medical image referring part, a medical record storing part, a process controlling part, an information extraction processing part, an image region specifying part, and an image processing part. The process controlling part specifies a medical image and extracts a medical record of a patient of the medical image. The information extraction processing part classifies terms on a sentence written in the medical record into predetermined types to structure the sentence, and extracts a region term from the structured sentence. The image region specifying part specifies the range of images showing a region corresponding to the region term from the medical image and specifies the position and range of the region. The image processing part displays at least the region position and range in a visually recognizable manner.

While an image obtained by a general electron microscope is affected by the shape and material of an object specimen, an image obtained from mirror electrons is affected by the shape of an equipotential surface on which the mirror electrons are reflected, thereby the image interpretation is complicated. A mirror electron microscope of the present invention is provided with the following means for controlling a reflecting plane of the mirror electrons according to the structure of an object pattern to be measured or a concerned defect.1) Means for controlling a potential difference between a specimen and an electron source equivalent to a height of a reflecting plane of a mirror electron beam according to a type, an operation condition of an electron source, and a type of a pattern on a specimen.2) Means for controlling an energy distribution of an illuminating beam with an energy filter 9 disposed in an illuminating system.It is thus possible to inspect a specimen according to a size and a potential of a pattern, which are distinguished from others.

A medical image is obtained and displayed. An electronic image interpretation report of the medical image is generated and displayed. The position of a lesion region in the medical image is input. A link character linked by a hyperlink to the medical image including the input position of the lesion region is inserted into the image interpretation report in such a manner that the link character is distinguishably displayed. The distinguishably displayed link character in the image interpretation report is selected. An index representing the position of the lesion region is displayed in the medical image based on the selection of the link character.

The invention discloses a medical image interpretation method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining an image analysis request which comprises a target medical image; adopting a pre-trained image recognition model to recognize the target medical image, and obtaining a feature map output by the last convolutional layer in the image recognition model; based on the feature map, obtaining a prediction probability value corresponding to each original focus category output by the image recognition model; determining the original lesion category with the maximum prediction probability value as a target lesion category; obtaining a map weight corresponding to a target lesion category, carrying out classified activation mapping on a characteristic map and the map weight by adopting an activation mapping formula, obtaining a thermodynamic mapping map, superposing the thermodynamic mapping map and a target medical image, generating a target thermodynamic map, and improving an image recognition rate.

More accurate search for similar cases can be carried out in the case where images at different time phases exist. A contrast enhancement information analysis unit obtains time phase information of search target images obtained at different time phases in the same examination from accompanying information of the images, and a similar case database storing similar case information sets each including examination ID, time phase information, a characteristic quantity, and image interpretation / diagnosis support information is searched in processing by a first similar case information search unit, a second similar case information search unit, and a judgment unit. A corresponding portion of the similar case information sets satisfying three conditions comprising agreement of the time phase information with the search target images, agreement of examination between the portion of the similar case information sets, and similarity of a content-based characteristic to the search target images is obtained.

The invention aims to provide a geometric structure based complex target SAR image simulation method, which can acquire simulation images with various viewing angles and various resolution ratios, and is used for assisting SAR image interpretation and automatic identification of complex targets. The method comprises the steps of: first, reading files of a target 3D model and acquiring spatial information, that is, calculating normal vectors of triangular surface elements through reading the vertex coordinates of triangular surface elements on the surface of the target and acquiring the spatial information of the target; second, carrying out SAR imaging geometrical simulation, that is, judging the surface element which receives radar signals on the surface of the target according to radar side looking imaging principles and recording the projection position of each of the visible surface element on the image; third, calculating the relative back scattering intensity of each position of the target model; and fourth, producing an SAR simulation image.

A method and apparatus for high quality, timely medical interpretations of radiological images acquired in one time zone and interpreted and a different time zone. The use of a different time zone allows images acquired at night to be interpreted during regular working daylight hours. The images can include images created by conventional x-ray technology, computed radiography, magnetic resonance imaging (MRI), computed tomography (CT), ultrasound imaging, and nuclear medicine equipment. The invention includes the transmission of these images, the interpretation of these images, and the transmission of the interpretations back to the originating facility. The interpretation is performed on high-resolution workstations and the written report is created either by voice recognition software or dictation and typed transcription.

An image interpretation report creating apparatus for retrieving a key image corresponding to that in the previous examination from among images taken in this examination to display it on an image display terminal. The apparatus includes: a follow-up observation examination determining unit for determining whether this examination is an object of follow-up observation; a previous report determining unit for determining, as previous report data, report data on the same patient from among the report data; a previous report data acquiring unit for acquiring the previous report data; an image data acquiring unit for acquiring image data at this time; a key image estimating unit for estimating a key image at a slice position corresponding to the previous examination based on the previous report data; and an image data output unit for outputting image data representing examination images containing the key image to the image display terminal.

Even though a client hospital has made an urgent image-interpretation request, if a designated radiologist is out of an image-interpretation center, a data center transfers the request to a portable terminal of the radiologist. Upon receiving the urgent request, the radiologist accesses the data center to download an image to be interpreted. An application server in the data center forms a whole image by subjecting the original image to a data amount reduction process, and delivers it to the portable terminal. The application server also forms a detailed image by cropping a desired area out of the original image, and delivers it to the portable terminal if necessary. The detailed image has higher resolution than the whole image because it is not subjected to the data amount reduction process. The radiologist makes a medical report with observing the image by the portable terminal and uploads it to the data center.

A medical image processing system having an image generation unit; an image quality inspection terminal; and an image interpretation terminal is provided. The system is capable of determining whether additional imaging or the like is required and the type objectively and rapidly prior to an image interpretation to be performed by a doctor to further improve the efficiency of the image interpretation and diagnosis. An additional imaging determining section is incorporated into a QA-WS (image quality inspection terminal). The determining section is configured to perform a predetermined image analysis on the image data generated by the image generation unit to determine whether additional imaging or the like is required and the type objectively. The inspection engineer performs image quality inspection, and directs additional imaging or the like, if necessary, by referring to the determination result at the QA-WS.