35 results about "Medical image computing" patented technology

Described are systems, media, and methods for applying deep convolutional neural networks to medical images to generate a real-time or near real-time diagnosis.

A system and method of computer aided analysis of medical images and detection of malignant lesions is described. Medical images obtained from multiple modalities are analyzed. Morphological features as well as temporal, i.e., kinetics features, are combined to compute a consolidated assessment of a possible lesion detected in the medical images. The system includes at least one kinetics module, which is capable of extracting kinetics features from a time sequence of MRI images or MRS data taken after administering a contrast enhancement agent to a patient. The consolidated assessment is presented to a user for confirmation or modification.

The invention provides a magnetic resonance image based cerebral micro-bleeding computer auxiliary detection system and belongs to the medical image computer auxiliary detection field. The magnetic resonance image based cerebral micro-bleeding computer auxiliary detection system comprises five portions of an image import module, an image preprocessing module, a characteristic extraction module, an automatic detection module and a cerebral micro-bleeding automatic detection report output module. According to the magnetic resonance image based cerebral micro-bleeding computer auxiliary detection system, the characteristics of T1, T2 and GRET2* images are comprehensively considered, the prior information of the cerebral micro-bleeding of different cerebral positions is obtained through a cerebral micro-bleeding focus prior distribution probability template, and a random forest classifier is combined to perform the automatic detection on the cerebral micro-bleeding focus; the system sensitivity is 0.890 and every case comprises 1.530 false positive focuses in average through a test; the magnetic resonance image based cerebral micro-bleeding computer auxiliary detection system is objective and high in repeatability in comparison with the traditional manual discriminant method and the magnetic resonance image based cerebral micro-bleeding computer auxiliary detection system is accurate and reliable in comparison with the existing computer auxiliary detection method; the operation is simple and convenient, the identification result of the cerebral micro-bleeding focus can be objectively provided, and meanwhile the abundant information is provided for the reference of doctors.

A medical image quality reporting and monitoring system for use in a medical imaging system comprises a medical image computer including, a display processor, a display and a report generator. The display processor generates data representing an image for display including a user selectable image element enabling a user to identify at least one medical image as having an image quality deficiency. The display presents the image. The report generator, in response to detection of selection of the image element, identifying at least one medical reduced quality image as having an image quality deficiency, automatically generates a report. The report comprises, data representing an anonymized reduced quality image having the image quality deficiency, a time of acquisition of the reduced quality image and imaging system acquisition settings used in acquiring the reduced quality image.

A system and method for detecting a protrusion in a medical image are provided. The method comprises: acquiring a medical image, wherein the medical image is of an anatomical part; segmenting the medical image; calculating a distance map of the medical image; calculating a gradient of the distance mapped medical image; and processing the gradient to detect a protrusion in the medical image. The gradient is processed by: projecting a plurality of rays from a location in the distance mapped medical image; calculating a value for each of the plurality of rays based on features of each of the plurality of rays and the gradient of the distance mapped medical image; summing and scaling the value of each of the plurality of rays; and detecting one of a sphere-like and polyp-like shape using the summed and scaled values of the plurality of rays, wherein one of the sphere-like and polyp-like shapes is the protrusion.

The invention provides a method for automatically generating a brain CT medical report based on weak supervised attention, relates to the three fields of medical images, computer vision and natural language processing, and designs a weak supervised attention mechanism WGAM to clearly guide an attention model to focus on a focus region so as to improve the accuracy of medical report generation. WGAM is a hierarchical structure and comprises two attention mechanisms of space attention and sequence attention, and the space attention is weakly supervised by a gradient weighted class activation mapping algorithm to obtain a better attention effect. A keyword-driven interactive loop network KIRN is designed as a language generation module to generate a brain CT medical report, a hidden layer state of the language generation module is activated through keyword information containing focus position information, and the accuracy of generating a brain CT image report is improved through dynamic interaction of LSTMword and LSTMsen. According to the method, the work of automatically generating the brain CT medical report is explored for the first time, and effectiveness is achieved.

The present invention relates to computer applying technology. The registration identifying system of the present invention consists of plate scanner with transparent medium adaptor, microcomputer with keyboard and display, laser printer electrically connected together via signal cables. The registration identifying process includes mainly adaptive enhancing of homolateral fundus vessel image; intersection point and pure node extraction of fundus vessel characteristic; normalization of fundus vessel characteristic nodes; and neighboring region registration and judgement of fundus vessel characteristic nodes. The computer-aided judgement means has light labor strength and other advantages.

In accordance with one or more embodiments herein, a system for generating an optimized parametrized conversion function T for converting an original medical image of a first image type into a converted medical image of a second image type is provided. The system comprises at least one processing unit configured to: obtain original medical images of the first and second image types; obtain an initial parametrized conversion function G to convert original medical images of the first image type into converted medical images of the second image type; calculate a first penalty P₁ based on at least one comparison of a first original medical image of the second image type with a first converted medical image of the second image type, that has been generated by applying a first parametrized conversion function G₁, which is based on the initial parametrized conversion function G, to a first original medical image of the first image type that forms an image pair with the first original medical image of the second image type and has thereby been determined to show the same part of the same patient; calculate a second penalty P₂ based on at least one comparison of an original medical image of the first image type and a converted medical image of the second image type that has been generated by applying a second parametrized conversion function G₂, which is based on the initial parametrized conversion function G, to the original medical image of the first image type, after converting the original medical image of the first image type and/or the converted medical image of the second image type into images of the same image type; and generate the optimized parametrized conversion function T based on the parameters of the initial parametrized conversion function G and at least said first and second penalties P₁ and P₂.

The invention discloses an image retrieval method based on a CNN (Convolutional Neural Network) feature vocabulary tree, and aims to solve the technical problem of low accuracy in an existing vocabulary tree method. The method comprises the following implementation steps that: firstly, generating the derivative image of each image in an image library, and extracting the CNN feature of each image in the image library; according to the extracted CNN feature, constructing the CNN feature vocabulary tree; then, generating the derivative image of each image to be retrieved, and extracting the CNN feature of each image to be retrieved; comparing the path of the CNN feature of each image to be retrieved with the path of the CNN feature of the relevant image of the image to be retrieved in the CNN feature vocabulary tree; calculating a distance between the image to be retrieved and the relevant image, and combining the distance between the image to be retrieved and the relevant image with initial similarity; and finally, according to the comprehensive similarity of each image to be retrieved and the relevant image, outputting the retrieval result of each image to be retrieved. The method is high in image retrieval accuracy and can be used for a medical image computer-assisted diagnostic system and a search-by-image system.

A method of diagnosing a disorder includes obtaining a medical image of a subject. A Helmholtz Minimum Free Energy is computed from the medical image. A negative slope of the Helmholtz Minimum Free Energy is determined, from which a glial force is computed. The existence of a disorder in the subject is diagnosed if a value of the glial force is within a predetermined range. The disorder can be, for example, a brain disorder, such as Alzheimer's disease, Parkinson's disease, and/or schizophrenia. Other examples of disorders are epilepsy and rheumatoid arthritis. The subject can be, for example, a human subject.

Systems and methods for automatically detecting a disease in medical images are provided. Input medical images are received. A plurality of metrics for a disease is computed for each of the input medical images. The input medical images are clustered into a plurality of clusters based on one or more of the plurality of metrics to classify the input medical images. The plurality of clusters comprise a cluster of one or more of the input medical images associated with the disease and one or more clusters of one or more of the input medical images not associated with the disease. In one embodiment, the disease is COVID-19 (coronavirus disease 2019).

A method, system and computer programs for computing simultaneous rectilinear paths using medical images are disclosed. The method comprises receiving a 3D medical image comprising voxels representing a volume of an anatomical region of a patient and a preliminary path determined by two points traversing said 3D medical image, wherein said 3D medical image has segmented therein at least one area of interest, the preliminary path comprising a security zone with a given distance; computing a distance map of said area of interest and mapping its voxels to a first value or to a second value depending on a distance threshold, the latter being equal to said given distance of the security zone; selecting the voxels having said second value and projecting them using a frustum that projects the preliminary path onto a single point, to obtain a 2D projected image that includes a plurality of rectilinear paths.

A method and a control module for calculating and displaying result data based on at least one medical image, which has been captured by an imaging device, are provided. At least one image is captured by the imaging device in a digital format with a plurality of bone fragments. Subsequently, a segmentation method is applied to the captured image for identification of the bone fragments contained in the image. Thereafter, a fragment-matching algorithm is executed on the segmented bone fragments for calculation of result data. The result data includes instruction data for assembling at least a part of the bone fragments, which is output on the monitor in a configurable format.

The embodiment of the invention discloses a medical image preprocessing method and system, and the method comprises the steps: constructing a medical image data set which comprises a normal image data set with normal image quality and an abnormal image data set with abnormal image quality; performing gradient calculation on the medical image data set, and respectively generating first gradient distribution corresponding to the normal image data set and second gradient distribution corresponding to the abnormal image data set; determining a gradient threshold according to the first gradient distribution and the second gradient distribution; acquiring a to-be-processed medical image, calculating a third gradient of the to-be-processed medical image, and acquiring an image category of the to-be-processed medical image according to a relationship between the third gradient and a gradient threshold; and executing corresponding operation according to the image category. According to the embodiment of the invention, before the medical picture data is input into the deep learning model for learning, the pictures with whitening or blackening quality are screened out, the noise of the pictures with poor quality is filtered out, and the training accuracy of the subsequent deep learning model is improved.

Systems and methods for automatic processing of input medical images are provided. A set of input medical images acquired at a plurality of locations on a patient is received. For each respective location of the plurality of locations, an image quality score is determined for each input medical image of the set of input medical images acquired at the respective location and one of the input medical images acquired at the respective location is selected based on the image quality scores. The selected input medical images are processed to correct for errors. One or more regions of interest are segmented from the processed selected input medical images. One or more hemodynamic measures are calculated from the processed selected input medical images based on the segmented one or more regions of interest. The calculated one or more hemodynamic measures are output.

Provided are an ultrasound imaging apparatus and a control method thereof, the ultrasound imaging apparatus including: an input/output interface; a storage; and at least one processor configured to: display, via the input/output interface, at least one resulting value calculated based on a plurality of medical images; when one of the at least one resulting value is selected by an input via the input/output interface, retrieve, from the storage, a plurality of measurement values and a plurality of medical images used to calculate the selected resulting value; and output, via the input/output interface, the retrieved plurality of measurement values and the retrieved plurality of medical images on a single display.