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 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.

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.

There is described a method for calculating a patient-specific hemodynamic parameter. The method comprises measuring at least one pressure measurement in an artery using an intravascular pressure measurement device, and taking at least one medical image of the artery from a medical imaging instrument, the at least one medical image of the artery being synchronous with the at least one pressure measurement. Both the pressure measurement and the medical image are fed to a computing system to calculate a flow from the at least one medical image, to calculate parameters of the artery from at least two artery pressure drops and corresponding flow components, and based on the flow and the parameters of the artery, to calculate a patient-specific hemodynamic parameter or a plurality thereof.

The invention discloses an image retrieval method based on a CNN feature vocabulary tree, and aims to solve the technical problem of low accuracy existing in the existing vocabulary tree method. The implementation steps are as follows: first generate the derivative images of each image in the image library, and extract the CNN features of each image in the image library, then construct a CNN feature vocabulary tree according to the extracted CNN features, then generate derivative images of each image to be retrieved, and extract The CNN feature of each image to be retrieved, by comparing the path of the CNN feature of each image to be retrieved and its related image in the CNN feature vocabulary tree, calculate the distance between the image to be retrieved and its related image, and compare the image to be retrieved and its related image The distance is combined with the initial similarity, and finally the retrieval results of each image to be retrieved are output according to the comprehensive similarity of each image to be retrieved and its related images. The image retrieval accuracy rate of the invention is high, and can be used in medical image computer aided diagnosis systems and image search systems.

A method for analyzing an abdominal disease based on a medical image, includes receiving and preprocessing a medical image obtained by photographing an abdominal region of a patient to detect a plurality of analysis candidate regions and setting one of the plurality of analysis candidate regions as a ROI, calculating a nodule grade based on surface unevenness of the ROI, calculating a cellular heterogeneity coefficient based on pixel homogeneity of the ROI, and predicting and outputting an abdominal disease value based on the nodule grade and the cellular heterogeneity coefficient.