264 results about "Medical image diagnosis" patented technology

A cross-time and cross-modality inspection method for medical image diagnosis. A first set of medical images of a subject is accessed wherein the first set is captured at a first time period by a first modality. A second set of medical images of the subject is accessed, wherein the second set is captured at a second time period by a second modality. The first and second sets are each comprised of a plurality of medical image. Image registration is performed by mapping the plurality of medical images of the first and second sets to predetermined spatial coordinates. A cross-time image mapping is performed of the first and second sets. Means are provided for interactive cross-time medical image analysis.

A cross-time inspection method for medical image diagnosis. A first set of medical images of a subject is accessed wherein the first set is captured at a first time period. A second set of medical images of the subject is accessed, wherein the second set is captured at a second time period. The first and second sets are each comprised of a plurality of medical image. Image registration is performed by mapping the plurality of medical images of the first and second sets to predetermined spatial coordinates. A cross-time image mapping is performed of the first and second sets. Means are provided for interactive cross-time medical image analysis.

The medical image diagnosis device of the invention includes image generating means configured to obtain image data of a tissue of an object and generate an image of the tissue of the object based on the image data, calculation means configured to calculate at least one of brightness and motion vectors of plural measurement points of the generated image, input means configured to specify an observation region of the image, a database in which a characteristic amount of at least one of the brightness and the motion vectors of the measurement points in respective images of plural different observation regions is set and stored in advance, checking means configured to read the characteristic amount of the observation region that is specified through the input means from the database and check the characteristic amount with results of calculation performed on the generated image by the calculation means, and ROI setting means configured to set a region of interest in the generated image based on checked results of the checking means.

A medical image diagnosis support device comprises an organ region setting means for setting an organ region on the medical image of the subject obtained by a medical imaging device, a deformation degree calculating means for calculating the deformation degree of the organ region set by the organ region setting means, a reference value storing means for storing the index of the deformation degree of the organ region as a reference value, a lesion detecting means for comparing the stored reference value with the deformation degree calculated by the deformation calculating means and for detecting existence of a lesion of the organ region from the comparison result, and a presenting means for presenting the existence to the examiner at least either visually or auditorily. Therefore, the device can make a diagnosis selectively only on an organ region deformed because of a lesion and present it to the examiner visually such as by means of an image display or auditorily such as by means of speech, thereby improving the efficiency of diagnosis.

By selecting at least one of an image and a report to be provided for an institute to which a patient is introduced, an object having the same series ID as that of the image or report is automatically obtained. Medical information including the object is generated and stored in an external medium. By selecting an image or the like to be provided to the institute to which a patient is introduced, address information of the selected image or the like and address information of an object or the like having the same series ID as that of the image or the like is automatically obtained. Medical information including the address information is generated and stored in an external medium.

The invention discloses a method for automatically generating a medical image diagnosis report based on the deep learning method. The method comprises steps that S1, a subject of the diagnosis reportis clustered based on the LDA algorithm, and the diagnosis report is saved separately according to the subject; S2, a subject vector is used as a label of each medical image; S3, CT images and PET images with different sizes are scaled to the same size as training data, subject vectors are used as labels, the VGGNet-19 is used as a network model for training, and a subject vector generation modelis obtained; S4, a text generation model is constructed; and S5, according to the subject vector of each image, the text of the corresponding subject is matched to obtain the diagnosis report of the image. The method is advantaged in that the method can be applied to scenes with images marked with lesions, a doctor has no need to manually summarize training data labels frequently, only the location and the size of the lesion should be marked, and the doctor's work is effectively reduced while the correct rate is improved.

A medical image diagnosis device according to an embodiment of the present invention includes: an imaging unit that takes an image of a subject, with an X-ray generation unit which exposes the subject to X-rays and an X-ray detector which detects X-rays that have passed through the subject, being supported on a supporter; a control unit that controls so as to rotate and move the supporter with respect to the subject and take images of the subject from a plurality of viewpoints; a storage unit that stores image data taken from a plurality of the viewpoints; an image processing unit that classifies a plurality of pieces of the image data stored in the storage unit into a plurality of imaging ranges to generate thumbnail images; and a display unit that displays thumbnail images generated by the image processing unit.

A PET gantry and a CT gantry are placed in parallel such that the CT gantry becomes remoter to a common examination couch having a movable couch table top board mounted with a subject person and the CT gantry is made to be movable. The gantries are controlled by a control portion in a console. At first, the CT gantry is moved in a left direction to separate from the PET gantry so that whole body CT scan is carried out for the subject person in a direction from the leg portion to the head portion. Successively, the subject person is passed through a tunnel portion from the leg portion to the head portion by moving the couch table top board in a right direction in a state of considerably separating the CT gantry from the PET gantry to thereby carry out whole body PET scan.

The invention belongs to the field of chemistry and relates to an organic near-infrared two-photon fluorescent dye with a structure in a formula I in the specification. The organic near-infrared two-photon fluorescent dye has the beneficial effects that after being excited, the organic near-infrared two-photon fluorescent dye simultaneously shows stronger luminous efficiency of single-photon near-infrared fluorescence and two-photon fluorescence; the efficiency of two-photon fluorescence is obviously improved compared with that of other carbocyanine dyes; living cell fluorescence microscope experiments show that probes prepared from the fluorescent dye can enter tumor cell lysosome through endocytosis and can be imaged and simultaneously monitored by single-photon fluorescence and two-photon fluorescence microscopes; the dye can achieve synchronous single-photon near-infrared fluorescence and two-photon fluorescence imaging in the in-vivo and in-vitro states; and the fluorescent dye has the characteristics o good water solubility and stable chemical properties, can be used or bio-macromolecular markers and in the field of medical image diagnosis and especially has strong application value in optical image guided tumor excision.

A medical imaging diagnosis apparatus for measuring the composite thickness of the tunica intima (42) and the tunica media (44) of a blood vessel of a subject by acquiring image data on the blood vessel.

In order to improve the accuracy of the IMT measurement of the composite thickness, the medical imaging diagnosis apparatus has extracting means for extracting the tunica intima (42) and the tunica exterma (46) of the blood vessel on the basis of the brightness information of the image data to measure the composite thickness of the tunica intima and the tunica exterma of the vessel in reference to the two extracted regions.

The invention discloses a nano probe material for imaging, which is capable of efficiently breaching blood-brain barriers. Firstly, a high temperature pyrolysis method is adopted for preparing inner core NaYF4:Yb/TM/Gd hydrophobic nano-particles, then an NaGdF4 shell is formed through epitaxial growth so as to form core/casing structured NaYF4: Yb/Tm/Gd and NaGdF4 nano-particles, then hydrochloric acid hydrophilic modification and sulfhydryl PEG modification are performed, and finally, the nano probe material is prepared through Angiopep-2 grafting, and is marked as ANG/PEG-UCNPs. The material can be used for efficient blood-brain barrier breaching, magnetic resonance imaging diagnosis and positioning before an cranial cavity glioma operation, near infrared fluorescence imaging in the operation and image mediating, the imaging effect is good, the sensitivity is high, the physiological system toxicity is low, and the material plays an important significance in successful clinic glioma removing operations and the development and the application of medical image diagnostic techniques.

A medical image diagnosis apparatus designates an imaging range of a subject from a projection image for designation of the imaging range, specifies a specific spot on the projection image, performs scanning for generating a three-dimensional medical image of the subject on the basis of the imaging range, finds out a three-dimensional target region from the three-dimensional medical image on the basis of the specific spot, and detects a candidate for an abnormal part in the three-dimensional target region.

A boundary 1 of a wall in an initial image of time-series images is decided automatically or manually. A boundary 2 is generated automatically or manually in a neighbor of the other boundary of the wall. A normalized image is generated on the basis of an image pattern of a region surrounded by the boundaries 1 and 2 and registered as a template image. In each of the time-series images, boundaries 1 and 2 that generate a normalized image most similar to the template image are calculated. In this manner, wall thickness change can be calculated automatically stably and accurately even in the case where luminance change in the boundaries of a wall is obscure. This method is useful for diagnosis of heart disease etc. in medical image diagnosis.

The invention discloses a GAN-based medical diagnosis model anti-attack method for solving the security problem of an artificial intelligence medical image diagnosis model. The method comprises the following steps: building a ResNet-101-based high-precision residual neural network diagnosis model for an acquired medical pathological image, and then building a GAN-based confrontation attack network model which comprises a generator G and a discriminator D, wherein the generator G is used for generating a medical image confrontation sample by superposing high-dimensional random noise disturbance x on an input medical image, and the discriminator D is used for discriminating the authenticity of the confrontation sample; employing a PatchGAN discriminator based on a feature extraction image block for designing three layers of feature blocks including a residual block, expansion convolution and a channel attention mechanism as a main method for feature extraction, so that convolution kernel receptive fields of different scales can extract more refined feature map information by using the method and an effective input medical image disturbance area is obtained; therefore, the anti-attack effectiveness of the medical diagnosis model is improved, and the medical diagnosis model can be reinforced and defended from the anti-attack.

An X-ray diagnosis apparatus displays X-ray moving images by irradiating a subject with X-rays and detecting X-rays that have penetrated the subject, and includes a selection mechanism and a display. The selection mechanism selects images of high importance from among the X-ray moving images based on working-state information related to the working state of the operator performing surgery on the subject. The display list displays the selected images as thumbnails.

A medical image interpretation services system and method is disclosed. The system or method determines a calculated workload based on reference workload values for the medical procedure codes associated with the medical image exams that a medical image interpreter has already won or has a probability of winning. The system or method can prevent a medical image interpreter (such as a radiologist, a pathologist, or a dermatologist) from bidding if the calculated workload exceeds workload limits set by the medical image interpreter or set by the system.

The invention provides a medical imaging diagnosis report auxiliary generation method and device. The method comprises the following steps: acquiring medical image description information input by a doctor; Performing semantic segmentation on the medical image description information to obtain a plurality of image semantic segments; Identifying the image semantic segments by using a pre-trained segment identification model to obtain a diagnosis opinion segment corresponding to each image semantic segment; And combining all the diagnosis opinions section by section to obtain diagnosis opinion information, and generating a medical image diagnosis report according to the diagnosis opinion information. The diagnosis report is automatically generated in an assisted manner when a doctor writes diagnosis suggestions based on the neural network technology, the efficiency of diagnosing a patient based on a medical image is improved, and the accuracy, consistency and credibility of medical diagnosis are improved.

The invention discloses a multifunctional medical image diagnosis device. The multifunctional medical image diagnosis device comprises a movable photography main unit, a photography flat bed and a chest radiography rack which are used independently or in a combined manner, wherein an X radiation source component, which can not only move up and down but also rotate, is mounted on the photography main unit; a plate drawer is mounted on the chest radiography rack; an image detection flat plate is placed on the photography flat bed or in the plate drawer; when the X radiation source component faces the photography flat bed, the photography main unit is combined with the photography flat bed for use, and lying posture photography diagnosis is realized; when the X radiation source component faces the plate drawer, the photography flat bed is combined with the chest radiography rack for use, and standing posture photography diagnosis is realized. The multifunctional medical image diagnosis device has the advantages that the problems of simplex function, low utility value, failure in prompt and precise diagnosis, and the like, of the traditional medical image diagnosis device are solved; multiple purposes can be realized; the cost is reduced; the usage rate is improved; the precision is greatly improved.