71 results about "Nuclear medicine" patented technology

The present invention relates to systems and methods for photometric endoscope imaging. The methods can further include chromoendoscopy and computer aided detection procedures for the imaging of body lumens and cavities.

The invention discloses a tumor MRI weak supervised learning analysis modeling method, which comprises the following steps: S1, constructing a tumor MRI segmentation network based on a full convolutional neural network to realize tumor MRI preliminary segmentation; S2, taking the tumor MRI segmentation network as a generator, taking the classification model as a discriminator, and proposing a generative adversarial training algorithm of the tumor MRI segmentation network; and S3, taking unlabeled image data in the medical image as additional input condition information of the generator model and the discriminator model, guiding a data generation process, and enhancing the stability of the segmentation-generative adversarial network. The invention also discloses a model established by usingthe tumor MRI weak supervised learning analysis modeling method. According to the method, the tumor target region and the endangered organ can be more accurately and automatically segmented under thecondition of fewer training samples, and the method is applied to target region and endangered organ sketching of tumor radiotherapy.

An imaging apparatus includes: an imaging unit that respectively generates, with imaging devices different from one another, a first captured image with a specific direction of a subject set in a longitudinal direction, a second captured image with an orthogonal direction orthogonal to the specific direction set in a longitudinal direction and including a subject adjacent to one side of the orthogonal direction of the subject included in the first captured image, and a third captured image with the orthogonal direction set in a longitudinal direction and including a subject adjacent to the other side of the orthogonal direction of the subject included in the first captured image; a detecting unit that detects a state of the imaging apparatus; and a control unit that determines, based on the detected state, a range of a target image as a target of display or recording among the first to third captured images.

A visceral fat area estimating system of the present invention comprises first input unit for inputting a height of an subject, second input unit for inputting a body weight of the subject, third input unit for inputting a fat mass of the subject, fourth input unit for inputting age of the subject, computation unit for computing a visceral fat area based on data from the first, second, third and fourth input unit, and display unit for displaying the visceral fat area computed by the computation unit. Therefore, the system can estimate a visceral fat area securely without concern for exposure of an subject to X-rays, at low costs, and with proper accuracy.

A method for defining a region of interest in a radiation image of a breast based on the result of shape analysis applied to a skin line estimate determined in the radiation image.

An image processing apparatus (804) includes a function obtaining portion (804a) configured to obtain a first optical transfer function which is different depending on a shooting condition and on a position in an image, a corrected image generating portion (804b) configured to generate a corrected image from the image using the first optical transfer function, and an image restoration portion (804c) configured to perform blind deconvolution processing using the corrected image to generate a restored image.

The invention discloses an intelligent lung cancer detection method and system based on image and machine smell fusion. The method comprises five steps of selecting a training object, acquiring a CT image, acquiring respiratory data, performing data fusion processing and outputting a detection result. According to the method, tumor imaging omics and machine olfaction metabonomics are fused; basedon lung cancer typing and staging result related data given to a pathological result by a professional doctor in the earlier stage, the lung cancer intelligent diagnosis model is constructed accordingto the exhaled air data of the patient, and the optimized model is obtained by verifying and testing the model; the lung cancer detection result can be obtained by inputting the CT image data and thebreathing data of the patient to be detected into the optimized model in the later period, the detection process is faster and more convenient, and the cost is lower.

The invention discloses a patient image color restoration method, device and equipment and a readable storage medium. The method comprises the steps: collecting a patient image through image acquisition equipment, wherein the patient image comprises a patient human body image part and a reference color image part; identifying a reference image color included in the reference color image part; calculating a conversion relation function between the reference image color and a known reference real color corresponding to the reference image color; at least correcting the human body image color ofthe patient human body image part in the patient image into a corresponding real color according to the calculated conversion relation function so as to obtain a color restoration image for traditional Chinese medicine diagnosis and treatment. Because the reference color image part and the patient human body image part are recorded in the same image, under the same illumination environment, the human body image color of the human body can be restored to the real color by utilizing the calculated corresponding relationship between the known real color and the image color corresponding to the known real color in the image, thereby facilitating the improvement of the accuracy of remote traditional Chinese medicine diagnosis and treatment.

Systems and methods for a digital image transfer system for guaranteed high speed and failsafe transfer and deep learning analysis of complicated digital images. In particular, the transfer methods and systems are suited for medical images, such as CT and MR scans, especially when a large number of images needs to be transferred and looked at immediately, such as when a patient is acute danger of life.

The invention relates to the technical field of medical image processing, and provides a three-dimensional medical image mark point extraction method and system, and the method comprises the steps of scanning a metal ball through a three-dimensional imaging device, and obtaining a three-dimensional image of the metal ball; performing threshold segmentation on the three-dimensional image, and binarizing image data of the three-dimensional image to form a binarized image; determining a plurality of polygonal regions in the binarized image; comparing the volume of the polygon in the image data with the actual physical volume of the metal ball, and eliminating interference data with too large or too small volume; solving gradients of the polygon data in the X direction and the Y direction on the surfaces of the Z direction and the negative Z direction in the image coordinate system, and obtaining a maximum point and a minimum point of the gradients in the Z direction; and according to the maximum point and the minimum point, optimizing the offset of the metal sphere mass point in the three-dimensional image on the XY plane due to the artifact, and further obtaining the position of the true centroid according to the offset value. A mass point extraction method is optimized to a certain extent, and the extraction precision of the mark points is improved.

The invention discloses a 2D and 3D image registration method and device. The method comprises the following steps: acquiring a 2D image and a 3D image to be registered; inputting the 2D image and the 3D image into a pre-trained 2D image feature extraction model and a pre-trained 3D image feature extraction model, and obtaining 2D image features and 3D image features containing spatial information in the same dimension; inputting the 2D image features containing the spatial information and the 3D image features containing the spatial information into a pre-trained registration model, and performing registration on the 2D image features containing the spatial information and the 3D image features containing the spatial information to obtain spatial transformation for registering the 2D image and the 3D image; and based on the spatial transformation, mapping and superposing the 3D image to a corresponding spatial position of the 2D image. According to the method, the image pair is directly registered, image preprocessing before registration is not needed, and the 2D and 3D image registration process is simplified to the maximum extent.

The invention relates to a medical image processing method. The method comprises the steps of obtaining a general model obtained by training according to a general image set; obtaining a first medicalimage corresponding to the target part and a category label corresponding to the first medical image, wherein the category label comprises a label representing a normal category and a label representing an abnormal category; retraining the general model through the first medical image and the corresponding category label to obtain an intermediate model; obtaining a second medical image corresponding to the target part and a target task label corresponding to the second medical image, wherein the second medical image is a medical image belonging to an abnormal category; and retraining the intermediate model according to the second medical image and the corresponding target task label to obtain a target task model corresponding to the target task, wherein the target task model is used for processing the third medical image to be processed to obtain a prediction result corresponding to the target task. By adopting the method, a target task model with a more accurate processing result canbe obtained through training.

Disclosed herein are methods for simulating the results of a visual field (VF) test using an optical coherence tomography (OCT) system. The disclosed methods may utilize structural information extracted from OCT image datasets, such as thickness measurements, or may utilize functional information, such as blood perfusion measurements, extracted from OCT angiography (OCTA) image datasets. Other embodiments may be described and claimed

The invention relates to a subcutaneous microvessel segmentation and three-dimensional reconstruction method based on optical coherence tomography. The subcutaneous microvessel segmentation and three-dimensional reconstruction method comprises the following steps of obtaining a two-dimensional image sequence through an FFOCT system and preprocessing; grouping the acquired two-dimensional images, and performing robust principal component analysis on each group of images to obtain an image background and a high-response microvascular region; and carrying out capillary segmentation and three-dimensional reconstruction on the image background and the high-response capillary region in combination with the position relationship between each group of images and the capillary boundary distributionin each group of images. Compared with the prior art, the method has the advantages that the global optical coherence tomography technology is applied to image recognition of venipuncture, the imaging precision is remarkably improved, blood vessel positioning is more accurate, and capillary clear imaging is more reliable.

The embodiment of the invention discloses an image processing method and device and a storage medium. According to the scheme, the method comprises the steps of obtaining multiple medical scanning images, determining a focus area according to the multiple medical scanning images, extracting feature information for the focus area in each medical scanning image to obtain multiple pieces of feature information, performing at least one time of feature combination on the multiple pieces of feature information to generate a target feature set, and determining focus attribute information according to the target feature set. According to the scheme provided by the embodiment of the invention, the feature information of the lesion area can be extracted, and the lesion attribute information is determined through feature combination, so that the lesion is diagnosed, and the efficiency and accuracy of medical scanning image analysis are improved.

A determination processing unit determines a disease region in a medical image including an axisymmetric structure. A first determination section of the determination processing unit generates a feature amount map of the medical image from the medical image. A second determination section second inverts the feature amount map with reference to a symmetry axis to generate an inverted feature amount map. A third determination section superimposes the feature amount map and the inverted feature amount map on each other and determines the disease region in the medical image using the feature amount map and the inverted feature amount map superimposed on each other.

The invention provides a DenseNet-based CT image classification method and a DenseNet-based CT image classification device for COVID-19 patients, which are used for classifying according to computed tomography images of suspected COVID19 patients to obtain a classification result. The method includes the following steps of: storing medical image information; preprocessing by using a preprocessing method to obtain preprocessed data; obtaining deep information and shallow information from the preprocessed data by using the trained dense connection neural network model, and fusing the deep information and the shallow information to obtain a fused feature vector; mapping the fusion feature vector to a low-dimensional space by using an activation function to obtain a classification probability prediction value; obtaining a CAM activation graph based on the internal parameters of the densely connected neural network model and the computed tomography image; displaying a computed tomography image, a classification probability prediction value, and a CAM activation map to assist a doctor in diagnosis. The method and the device are suitable for an early screening stage of an epidemic situation area, the problem of too high false negative of accounting detection can be solved, and the diagnosis efficiency can be improved.

According to aspects of the present disclosure, an imaging medical device may include an elongated member having a proximal end, and distal end having an imaging component configured to transmit an analog imaging signal. The assembly also may include a proximal member having a distal end connected to the proximal end of the elongated member. The proximal end may be configured to receive a degraded analog imaging signal based on the analog signal and transmit an amplified analog imaging signal based on the degraded analog imaging signal. The analog imaging signal transmitted by the imaging component may be degraded during transmission to the proximal member to become the degraded analog imaging signal. The assembly also may include a signal processor in electronic communication with the proximal member and configured to receive and process the amplified analog imaging signal and generate a digital signal based on the amplified analog signal.

A display control apparatus, includes: at least one processor and/or at least one circuit to perform the operations of the following units: an input unit configured to acquire an input image which is an image captured by an imaging apparatus; a generation unit configured to generate at least one zoom image which is an image generated by magnifying a part of the regions of the input image; an acquisition unit configured to acquire focus information of the imaging apparatus; and a determination unit configured to determine which one of (1) the input image, (2) the zoom image and (3) both of the input image and the zoom image are to be displayed as a display image on a display unit on the basis of the focus information.

The invention discloses a medical image enhancement method, which is realized based on a bidirectional generative adversarial network architecture. The architecture comprises two generator/discriminator pairs, and generator learning converts an image in a low-quality image domain or a high-quality image domain into a corresponding image in the high-quality image domain or the low-quality image domain. A discriminator distinguishes a real image in a low-quality image domain or a high-quality image domain from an image converted from the real image in the high-quality image domain or the low-quality image domain, the architecture introduces constraint terms in an objective function of a bidirectional generative adversarial network, and the constraint terms include an illumination regularization term and a structure loss term. The invention provides a novel medical image enhancement frame, and the imaging quality of the medical image is improved.