19 results about "Computer aided detection" patented technology

According to an exemplary embodiment of the disclosure, an imaging system and method is provided for determining the need for generation of enhanced diagnostic images of a patient. The imaging system includes a radiation source operable at to emit radiation at multiple energy levels, a detector alignable with the radiation source, a controller operably connected to the radiation source and detector to generate image data in an imaging procedure, and a computer aided detection (CAD) system configured to analyze low energy (LE) images to locate regions of interest (ROI) and / or other triggering attributes, characteristics or findings within the object. Upon locating one or more triggering attributes, characteristics or findings within the LE images, the system and method can acquire one or more high energy (HE) images of the object, and can process the one or more LE images and the one or more HE images to form enhanced diagnostic images.

According to an exemplary embodiment of the disclosure, an imaging system and method is provided for determining the need for generation of enhanced diagnostic images of a patient. The imaging system includes a radiation source operable at to emit radiation at multiple energy levels, a detector alignable with the radiation source, a controller operably connected to the radiation source and the detector to generate image data in an imaging procedure, and a computer aided detection (CAD) system configured to analyze initial projection images to locate any regions of interest (ROI) within the object. Upon locating analyzing one or more ROIs within the initial projection images, the system and method can determine imaging parameters to acquire one or more additional projection images of the object, and can process the one or more initial projection images and the one or more additional projection images to form one or more enhanced diagnostic images.

The present invention relates to the technical field of image analysis and proposes a method and system for detecting structural distortion based on dual-view digital breast tomosynthesis, comprising the following steps: acquiring a three-dimensional breast tomosynthesis image containing two projection position perspectives and processing the image into a two-dimensional image slice; marking the position of structural distortion in the two-dimensional image slice using a bounding box; pairing the marked two-dimensional image slices from the two projection position perspectives belonging to the same breast; predicting the two-dimensional detection frames corresponding to the position of structural distortion in the paired two-dimensional image slices using a computer-aided detection model and extracting a representation vector of the breast tissue structure within the two-dimensional detection frame; matching the two-dimensional detection frames in the image slices from the two projection position perspectives using the breast tissue structure representation vector of the paired two-dimensional image slice; fusing the two-dimensional detection frames into a three-dimensional detection frame; and eliminating part of the three-dimensional detection frame based on information from a single perspective and a dual perspective to obtain a final retained three-dimensional detection frame.

A method for training a multi-class neural network for diagnosing ovarian tumors using ultrasound images includes obtaining ultrasound image data from a plurality of diagnostic centers, annotating each image of the image data, training a series of initial neural networks to perform multi-class classification, evaluating the performance of each initial neural network of the series of initial neural networks; identifying an optimal set of hyperparameter; and training a final neural network using the optimal set of hyperparameters.

The present invention relates to the technical field of image analysis, and provides a dual-view digital breast tomosynthesis-based architectural distortion detection method and system. The method comprises the following steps: collecting three-dimensional breast tomosynthesis images of two projection position views and processing same into two-dimensional tomographic slices; using bounding boxes to label positions of architectural distortions in the two-dimensional tomographic slices; pairing the labeled two-dimensional tomographic slices of the two projection position views of the same breast; using a computer-aided detection model to predict two-dimensional detection boxes corresponding to the positions of the architectural distortions in the paired two-dimensional tomographic slices and to extract from the two-dimensional detection boxes representation vectors of breast tissue structures; using the representation vectors of the breast tissue structures of the paired two-dimensional tomographic slices to match the two-dimensional detection boxes in the tomographic slices of the two projection position views; fusing the two-dimensional detection boxes into three-dimensional detection boxes; and, on the basis of single-view and dual-view information, removing some of the three-dimensional detection boxes to obtain finally kept three-dimensional detection boxes.

Systems and methods are provided for processing images captured by a capsule camera system. According to one method, a frame sequence comprises panoramic picture representative of a GI scene covering substantially a lateral 360-degree Field-of-View is received. CADe (computer-assisted detection) is applied to detect one or more target abnormalities in the frame sequence, where said applying the computer-assisted detection (CADe) results in one or more CADe frames and each CADe frame contains at least one detection area containing a detected abnormality or a false positive. Circle shift is applied laterally to a target CADe frame to shift a detection area to a lateral center or close to the lateral center of the target CADe frame. The CADe frames comprising the target CADe frame are provided with the detection area shifted to the lateral center or close to the lateral center of the target CADe frame.

Methods and system for filtering, sorting, and displaying images are provided. The method can include receiving a request to view two or more images associated with a patient and receiving a request to perform Computer Aided Detection and Diagnosis (CAD) on the two or more images. The method can include performing CAD on the two or more images. Performing CAD can include identifying at least one characteristic of each of the two or more images, respectively. The method can include sorting the two or more images to generate an image order, the image order determined based at least in part on the at least one characteristic of each of the two or more images. The two or more images can be transferred from the one or more computing devices to the client device, and the two or more images can be displayed in the image order.

This invention relates to the fields of intelligent manufacturing and computer-aided inspection technology, and particularly to a system for constructing and reasoning a knowledge base for precision machining geometric error inspection operators. The system includes a feature parsing module, used to read a 3D solid model containing product geometric technical specifications, extract geometric surface features and associated tolerance specifications from the model, wherein the tolerance specifications include tolerance thresholds, and convert the geometric surface features and tolerance specifications into semantic ontology instances, outputting a set of element instances. In this invention, by automatically parsing the geometric features and geometric tolerance semantics in the 3D solid model, and combining this with actual point cloud data obtained from on-machine measurement for error assessment and reverse calculation of compensation parameters, a closed-loop mapping from design tolerance semantics to CNC system compensation instructions is achieved. This enables the machining equipment to automatically correct the tool position and coordinate system offset based on actual inspection results, thereby improving the machining accuracy and consistency of parts.

The invention discloses a method for detecting openness of permeability transition pores (MPTP) of peony pollen mitochondria under physiological conditions by computer assistance, which comprises the following steps: preparing Calcein-AM staining working solution and CoCl2 solution, preparing pollen cells to be stained, grouping staining, staining the pollen cells, preparing stained pollen flakes, observing, shooting, and analyzing by computer-aided software (Aivia). And pollen MPTP open fluorescence intensity analysis is carried out. The method has the beneficial effects that the dyeing concentration and steps of Calcein-AM / CoCl2 are optimized aiming at peony pollen cells, the pollen cells and the fluorescence intensity of the pollen cells on each image in different dyeing groups are accurately identified by combining computer-aided analysis, pollen self-luminescence interference is eliminated by taking an undyed group as a reference, and the detection accuracy of the pollen cells is improved. By creating an object classification model based on computer deep learning, fluorescence intensity intervals of MPTP dyeing are accurately divided, and a workflow is created to realize batch processing. According to the method disclosed by the invention, the opening accuracy and visibility of the Calcein-AM / CoCl2 staining method for determining the MPTP are greatly improved, and batch image analysis and processing are realized.

The invention discloses a body-in-white data inspection method, and relates to the technical field of vehicles. The inspection method comprises the following steps: inspecting body-in-white data according to guidance items preset in a computer-aided detection system, wherein the guidance items comprise a first-level inspection item and a second-level inspection item; wherein the first-level inspection items comprise data static inspection, manufacturability inspection, opening and closing piece inspection, sealing inspection, bill of material inspection and motion inspection, and the second-level inspection items comprise preset second-level items and second-level item inspection content; and the computer-aided detection system carries out data inspection on the body-in-white according to the guidance of the first-level inspection item, the second-level item and the inspection content of the second-level item, and generates a problem report file. By means of the checking method, the high-frequency problem and the important influence problem in the trial-manufacturing link can be checked, checking personnel do not need to judge which items need to be checked according to the working experience of the checking personnel, and the operation difficulty of the checking personnel is reduced.

The invention relates to the technical field of computer-aided detection of fluid machinery, in particular to a centrifugal fan blade geometric feature determination method, device and equipment and a medium, and aims to solve the problems that a traditional determination method of a mean camber line is large in calculation amount and low in processing efficiency. The method comprises the steps of determining a first arc point set and a second arc point set which are used for representing the surface shape of the centrifugal fan blade; establishing a nonlinear analytical model for a first point in the first arc point set based on parameterized representation of an inscribed circle, the nonlinear analytical model defining a geometric tangent constraint based on the first point and an unknown second point on the second arc; determining the position of an unknown second point on the second arc line according to the nonlinear analysis model; calculating a central point of the inscribed circle based on the first point and the determined second point; on the basis of traversing all first points in the first arc point set, fitting a mean camber line by using a plurality of central points; and determining at least one geometrical characteristic of the centrifugal fan blade by using the mean camber line.

Methods and system for filtering, sorting, and displaying images are provided. The method can include receiving a request to view two or more images associated with a patient and receiving a request to perform Computer Aided Detection and Diagnosis (CAD) on the two or more images. The method can include performing CAD on the two or more images. Performing CAD can include identifying at least one characteristic of each of the two or more images, respectively. The method can include sorting the two or more images to generate an image order, the image order determined based at least in part on the at least one characteristic of each of the two or more images. The two or more images can be transferred from the one or more computing devices to the client device, and the two or more images can be displayed in the image order.

The present invention provides an effective method and system for viewing a frame sequence generated from a capsule camera system. According to one method, the frame sequence comprising a picture of a GI scene covering a field of view (FoV) is received. CADe (computer-assisted detection) is applied to detect one or more target abnormalities in the frame sequence. Horizontal location of the detection area in a target CADe frame is determined. In response to the horizontal location of the detection area, circle shift laterally is applied to the target CADe frame to shift said at least one detection area to a lateral center or close to the lateral center of the target CADe frame. The CADe frames are provided.

The invention relates to a GIS defect detection method based on SURF multi-feature point comparison. The method comprises the following steps: acquiring a normal X-ray image and a to-be-detected X-ray image of GIS equipment; performing pretreatment; feature points of the preprocessed normal X-ray image and the to-be-detected X-ray image are identified by using an SURF algorithm, image registration is carried out by using an FLANN fast approximate nearest neighbor search matching algorithm, and different regions p are found out; and carrying out defect classification on the detected different areas p. According to the invention, image registration is carried out by using an SURF multi-feature point comparison technology, and different areas between the X-ray image to be detected and a normal image are automatically identified, so that the automatic process improves the detection speed, reduces the subjectivity of manual judgment, and reduces misjudgment caused by insufficient experience; by converting manual detection into computer-aided detection, the defect detection rate is greatly improved, the labor cost is reduced, and meanwhile, the burden of workers is also relieved.

Aspects of the embodiments described herein are related to systems, methods, and computer products for performing computer-aided detection of fraud device installation events, especially at an Automated Teller Machine (ATM). Aspects of embodiments described herein provide artificial intelligence systems and methods that detect the presence of obstructions and persons to determine when a fraud device installation event occurs. The fraud detection system performs object detection and can determines whether a detected access event has an associated transaction to determine that a fraud device installation event occurs. The fraud detection system can also track the time he camera view is obstructed, the activity time of the person standing at the monitored device when no transaction occurs, and detect objects that resemble fraud devices to determine if a fraud device installation event occurs.

The invention relates to the technical field of computer detection, and discloses an industrial computer aided detection device which comprises a bottom plate, a conveying table fixedly connected to the top of the bottom plate, a sliding table fixedly connected to the bottom of the inner wall of the bottom plate, a protection plate fixedly connected to the top of the bottom plate, and a removing assembly fixedly connected to one end of the conveying table and the right side of the protection plate. Comprising a connecting shaft rotationally connected with the bottom of the inner wall of the containing plate, a connecting ring is fixedly connected to the surface of the connecting shaft, an absorbing film is fixedly connected to the top of the connecting shaft, and a stirring film is fixedly connected to the end, away from the absorbing film, of the connecting ring. By arranging the clearing assembly and the absorption ball, heat dissipated by the bottom of the computer is absorbed, and due to the fact that a large amount of heat generated in the industrial computer is accumulated at the bottom during high-load operation of the industrial computer, the heat at the bottom of the industrial computer can be absorbed, and therefore when the internal heat of the computer is detected, the detection accuracy is improved. And a more accurate heat value can be obtained.

This application provides a computer-aided detection and diagnosis system for breast microcalcifications, comprising: an acquisition unit for acquiring at least two breast X-ray images of the same breast tissue from different projection angles as a target view group; a region detection unit for detecting suspected microcalcification candidate regions in each single view to obtain a candidate region set corresponding to each single view; based on the geometric projection relationship between different views in the target view group, performing cross-view pairing and association on candidate regions from different views to establish candidate region pairs characterizing the image appearance of the same potential microcalcification at different projection angles; an extraction module for extracting cross-view consistency features for each candidate region pair; a calculation unit for fusing the cross-view consistency features corresponding to each candidate region pair and its internal image features in each single view to form an enhanced feature vector of the potential microcalcification; and obtaining the benign or malignant classification result of the corresponding potential microcalcification.

The present disclosure relates to the technical field of computer-aided detection of fluid machinery, and particularly relates to a centrifugal fan blade geometric feature determination method, device, equipment and medium, which is used to solve the problems of large calculation amount and low processing efficiency of traditional determination methods of middle camber lines, and the method comprises: determining a first camber line point set and a second camber line point set for representing the surface shape of the centrifugal fan blade; for a first point in the first camber line point set, a nonlinear analytical model is established based on the parametric representation of an inscribed circle, the nonlinear analytical model defines a geometric tangent constraint based on the first point and an unknown second point on the second camber line; the position of the unknown second point on the second camber line is determined according to the nonlinear analytical model; the center point of the inscribed circle is calculated based on the first point and the determined second point; the middle camber line is fitted based on the traversal of all first points in the first camber line point set and the use of multiple center points; and at least one geometric feature of the centrifugal fan blade is determined by using the middle camber line.