109 results about "Capsule endoscopy" patented technology

A system and method for automated image analysis which may enhance, for example, capsule endoscopy diagnosis. The system and methods may reduce the time required for diagnosis, and also help improve diagnostic consistency using an interactive feedback tool. Furthermore, the system and methods may be applicable to any procedure where efficient and accurate visual assessment of a large set of images is required.

Apparatus and methods for capsule endoscopy are described for locating, positioning, steering, aiming and tracking of an endoscopy capsule (100) within a patient's esophagus and stomach. The apparatus includes an endoscopy capsule (100) with a magnetic element (110), an external capsule positioning system (200) including at least one magnet (202) movable along a track (204) for positioning the endoscopy capsule (100) within a patient. Also described are apparatus and methods for performing endoscopic spectroscopy using different wavelengths of light and other imaging technologies to diagnose various disease conditions, such as premalignant or inflammatory changes and internal bleeding.

A device, system and method for automatic detection of contractile activity of a body lumen in an image frame is provided, wherein image frames during contractile activity are captured and/or image frames including contractile activity are automatically detected, such as through pattern recognition and/or feature extraction to trace image frames including contractions, e.g., with wrinkle patterns. A manual procedure of annotation of contractions, e.g. tonic contractions in capsule endoscopy, may consist of the visualization of the whole video by a specialist, and the labeling of the contraction frames. Embodiments of the present invention may be suitable for implementation in an in vivo imaging system.

The invention discloses a method and a system for processing images based on photographing in vivo by a wireless capsule endoscopy or a video endoscope. The method comprise the following steps of: (1) continuously capturing two-dimensional reversed images of an intestinal canal inner wall through a reversed projection of a image sensor of the wireless capsule endoscopy or the video endoscope to the intestinal wall, and sending the two-dimensional reversed images with continuous sequences by a wireless sending device of the wireless capsule endoscopy or the video endoscope to an image processing device for storage; (2) identifying a superposition part of the continuous sequences of the two-dimensional reversed images obtained from the step (1) by the image processing device; and (3) cutting and splicing the superposition part of the continuous sequences of the reversed images by the image processing device to form a three-dimensional image which presents the whole intestinal canal inner wall. The method can reduce time on studying photographed images by medical workers and greatly improve diagnosis efficiency.

Systems and methods for extracting and measuring motion from images capture during capsule endoscopy in accordance with embodiments of the invention are disclosed. In one embodiment of the invention, an endoscope system configured to generate a spatial index of images captured along a passageway includes a processor and a camera configured to capture a plurality of images as the camera moves along a passageway, wherein the processor is configured to compare sets of at least two images from the plurality of images, determine motion of the camera along the passageway using the sets of at least two images, determine the distance the camera traveled along the passageway at the point at which an image in each of the sets of at least two images was captured, and generate a spatial index for the plurality of images by associating distances traveled along the passageway with the images.

The invention discloses a capsule endoscopic image three-dimensional reconstruction method and system. The capsule endoscopic image three-dimensional reconstruction method comprises the following steps of calibrating a monocular camera of the capsule endoscopy to obtain internal and external parameters of the camera; selecting a picture sequence taken by a monocular camera and correcting the picture sequence; detecting feature points of the corrected image; matching and tracking the obtained feature points to form the trajectory of the feature points; carrying out the image photographic reconstruction; carrying out the three-dimensionally reconstruction on the image processed in step S5. The invention generates a stereoscopic and accurate 3d dense point cloud model through a monocular picture sequence, and completes three-dimensional reconstruction. The brightness of the feature point extraction picture of the invention is unchanged, the feature points can be well matched and tracked,and the effect of the three-dimensional reconstruction is more robust. Compared with the traditional monocular 3D reconstruction method, feature extraction and tracking speed is faster, and the real-time 3D reconstruction can be achieved.

The invention discloses an alimentary canal anatomical position identification method and device. The method comprises the steps that a training set and a test set are acquired; a deep network model based on a deep learning framework is selected to act as the current deep network model, the current deep network model is trained by using the training set, the trained current deep network model is tested by using the test set and the identification accuracy data of the current deep network model are obtained, whether the identification accuracy data meet the preset accuracy requirements is judged, training is completed if the judgment result is yes, or the deep network model obtained by adjustment of the trained current deep network model is determined as the current deep network model, andthe process returns to the step of performing training on the current deep network model by using the training set; and the alimentary canal anatomical image acquired by the capsule endoscopy is inputted to the completely trained deep network model so that the corresponding alimentary canal anatomical position of the alimentary canal anatomical image outputted by the deep network model is obtained. Accurate locating of the capsule in the body can be realized.

The invention discloses an elastic rod guiding type capsule endoscopy robot parking and pose adjusting device and method and relates to an endoscope micro capsule robot. The elastic rod guiding type capsule endoscopy robot parking and pose adjusting device comprises a capsule casing, a driving motor, a screw nut mechanism, a guiding mechanism and a foldable mechanism; The driving motor drives a screw to rotate to drive a nut to move along the guiding rod and enable the foldable mechanism to collect and release to achieve robot parking and positioning; or the screw drives the nut to rotate relative to the foldable mechanism which is folded and positioned inside an intestinal tract to drive a capsule function cabin to rotate surrounding an axis and accordingly pose of the robot is adjusted. The capsule casing and an elastic skin which covers the foldable mechanism defines the integral capsule endoscopy robot to be a seal chamber. The elastic rod guiding type capsule endoscopy robot parking and pose adjusting device has the advantages of enabling the structure to be simple through an under-actuated mode; solving the problems that the capsule endoscopy robot is large in size, swallow is not easy, and wriggle inside the intestinal tract is difficult; achieving omnibearing diagnosis and treat of a gastrointestinal tract of a patient.

The invention discloses a capsule endoscopy automatic focusing system which belongs to the technical field of medical apparatus, wherein the capsule endoscopy enters human body gastrointestinal tract by being taken orally, non-invasively detects internal wall image of the human body gastrointestinal tract, and sends the internal wall image to the outside; an outside image data receiving device is arranged in vitro to wirelessly receive the internal wall image data of the gastrointestinal tract, and transmits the image data to an outside data processing system. When the image acquired by the capsule endoscopy is unclear, an outside focusing controller sends out focusing control signal, a wireless transceiving functional module in the capsule endoscopy receives the control signal, a capsule controller and a lens back and forth displacement control device driver realize the quantitative control of the lens to obtain clear detecting image. The outside focusing controller is arranged in vitro to realize the focusing control of an imaging system of the capsule endoscopy. The outside data processing system realizes the display and processing of the image data of the gastrointestinal tract.

The invention provides a capsule endoscopy, which comprises a capsule-shaped hard casing, an optical front cover arranged at one end of the casing and a circuit board arranged in an inner cavity of the casing. The circuit is provided with a lens, an image sensor, an annularly-arranged light-emitting diode (LED) lamp group and a microprocessor. The circuit board comprises a first rigid section, a second rigid section and a third rigid section which are in U-shaped connection, wherein the second rigid is positioned between the first rigid section and the third rigid section, the second rigid section is parallel to the central axis of the casing, a pressure sensor is positioned on the lateral surface of the second rigid section close to the inner wall of the casing, an elastic portion capable of deforming along the radial direction of casing is positioned on the lateral wall of the casing, the inner lateral wall of the elastic portion is in contact with the pressure sensor, and the outer lateral wall of the elastic portion and the outer wall of the casing are in smooth transition. The capsule endoscopy can shoot images of gastrointestinal tracts and can detect whether pressure in the gastrointestinal tracts is normal.

The invention provides a capsule endoscopy image retrieval method based on visual vocabularies and local descriptors. The method concretely comprises the following steps of: building an image library, wherein the image library comprises standard case images and images to be retrieved; converting capsule endoscopy images from an RGB (Red, Green and Blue) color space into an HSI (Hue, Saturation and Intensity) color space, performing quantization processing and extracting a color histogram; extracting an LBP (Local Binary Patterns) texture histogram of the capsule endoscopy images; performing weighing blending on color features and texture features to obtain the visual vocabularies of the images; extracting Sift (Scale invariant feature transform) feature descriptors of the capsule endoscopy images; and performing similarity testing to obtain retrieval results. The method provided by the invention is used for capsule endoscopy image processing; the work intensity of film reading doctors is effectively reduced; and the diagnosis efficiency is improved.

The invention provides a capsule endoscopy tablet and a detection method thereof. The capsule endoscopy tablet comprises an outer package structure body and a tablet core. A sealing cavity formed by the outer package structure body is filled with the tablet core. The outer package structure body comprises a time control part. The time control part comprises slow-releasing enteric-coating material and colon locating and dissolving material. The tablet core comprises material used for changing colors of urine and/excreta. By recognizing changes in colors of urine and/excreta, judgments can be made as to whether an examinee is suitable for examination of capsule endoscopy or not.

The invention discloses a capsule endoscopy system. The capsule endoscopy system is characterized by comprising a capsule endoscopy provided with a Bluetooth transmission module, a mobile terminal recorder carried by a detected person, a cloud server and an image processing terminal established in a hospital, wherein the Bluetooth transmission module of the capsule endoscopy is connected with the mobile terminal recorder in a Bluetooth communication mode, the mobile terminal recorder is connected with the cloud server in a communication mode through a wireless network, the cloud server is connected with the image processing terminal in a network communication mode, the mobile terminal recorder receives image data obtained by the capsule endoscopy and uploads the image data to the cloud server, the image data are stored, and the image processing terminal downloads the image data from the cloud server. By the adoption of the capsule endoscopy system, the detected person can conveniently and safely conduct capsule endoscopy detection outside the hospital by himself.

The application discloses a capsule endoscopy motion control method. The method comprises the steps that the actual motion state of the capsule endoscopy detected by a sensor arranged in the capsule endoscopy is received; the capsule endoscopy is located in a magnetic field produced by a solenoid; based on the actual motion state and an input expected motion state, the control voltage of the solenoid is calculated by means of a control model; the power supply voltage of the solenoid is adjusted based on the control voltage, so that the forced condition of the capsule endoscopy is changed until the capsule endoscopy reaches the expected motion state. According to the method, the magnetic field is produced by the solenoid, and the magnetic field can be effectively adjusted through adjustment of the power supply voltage of the solenoid, so that active control of the capsule endoscopy is achieved in combination with closed-loop feedback control, and the capsule endoscopy is applicable to detection of the highly dynamic environment of a human stomach. The application further discloses a capsule endoscopy motion control system, and the system also has the above advantages.

The invention discloses a controllable capsule endoscopy control method. The method includes: searching a capsule endoscopy in the stomach; partitioning the gastral cavity into areas in preset quantity; in each area, sequentially adopting an external magnet for attracting the capsule endoscopy to the upper wall of the stomach, adjusting a lens of the capsule endoscopy to be downward to form a first preset included angle with the horizontal plane, controlling the capsule endoscopy to rotatably shoot by taking the vertical direction as an axis, and changing the angle to continue rotatable shooting; controlling the capsule endoscopy to fall down to the lower wall of the stomach, adjusting the lens of the capsule endoscopy to be upward to form a second preset included angle with the horizontal plane, controlling the capsule endoscopy to rotatably shoot by taking the vertical direction as an axis, and changing the angle to continue rotatable shooting. The controllable capsule endoscopy control method has advantages that manual operations of doctors are avoided, the capsule endoscopy completes examination automatically according to a planned route under guidance of an external magnetic field, and the examination coverage rate can be increased.

The invention provides a capsule endoscopy system with a motion positioning function and a capsule endoscopy of the capsule endoscopy system. A motion sensing module is arranged on the capsule endoscopy, when the capsule endoscopy enters the body of a patient, the motion sensing module can detect own motion state, generate motion information and output the motion information to an external device through a radio frequency module, the position information, in the human body at a certain moment, of the capsule endoscopy can be calculated according to the position and motion information of the patient , a photo containing the position information can be obtained by combining the position information with the photo, so that people know which portion the photo is taken for, and a doctor does not need to depend on clinical experience too much when diagnosing the patient, which is beneficial to disease diagnosis.

The invention discloses an alimentary tract dissection position recognition device, which comprises an acquisition module, a training module and a classification module, wherein the acquisition moduleis used for acquiring a training set and a test set; the training module is used for selecting a deep learning framework-based deep network model as the current deep network model, the training set is used to train the current deep network model, the test set is used to obtain recognition precision data of the current deep network model, whether the recognition precision data meet a preset precision requirement is judged, if yes, the training is completed, if not, a deep network model obtained after the current deep network model after training is adjusted is determined to be the current deepnetwork model, and the step of using the training set to train the current deep network model is returned; and the classification module is used for inputting an alimentary tract dissection picture acquired by capsule endoscopy to the deep network model which completes training, and an alimentary tract dissection position corresponding to the alimentary tract dissection picture outputted by the deep network model is obtained. Thus, accurate positioning of the capsule in the body is realized.

The invention discloses a pawl resetting type capsule endoscopy robot parking and pose adjusting device and method and relates to an endoscope micro capsule robot. The pawl resetting type capsule endoscopy robot parking and pose adjusting device comprises a capsule casing, a driving motor, a screw nut mechanism, a guiding mechanism and a foldable mechanism; The driving motor drives a screw to rotate to drive a nut to move along the guiding rod and enable the foldable mechanism to collect and release to achieve robot parking and positioning; or the screw drives the nut to rotate relative to the foldable mechanism which is folded and positioned inside an intestinal tract to drive a capsule function cabin to rotate surrounding an axis and accordingly pose of the robot is adjusted. The capsule casing and an elastic skin which covers the foldable mechanism defines the integral capsule endoscopy robot to be a seal chamber. The pawl resetting type capsule endoscopy robot parking and pose adjusting device has the advantages of enabling the structure to be simple through an under-actuated mode; solving the problems that the capsule endoscopy robot is large in size, swallow is not easy, and wriggle inside the intestinal tract is difficult; achieving omnibearing diagnosis and treat of a gastrointestinal tract of a patient.

The invention discloses a controllable capsule endoscopy, and solves the problem that the position and the time of the capsule endoscopy cannot be controlled manually in the prior art. The controllable capsule endoscopy comprises a capsule endoscopy, a connecting device, a soluble line and a connecting line, wherein the connecting device is arranged at the tail end of the capsule endoscopy, the connecting device is further connected with the soluble line, the connecting line for pulling the capsule endoscopy is connected with the soluble line, and the diameter of the connecting line is not more than 2 mm. When in use, the capsule endoscopy can be pulled by controlling the connecting line, can stay at any position for a long time, and can be positioned at the position required by a doctor to take more images, so as to meet the diagnosis requirement of the clinician. Otherwise, according to the controllable capsule endoscopy provided by the invention, the soluble line can be melted and the connecting line can be pulled out after a certain time checking of the intestines and the stomach, then the capsule endoscopy is naturally separated with the connecting line, and further checking to the remote end intestines and stomach is conducted, and after checking, the capsule endoscopy can be removed from the body.

The invention discloses a capsule endoscopy system with an ultrasonic positioning function and a capsule endoscopy of the capsule endoscopy system. The capsule endoscopy system is provided with an ultrasonic receiving module, after receiving ultrasonic signals emitted by an ultrasonic emitting array, the ultrasonic receiving module can send out beacon signals through a radio frequency unit, the beacon signals express that the ultrasonic signals are already received, and at the moment the time for ultrasonic emitted by an ultrasonic emitter to reach an ultrasonic receiver can be calculated by using the emitting time of the corresponding ultrasonic emitter in the ultrasonic emitting array and the time for generating the beacon signals, and the distance between a corresponding ultrasonic emitter and the ultrasonic receiving module can be obtained by using a sound velocity formula. The position, in the human body of a patient, of the ultrasonic receiver can be calculated in this way, so that a photo containing position information is obtained, people know which portion the photo is taken for, and a doctor does not need to depend on clinical experience too much when diagnosing the patient, which is beneficial to disease diagnosis.

The invention provides a presumption method and device for a capsule endoscopy position. The method comprises the steps that magnetic field source parameters are called, a first magnetic field intensity of the capsule endoscopy position is received, based on the magnetic field source parameters and the first magnetic field intensity, the capsule endoscopy position is obtained, and the capsule endoscopy position is output. According to the presumption method, the magnetic field intensity of the periphery of the magnetic field source can be calculated through magnetic field source parameters, then through combining the magnetic field intensity of the capsule endoscopy position, the presumption of the capsule endoscopy position can be achieved, and the presumption of the capsule endoscopy position inside the human body is achieved.

The invention discloses an artificial intelligence capsule endoscopy examination method and an artificial intelligence capsule endoscopy examination system based on deep reinforcement learning. The method comprises the following steps: acquiring an image of the gastral cavity environment by adopting a capsule endoscopy, and extracting characteristic values of the image; inputting the characteristic values of the image into a pre-trained deep reinforcement learning model, thus obtaining maximum value movements capable of being executed; by utilizing the maximum value movements output by the deep reinforcement learning model, generating a corresponding control instruction according to the state of the capsule endoscopy, and controlling the capsule endoscopy to carry out autokinetic movementin the complicated gastral cavity environment; after the movements of the autokinetic movement are completed, acquiring a return value according to the actual completion status; and judging that whether the capsule endoscopy arrives at a final position or not. The method and the system aim at realizing the purposes that through training, the capsule endoscopy can make the correct decision in the complicated and high-dynamic gastral cavity environment, the capsule endoscopy can be controlled to carry out autokinetic movement in the complicated gastral cavity environment, and the examination forthe whole stomach is intelligently and efficiently realized without omission.

The invention discloses a capsule endoscopy having an accurate positioning function. The capsule endoscopy comprises a capsule shell, a pH sensor, a photographic device, a control device and a positioning device; the positioning device comprises micro legs, rubber wheels, pressure sensors, springs and a motor, wherein the micro legs are arranged on the outer sides of the capsule shell; one end of each of the micro legs is connected to the corresponding rubber wheel; revolution measuring devices are arranged on the rubber wheels; the springs and the motors are connected to the other ends of the micro legs; under the control of the springs, the micro legs are expanded; the micro legs, driven by the motor, contract; and the pressure sensors are additionally arranged on the springs. According to the capsule endoscopy having the accurate positioning function provided by the invention, through the rotation of the rubber wheels and by converting the revolution into a distance, accurate positioning inside the digestive tract of a human body is achieved; and meanwhile, by virtue of the micro legs and the rubber wheels connected to the micro legs, any instable and non-forward movement is minimized, so that the photographic device in the capsule can record stable images or videos.

The invention discloses a controllable capsule endoscopy which can be used for taking pictures of any parts of the digestive system (such as esophagus, stomach, small intestine and the like) from any angle by manual control, increasing the utilization rate and reducing the diagnosing cost. The controllable capsule endoscopy (1) comprises a capsule endoscopy body, a tail line (2) marked with scales is connected to the tail end of the controllable capsule endoscopy (1), and the diameter of the tail line (2) is smaller than 3 millimeters.