31 results about "Small Lesion" patented technology

This invention describes a method for increasing the speed of the parabolic marching method by about a factor of 256. Firstly, to form true 3-D images or 3-D assembled from 2-D slices. Secondly, the frequency of operation can be increased to 5 MHz to match the operating frequency of reflection tomography. This allow the improved imaging of speed of sound which in turn is used to correct errors in focusing delays in reflection tomography imaging. This allows reflection tomography to reach or closely approach its theoretical spatial resolution of ½ to ¾ wave lengths. A third benefit of increasing the operating frequency of inverse scattering to 5 MHz is the improved out of topographic plane spatial resolution. This improves the ability to detect small lesions. It also allow the use of small transducers and narrower beams so that slices can be made closer to the chest wall.

Disclosed herein are method(s) and device(s) capable of generating a small lesion as deep as a few millimeters beneath the skin's surface and several cubic millimeters in volume in orders of magnitude less time, namely, tens of milliseconds. More specifically, in one exemplary embodiment, a method of treating tissue (e.g., skin) is provided which includes generating one or more ultrasound pulses with each pulse having a pulse width shorter than a thermal relaxation time of a tissue treatment volume, and applying one or more of said ultrasound pulses to at least one portion of the tissue treatment volume to generate one or more treatment areas in a region. Methods of treating tissue can include effecting a therapeutic treatment in said region of the tissue, and / or effecting a cosmetic treatment in said target region.

The invention discloses an X-ray imaging system and method based on grating phase contrast and photon counting. X-rays become coherent X-rays after being shaped through a light source grating; the coherent X-rays containing phase changes after penetrating through samples form beam-split X-rays through a phase grating; the phase changes of the X-rays are converted into light intensity changes after the X-rays pass an analyzing grating; a photon counting detector is used for recording phase contrast information of the X-rays with different intensities; sectional images based on phase contrast are obtained through a three-dimensional reconstruction system; finally, components and interior fine structure information of the soft tissue samples are obtained. The system and method can be used for detecting soft tissue samples in the pathology department, the radiology department and the scientific research department of a hospital, early lesion information such as small lesions in the tissue samples can be found easily, and the detection rate is greatly increased.

The invention discloses a method for detecting diseases and pests of field crops based on an SSD convolution network. At first, the VGG deep convolution neural network is used to extract the primary features of the image of the disease and insect pests, then multi-scale feature extraction is carried out to evaluate different aspect ratios of plaque and pest detection frames at each position in several feature images output from different convolution layers and to detect plaque and pest in various shapes and sizes of leaf images. The invention can learn the multi-level characteristics from lowto high, quickly realizes the detection of diseases and pests with high precision, greatly improves the detection capability of small lesions and pests, and is particularly suitable for the detectionof diseases and pests of crop leaves based on the video leaf image of the Internet of Things.

An auxiliary device for attenuating pain of injections, characterized in that said auxiliary device comprise a plate portion including a plurality of pointed elements adapted to be pressed on a user skin at a region about or near an injection point, to reduce a needle puncture pain; said device can be always used for attenuating pain of injections, traumas, small lesions, hair removing operations, and inflammation conditions.

The invention provides a chronic obstructive pulmonary disease detection system based on a deep neural network. The system comprises a preprocessing module, which is used for carrying out gray-scale treatment on an obtained chest CT image of a first patient and extracting a plurality of pulmonary lobule area images of the chest CT image obtained after gray-scale treatment; and a detection module,which is used for inputting obtained body mass index BMI of the first patient and the plurality of pulmonary lobule area images into a trained deep neural network model, and obtaining probability of the first patient in getting the chronic obstructive pulmonary disease. The chronic obstructive pulmonary disease detection system based on the deep neural network, through combination of the deep neural network and medical images, and with clinical experience knowledge obtained by diagnosing the COPD manually being as prior knowledge, carries out detection on early-stage pulmonary lobule small lesions, and carries out highly-reliable prediction on the cases, thereby improving COPD detection accuracy.

The invention provides a drug-coating balloon catheter and a production method and application thereof. The method includes: preparing active drug seed crystals, and screening the seed crystals 1-3 micrometers in length to prepare active drug seed crystal suspension; adding the active drug seed crystal suspension, an active drug solution and an additive solution into different channels of a coating machine, mixing and atomizing the active drug seed crystal suspension, the active drug solution and the additive solution at the nozzle tip end of the ultrasonic sprayer of the coating machine, spraying to the surface of a balloon dilatation catheter to obtain drug coating with an appropriate crystal size, and performing homogenizing post-processing to obtain the drug-coating balloon catheter with homogeneous crystals. The drug-coating balloon catheter and the production method thereof have the advantages that the drug coating is firmly combined with a balloon, and drug crystals are even and complete; small drug loss during balloon preparation and in-vivo conveying can be guaranteed, concentration of effective drugs entering the blood vessel wall of a lesion part is high, high drug loading efficiency is achieved, intravascular in-situ stenosis or restenosis can be treated effectively, the risks of late thrombosis and restenosis are reduced, and the positive remodeling of blood vessels can be formed at the same time.

The invention discloses an intelligent biological microscope, which belongs to the field of microscopy and particularly relates to an intelligent biological microscope capable of automatic focusing, splicing an image and recognizing a formed element. A hardware module and an image acquisition module are connected with a computer through a connection line, and the software module operates at a computer end. Through cooperation of three stepping motors and an industrial camera, automatic focusing and image photographing of a monocular microscope can be completed, the image processing software operating at the computer end outputs a split large-view field image through preprocessing, image registration, transform model establishment, image transform and image fusion, and finally, an algorithmunit in the software operates to perform formed element recognition and counting on the outputted image. During the use process, one-button operation is adopted, the workload of a doctor is greatly reduced, small lesions and difficult cases can be extremely highly recognized, and quantitative analysis of post-processing provides a reliable reference for doctor diagnosis.

The invention provides a rotating multi-angle surface reconstruction method and a device for a tubular cavity tissue. The method includes the steps of obtaining an imaging surface of the tubular cavity tissue by means of a coordinate transformation method, determining an imaging angle of an area of interest on the imaging surface based on structure characteristics of the area of interest, and reconstructing and displaying tubular cavity tissue imaging based on the tubular cavity tissue information of the determined imaging angle in the vector direction as well as the positional relationship among various sampling points on the center line of the tubular cavity tissue. With the rotating multi-angle surface reconstruction method and the device, clinical staff can use an image surface reconstructed to flexibly, easily, quickly and effectively detect small lesions in the tubular cavity tissue.

The present invention relates to a mammography detector consisting of a mammography detector having multiple sensors, such as a high resolution sensor for detecting very small lesions, a high contrast sensor for detecting the exact size of a lesion, a mammography sensor, and a CT sensor; and to a mammography device capable of acquiring 3D images by rotating an X-ray emitting unit and the mammography detector by more than 185 degrees with respect to a breast to be examined. The mammography device includes a main body, a gantry connected to the main body so as to be capable of moving vertically, an X-ray emitting unit mounted on one end of the gantry, and an X-ray detector mounted on the opposite end of the gantry at a position opposite the X-ray emitting unit, and comprises: a first rotating means provided within the main body in order to rotate the gantry; and a pressing means for pressing the breast of a patient while the patient is standing, and including a supporting panel provided on a rotational axis of the first rotating means, and a pressing panel capable of vertical movement on the axis of rotation so as to press the breast on the supporting panel, and connected to the main body while physically separated state from the gantry. The X-ray detector includes a CT sensor, and a 3D image is acquired by rotating the gantry by at least a certain angle, with the pressing means pressing the breast of the patient.

The invention discloses a gastrointestinal tract contrast medium and the contrast medium comprises the following components in parts by weight: 1000 parts of purified water, 0.3-20 parts of one or more of pure iodine and iodides in the purified water, and 1-8 parts of edible liquid paraffin, wherein the weight of iodine and iodides is calculated by 100% of pure iodine. The gastrointestinal tract contrast medium has the advantage that the contrast medium is safe and effective and has no toxic and side effects, the contrast medium can be fast filled in the part of body which is needed to imaged, and the contrast medium filled in the intracavity can form imaging oral contrast medium with a certain threshold specific density on the adjacent organ and lesion (nidus). After drunken, the contrast medium of the invention is not easy to absorb and can be discharged fast; the physiochemical performance of the contrast medium is stable, the comparison is obvious, the image is clear, the effective diagnosis rate reaches above 97%, the detecting ability is excellent especially for the observation of midabdomen, lower abdomen and pelvic cavity and the diagnosis of the small lesion (nidus), and the sensitivity and specificity for detecting early tumors and lesions in the gastrointestinal tract can be increased.

The invention relates to an optical fiber finger for detecting flexibility of a prostate and a detection method. The optical fiber finger comprises a laser light source, a sine excitation wave, a medical plastic membrane for being in contact with the prostate, a mono-mode sensing optical fiber for sensing vibration of the membrane, a 45-degree end face angle sensing mono-mode optical fiber processed by a polishing process, an optical fiber connector for connecting the mono-mode sensing optical fiber and an optical fiber detector, and an optical fiber detector for detecting toughness information of tissues. Aiming at the technical requirements on direct detection of the prostate, the invention designs the low-cost optical fiber finger capable of penetrating into a human body so as to carry out diagnosis on prostatic lesions; the size of each sensor is smaller than 5mm; paint brought to a patient by the prostatic lesions is greatly reduced. Meanwhile, small lesion tissues difficult to find can be detected, so that probability of finding abnormal tissues in the early stage is improved.

The invention discloses a medical image small lesion segmentation method, which comprises the steps that a segmentation network is formed by attention modules of a rough segmentation first stage, a refined second stage and a segmentation error region, and five-fold cross validation is used in the training of the first stage; during cross validation, each sample of the training set is contained inthe validation set, and all the samples have an opportunity to be regarded as data of the validation set and are tested on a model trained on the corresponding training set; a prediction result of thefirst stage is compared with a real segmentation result to obtain a difference which reflects a difficult-to-predict part of the model, and mismatching information is taken as supervision of the second stage; and in the second stage, the information enhancement features are input into a DA module, and an attention mechanism is used, so that the segmentation precision of the network is enhanced.

The invention discloses a balloon catheter, which comprises: a hypotube having an expansion chamber; an inner tube having an expansion chamber, and an outer tube having an outer diameter, wherein theinner tube is located inside the outer tube, the inner tube and the outer tube are coaxially arranged on the longitudinal axis, and a distal end of the hypotube is located between a proximal end of the outer tube and a proximal end of the inner tube; a balloon having only a tapered portion, wherein the proximal end of the balloon is coupled to the distal end of the outer tube, the distal end of the inner tube is positioned within the balloon and coupled to the distal end of the balloon; and a plurality of guide wires located between the inner tube and outer tube, wherein the proximal end of each guide wire is fixed to the distal end of the hypotube. The balloon catheter of the present invention can ensure the flexibility of the guide wire at the distal end while ensuring the pushing performance and anti-bendability of the guide wire at the distal end, and can smoothly pass the balloon catheter through the small lesion to improve the penetration performance of the balloon catheter.

An improved method for enhancing the contrast between background and lesion areas of a breast undergoing dual-head scintimammographic examination comprising: 1) acquiring a pair of digital images from a pair of small FOV or mini gamma cameras compressing the breast under examination from opposing sides; 2) inverting one of the pair of images to align or co-register with the other of the images to obtain co-registered pixel values; 3) normalizing the pair of images pixel-by-pixel by dividing pixel values from each of the two acquired images and the co-registered image by the average count per pixel in the entire breast area of the corresponding detector; and 4) multiplying the number of counts in each pixel by the value obtained in step 3 to produce a normalization enhanced two dimensional contrast map. This enhanced (increased contrast) contrast map enhances the visibility of minor local increases (uptakes) of activity over the background and therefore improves lesion detection sensitivity, especially of small lesions.

The invention discloses an automatic quantitative analysis system and an interpretation method for white matter lesions, which utilize an artificial intelligence method to automatically and accurately sketch lesions, accurately calculate the volume of the white matter lesions and provide possibility for accurate evaluation of disease progression. Meanwhile, the invention provides the automatic interpretation system, multi-dimensional information such as anatomical positioning, morphological structure, lesion size, lesion occurrence time and bleeding of lesions is determined through human-computer interaction, lesion positioning visualization, image index quantification, report term standardization and operation interface friendliness are achieved, logic analysis is automatically made, disease judgment is accurately obtained, and inconformity between a conclusion and description and missing report of important conclusions are avoided.

The invention discloses a multiple-adjustable type medical reflecting mirror. The multiple-adjustable type medical reflecting mirror comprises a reflecting mirror which is in a concave mirror shape, awearing headband and a universal joint for connecting the headband with the reflecting mirror body, wherein an observing hole is formed in the center of the reflecting mirror; a rotatable magnification mirror scaffold is arranged on the back side of the reflecting mirror; and a plurality of magnification mirrors with different multiples are mounted on the magnification mirror scaffold. The multiple-adjustable type medical reflecting mirror also comprises an adjusting device which is used for driving the magnification mirror scaffold to be rotated; and the observing hole is positioned on a path around which the magnification mirrors positioned on the magnification mirror scaffold rotate. According to the medical reflecting mirror having the structure disclosed by the invention, a lens hasthree visual fields including an effect of magnifying five times, an effect of magnifying 2.5 times and a normal observing port, so that small lesions can be observed, misdiagnosis and improper treatment can be reduced, unnecessary inspection items of patients can be reduced, and the diagnose and treatment quality can be improved.

The embodiment of the invention provides a video-assisted thoracoscope locating and marking method, which comprises the following steps of: obtaining locating information which includes the locating information of lesion; determining a preoperative locating mode according to the locating information; locating the lesion according to the preoperative locating mode, and obtaining the locating information of the lesion; carrying out a real-time calibration by combining with ultrasonic technique during the operation to obtain marking information; and resecting the lesion according to the locatinginformation and marking information of the lesion. By the adoption of the video-assisted thoracoscope locating and marking method, different preoperative locating methods are provided, meanwhile, theultrasonic three-dimensional real-time calibration technique is adopted during the operation to obtain the locating information of the lesion and the marking information related to the lesion, so thatthe lesion is accurately located and a definite surgical excision edge is provided at the same time, thereby avoiding unnecessary excision of the lesion, and overcoming the problem that an existing locating and marking method cannot accurately locate and mark small lesions, which leads to large excision range.

The invention discloses a positioning scanning assisting device used for magnetic resonance limb small lesion examination. The device comprises a plastic cube. One surface of the plastic cube is provided with a plurality of first pipes parallel to each other. An opposite surface of the surface is provided with a plurality of second pipes which are parallel to each other and are vertical to the first pipes. Centers of other four surfaces of the plastic cube are respectively provided with a lifting lug, providing convenience for binding the device on a limb by bandages. The first pipes and the second pipes are internally provided with constrast medium small tubes. The device is made of a PVC plastic, and is convenient in material getting and low in manufacturing cost. The device can be boundon a limb according to specific conditions of lesion. After a technician scans a location map, a key scanning region can be rapidly determined according to constrast medium development conditions, soas to accurately position size of suspected limb small lesion. The device can be repeatedly used after being disinfected by medicinal alcohol.

The present invention discloses an anchoring positioning device and a video-assisted thoracic surgery system guided by electromagnetic navigation. The anchoring positioning device comprises a positioning lead and a sensing plug, and the positioning lead comprises an anchoring head, a sensing probe and a conduit tube; and the anchoring head and the sensing probe are arranged in the conduit tube, the anchoring head can be anchored on lesions, and the sensing probe can detect a current position coordinate. Therefore, in a surgery process, when the positioning lead goes deep into the lesions, position prompt information of the sensing probe can accurately judge whether the lesions are reached, and after the lesions are reached, the anchoring head can be anchored on the lesions, so that the far, deep and small lesions can be effectively positioned.

The invention relates to an optical fiber finger for detecting flexibility of a prostate and a detection method. The optical fiber finger comprises a laser light source, a sine excitation wave, a medical plastic membrane for being in contact with the prostate, a mono-mode sensing optical fiber for sensing vibration of the membrane, a 45-degree end face angle sensing mono-mode optical fiber processed by a polishing process, an optical fiber connector for connecting the mono-mode sensing optical fiber and an optical fiber detector, and an optical fiber detector for detecting toughness information of tissues. Aiming at the technical requirements on direct detection of the prostate, the invention designs the low-cost optical fiber finger capable of penetrating into a human body so as to carry out diagnosis on prostatic lesions; the size of each sensor is smaller than 5mm; paint brought to a patient by the prostatic lesions is greatly reduced. Meanwhile, small lesion tissues difficult to find can be detected, so that probability of finding abnormal tissues in the early stage is improved.

The invention relates to a lesion area quantification method based on a mammary gland molybdenum target image, and the method comprises the steps: carrying out the detection network training of a mammary gland lesion area through an efficientdet-d8 network and a YOLOV5 network, and obtaining a detection model; performing breast lesion area segmentation training through a Unet network structure, performing two Unet network structure training according to the size of the breast molybdenum target image, performing segmentation network training on a large lesion area, and training a segmentation model on a small lesion area; after the detection model and the segmentation model are obtained, carrying out verification respectively; calculating the position of a lesion area through a detection model and a segmentation model according to an acquired mammary gland molybdenum target image, calculating the size and density distribution of the lesion area through a segmentation result, obtaining a benign and malignant confidence score through a detection result, and providing diagnosis assistance information through positioning and quantification of the lesion area. The problem that human experience is insufficient when breast diseases are read can be solved, and doctors are helped to locate and analyze the diseases.

The invention relates to medical instruments, and particularly relates to a balloon expansion type absorbable vein stent. The stent is of a cylindrical net structure and is divided into a lesion section stent body supported at the vein occlusion or stenosis position and an adjacent normal vein section stent body supported at the adjacent position of the lesion section stent body. The mesh diameter of the adjacent normal vein section stent body is larger than or equal to that of the lesion section stent body. The stent is made of absorbable materials. The absorption time of the lesion section stent body is longer than that of the adjacent normal vein section stent body. A balloon is sleeved with the stent, and the stent is supported and placed into the vein through expansion of the balloon. The stent is placed in the vein through expansion of the balloon, and is accurate in positioning, good in wall attaching performance and small in thrombosis probability. The stent can be completely absorbed, the part supporting the normal vein section is fast absorbed, the influence on the vein is small, the lesion section is slow in absorption, and supporting force is good.