34 results about "Lesion analysis" patented technology

The invention discloses a wireless capsule endoscope small intestine lesion computer auxiliary detection system and method. At present, the technology of the capsule endoscope in the aspect of intelligent lesion identification and accurate positioning is very limited. The data input module is used for acquiring the video data of the wireless capsule endoscope of the patient, and an image of the capsule endoscope is obtained by extracting a video frame technology; the image preprocessing module is used for preprocessing the image of the wireless capsule endoscope, the small intestine image recognition module is used for recognizing and extracting a small intestine image and an image sequence in the preprocessed capsule endoscope image; the small intestine lesion analysis and positioning module is used for identifying and classifying the small intestine lesion and extracting the specific position of the focus; the user interaction module forms an auxiliary diagnosis result according to the small intestine lesion information and the analysis result of the positioning module, and the doctor can confirm, modify or input the medical advice so as to form a diagnosis report. According to the invention, the practical value of the capsule endoscope in clinic is promoted, so that a more efficient and more standard diagnosis mode is formed.

A system and method for performing quantitative lesion analysis in molecular breast imaging (MBI) using the opposing images of a slightly compressed breast that are obtained from the dual-head gamma camera. The method uses the shape of the pixel intensity profiles through each tumor to determine tumor diameter. Also, the method uses a thickness of the compressed breast and the attenuation of gamma rays in soft tissue to determine the depth of the tumor from the collimator face of the detector head. Further still, the method uses the measured tumor diameter and measurements of counts in the tumor and background breast region to determine relative radiotracer uptake or tumor-to-background ratio (T/B ratio).

The invention discloses an ultrasonic scanning real-time control method. The ultrasonic scanning real-time control method comprises: acquiring a plurality of ultrasonic images for a human chest continuously collected by an ultrasonic probe at specified coordinates; determining the integrity of each ultrasonic image, and storing at least three ultrasonic images of which the integrity meets the requirements; calculating a correlation coefficient between the stored ultrasonic images, and storing the ultrasonic image with the correlation coefficient higher than a first preset threshold as an imagesequence; calculating the sharpness of each ultrasonic image in the image sequence, and if the obtained sharpness is lower than a second preset threshold, adjusting the pose of the ultrasonic probe according to the specified coordinates, and reacquiring an ultrasonic image. Real-time control of the movement of the ultrasonic probe is realized by feedback of the ultrasonic image, thereby ensuringthat the ultrasonic image finally obtained by the ultrasonic probe in a specified area can clearly and completely display all pathological structures and meets the requirements of lesion analysis.

A system and method for performing quantitative lesion analysis in molecular breast imaging (MBI) using the opposing images of a slightly compressed breast that are obtained from the dual-head gamma camera. The method uses the shape of the pixel intensity profiles through each tumor to determine tumor diameter. Also, the method uses a thickness of the compressed breast and the attenuation of gamma rays in soft tissue to determine the depth of the tumor from the collimator face of the detector head. Further still, the method uses the measured tumor diameter and measurements of counts in the tumor and background breast region to determine relative radiotracer uptake or tumor-to-background ratio (T/B ratio).

The present invention relates to a Raman probe for in-vivo and in-situ puncture diagnosis. The Raman probe is in a puncture type, and can enter organ tissues in a human body for performing in-vivo and in-situ puncture detection and reduce damage by using an elongated needle for puncture or needle for biopsy to extend a conventional Raman probe. Optical components in a puncture needle cavity can achieve the extension of the incident light and the collection of scattered light. The Raman probe has the advantages of simple structure, convenient disassembly, easy disinfection, reusability, and high sensitivity and reliability, is suitable for in-vivo and in-situ detection of organ tissues and lesion analysis, and provides support and help for early accurate diagnosis and timely and accurate treatment for tumors. The Raman probe can be used for detecting the difference of the molecular structure of the biological tissue, and can also diagnose whether the organ tissue in the organism undergoes mutation or not according to the detected Raman signal.

The invention belongs to the technical field of machine learning, and particularly relates to a lung medical image analysis method, device and system. The lung medical image analysis method comprises the steps of segmenting a lung field and a lung lesion area from an acquired lung medical image, calculating an ROI (Region of Interest) containing the lung field and the lung lesion area, and cutting an input picture for image recognition in the lung medical image according to the ROI. And inputting the input picture into a second-stage detection model, further extracting feature parameters, and obtaining a final lesion analysis result output by a preset semantic segmentation model. By means of the lung medical image analysis method, device and system, multiple lung lesions can be recognized and classified and judged at the same time, and the device is high in efficiency and accuracy of lung medical image analysis and has good application prospects.

The invention provides an ROI mark point matching method based on an intravascular unltrasound image, and relates to the field of computer medical image analysis. The method is characterized by including the steps of firstly, conducting background suppression on the area, except the ROI, of an IVUS image, extracting an ROI image, and setting even mark points of an original image; secondly, setting a search window on a to-be-matched image according to the limitation of blood vessel wall deformation and the fact that no rotation conversion can happen between collected images, wherein the size of the search window is set according to the maximum deformation amount of endangium; thirdly, finding a matched point in the search window through a traversing method, and using the central position of a search sub-image as the matched point, wherein the search sub-image and a neighborhood sub-image of the mark points have the maximum mutual correlation similarity measure. Compared with an ordinary matching algorithm, the method is short in matching time and high in accuracy. By means of the method, the displacement situations of blood vessels before and after deformation can be provided, conditions are provided for elastic computing, and the good foundation is provided for the lesion analysis.

The invention discloses an endocardium point-in-point insertion dynamic surface reconstruction method for use in a cardiac mapping system, comprising: A1: a catheter collects four affine independent points, and is initialized into a tetrahedral mesh by the above four affine independent points; A2: new sampling points are inserted, and a set of surface triangular patches that need to be replaced ina currently reconstructed surface mesh is calculated according to the newly inserted sampling points; A3: a Delaunay triangulation structure is updated, and also the current surface mesh structure isalso updated; A4: the currently reconstructed surface mesh is optimized by using local expansion and engraving; and A5: isolated points already in the Delaunay triangulation structure but not in thesurface mesh are inserted to improve the quality of the surface mesh. The above surface reconstruction method is more suitable for the sampling point step of the catheter in the operation, and is morefriendly to the doctor to grasp the current sampling situation, so as to significantly improve the reconstruction efficiency of the endometrial surface of the cardiac mapping system, and to better improve services of the lesion location and lesion analysis for the doctor.

The invention provides an energy assisted medical intelligent system which is characterized in that the system comprises an energy injection scheme formulation system and an energy injection scheme execution system, the energy injection scheme formulation system comprises a data acquisition unit, a data analysis unit and an energy injection scheme formulation unit, and the energy injection schemeexecution system includes an energy injection control unit and an energy injection unit. Through the system, the medical record data and detection data of a patient and a diagnosis result of a doctorare collected, after the collected data is analyzed, a disease cause, pathogenesis, pathology and a lesion analysis result are obtained, an energy injection plan is made, an energy injection control signal is emitted, and the energy injection device is started to accurately perform energy injection on a target person. The system is safe and reliable, the self-healing power and resistance of a human body are improved, the system can be used in any place, the burden on a hospital is greatly reduced, and the medical cost is reduced.

Described herein is a computer implemented method that includes receiving at a data processor two or more digital data files representing medical images of a same modality; performing group-wise 3D registration of the digital data files representing medical images of a same modality; and parallel lesion detection and analysis on the digital data files representing the medical images.

The embodiment of the invention provides a lung lesion analysis method and device, electronic equipment and a storage medium, and the method comprises the steps: inputting a to-be-analyzed chest imageinto a lesion positioning model, and obtaining a lung lesion positioning result of the chest image outputted by the lesion positioning model; and inputting the fused image determined based on the chest image and the lung focus positioning result of the chest image, or inputting the chest image and the lung focus positioning result of the chest image into a focus analysis model to obtain a lung focus analysis result of the chest image output by the focus analysis model. The lung lesion analysis result can comprehensively cover all lung lesions including tiny lesions and atypical lesions, and the reliability and accuracy of lung lesion analysis are ensured.

The embodiment of the invention provides a focus analysis method and device based on medical images, electronic equipment and a computer readable storage medium. The invention solves the problem thatfocus analysis in the medical image is not comprehensive and not accurate enough in the prior art. The focus analysis method comprises the following steps: extracting focus characterization data basedon medical image data; extracting focus feature information based on the focus representation data; inputting the lesion feature information into a first machine learning model to obtain a first lesion feature vector; inputting the medical image data and the focus representation data into a second machine learning model to obtain a second focus feature vector; combining the first lesion feature vector and the second lesion feature vector to obtain a fusion feature vector corresponding to the lesion; and obtaining an analysis result of the focus according to the fusion feature vector.

The invention discloses a method for establishing an intracranial angiography enhanced three-dimensional model based on transfer learning. The method comprises the following steps: acquiring a bright blood image group, a black blood image group and an enhanced black blood image group; preprocessing to obtain a first bright blood image and a first black blood image; taking the corresponding first black blood image as a reference for each first bright blood image, and obtaining a registered bright blood image group by using mutual information based on Gaussian distribution sampling and a registration method of an image pyramid; performing flow empty artifact elimination to obtain an artifact-eliminated enhanced black blood image group; subtracting corresponding images in the artifact elimination enhanced black blood image group and the black blood image group to obtain K contrast enhanced images; and establishing a blood three-dimensional model by utilizing the registered bright blood image group and adopting a transfer learning method, and establishing a blood vessel three-dimensional model of blood boundary expansion by utilizing the registered bright blood image group. The whole state of the intracranial blood vessel can be simply, conveniently, rapidly and visually obtained clinically so that intracranial vascular lesion analysis can be conducted.

A system for facilitating lesion analysis accesses a first data structure comprising a plurality of entries including anatomic location information and annotation information associated with a plurality of lesions represented in a first set of cross-sectional images. The system displays a respective representation of each of the plurality of entries and presents a second set of cross-sectional images. The system receives user input triggering selection of a particular entry of the plurality of entries of the first data structure. In response to the user input, the system (i) presents a particular cross-sectional image and a particular lesion of the first set of cross-sectional images associated with the particular entry, (ii) identifies a predicted matching cross-sectional image from the second set of cross-sectional images, and (iii) presents the predicted matching cross-sectional image simultaneously with the particular cross-sectional image, particular anatomic location information, and particular annotation information.

Disclosed is a method for analyzing a lesion based on a medical image, which is performed by a computing device. The method may include: obtaining positional information of a suspicious nodule which exists in the medical image; generating a mask for the suspicious nodule based on a patch of the medical image corresponding to the positional information; and determining a class for a state of the suspicious nodule based on the patch of the medical image and the mask for the suspicious nodule.