15 results about "Thyroid tumors" patented technology

The invention discloses a thyroid tumor diagnosis method and system based on ultrasonic and cytological image conjoint analysis. The method comprises the following steps: converting a thyroid B ultrasonic image of a patient to be diagnosed into an image feature vector FUS; performing structured feature extraction on the thyroid cytological image of the patient to be diagnosed to obtain a structured feature vector FCYTO; the image feature vector FUS and the structured feature vector FCYTO are converted into a fusion Token sequence; and inputting the Token into a multi-modal feature fusion and prediction network based on a Transform architecture, and carrying out feature fusion and classification prediction so as to obtain the probability that the thyroid tumor of the patient to be diagnosed is malignant. The thyroid tumor diagnosis based on multi-modal fusion is carried out on the basis of ultrasonic and cytological images, so that the diagnosis accuracy is improved.

The invention discloses an automatic diagnosis method of a thyroid pathological image, and belongs to the technical field of medical pathological image auxiliary intelligent diagnosis, and the method comprises the following steps: constructing a thyroid tumor pathological image data set, preprocessing a pathological image, carrying out multi-scale fusion, carrying out feature extraction, carrying out feature fusion, inputting a CLAM-SB multi-instance learning model, and generating a visual heat map. The invention provides a thyroid pathology image automatic diagnosis method based on weak supervision multi-instance learning and multi-scale feature fusion, which can effectively improve the accuracy of pathology tissue region segmentation and pathology image classification, reduce the workload of pathologists and improve the diagnosis efficiency and reliability.

The invention discloses a thyroid tumor classification and recurrence risk prediction method based on deep learning, and belongs to the field of medical image processing, and the method comprises the following steps: collecting and preprocessing multi-modal data related to thyroid follicular carcinoma FTC or follicular adenoma FTA; performing feature extraction on the preprocessed multi-modal data to obtain image features and pathological features; respectively adopting different fusion and optimization methods for the combination of the image features and the pathological features and the image features to obtain a first optimized fusion feature and a second optimized fusion feature; and inputting the first optimized fusion feature into a preoperative classification model to obtain a thyroid tumor type classification probability, and inputting the second optimized fusion feature and the pathological feature into a postoperative recurrence risk prediction model to obtain a recurrence risk score. By means of the multi-mode image classification model and the recurrence risk prediction model which are specially constructed, the sensitivity and specificity of preoperative classification are improved, and accurate individualized management is provided for postoperative patients.

The invention discloses a thyroid tumor evaluation system based on combination of an ultrasonic image and pathological data, and relates to the technical field of auxiliary decision making. Comprising the steps that an image acquisition module preprocesses a thyroid ultrasound image; the pathology acquisition module is used for extracting structured data containing pathology malignancy scores and molecular marker expression parameters; the feature extraction module generates feature vectors from the images and the pathological data respectively; the region screening module dynamically generates an image region sensitivity threshold value based on the molecular marker and the pathological malignant score; a weighted extraction module recognizes an image suspicious region and generates weighted features according to the image suspicious region; the multi-modal fusion module fuses bimodal features through a weight distribution rule; and the evaluation decision module outputs benign and malignant prediction results and confidence scores. Dynamic sensitivity regulation and control of deep coupling of pathological semantics and image features are realized, and image suspicious region identification precision and cross-modal decision reliability precision are improved.

The invention discloses a compound traditional Chinese medicine preparation for improving tumor immunity and resisting tumors, belongs to the technical field of anti-tumor traditional Chinese medicines, and discloses a compound traditional Chinese medicine preparation for improving tumor immunity and resisting tumors. The traditional Chinese medicine composition comprises the following components in parts by weight: 10-25 parts of ginseng, 15-18 parts of selfheal, 12-18 parts of seaweed, 12-19 parts of astragalus membranaceus, 10-16 parts of angelica sinensis, 18-30 parts of oldenlandia diffusa, 10-15 parts of fleece-flower root, 10-14 parts of poria cocos, 10-16 parts of thunberg fritillary bulb, 8-14 parts of pseudobulbus cremastrae seu pleiones and 8-17 parts of curcuma zedoary. Through the specific pharmacological action, growth and proliferation of thyroid tumor cells are inhibited, the development speed of tumors can be slowed down, the malignancy degree of the tumors can be reduced, apoptosis of the thyroid tumor cells can be induced, and the number of the tumor cells can be effectively reduced by inducing apoptosis of the tumor cells, so that the anti-tumor purpose is achieved.

The invention provides a thyroid tumor postoperative intelligent nursing system based on multi-dimensional health data, and relates to the field of medical data processing, and the system comprises a map building module which is used for building a thyroid tumor postoperative complication map; the information acquisition module is used for acquiring multi-dimensional health data of the patient; the scheme generation module is used for determining a thyroid tumor postoperative nursing scheme according to the multi-dimensional health data of the patient and the thyroid tumor postoperative complication atlas; the state monitoring module is used for collecting thyroid tumor postoperative real-time state information of the patient according to the thyroid tumor postoperative nursing scheme of the patient; the nursing prompting module is used for carrying out nursing risk prompting according to the thyroid tumor postoperative real-time state information and the thyroid tumor postoperative complication atlas of the patient; the recurrence follow-up visit module is used for obtaining complication monitoring information of the patient and conducting follow-up visit prompting, and the intelligent nursing system has the advantages that personalized intelligent nursing after the thyroid tumor operation is achieved, and the real-time performance and quality of nursing are improved.

The invention relates to a medicine for treating tumors, in particular to a tumor cell membrane and TKI co-modified sound-sensitive nano material, a preparation method thereof and application of the sound-sensitive nano material in the medicine for treating the tumors, and aims to solve the problems that in an existing thyroid cancer treatment method, the side effect is large when TKI is singly used; or the problem of insufficient curative effect caused by low bioavailability of the sound-sensitive material in SDT and poor aggregation of the tumor site is solved. The material comprises TKI, a sound-sensitive nano material body and a tumor cell membrane, the sound-sensitive nano material body is of a hollow structure; wherein one part of TKI is embedded in pores in the sound-sensitive nano material, and the other part of TKI is adsorbed on the outer surface of the sound-sensitive nano material body; the tumor cell membrane is coated on the outer surface of the sound-sensitive nano material body. The preparation method comprises the following steps: preparing FeTBP, preparing FeTBP loaded with TKI, and preparing a tumor cell membrane and TKI co-modified material FL (at) M. The invention also provides application of the material in medicines for treating tumors. The curative effect on thyroid tumor is improved.

The invention relates to the technical field of multi-modal image analysis, in particular to a thyroid tumor preoperative ultrasonic image multi-modal analysis system and a thyroid tumor preoperative ultrasonic image multi-modal analysis method. The method comprises the following steps of: acquiring a matching vector between each point in a gray-scale image of a current patient and a corresponding point in a target modal image with the nearest time domain; further extracting a breathing signal, and dividing a breathing stage and a breathing cycle; further dividing an abnormal region and a normal region according to change similar characteristics of displacement vectors of all points in each block region between different respiratory cycles; further in each type of breathing stage, according to the difference between the matching vector in the normal region and the matching vector in the corresponding alignment region, correcting the matching vector in the abnormal region, and obtaining a normal matching vector; and finally, generating a three-dimensional fusion image, and correcting an abnormal matching vector by using a healthy person alignment region, so that coupling interference of respiratory movement and tumor compression can be effectively eliminated, and the accuracy of multi-modal image fusion is improved.

The application discloses a thyroid tumor evaluation system based on ultrasound images and pathological data, and relates to the technical field of auxiliary decision-making.The image acquisition module is used for pre-processing thyroid ultrasound images;the pathological acquisition module is used for extracting structured data containing pathological malignant scores and molecular marker expression parameters;the feature extraction module is used for generating feature vectors from the image and pathological data respectively;the region screening module is used for dynamically generating image region sensitivity threshold values based on molecular markers and pathological malignant scores;the weighted extraction module is used for identifying image suspicious regions and generating weighted features accordingly;the multi-modal fusion module is used for fusing double-modal features through a weight distribution rule;and the evaluation decision module is used for outputting benign and malignant prediction results and confidence scores.The application realizes dynamic sensitivity regulation and control of pathological semantics and image feature deep coupling, and improves the image suspicious region identification accuracy and the accuracy of cross-modal decision reliability.

The invention relates to the technical field of surgical path planning, in particular to a robot-assisted mammary gland thyroid tumor minimally invasive excision path planning method and system, and the method comprises the following steps: collecting tissue structures, poses and response contents, carrying out synchronous processing according to timestamps, recognizing vascular structures, extracting spatial differences, expanding candidate regions, and reading gray variance. And judging an included angle relation, analyzing displacement change, and generating a path planning result. According to the method, a data fusion system with a unified time index is constructed, an organizational structure, pose information and perceptual response are integrated, the time sequence consistency of input data is enhanced, the trend change of an operation area is clarified through blood vessel direction continuity and a spatial difference value extraction mode, boundary continuity recognition is achieved in combination with boundary area gray and variance features, and the recognition accuracy is improved. The advancing direction is corrected based on the path and blood vessel included angle relation, the path node sequence and the adjustment range are dynamically judged according to the displacement difference, and the response capacity and stability of path planning to intraoperative changes are improved.

The invention relates to the technical field of terahertz near-field imaging, in particular to a thyroid tumor tissue area identification method for a terahertz near-field system. According to the technical scheme, the method comprises the following steps: preliminarily partitioning a thyroid section by using an optical microscope to identify a suspected tumor tissue region; in the suspected tumor tissue area, an optical microscope is used for amplifying and partitioning, and the tumor tissue area is subdivided based on the surface convex-concave flat condition. According to the invention, the optimal imaging area of the terahertz near-field system is quickly positioned through a systematic partition screening process, so that the detection efficiency is improved; a flat area with sparse fibers is preferably selected as a target spot, so that the capturing probability and imaging quality of tumor cells are improved; the standardized morphological feature recognition process reduces the dependence on the experience of operators, realizes the effective combination of the optical microscope and the terahertz system, and solves the key technical obstacle of target pre-screening.

This invention discloses a Monte Carlo simulation method and system for iodine-131 drug treatment of thyroid tumors. The method includes: constructing a three-dimensional geometric model simulating radiation transport in a Monte Carlo simulation platform, including a first region model simulating neck soft tissue, a second region model embedded within this model simulating lesions, and a third region model assessing the impact of the radiation environment; configuring the physical processes simulating iodine-131 decay and particle-matter interactions based on the geometric model; defining a particle emission source based on iodine-131 decay data within the second region model; executing the simulation to obtain first energy deposition data for assessing tumor absorbed dose and second energy deposition data for assessing radiation leakage. Compared with existing technologies, this invention constructs a simulation method integrating neck, lesion, and environmental assessments, simultaneously outputting quantitative data on tumor dose and environmental leakage, achieving an intuitive quantitative assessment of the internal distribution and external impacts of the radiation field during iodine-131 treatment.

The utility model discloses a pair of novel thyroid surgery grasping forceps, which relates to the field of surgical forceps, and comprises a forceps rod, a forceps tail and a forceps head, the forceps head is in a circular ring shape, and the forceps head is bent towards the inner side by a certain radian. The side face and the bottom of the goiter sac can be wrapped, the thyroid tumor can be effectively grabbed, and the problems that a traditional instrument cannot conduct effective clamping and limited traction, and the thyroid tumor is fractured and bleeding is caused due to excessive traction are solved.

The invention provides a thyroid tumor B-ultrasonic diagnosis method and system based on multi-model integration, and the method comprises the steps: segmenting a nodule in a thyroid tumor B-ultrasonic image through a neural network I, and obtaining a preliminary binary nodule segmentation image; segmenting nodules in the thyroid tumor B ultrasonic image by using a neural network II to obtain a fine binary nodule segmentation image; combining the preliminary binarization nodule segmentation image and the fine binarization nodule segmentation image to obtain a maximized ROI nodule image; and respectively inputting the maximized ROI nodule image into a plurality of classification models, and predicting whether the nodule is malignant or not through voting results of the plurality of classification models. And fusing the nodule images segmented by the plurality of neural networks, and predicting whether the nodule is malignant or not through voting structures of the plurality of classification models.

The present application provides an artificial intelligence-based tumor rehabilitation diagnosis and treatment system and method. The system uses a global contour of the tumor edge in the target patient's tumor ultrasound image, and constructs an edge guidance baseline for fine-grained identification of the local tumor edge in the tumor ultrasound image based on the geometric constraint characteristics of the global contour edge. Multiple identification partitions of the local tumor edge are extracted from the tumor ultrasound image based on the projection intersection relationship between the edge guidance baseline and the global contour in the same projection space. The multi-dimensional target features of the tumor edge in the tumor ultrasound image are determined based on the edge wrinkle coefficient of the tumor nodule in each identification partition and the spatial difference relationship between the edge guidance baseline in each identification partition and the contour line of the corresponding global contour. The benign and malignant identification results of the target patient's thyroid tumor are determined based on the multi-dimensional target features. The solution provided by the present application can capture the invasive growth pattern of the tumor from the tumor ultrasound image.