The invention relates to a thyroid CT image computer-aided diagnosissystem and method. The problem that currently, many defects exist in the thyroiddisease diagnosis through physical examination, ultrasonic scanning and radioisotope scanning is solved. The system comprises an input module, an image texture characteristic extracting module, a classified diagnosis module and an output module which are sequentially connected. The method includes the steps of conducting outline segmenting and extracting on an image, then conducting texture characteristic analysis on the image to obtain the 28-dimension texture characteristic, and finally substituting the 28-dimension texture characteristic into a diagnosis model to obtain a diagnosis result and a statistics index. The thyroid CT image computer-aided diagnosissystem and method have the advantages that non-invasiveness, rapidness and timeliness are achieved; no chemical reagents or the like are needed, and cost is low; complexity of a lesion thyroid texture characteristic sample set is effectively reduced, and identification accuracy can be further improved; the result is not affected by man-made subjective factors and is prevented from being affected by man-made subjective factors in the pathological examination and other examinations.
The invention relates to an auxiliary diagnostic kit of thyroid diseases, and discloses a tetraiodothyroxide test kit which comprises tetraiodothyroxide testing particles, tetraiodothyroxide resisting antibody marked by biotin and disintegrating agent; wherein triiodothyronine testing particles are luminous particles coated by diiodothyronine, and the disintegrating agent is 8-anilino-1- naphthalenesulfonic acid ammonium salt hydrate. The invention also discloses a use method of a triiodothyronine kit. The kit can be combined with other serum and clinical information for the auxiliary diagnosis of thyroid diseases and the monitoring of the treatment effect of relevant patients.
The invention discloses a thyroid nodule recognition method based on a generative adversarial network. The thyroid nodule recognition method comprises the following steps: screening the data of a patient suffering from a thyroiddisease, building a thyroid nodule database, and carrying out circling marking on thyroid nodules and thyroid parenchyma; semantic segmentation: taking U-net as a condition of a generative network to generate an adversarial network model, and inputting an annotated image to realize semantic segmentation; benign and malignant classification input: after multiple convolution, activation and pooling, using a full connection layer to integrate the extracted features to realize image benign and malignant judgment by the convolutional neural network; after the lesion isinput into the convolutional neural network, automatically classifying the lesion and outputting a benign and malignant judgment result of the lesion by the convolutional neural network; and giving areference diagnosis report of the illness state of the patient according to the training result. The thyroid nodule recognition method based on a generative adversarial network can improve thyroid nodule benign and malignant judgment accuracy of doctors, can reduce the thyroid screening time of ultrasound, can reduce the working intensity of medical staff, and can increase the satisfaction degreeof patients.
This invention provides a human hypothyroid peroxid enzymeantibodymagnetic separationenzyme immune measurement method, whose steps are the following: to add sample to react with immune; to wash and to join two anti-enzyme indicate reagent and to wash again; to add monophosphatase fenolftaleina substrate solvent; to terminate color forming and to read absorbing value. The advantages in this invention are the following: it uses reformed human hypothyroid peroxid enzyme antigen fold immune magnetism micro ball as fixed phase and uses alkalescence phosphate enzyme as mark enzyme. Through the quantitative measurement of peroxid enzyme antigen of the hypothyroid patient and normal serum and other clinic symptom, it can judge whether the patient has got the self-immune hypothyroid illness.
The invention provides a thyrotropin (TSH) chemiluminescent immunoassay quantitative detection kit and a preparation method thereof. The invention has the advantages that the reaction pattern of the double antibody sandwich method is adopted, the chemiluminescent technology combining with the technology of fluorescin isothiocyanate-anti-fluoresceinisothiocyanate is effectively utilized, horse radishperoxidase is adopted to be as the marker enzyme to quantitatively detect the content of TSH in the human serum sample, the detection sensitivity is guaranteed, and the raw materials are greatly saved. The kit of the invention has high sensitivity, good repeatability, short reaction time, good stability and long reagent validity, and can provide the experimental basis timely for the clinical diagnosis and the treatment of thyroid disorders.
The invention provides a chemiluminescent immunoassay kit for thyroidperoxidase autoantibodies and a preparation method thereof. The invention has the advantages that the reaction pattern of the double antigen sandwich method is adopted, the chemiluminescent technology and the biotin-avidin immune amplifying technological principle are effectively utilized, horse radishperoxidase is adopted to be as the marker enzyme, the content of the thyroidperoxidase autoantibodies in human serum samples is quantitatively detected, and the detection sensitivity can be ensured. The kit of the invention has the advantages of high sensitivity, good repeatability, good stability and high detection efficiency, and can provide a timely and reliable experimental basis for the clinical diagnosis and the treatment of thyroid disorders.
Immunological assays for several biological markers for thyroid disorders in a biological sample are performed in a single test with a combination of sandwich-type, sequential competitive, and serological assays by the use of particles classified into groups that are distinguishable by flow cytometry, one group for the assay of each marker. Each group of particles is coated with a different immunological binding member, and coating densities, co-coating materials, and special buffer solutions are used to adjust for differences in the sensitivities and dynamic ranges of each of the markers in the typical sample.
The invention discloses an operation pillow for a thyroiddisease. The operation pillow comprises a bottom plate; a jugalar plate is arranged on the bottom plate; a first airbag is arranged on the jugalar plate; the operation pillow for the thyroiddisease enables a patient to more comfortably lie through the first airbag and a second airbag; as the second airbag is designed into an elliptical column shape, the position of a neck is heightened, so that a doctor is wider in visual field during operation; a first electric telescopic rod is arranged on equipment, and a head of the patient can be moved at any moment through the first electric telescopic rod, so that the patient can be more comfortably operated; a second electric telescopic rod is also arranged on the equipment, and the head of the patient can be clamped through the second electric telescopic rod to prevent the patient from moving back and forth during operation; a table lamp is also arranged on the equipment, and the doctor can see more clearly during operation through the table lamp; the equipment is simple in structure, and the height of the surgical pillow for the thyroiddisease can be freely adjusted; meanwhile, the best visual field during operation can be displayed.
The invention relates to an auxiliary diagnosis reagent kit of thyroid diseases, which discloses a triiodothyronine detection reagent kit. The triiodothyronine detection reagent kit comprises triiodothyronine detection particles, biotin marked anti-triiodothyronine antibodies and dissociation agents, wherein the triiodothyronine detection particles are diiodothyronine covered luminous particles, and the dissociation agents are 8-anilino group-1-ammonium naphthalenesulfenesulfonate. The invention also discloses a use method of the triiodothyronine detection reagent kit. The reagent kit of the invention can be combined with other blood serum and clinic information to be used for auxiliary diagnosis on the thyroid diseases and the monitoring on the relevant patient treatment effect.
The invention provides a thyroiddisease diagnosis method based on an SPECT image. A convolutional neural network with an improved DenseNet network structure is used for image classification. Parameters influencing the weight are added to cross-layer connection in a Dense block, and the weight of the feature map of each layer is dynamically adjusted in training, so that the network has higher flexibility and the classification performance is improved. Implementations show that the method can achieve better performance than other deep learning methods. The method can be widely applied to thyroiddisease diagnosis and other image classification problems.
The present invention is based upon the discovery that mutant alpha subunits and mutant beta subunits each comprising amino acid substitutions relative to the wild type can be produced and assembled to form a mutant TSH heterodimer or TSH analog that possesses higher bioactivity in vitro and longer half lifein vivo. Accordingly, the present invention provides methods for using mutant TSH heterodimers, TSH analogs, fragments, and derivatives thereof for treating or preventing diseases of the thyroid, in particular thyroidcancer. The invention also relates to methods of diagnosis, prognosis and monitoring for thyroid-related functions. Pharmaceutical and diagnostic compositions, methods of using mutant TSH heterodimers and TSH analogs with utility for treatment and prevention of metabolic and reproductive diseases are also provided.
The invention discloses a surgical pillow for thyroid diseases. The surgical pillow comprises a back pillow, a headrest and a fixing base, wherein the upper end of the fixing base is provided with a notch, the inner bottom end of the fixing base is fixedly installed with a lifting mechanism, the lifting mechanism comprises a motor, the motor is fixedly installed on one side of the outer wall of the fixing base by a bolt, a power output end of the motor penetrates the fixing base and is fixedly connected with a threaded screw, the surface of the outer wall of the threaded screw is provided withleft-handed threads and right-handed threads, the left-handed threads are located at one ends of the right-hand threads, and threaded sliding sleeves are installed outside the left-hand threads and the right-hand threads in a slide manner respectively. Through the installed lifting mechanism, the adjustment can be performed according to the actual height of a patient, so that the headrest can reach the best position, and thereby not only the comfort of the patient can be improved, but also a height of the headrest can be adjusted conveniently and quickly to thereby adjust a height of the headand neck to adapt to operations of different operations and examinations.
The invention discloses a thyroidnuclear medicineimage diagnosis method based on deep learning, and belongs to the technical field of information. The problem that thyroidnuclear medicineimage diagnosis is limited to a certain extent and the diagnosis efficiency is low in the prior art is solved. The method comprises the following steps: determining an ROI area by using a three-channel threshold detection method, and cutting pictures; performing scaling, rotation and Gaussiannoise addition processing on the focus image set to form an extended sample data set; establishing a convolutionalneural network for image diagnosis, and training the network by using the training set to obtain a trained novel diagnosis model; performing disease diagnosis on the test set by using the trained diagnosis model to obtain a thyroiddisease diagnosis result of each medical image. According to the method, the trained model has higher robustness, and the popularization possibility of the model in hospitals is enhanced.
The invention discloses a human bodythyroid weight measuring method based on SPECT (Single Photon EmissionComputed Tomography) planar imaging, and mainly solves the problem in an existing thyroid weight measuring method that an error is big and efficiency is low since an area of interest is manually drawn. The method comprises the following implementation steps of: (1) inputting a planar imaging graph of the thyroid; (2) carrying out graying on the planar imaging grahp of the thyroid; (3) carrying out binaryzation on the planar imaging graph of the thyroid; (4) extracting the area of interest; (5) calculating the area of the area of interest; (6) calculating the longest diameters of the left and right half leaves of the area of interest; and (7) calculating the quality of the thyroid. The method has the advantages that the integrity of the SPECT planar imaging graph can be guaranteed, the area of interest is effectively segmented, feature information is extracted and the weight of the thyroid is quickly calculated. The thyroid weight measurement can be efficiently finished under a situation that the accuracy is guaranteed, and the method can be used for estimating a drug dosage according to the weight of the thyroid in clinic thyroid disease treatment.