21 results about "Pathology Examination" patented technology

The invention provides an automatic tumor budding identification method fusing pathological staining migration and YOLO target detection. The method comprises the following steps: training Hamp by using a CUT model; a staining migration model is established from the E image to the immunohistochemical image, and the staining migration model is utilized to carry out Hamp; e, converting the dyed full-width pathological section into a cytokeratin dyed full-width pathological section; and performing tumor budding detection on the generated full-width pathological section dyed by the cytokeratin by using a TB-YOLO model improved on the basis of YOLOv10. According to the method, the CUT is combined for pathological image staining migration, the IHC image generated through TB-YOLO analysis is used for tumor budding detection, meanwhile, accurate translation and detection of positive signals are ensured, richer diagnosis information is provided for pathologists, the diagnosis accuracy is improved, the pathological examination cost of patients is reduced, and the purpose that only Hamp is used for diagnosis is achieved. And E, the tumor budding is accurately detected by the dyed image, so that the comparability of medical images in different dyeing modes and the applicability of a cross-dyeing method are improved.

The invention relates to the technical field of medical instruments, in particular to a uterine cavity tissue cutting biopsy device which comprises an outer tube, an inner tube, an inner tube pushing and rebounding mechanism and a negative pressure collecting mechanism, the inner tube pushing and rebounding mechanism and the negative pressure collecting mechanism are connected with the inner tube, the outer tube is provided with a cutting sampling opening, the inner tube is provided with a cutting head, and the inner tube pushing and rebounding mechanism drives the inner tube to axially move back and forth. The negative pressure sampling device further comprises a rotary rebound mechanism which is nested outside the inner pipe, and the inner pipe pushes the rebound mechanism to drive the inner pipe to axially move back and forth and rotate and rebound at the same time, so that the cutting head is driven to rotate and cut back and forth. According to the uterine cavity tissue cutting biopsy device, an external power source is not needed, heat damage can be thoroughly eliminated, sufficient and effective cutting can be achieved without additional driving force and additional operation during use, the integrity of a cut sample can be kept as far as possible, and the uterine cavity tissue cutting biopsy device has the advantages of being free of heat damage, free of noise, free of vibration, convenient to operate and capable of avoiding inaccurate pathological examination.

The invention relates to the field of image processing, and provides a medical examination film reading control method and device and an image filing and communication system. The method comprises the steps that pathological detection results are added into a queue, and when the remaining radiograph reading completion duration corresponding to any two pathological detection results in the queue is larger than or equal to a first threshold value, the more key pathologies hit by the pathological detection results are, the higher the priority is; and generating a label and sending the label to an image archiving and communication system, determining a film reading sequence corresponding to the object by the system according to the label, displaying the image and the label of the object based on the film reading sequence, and updating the film reading sequences corresponding to other objects. For different objects with sufficient remaining radiograph reading completion time, according to the method, examination of suspected critical pathology objects is put at a higher priority, so that the purpose of accelerating the radiograph reading of critical pathology examination is achieved, the actual time consumption of medical examination of the suspected critical pathology objects is shortened, and the medical examination efficiency is improved. And the occurrence of acute diseases, dangerous diseases and worsening caused by too long film reading time is reduced.

The invention relates to the field of image analysis, and discloses a placenta implantable disease grading diagnosis method based on a multi-modal deep fusion model. The method comprises the following steps: collecting patient information including basic information, ultrasonic images, imaging examination results and pathological examination results, and constructing a data set for training a placenta implantable disease grading diagnosis model according to the patient information; constructing and training a numerical feature encoder and an ultrasonic image encoder by using the data set; and constructing and training a multi-modal deep fusion model by using the data set, the trained numerical feature encoder and the trained ultrasonic image encoder. According to the method, the problem of insufficient accuracy of the single-mode model in the classification diagnosis task of the placenta implantable disease is solved, and the diagnosis performance is effectively improved.

The invention relates to the technical field of medical biopsy instruments, in particular to an endoscopic biopsy device for respiration and critical diseases, which comprises a catheter, a cylindrical sealing piston head is slidably mounted in the catheter, an up-down through vent hole is formed in the sealing piston head, and one end, positioned in vitro, of the catheter is connected with negative pressure; a branch pipe with the tail end sealed is further arranged at the end extending out of the body, a stay wire hole is formed in the center of the sealing piston head, and a stay wire is slidably installed in the stay wire hole. One end of the pull wire extends out of the branch pipe and is provided with a pull ring; one end, far away from the pull ring, of the pull wire is provided with an umbrella-shaped cutting head and a limiting ring; the bottom of the cutting head is provided with a circle of annular cutting edge, the annular cutting edge is located above the sealing piston head, the limiting ring is located below the cutting head, and the distance between the annular cutting edge and the cutting head is larger than the height of the sealing piston head. According to the scheme of combining negative pressure adsorption and mechanical cutting, the tissue sample size larger than that of traditional biopsy forceps can be obtained, and the requirements of pathological examination are effectively met.

This invention relates to the field of medical data processing technology, and in particular to a method and apparatus for predicting the survival of cancer patients. The method includes: acquiring molecular pathological examination results, histopathological examination results, and radiological imaging results of a target cancer patient; extracting features from the molecular pathological examination results, histopathological examination results, and radiological imaging results to obtain gene features, pathological image features, and MRI image features; fusing and stitching the gene features, pathological image features, and MRI image features to obtain a final fused feature; and predicting the actual survival range of the target cancer patient based on the final fused feature. This solves the problems of existing cancer survival prediction methods that often rely on single-modal information such as pathological images or radiological images, resulting in limited predictive performance and generalization ability, and making it difficult to provide sufficient and comprehensive reference for doctors and patients.

This invention provides a multimodal microscopic imaging integrated detection system, relating to the field of microscopic optical detection technology. It includes a bright-field microscopic imaging module sharing a tissue section sampling optical path assembly, and at least two of three modules: a polarized light microscopic imaging module, a fluorescence microscopic imaging module, and a micro-Raman spectroscopy detection module. The bright-field, polarized light, and fluorescence microscopic imaging modules share an imaging optical path assembly. The micro-Raman spectroscopy detection module includes a Raman spectrometer and a laser for irradiating tissue sections to excite Raman scattering light. The beneficial effect of this invention is that, based on bright-field microscopic imaging, it introduces multiple characteristic imaging or spectroscopic technologies such as polarized light imaging, fluorescence imaging, and Raman spectroscopy. Through multimodal information complementarity, it enriches the differential information between cancerous tissues and normal, inflammatory lesions, etc., significantly improving the speed and efficiency of pathological examination and enabling rapid and accurate intraoperative cancer diagnosis.

Embodiments of the present application relate to the technical field of examination result analysis, and provide a cervical lesion related examination result analysis method and apparatus, a device, and a medium. The method comprises: receiving a case report picture uploaded by a current user terminal, and reading case data in the case report picture; acquiring prediction result information corresponding to the case data on the basis of a current prediction model, and selecting optimal expert information on the basis of the prediction result information; pushing the case data and the prediction result information to an expert terminal corresponding to the optimal expert information, and receiving a final clinical analysis result fed back by the expert terminal; and sending the final clinical analysis result to the current user terminal corresponding to a current user. The present application sends a final clinical analysis result to a current user terminal, so that a current user can conveniently check the final clinical analysis result, and choose whether to perform further pathological examination on the basis of the final clinical analysis result, so that the rationality of medical resource use is improved.

This invention relates to a visual medical probe, comprising an outer probe tube, an injection tube, an examination lens, an image guide bundle, a light-transmitting lens, and a light guide beam. The light-transmitting lens is disposed at the front end of the outer probe tube, the examination lens is disposed on the light-transmitting lens, the light guide beam passes through the outer probe tube and connects to the light-transmitting lens, and the image guide bundle passes through the outer probe tube and connects to the examination lens. An injection tube is located inside the outer probe tube, with its front end inserted into the light-transmitting lens, the front end of the injection tube being flush with the front surface of the light-transmitting lens. The beneficial effects of this invention are: the use of a small-diameter, moderately flexible outer probe tube with an examination lens at the front end is particularly suitable for fistula exploration; the injection tube allows for drug irrigation within the fistula and cleaning of the examination lens; the splashing tongue at the probe tip significantly improves the effectiveness of fistula irrigation and lens cleaning; the injection tube also allows for biopsy of the fistula and internal opening tissue for pathological examination; and when used in conjunction with a medical laser or high-frequency electrosurgical unit, it enables precise minimally invasive treatment of anal fistulas. This invention significantly improves the diagnostic and treatment methods for anal fistulas and other fistula tracts.

The invention relates to the field of pathological examination and diagnosis equipment, in particular to a pathological image synchronous reading system. The system comprises a scanner, a positioning camera and terminal equipment, according to the system, a scanner is used for identifying which case section a specific pathological section to be reviewed is so as to call a corresponding WSI, a positioning camera is used for collecting an image of an objective lens containing the pathological section and a microscope, and projection coordinates of the objective lens on the pathological section are determined according to the image; the position of the pathological section on the objective table is adjusted after the coordinate of the visual field center of the WSI on the WSI is changed, the visual field center of the WSI is adjusted after the position of the pathological section on the objective table is changed, the center of the visual field of the microscope is automatically made to be consistent with the center of the visual field of digital section browsing, and digital-microscope real-time combined reading is achieved. And the defect of pure digital film reading is effectively overcome.

The application provides a pathology teaching-oriented adaptive test paper generation method, device and equipment, and relates to the technical field of educational information processing, and comprises the following steps: determining evaluation index values corresponding to pathology teaching test questions contained in a pathology teaching question bank; performing data integrity inspection on the evaluation index values; in the case of passing the data integrity inspection, establishing examinee characteristic groupings, and associating the pathology teaching test questions to their matching examinee characteristic groupings; performing quality evaluation on the evaluation index values corresponding to the pathology teaching test questions associated to the examinee characteristic groupings, and then determining the evaluation results of the pathology teaching test questions in their associated examinee characteristic groupings; in the case of receiving a test paper grouping request uploaded by a user, generating a pathology teaching test paper corresponding to the test paper grouping request based on the pathology teaching test questions and their evaluation results. The application can significantly improve the efficiency of case screening, grading and test paper grouping processes, so as to meet the increasingly enhanced pathology examination requirements.

The invention provides a construction method of a rat xerophthalmia model, which utilizes scopolamine hydrobromide and 1% atropine sulfate ophthalmic gel to jointly induce xerophthalmia so as to induce comprehensive symptoms of rat xerophthalmia. After scopolamine hydrobromide is subcutaneously injected into a rat and atropine ophthalmic gel is dropwise added to eyes of the rat, difference appears in tear secretion, tear film rupture time and cornea staining detection from the second week, the symptom stability can last for more than one month, and obvious difference also exists in pathological examination of an anatomical end point and a TUNEL test. Hypodermic injection of scopolamine hydrobromide can inhibit parsympathetic nerve excitation so as to inhibit gland secretion, so that lacrimal secretion is insufficient; and meanwhile, the atropine ophthalmic gel can inhibit parasympathetic nerves, so that the threshold value of tear secretion is increased, and the tear secretion is reduced. The xerophthalmia model has the advantages that the modeling time is short, the modeling process is not limited by environment temperature and humidity, and model animals after modeling have small individual differences and high symptom specificity.

The invention discloses a to-be-checked fever pathogenesis classification method based on two-stage feature selection, and relates to the technical field of computer processing, and the method comprises the following steps: S01, obtaining a clinical data set of a to-be-checked fever patient, and carrying out the preprocessing of the data set, so as to obtain a standard data set, wherein the clinical data set comprises medical indexes of clinical symptoms, epidemiological history, past medical history, physical sign physical examination, assay examination, images and pathological examination and at least 16 disease cause diagnosis results corresponding to the medical indexes; the pathogenesis diagnosis result comprises at least 16 to-be-checked fever pathogenesis. From the perspective of feature selection, the method mainly solves the two problems that a large number of irrelevant features and redundant features exist in a high-dimensional small sample data set to affect classification precision and model overfitting, improves the accuracy of a machine learning model on a fever to-be-checked data set, can assist a doctor in diagnosing the condition of a patient, and reduces the workload.

The utility model provides a tissue sample quick sampling tool for animal pathological examination, which comprises a roll shaft, sampling ports are uniformly arranged around the roll shaft, the lower end of each sampling port is provided with an adjusting structure, the adjusting structure comprises a rotating rod fixedly connected with the roll shaft, the other end of the rotating rod is movably connected with a push rod, and the push rod is connected with the roll shaft. The outer part of the pushing rod is sleeved with an outer shell corresponding to the rotating rod, the rotating rod is pushed forward by arranging the pushing rod, the rotating rod is driven by the outer shell to rotate, then the rotating rod drives the roll shaft to rotate, and in the rotating process of the roll shaft, the sampling ports around the roll shaft are driven to do circular motion, so that sampling is realized; according to the sampling device, in the sampling process, the animal feels comfortable similar to combing, overexertion of the animal is avoided, along with rotation advancing of the roller shaft, part of skin debris samples can be taken down through the sampling port, and part of hair samples can be taken down in the rotation process.

The utility model relates to the technical field of specimen cutting, in particular to a pathological sampling device for a cervical conization specimen, which comprises a base, a center rod, a sliding frame and a plurality of connecting boxes, the bottom end of the center rod is fixedly connected to the top surface of the base, a plurality of strip-shaped grooves are formed in the side surface of the center rod, and the sliding frame is arranged at the top of the center rod. A plurality of connecting boxes are fixedly connected to the inner side face of the sliding frame, and sliding bases are slidably connected to the inner side faces of the connecting boxes. According to the tissue specimen cutting device, the sliding seat is connected to the inner side face of the connecting box in the sliding mode, the cutting knife can move downwards to cut tissue specimens, in the cutting process, the sliding seat can slide in the connecting box, the cutting knife can cut the tissue specimens in a sliding mode, the downward extrusion force of the cutting knife on the tissue specimens is small, large deformation of the tissue specimens is avoided, and the cutting efficiency is improved. Moreover, the tissue specimen can be conveniently, uniformly and straightly cut, and the subsequent pathological examination of the tissue specimen is facilitated.

The utility model relates to the technical field of pathological examination, and discloses an HE staining slide oven which comprises an oven body, a stand column is fixedly arranged in the oven body, electric heating wires are fixedly arranged on the surface of the stand column and the inner wall of the oven body, a timing controller for controlling the electric heating wires in a timing mode is fixedly installed on the top of the oven body, and the timing controller is connected with the stand column. A rotating disc is rotationally arranged in the middle of the top end of the box body, a driving assembly for driving the rotating disc to rotate is arranged at the top end of the box body, and a plurality of threaded sleeves are fixedly arranged on the surface of the rotating disc; by arranging the multiple limiting assemblies, the HE dyeing slides can be loaded in batches conveniently, the slides can be separated and protected, the limiting assemblies carrying the slides can be rapidly placed in the box body conveniently through the plungers and the threaded sleeves, the baking time of the electric heating wires on the slides can be controlled through the timing controller, manual timing is not needed, and the time-saving and labor-saving effects are achieved. And the phenomenon that the slices fall off due to too short baking time is avoided.

The invention discloses a vulva intraepithelial neoplasia prediction method based on infrared thermal imaging, and relates to the technical field of computer-aided diagnosis systems and medical imaging. The method is realized based on a prediction system, and the system comprises an image collection module which is used for collecting an infrared thermal imaging image; the image preprocessing module is used for preprocessing the acquired infrared thermal imaging image, including noise removal and contrast enhancement; and the image segmentation module is used for selecting three uniformly distributed ROIs (Region of Interest) with 3 * 3 pixels in each lesion area, and averaging the temperatures in the three ROIs to obtain a lesion temperature value. The infrared thermal imaging technology is adopted, direct contact with the skin of a patient is not needed, and trauma of traditional pathological examination is avoided; through image segmentation, feature value extraction, principal component analysis and training and verification of multiple machine learning algorithms, high-accuracy classification of VIN, vulva epithelial non-neoplastic lesions and normal skin is realized, and the accuracy and reliability of diagnosis are improved.

This invention provides a combination of serum biomarkers for the diagnosis of gastric cancer and their applications. This invention is the first to discover that CHI3L1, FCGBP, TFF2, and VSIG2 are significantly elevated in the serum of gastric cancer patients. ROC curve analysis verified that the combination of these four proteins as serum biomarkers can effectively distinguish between gastric cancer patients and healthy controls, and that combined use can better differentiate between early and late-stage gastric cancer patients, demonstrating superior diagnostic value for gastric cancer. Compared with traditional methods for gastric cancer diagnosis, the serum biomarker combination established in this invention is non-invasive, improving the accuracy of gastric cancer diagnosis. It can be used as a health screening test and provides an efficient and non-invasive detection method for gastric cancer patients who cannot undergo pathological examination.

The present application relates to the field of medical image analysis, and particularly relates to a placenta implantation disease grading method and system based on multi-modal data, the method steps comprising: S1: collecting clinical information, medical image information and pathological examination results of a patient to form sample data; S2: constructing a data set used by a training model based on the sample data, and training a placenta implantation disease grading diagnosis model; S3: using the trained placenta implantation disease grading diagnosis model to perform grading diagnosis on the patient. The present application solves the problem of coarse grading granularity and insufficient accuracy of placenta implantation disease in the prior art by fusing medical image features and clinical feature data to construct a deep learning model, and realizes accurate grading of placenta adhesion, implantation and penetration.

The application provides a differential model based on CT enteroclysis imageomics and clinical features, and relates to the technical field of medical treatment.The differential model comprises the data of clinical information, laboratory examination, image examination, enteroscopy and pathological examination, extracts the imageomics of intestinal wall and mesenteric fat characteristics based on CT enteroclysis, and constructs a differential diagnosis model of Crohn's disease and intestinal tuberculosis through machine learning.The differential diagnosis model of Crohn's disease and intestinal tuberculosis is constructed by integrating the clinical features and the imageomics parameters of CT enteroclysis, and is significantly better than a single model.The imageomics characteristics reveal the essential differences of the two diseases in the texture of intestinal wall and mesenteric fat.The nomogram constructed by the application provides a convenient visual tool for the clinic, and is particularly suitable for precise diagnosis in tuberculosis high-incidence areas.

The invention discloses application of HER-2 combined with a three-level lymph structure in diagnosis and treatment of mixed hepatocyte-bile duct cell carcinoma. A prognosis evaluation system and a treatment decision mode constructed on the basis of HER-2 detection are beneficial to establishment of a standard cHCC-CCA prognosis system, and the HER-2 detection can adopt a clinical conventional immunohistochemical method and is directly in butt joint with an existing pathological examination process, so that the clinical transformation threshold is effectively reduced, and the clinical treatment efficiency is improved. The clinical practicability and operability are obvious. Meanwhile, the expression level of HER-2 can reflect whether the patient can directly benefit from adjuvant chemotherapy, so that treatment schemes can be quickly generated for different patients after pathological examination. Moreover, the invention also discloses the association between the HER-2 and the tumor immune microenvironment, and provides a new thought for developing HER-2 and TLS combined prognosis products and targeted drug combined immunotherapy strategies.