6 results about "Azoospermatism" patented technology

This invention provides a biomarker for spermatogenesis disorders and its application, wherein the biomarker is the MNDA molecule. This application characterizes the functional abnormalities or spermatogenesis disorders of Sertoli cells by detecting the expression level of MNDA molecules on cells in testicular tissue sections, and can therefore be used for the clinical diagnosis of non-obstructive azoospermia.

The invention discloses a method for distinguishing obstructive azoospermia and non-obstructive azoospermia based on ultrasonic images and machine learning, and relates to the technical field of image analysis and machine learning, all patients are subjected to bilateral scrotum ultrasonic examination before operation; patients are divided into a training set, a validation set, and a test set according to the use of the dataset. In the training set, image omics features are extracted from the left testis ultrasonic image and the right testis ultrasonic image, and key features related to obstructive azoospermia are screened out; on the basis of the selected radiomics features, five machine learning models are constructed, including a k-nearest neighbor model, a logistic regression model, a multi-layer perceptron model, a random forest model and a support vector machine model; analyzing and evaluating the diagnostic performance and clinical application value of the model in the three groups of data through an ROC curve and a clinical decision curve; and explaining the final machine learning model by using SHAP analysis. The method has important value in distinguishing obstructive azoospermia and non-obstructive azoospermia, wherein the logistic regression model shows better diagnostic performance compared with other four models.

The invention discloses a new application of lenalidomide (CC-5013) in the treatment of male oligospermia and azoospermia caused by hepatitis E virus (HEV) infection or the improvement of sperm quality, and particularly discloses a new application of lenalidomide (CC-5013) in the treatment of male oligospermia and azoospermia caused by hepatitis E virus (HEV) infection. The lenalidomide is proved to have an obvious treatment effect on sperm quality reduction caused by HEV infection through sperm staining, sperm motility detection, testis pathology analysis, quantitative detection of sperm development key genes and other methods by utilizing an HEV infected mouse model. The treatment scheme provided by the invention is safe and effective, good in treatment effect and low in medicine cost, is suitable for rapid treatment of male reproductive injuries such as male azoospermia, oligospermia and poor sperm quality caused by virus infection, and provides medicine support for diagnosis and treatment of male infertility patients caused by HEV infection.

The invention provides a dyszoospermia biomarker and an application thereof. The biomarker is an MNDA molecule. According to the application, the state of dysfunction or dyszoospermia of Sertoli cells is represented by detecting the expression level of MNDA molecules on cells in a testicular tissue slice, so that the application can be used for clinical diagnosis and the like of non-obstructive azoospermia.

The invention provides a stepped azoospermia diagnosis and treatment decision support system based on deep learning, and relates to the technical field of diagnosis and treatment decision systems. Comprising a first stage of clinical decision enhancement type TabTransform and a second stage of multi-task perception type TabTransform. In the first stage, a sperm extraction result is predicted based on clinical data, a sperm extraction success rate is predicted, an operation is recommended when the success rate is higher than a threshold value, and an operation decision is given; otherwise, triggering the second stage, introducing high-dimensional gene data deep analysis, and accurately predicting the disease subtype. According to the system, through a progressive data integration mechanism, intelligent transition from preliminary screening to precise typing is achieved, and the pain point problems that in a traditional diagnosis and treatment system, single-dimensional data prediction is achieved, the diagnosis and treatment process is fragmented, and clinical doctors have no quantitative standards for diagnosis and are too subjective and one-sided are effectively solved. The scientificity and the consistency of operation decisions are kept, and a scientific basis is provided for a subsequent personalized treatment scheme.