5 results about "Predictive value" patented technology

The invention provides a DenseNet-based CT image classification method and a DenseNet-based CT image classification device for COVID-19 patients, which are used for classifying according to computed tomography images of suspected COVID19 patients to obtain a classification result. The method includes the following steps of: storing medical image information; preprocessing by using a preprocessing method to obtain preprocessed data; obtaining deep information and shallow information from the preprocessed data by using the trained dense connection neural network model, and fusing the deep information and the shallow information to obtain a fused feature vector; mapping the fusion feature vector to a low-dimensional space by using an activation function to obtain a classification probability prediction value; obtaining a CAM activation graph based on the internal parameters of the densely connected neural network model and the computed tomography image; displaying a computed tomography image, a classification probability prediction value, and a CAM activation map to assist a doctor in diagnosis. The method and the device are suitable for an early screening stage of an epidemic situation area, the problem of too high false negative of accounting detection can be solved, and the diagnosis efficiency can be improved.

According to the technical scheme, the Tiny-YOLOv3-based pneumonia image target detection method comprises the following steps that (1) an original XML file is analyzed into TXT, and each row of the TXT file specifically comprises an image absolute path, coordinate values of the upper left corner and the lower right corner of a pneumonia focus and the probability that the focus exists; 2) the training data are trained by using a target detection model Tiny-YOLOv3, and finally a predicted value is obtained; (3) the difference between the position information and the probability information in the obtained predicted value and the position information and the probability information corresponding to the real value in the training set is processed through a loss function, and finally the convolution kernel parameter of the convolution operation in the feature extraction network is adjusted according to the processing result of the loss function; and 4) a to-be-detected pneumonia image is input to the trained target detection model, and the target detection model outputs a detection result which specifically comprises a coordinate value and a probability value. The method improves the model training precision, and enables the prediction result to be more accurate.