Device, method and equipment for predicting benign and malignant substances of liver cirrhosis nodules and medium

The invention relates to the technical field of bioinformatics, and discloses a liver cirrhosis nodule benign and malignant substance prediction device, method and equipment and a medium, and the device comprises a data obtaining module which is used for obtaining a first image and clinical information; the image sketching module is used for performing region-of-interest sketching on the first image to obtain a second image; the feature extraction module is used for extracting a first manual feature and a first learning feature from the second image; the feature screening module is used for screening out a second manual feature from the first manual features and screening out a second learning feature from the first learning features; the score output module is used for inputting the second manual feature into the first regression model to output a radiomics score, and inputting the second learning feature into the first regression model to output a deep learning score; and the prediction module is used for i