Pulmonary nodule benign and malignant prediction method and device

Abstract

The invention provides a pulmonary nodule benign and malignant prediction method and device, and the method comprises the steps: obtaining a chest flat-scanning thin-layer CT image, carrying out region-of-interest delineation of pulmonary nodules in the CT image layer by layer to acquire the clinical information and pathological information of a patient; extracting an image omics feature of the pulmonary nodule in the region-of-interest based on a PyRadio toolkit; screening the image omics features by using a plurality of feature selection algorithms; training a deep convolutional neural network model by using the CT image to acquire deep learning features, forming a multi-dimensional clinical feature vector in combination with clinical information of the patient, and splicing the deep learning features, the clinical features and the imaging omics features to obtain a multi-modal feature vector; and establishing a pulmonary nodule benign and malignant prediction model by using variousclassifier algorithms based on the multi-modal feature vector, and analyzing a prediction result by using the pathological information of the patient to obtain an optimal pulmonary nodule benign and malignant prediction model to perform benign and malignant prediction on the pulmonary nodule.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a method and device for predicting benign and malignant pulmonary nodules. Background technique [0002] Lung cancer is a major cancer that endangers human health. It has the characteristics of high incidence and low survival rate. Early diagnosis of lung cancer is particularly important to improve the survival rate of patients. Pulmonary nodules, as small lesions in the lung, are closely related to the formation of lung tumors. Therefore, the judgment of benign and malignant pulmonary nodules plays a vital role in the early screening of lung cancer. [0003] In recent years, radiomics has been widely used in many fields of cancer research. Radiomics refers to the use of computers to extract a large number of hidden image features from radiological images with high throughput, and to apply a large number of automated data characterization algorithms to convert image data in re...

AI Technical Summary

Problems solved by technology

However, clinically, it is often not sufficient to judge benign and malignant pulmonary nodules only by imaging features, and more predictive factors that indicate the nature of the disease, such as patient clinical information, carcinoembryonic antigen (CEA) and other serum Tumor markers, smoking history, family history of cancer, previous history of malignant tumors, standard uptake value (SUV) of PET-CT, etc.

[0005] Therefore, in the benign and malignant judgment methods of pulmonary nodules relying on CT image features, the method based on radiomics often has the disadvantages of low accuracy and poor prediction effect; while the method based on deep learning has higher prediction accuracy, but the model lack of explainability

In addition, because these methods rely solely on CT image features, it is often difficult to judge benign and malignant nodules with relatively small diameters.

Images