Pulmonary nodule auxiliary diagnosis system based on adversarial network and Faster R-CNN

Abstract

A pulmonary nodule auxiliary diagnosis system based on an adversarial network and a Faster R-CNN belongs to the technical field of medical instruments and comprises a data acquisition module used foracquiring CT image data of the lung of a patient, a pulmonary parenchyma segmentation module used for segmenting to obtain complete pulmonary parenchyma, and a pulmonary nodule detection network constructed based on a deep learning model. The pulmonary parenchyma segmentation image is input into the pulmonary nodule detection network for nodule detection and identification; and qualitative and quantitative data of the pulmonary nodules are determined automatically, the qualitative and quantitative data is displayed to a user, and finally an image-text diagnosis report is given to assist a doctor in diagnosis. According to the invention, accurate detection and diagnosis of tiny pulmonary nodules can be carried out, the film reading problem can be more rapidly, accurately and scientificallysolved for doctors, and imaging support is provided for clinical auxiliary decision making of lung cancer.

Description

technical field [0001] The present invention relates to the technical field of medical diagnosis, in particular to a pulmonary nodule assisted diagnosis method and system based on an adversarial network and Faster R-CNN. Background technique [0002] Lung cancer is one of the malignant tumors with the fastest growing morbidity and mortality worldwide, and has seriously endangered human health. In our country, most cases of clinical diagnosis of lung cancer are in the late stage, and the best opportunity for treatment has been missed. Therefore, early screening, early diagnosis and early treatment of high-risk groups are important measures to improve lung cancer survival and reduce lung cancer mortality. [0003] Early lung cancer is mainly manifested as solitary pulmonary nodules with a diameter less than 3 cm. Low-dose computed tomography (LDCT) is the main screening method for early lung cancer. It can detect small lesions in advance and detect and resect malignant pulmon...

AI Technical Summary

Problems solved by technology

Traditional machine learning methods use artificially designed features, and the features of pulmonary nodules are complex. Such features may involve a lot of professional domain knowledge, and it is difficult to adapt to new data and diagnostic scenarios, and there is a high false positive rate.

In addition, the existing part of the auxiliary diagnosis method and CAD system using deep learning is not fully automatic, the processing speed is slow, and it is difficult to obtain the diagnosis results in real time, so there is a lot of room for improvement

Images