A pulmonary nodule detection method and system based on a CT image

Abstract

The invention discloses a pulmonary nodule detection method and system based on a CT image. The detection method specifically comprises the following steps: (1) rapid positioning processing based on aUNet network: obtaining a mask of a suspected pulmonary nodule by using a model based on the UNet network; (2) target detection processing based on a DSSD network: processing an image block corresponding to the pulmonary nodule mask obtained in the step (1) by using a DSSD network-based model to obtain a pulmonary nodule detection result; And (3) false positive screening processing based on 3DCNN: screening the candidate nodules by using a 3DCNN-based model to remove the false positive nodules. Compared with the prior art, the whole process of the method for detecting the pulmonary nodules inthe CT image and the design of all functional modules are improved, ideal detection performance is achieved, that is, the method can be used for detecting various types of pulmonary nodules, and compared with the prior art, manual intervention on a detection result can be effectively reduced.

Description

Technical field [0001] The invention belongs to the technical fields of medical image analysis and computer-aided diagnosis, and more specifically, relates to a method and system for detecting pulmonary nodules based on CT images. Background technique [0002] Lung cancer is one of the most dangerous diseases causing cancer death, accounting for two-thirds of all cancers and with a 5-year survival rate of 18%. Clinical experience shows that if lung cancer can be diagnosed at an early stage, the patient's chance of survival will be greatly improved. Diagnostic methods using lung-based computed tomography (CT) images are an important strategy for early diagnosis of lung cancer and improving patient survival rates. Among diagnostic methods based on medical imaging, accurate detection of pulmonary nodules is an important step in diagnosing early lung cancer. It is of great clinical significance to develop a robust automatic detection system for pulmonary nodules. However, due...

AI Technical Summary

Problems solved by technology

Furthermore, it is also challenging to develop a robust detection system due to the high similarity between pulmonary nodules and their surrounding tissues.

For example, for concurrent nodules, since the gray scale of the nodules and the lung wall is almost the same, it is difficult for us to automatically locate its exact location

Similarly, for small nodules with a diameter of less than 6 mm, it is difficult to distinguish such nodules due to their similar gray scale with the surrounding noise

Images