Pulmonary nodule detection device and method based on shape template matching and combining classifier

Abstract

A pulmonary nodule detection device and method based on a shape template matching and combining classifier comprises an input unit, a pulmonary parenchyma region processing unit, a ROI (region of interest) extraction unit, a coarse screening unit, a feature extraction unit and a secondary detection unit. The input unit is used for inputting pulmonary CT sectional sequence images in format DICOM; the pulmonary parenchyma region processing unit is used for segmenting pulmonary parenchyma regions from the CT sectional sequence images, repairing the segmented pulmonary parenchyma regions by the boundary encoding algorithm and reconstructing the pulmonary parenchyma regions by the surface rendering algorithm after the three-dimensional observation and repairing; the ROI extraction unit is used for setting a gray level threshold and extracting the ROI according to the repaired pulmonary parenchyma regions; the coarse screening unit is used for performing coarse screening on the ROI by the pulmonary nodule morphological feature design template matching algorithm and acquiring selective pulmonary nodule regions; the feature extraction unit is used for extracting various feature parameters as sample sets for the post detection according to selective nodule gray levels and morphological features; the secondary detection unit is used for performing secondary detection on the selective nodule regions through a vector machine classifier and acquiring the final detection result.

Description

technical field [0001] The invention belongs to the field of medical image processing, and relates to a pulmonary nodule detection device based on shape template matching combined with a classifier. Accurate detection of pulmonary nodules is the core content of early computer-aided diagnosis (Computer Aided Diagnosis, CAD) of lung cancer based on CT images. Background technique [0002] According to the 2014 global cancer report, as early as 2012, the total number of lung cancer cases in the world was about 1.825 million, accounting for 13% of malignant tumors, and it was the highest incidence of malignant tumors. Among them, China is the country with the largest number of deaths from lung cancer in the world. The increasing incidence of lung cancer is related to factors such as population aging, urban industrialization, rural urbanization, environmental pollution, and unhealthy lifestyles. Early diagnosis of lung cancer plays an important role in the treatment and prognos...

AI Technical Summary

Problems solved by technology

Comparing the two types of pulmonary nodule classification algorithms, it can be found that the sensitivity of the template matching detection method is higher, the overall sensitivity is above 95%, and the highest sensitivity can reach 100% by optimizing the setting of matching parameters, but its false positive is also high ; while the classifier detection method has a strong dependence on the sample size, feature parameters and classifier selection, although the sensitivity is relatively low, it has a better effect in reducing false positives

Images