A feature extraction method for pulmonary nodules based on an improved deep Boltzmann machine

Abstract

The invention discloses a method for feature extraction and classification of benign and malignant pulmonary nodules based on an improved deep Boltzmann machine, comprising the following steps: step A, segmenting pulmonary nodules from CT images by threshold probability image map method to obtain regions of interest (ROI), and cut into nodule images of the same size; step B, design a supervised deep learning algorithm Pnd-EBM to realize the diagnosis of pulmonary nodules, which includes three major steps: B1 adopts a deep Boltzmann machine based on ( DBM) extracts the features with deep expressive ability of pulmonary nodule ROI; B2, uses sparse cross-entropy penalty factor to improve the cost function to solve the phenomenon of "feature homogeneity" in the training process; B3, uses extreme learning machine (ELM) The extracted features of pulmonary nodules are classified into benign and malignant. The method of the present invention is based on the improved deep Boltzmann machine pulmonary nodule feature extraction method, which is superior to the traditional feature extraction method, avoids the complexity of manual extraction and the difference of feature selection, and can provide reference for clinical diagnosis.

Description

technical field [0001] The invention relates to feature extraction of pulmonary nodules, in particular to a method for extracting features of pulmonary nodules based on an improved deep Boltzmann machine. Background technique [0002] Traditional computer-aided diagnosis (CAD) analysis of pulmonary nodules generally adopts nodule segmentation based on morphology and manual extraction of texture features or shape features of pulmonary nodules. This classification method based on the underlying features can overcome the inertia of the human eye and the insensitivity to grayscale images, and improve the accuracy of nodule recognition and diagnosis by radiologists. To some extent, it depends on experience and luck; and the description of nodules using morphology is inaccurate, such as the definition of nodule margins is vague and subjective. The unsupervised method based on the deep Boltzmann machine can allow the machine to automatically learn the deep structural features of t...

AI Technical Summary

Problems solved by technology

This classification method based on the underlying features can overcome the inertia of the human eye and the insensitivity to grayscale images, and improve the accuracy of nodule recognition and diagnosis by radiologists. Depends on experience and luck to some extent; and the description of nodules using morphology is inaccurate, such as the definition of nodule margins is vague and subjective

Images