Lung cancer screening method based on neural network

Abstract

The invention discloses a lung cancer screening method based on a neural network, and the method comprises the steps: data preparation: mainly completing the importing of data from a hospital data system and the calibration of data at the stage; preprocessing of the data, namely preprocessing the data and segmenting a lung region in the stage; constructing and training of a three-dimensional RPN network, namely training the RPN network by using the acquired data and the calibration result; training networks suitable for different resolutions, and constructing a combination strategy; carrying out pulmonary nodule detection on the input three-dimensional CT image by using the trained model, and outputting predicted pulmonary nodule information including a central point three-dimensional coordinate and the diameter of the pulmonary nodule; constructing a neural network based on an attention mechanism according to the three-dimensional coordinates and the diameter of the central point given in the step 5, and judging the property of the pulmonary nodule. According to the method, candidate nodule detection is directly carried out on three-dimensional input, so that candidate detection is more comprehensive and reliable.

Description

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine

Login to view more

AI Technical Summary

Benefits of technology

Introduction: The present inventor describes an algorithm called Multi-Resolved Neural Network (MNN) which helps identify small objects like blood vessels or lungs within 3D images. By combining these object recognition techniques together, MNNeL uses fewer computational steps than previous methods while also improving their accuracy over other image processing algorithms such as threshold adjustment. Additionally, they suggest integrating them into one system where all relevant parts of each segment may be identified simultaneously without any extra effort. Overall, the technology described in the patents allows researchers to efficiently analyze large amounts of data containing important details about pulmonary tissue structures.

Problems solved by technology

Technological Problem addressed in this patents relates to improving diagnostic accuracy when analyzing pulmial tumors through quantifying their characteristic attributes such as shape, texture, density, etc., especially at finer levels like microscopic level (<1 mm). Existing techniques have limitations due to factors including complexity involved in extracting important featural elements, difficulty ensuring effective identification of neoplastic cells during imaging procedures, and lack of consideration about how well the brain works properly without over-interpreting its main purpose.

Images