Diagnosis model constructed based on artificial intelligence fusion multi-modal information and used for various pathology types of benign and malignant pulmonary nodules

Abstract

The invention relates to a diagnosis model constructed based on artificial intelligence fusion multi-modal information and used for various pathology types of benign and malignant pulmonary nodules. The method comprises the steps: constructing a multi-resolution 3D multi-classification deep learning network model; constructing a machine learning multi-classification model; training the constructedmulti-resolution 3D deep learning model by using CT image, and obtaining a weight; training the constructed machine learning multi-classification model by using lung tumor marker information, and obtaining a weight; and fusing the lung CT imaging information and the lung tumor marker information at the tail end of the model by migrating the weights of the deep learning network and the machine learning network model through migration learning. According to the invention, a deep learning network model and a machine learning model are adopted to respectively mine deep features related to pathological type classification in a lung CT image and a lung tumor marker, and the fusion of the CT image and the lung tumor marker multi-modal information is realized by fusing the two network models to rapidly diagnose the specific pathology type of the pulmonary nodule.

Description

technical field [0001] The invention belongs to the field of medical image processing, and in particular relates to constructing diagnostic models of various pathological types of benign and malignant pulmonary nodules based on fusion of lung CT images and tumor marker multimodal information. Background technique [0002] Early detection and treatment of pulmonary nodules in patients with lung diseases is a key measure to reduce lung cancer mortality. The traditional diagnosis of benign and malignant pulmonary nodules is mostly based on the combination of lung CT imaging examination and lung tumor marker examination by clinical medical workers to jointly diagnose benign and malignant pulmonary nodules. This needs to rely on the personal clinical experience of medical workers, increasing their work pressure, and because the doctor's personal experience level is uneven, the traditional diagnosis method is easily affected by the doctor's personal experience level, and the diagn...

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide an artificial intelligence-based diagnostic method for the above-mentioned existing benign and malignant pulmonary nodules with low practical work efficiency, high dependence on personal clinical experience, and inability to classify and diagnose specific pathological types of pulmonary nodules at the same time. Constructing a diagnostic model of benign and malignant pulmonary nodules with multiple pathological types by fusing multimodal information

Images