Auxiliary electronic stethoscope signal discrimination method based on deep learning

Abstract

The invention provides an auxiliary electronic stethoscope signal discrimination method based on deep learning. Based on complex sound signals of cardiac beating, useless sound signals are filtered out by using wavelet transform, and noise filtering processing is performed on the heart sound of the cardiac beating signals. Based on different characteristics of each stage of the cardiac beating period, the heart sound signals are segmented, the corresponding acoustic characteristics are extracted and processed through an artificial neural network algorithm so that whether the heart sound signals are normal can be judged, the doctor can be assisted to judge the disease of the patient, the better denoising effect can be realized, the accuracy is higher and the robustness is better. Compared with the conventional electronic stethoscope, the heart sound signals are processed more finely and the more specific and complete result can be obtained, and the doctor can be assisted to perform diagnosis so that the advantages of the method are further highlighted after further development of the future remote medical diagnosis.

Description

technical field [0001] The invention belongs to the technical field of medical information processing, in particular to a deep learning-based auxiliary electronic stethoscope signal discrimination method. Background technique [0002] Modern medicine begins with the invention of the stethoscope, which is mainly used to collect and amplify sounds from the heart, lungs, arteries, veins and other internal organs. Since the traditional stethoscope was used clinically on March 8, 1817, its shape and sound transmission method have been continuously improved, but its basic structure has not changed much. It is mainly composed of a sound pickup part, a conductive part and a listening part. [0003] The electronic stethoscope uses electronic technology to amplify the sound of the body, which overcomes the shortcoming of the high noise of the acoustic stethoscope. The electronic stethoscope can amplify and process the sound wave electric signal of the sound that needs to be converted...

AI Technical Summary

Problems solved by technology

However, the acquired sound signal needs to be judged by a doctor, which is essentially the same as an ordinary stethoscope. It is completely dependent on the doctor's experience and medical knowledge for diagnosis, and cannot play a very good auxiliary role.

Images