Intelligent lung disease diagnosis system based on voice and breath sound analysis

By using hierarchical excitation control based on speech and breath sound analysis, the location of lung lesions can be accurately located, solving the problem that existing technologies cannot provide the spatial location of lung abnormalities, and enabling precise diagnosis and treatment guidance for lung diseases.

CN122398262APending Publication Date: 2026-07-17HEFEI NO 2 PEOPLES HOSPITAL
2 Cites 0 Cited by

Patent Information

Application Number
CN202610526996.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-04-21
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

Existing lung sound diagnostic systems cannot provide specific spatial location information of lung abnormalities, and therefore cannot provide location guidance for targeted therapy or interventional surgery.

Method used

A lung disease intelligent diagnostic system based on speech and breath sound analysis is adopted. The system acquires speech excitation signals and lung sound response signals through a signal acquisition module, and performs three-level progressive excitation control in combination with a hierarchical excitation control module, including wideband pulse excitation, frequency sweep excitation and narrowband tuning excitation, to accurately locate the lesion.

Benefits of technology

It enables precise localization of lung lesions and intelligent identification of disease types, providing spatial coordinate information and type judgment of lesions to support precision clinical treatment.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a lung disease intelligent diagnosis system based on voice and breath sound analysis, and relates to the technical field of medical diagnosis. The system obtains a voice excitation signal sent by a subject according to a preset text, collects a lung sound stress signal at a chest wall grid position, and realizes focus positioning through three-layer progressive excitation control: in the first layer, broadband pulse excitation is adopted, the standardized deviation of lung sound stress energy of each anatomical partition is calculated, and candidate abnormal partitions are screened; the second layer adaptively determines a frequency sweep range according to a standardized energy deviation direction, calculates a frequency response ratio by adopting frequency sweep excitation and identifies an abnormal frequency band; the third layer determines a focusing frequency band according to the abnormal frequency band, adopts narrowband tuning excitation to calculate a lung sound energy gradient module value and perform region growth, and after a focus region is formed, calculates a weighted centroid as a focus position; the problem that an existing lung sound diagnosis system can only judge whether abnormity exists or not and cannot locate the focus position is solved, and spatial position guidance is provided for precise treatment of lung diseases.
Need to check novelty before this filing date? Find Prior Art