DEVICE, SYSTEM AND METHOD FOR DETECTION OF FLUID ACCUMULATION

• US 20150190091A1
• Filed: 08/14/2013
• Published: 07/09/2015
• Est. Priority Date: 08/14/2012
• Status: Active Grant

• Current Assignee: Nanyang Technological University
• Original Assignee: Nanyang Technological University
• Inventors: Ser, Wee, Yang, Feng, Yu, Junfeng
• Granted Patent: US 10,368,804 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: A61B 2560/0475 Special features of memory means, e.g. removable memory cards
• CPC Class Codes: A61B 2562/0204 Acoustic sensors
• CPC Class Codes: A61B 5/4875 Hydration status, fluid retention of the body
• CPC Class Codes: A61B 5/7225 Details of analog processing, e.g. isolation amplifier, gain or sensitivity adjustment, filtering, baseline or drift compensation A61B5/30, A61B5/316 take precedence; transformers for specific applications H01F38/00; amplifiers H03F
• CPC Class Codes: A61B 5/726 using Wavelet transforms
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: A61B 5/7275 Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
• CPC Class Codes: A61B 5/7278 Artificial waveform generation or derivation, e.g. synthesising signals from measured signals A61B5/327 takes precedence
• CPC Class Codes: A61B 7/04 Electric stethoscopes microphones, acoustic transducers therefor H04R
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06F 2218/00 Aspects of pattern recognition specially adapted for signal processing
• CPC Class Codes: G06V 2201/03 Recognition of patterns in medical or anatomical images

Abstract

A method of detecting a level of fluid accumulation in an internal organ of a subject is proposed, as well as a system for carrying out the method. The method comprises: providing at least one classifier trained to distinguish between two or more levels of fluid accumulation; acquiring an audio signal (110) generated by said internal organ; and processing, using at least one processor (134), said audio signal (110) by: performing feature extraction to generate at least one feature vector from the audio signal; and assigning a fluid level from the two or more levels to the audio signal by passing the at least one feature vector to the at least one classifier.

Claims

1. A method of detecting a level of fluid accumulation in an internal organ of a subject, comprising:

providing at least one classifier trained to distinguish between two or more levels of fluid accumulation;

acquiring an audio signal generated by said internal organ; and

processing said audio signal by;

performing feature extraction to generate at least one feature vector from the audio signal;

assigning a fluid level from the two or more levels to the audio signal by passing the at least one feature vector to the at least one classifier.

2. A method according to claim 1, wherein the levels are presence of fluid and absence of fluid.

3. A method according to claim 1, wherein said audio signal is segmented into consecutive time windows, and a feature vector is generated for each time window.

4. A method according to claim 3, wherein said consecutive time windows at least partially overlap.

5. A method according to claim 1, wherein selected components of each feature vector are passed to the at least one classifier.

6. A method according to claim 1, wherein each feature vector is passed to the or each said classifier, to generate a plurality of tentative fluid levels for the audio signal;

and wherein said assigning comprises selecting the most frequent level from amongst the plurality of tentative fluid levels.

7. A method according to claim 1, wherein the feature extraction comprises performing one or more of the following on the audio signal:

determining mel-frequency cepstral coefficients;

determining perceptual linear prediction coefficients;

determining linear prediction coefficients;

or determining coefficients of a wavelet transform.

8. A method according to claim 1, wherein the at least one classifier comprises at least one linear classifier.

9. A method according to claim 1, wherein the at least one classifier comprises at least one non-linear classifier.

10. A method according to claim 1, further comprising training the or each said classifier.

11. A method according to claim 10, wherein said training comprises:

acquiring audio signals from a plurality of subjects having known levels of fluid accumulation;

performing feature extraction on the audio signals to generate a plurality of feature vectors; and

performing feature selection on the plurality of feature vectors to identify one or more components of the feature vectors which are useful for discriminating between the two or more levels.

12. A method according to claim 11, wherein feature selection is performed by identifying the N most important features from the feature vectors.

13. A method according to claim 12, wherein the importance of a feature is calculated according to:

14. A method according to claim 1, wherein said acquiring comprises positioning at least one sensor on the subject or subjects in proximity to said internal organ such that the sensor is acoustically coupled to the internal organ.

15. A system for detecting a level of fluid accumulation in an internal organ of a subject, comprising:

at least one sensor positionable on the subject to measure an audio signal from said internal organ;

a memory configured to store data representing the audio signal; and

at least one processor in communication with the memory and being configured to;

retrieve, from said memory, data representing at least one classifier trained to distinguish between two or more levels of fluid accumulation;

process said audio signal by performing feature extraction to generate at least one feature vector from the audio signal; and

assign a fluid level from the two or more levels to the audio signal by passing the at least one feature vector to the at least one classifier.

16. A system for detecting a level of fluid accumulation in an internal organ of a subject, comprising:

at least one sensor positionable on the subject to measure an audio signal from said internal organ; and

at least one processor configured to

perform feature extraction to generate at least one feature vector from the audio signal; and

assign to the audio signal a fluid level which is one of a set of two or more levels by passing the at least one feature vector to at least one classifier trained to distinguish between the two or more levels of fluid accumulation.

17. (canceled)