US 11,696,703 B2
Digital stethoscope for detecting a respiratory abnormality and architectures thereof
Ian Mitra McLane, Baltimore, MD (US)
Assigned to Sonavi Labs, Inc., Baltimore, MD (US)
Filed by Sonavi Labs, Inc., Baltimore, MD (US)
Filed on Jul. 20, 2020, as Appl. No. 16/933,430.
Application 16/933,430 is a continuation of application No. 16/659,371, filed on Oct. 21, 2019, granted, now 10,750,976.
Prior Publication US 2021/0145311 A1, May 20, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. A61B 5/00 (2006.01); A61B 5/08 (2006.01); A61B 7/00 (2006.01); A61B 7/04 (2006.01); A61B 5/0205 (2006.01)
CPC A61B 5/0823 (2013.01) [A61B 5/0205 (2013.01); A61B 5/0816 (2013.01); A61B 5/7264 (2013.01); A61B 5/7275 (2013.01); A61B 7/003 (2013.01); A61B 7/04 (2013.01)] 15 Claims
OG exemplary drawing
 
1. A digital stethoscope for detection of a respiratory abnormality comprising:
a microphone configured to detect an auditory signal;
a field programmable gate array (FPGA), coupled to the microphone, configured to:
receive, from the microphone, the auditory signal,
generate an auditory spectrogram based on the auditory signal,
perform a spatial convolution procedure on the auditory spectrogram to generate one or more convolution values, wherein the one or more convolution values represent a compressed version of a matrix portion of the auditory spectrogram, and wherein the spatial convolution procedure is trained to generate one or more features for detecting the respiratory abnormality,
apply one or more weights to the one or more convolution values, wherein the one or more weights are trained for detection of the respiratory abnormality,
generate a classification value based on applying the one or more weights to the one or more convolution values, wherein the classification value indicates the auditory signal includes the respiratory abnormality, and
transmit the classification value to a display unit for outputting the classification value; and
the display unit, coupled to the FPGA, configured to display the classification value.