US 11,769,039 B2
System for determining the presence of a substance of interest in a sample
Jerome Troy, Newark, DE (US); John W. Edwards, Frederick, MD (US); Heather Goldman, Westminster, MD (US); David Joiner, Edgewood, MD (US); and William Miller, Boyds, MD (US)
Assigned to Smiths Detection, Inc., Edgewood, MD (US)
Filed by Smiths Detection, Inc., Edgewood, MD (US)
Filed on Jul. 5, 2022, as Appl. No. 17/857,256.
Application 17/857,256 is a continuation of application No. 16/635,633, granted, now 11,379,709, previously published as PCT/US2018/044574, filed on Jul. 31, 2018.
Claims priority of provisional application 62/539,167, filed on Jul. 31, 2017.
Prior Publication US 2023/0004784 A1, Jan. 5, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06N 3/045 (2023.01); G06N 3/08 (2023.01); H01J 49/00 (2006.01); H01J 49/02 (2006.01)
CPC G06N 3/045 (2023.01) [G06N 3/08 (2013.01); H01J 49/0036 (2013.01); H01J 49/025 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A server for analyzing spectrometry data to determine the presence of a substance of interest in a sample, the server comprising:
a data store comprising executable instructions for at least one convolutional neural network (CNN) configured to process images; and
a processor coupled to the data store and configured to execute the instructions to operate the at least one CNN;
wherein the server is configured to:
obtain spectrometry data, wherein the spectrometry data is arranged in at least one two dimensional array;
operate a first one of the convolutional neural networks (CNNs) to process the spectrometry data to obtain a first CNN output;
apply a mask to the spectrometry data to obtain masked data;
operate a second one of the CNNs to process the masked data to obtain a second CNN output; and
determine if the substance of interest is present in the sample based on both the first CNN output and the second CNN output.