US 11,686,703 B2
Automated analysis of analytical gels and blots
Nilesh Saratkar, Secaucus, NJ (US); Stanley Naides, Secaucus, NJ (US); and Michelle A. Cleveland, Secaucus, NJ (US)
Assigned to Quest Diagnostics Investments LLC, Secaucus, NJ (US)
Appl. No. 16/956,208
Filed by Quest Diagnostics Investments LLC, Secaucus, NJ (US)
PCT Filed Dec. 21, 2018, PCT No. PCT/US2018/067181
§ 371(c)(1), (2) Date Jun. 19, 2020,
PCT Pub. No. WO2019/126693, PCT Pub. Date Jun. 27, 2019.
Claims priority of provisional application 62/610,078, filed on Dec. 22, 2017.
Prior Publication US 2020/0319140 A1, Oct. 8, 2020
Int. Cl. G01N 27/447 (2006.01); G06V 20/69 (2022.01)
CPC G01N 27/44721 (2013.01) [G06V 20/695 (2022.01); G06V 20/698 (2022.01)] 16 Claims
OG exemplary drawing
 
1. A system to process data from an analytical gel or blot, comprising:
(i) a lane detector, executed by one or more processors, to identify a plurality of lanes in a first digital image, wherein the first digital image comprises an analytical gel or blot;
(ii) a feature generator to determine a lane intensity vector for each of the plurality of lanes in the first digital image, wherein the lane intensity vector passes through the length of the plurality of lanes;
(iii) a classifier to:
determine a correlation score for each of the plurality of lanes in the first digital image, wherein the correlation score is based on the lane intensity vector for a respective lane of the plurality of lanes and a reference lane intensity vector; and
associate a classification to the each of the plurality of lanes in the first digital image based on the correlation score for the respective lane in the first digital image, wherein the classification is a phenotype; and
(iv) an image preprocessor to convert the digital image into a grayscale image.