Processing

Please wait...

Settings

Settings

Goto Application

1. WO2022010997 - NEURAL NETWORK ANALYSIS OF LFA TEST STRIPS

Publication Number WO/2022/010997
Publication Date 13.01.2022
International Application No. PCT/US2021/040665
International Filing Date 07.07.2021
Chapter 2 Demand Filed 06.04.2022
IPC
G16B 20/00 2019.1
GPHYSICS
16INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
BBIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
20ICT specially adapted for functional genomics or proteomics, e.g. genotype-phenotype associations
CPC
G06K 9/6256
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6217Design or setup of recognition systems and techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
6256Obtaining sets of training patterns; Bootstrap methods, e.g. bagging, boosting
G06K 9/6271
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6267Classification techniques
6268relating to the classification paradigm, e.g. parametric or non-parametric approaches
627based on distances between the pattern to be recognised and training or reference patterns
6271based on distances to prototypes
G06T 7/00
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
7Image analysis
G16H 30/40
GPHYSICS
16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
30ICT specially adapted for the handling or processing of medical images
40for processing medical images, e.g. editing
Applicants
  • EXA HEALTH, INC. [US]/[US]
Inventors
  • KUMAR, Mayank
  • MILLER, Kevin J.
  • SCHERF, Steven
  • SATISH, Siddarth
Agents
  • SCHEER, Bradley W.,
  • BLACK, DAVID W., Reg. No. 42,331
  • BEEKMAN, Marvin, Reg. No. 38,377
  • ARORA, Suneel, Reg. No. 42,267
  • BIANCHI, Timothy E., Reg. No. 39,610
  • PERDOK, Monique M., Reg. No. 42,989
  • LANG, Allen R., Reg. No. 58,829
Priority Data
63/049,21308.07.2020US
Publication Language English (en)
Filing Language English (EN)
Designated States
Title
(EN) NEURAL NETWORK ANALYSIS OF LFA TEST STRIPS
(FR) ANALYSE DE RÉSEAU DE NEURONES ARTIFICIELS DE BANDELETTES RÉACTIVES DE LFA
Abstract
(EN) Example methods and systems train an end-to-end neural network machine to analyze images of lateral flow assay test strips by learning non-linear interactions among lighting variations, test strip reflections, bi-directional reflectance distribution functions, angles of imaging, response curves of smartphone cameras, or any suitable combination thereof. Such example methods and systems improve the limit of detection, the limit of quantification, and the coefficient of variation in the precision of quantitative test results, under ambient light settings.
(FR) Des procédés et des systèmes donnés à titre d'exemple entraînent une machine de réseau de neurones artificiels de bout en bout à analyser des images de bandelettes réactives d'immunochromatographie (LFA) par apprentissage d'interactions non linéaires parmi les variations d'éclairage, les réflexions des bandelettes réactives, les fonctions de répartition de réflectance bidirectionnelle, les angles d'imagerie, les courbes de réponse de caméras de téléphones intelligents, ou toute combinaison appropriée de ceux-ci. De tels procédés et systèmes donnés à titre d'exemple améliorent la limite de détection, la limite de quantification et le coefficient de variation de la précision de résultats d'analyse quantitative, dans des conditions de lumière ambiante.
Latest bibliographic data on file with the International Bureau