Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020081668 - DEFECT DETECTION IN LYOPHILIZED DRUG PRODUCTS WITH CONVOLUTIONAL NEURAL NETWORKS

Publication Number WO/2020/081668
Publication Date 23.04.2020
International Application No. PCT/US2019/056511
International Filing Date 16.10.2019
IPC
G16H 20/10 2018.01
GPHYSICS
16INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
20ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
10relating to drugs or medications, e.g. for ensuring correct administration to patients
G06N 20/00 2019.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
G06Q 10/10 2012.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
QDATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
10Administration; Management
10Office automation, e.g. computer aided management of electronic mail or groupware; Time management, e.g. calendars, reminders, meetings or time accounting
CPC
G06F 16/53
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
16Information retrieval; Database structures therefor; File system structures therefor
50of still image data
53Querying
G06F 17/15
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
17Digital computing or data processing equipment or methods, specially adapted for specific functions
10Complex mathematical operations
15Correlation function computation ; including computation of convolution operations
G06N 20/00
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
G06N 3/04
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
G06T 2207/20081
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
2207Indexing scheme for image analysis or image enhancement
20Special algorithmic details
20081Training; Learning
G06T 2207/20084
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
2207Indexing scheme for image analysis or image enhancement
20Special algorithmic details
20084Artificial neural networks [ANN]
Applicants
  • GENENTECH, INC. [US]/[US]
Inventors
  • LI, Zheng
  • TSAY, Calvin
Agents
  • CHOI, Hogene, L.
Priority Data
16/654,20016.10.2019US
62/748,30419.10.2018US
62/852,23723.05.2019US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) DEFECT DETECTION IN LYOPHILIZED DRUG PRODUCTS WITH CONVOLUTIONAL NEURAL NETWORKS
(FR) DÉTECTION DE DÉFAUTS DANS DES PRODUITS MÉDICAMENTEUX LYOPHILISÉS AVEC DES RÉSEAUX NEURONAUX CONVOLUTIFS
Abstract
(EN)
In one embodiment, a method includes receiving one or more querying images associated with a container of a pharmaceutical product, each of the one or more querying images being based on a particular angle of the container of the pharmaceutical product, calculating one or more confidence scores associated with one or more defect indications, respectively for the container of the pharmaceutical product, by processing the one or more querying images using a target machine-learning model, and determining a defect indication for the container of the pharmaceutical product from the one or more defect indications based on a comparison between the one or more confidence scores and one or more predefined threshold scores, respectively.
(FR)
Selon un mode de réalisation, un procédé consiste à recevoir une ou plusieurs images d'interrogation associées à un récipient d'un produit pharmaceutique, chacune des une ou plusieurs images d'interrogation étant basée sur un angle particulier du récipient du produit pharmaceutique, à calculer un ou plusieurs scores de confiance associés à une ou plusieurs indications de défaut, respectivement pour le récipient du produit pharmaceutique, par traitement de l'image ou des images d'interrogation à l'aide d'un modèle d'apprentissage machine cible, et à déterminer une indication de défaut pour le récipient du produit pharmaceutique à partir de l'indication ou des indications de défaut sur la base d'une comparaison entre le ou les scores de confiance et un ou plusieurs scores de seuil prédéfinis, respectivement.
Also published as
Latest bibliographic data on file with the International Bureau