20240020817. DEFECT DETECTION IN LYOPHILIZED DRUG PRODUCTS WITH CONVOLUTIONAL NEURAL NETWORKS simplified abstract (Genentech, Inc.)
DEFECT DETECTION IN LYOPHILIZED DRUG PRODUCTS WITH CONVOLUTIONAL NEURAL NETWORKS
Organization Name
Inventor(s)
Zheng Li of South San Francisco CA (US)
DEFECT DETECTION IN LYOPHILIZED DRUG PRODUCTS WITH CONVOLUTIONAL NEURAL NETWORKS - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240020817 titled 'DEFECT DETECTION IN LYOPHILIZED DRUG PRODUCTS WITH CONVOLUTIONAL NEURAL NETWORKS
Simplified Explanation
The abstract describes a method for analyzing images of pharmaceutical product containers to detect defects.
- The method involves receiving one or more images of a container from different angles.
- Confidence scores are calculated for various defect indications using a machine-learning model.
- A defect indication for the container is determined by comparing the confidence scores with predefined threshold scores.
Potential applications of this technology:
- Quality control in pharmaceutical manufacturing: This method can be used to quickly and accurately identify defects in pharmaceutical product containers, ensuring that only high-quality products are released to the market.
- Inspection in the packaging industry: The method can also be applied to other industries that involve packaging, such as food and beverage, to detect defects in containers and prevent faulty products from reaching consumers.
Problems solved by this technology:
- Manual inspection limitations: Traditional manual inspection methods for detecting defects in containers can be time-consuming, subjective, and prone to human error. This technology automates the process and provides objective results.
- Efficiency and accuracy: By using machine learning and automated image analysis, this method can significantly improve the efficiency and accuracy of defect detection compared to manual inspection.
Benefits of this technology:
- Cost savings: Automating the defect detection process reduces the need for manual labor and can lead to cost savings for pharmaceutical manufacturers and packaging companies.
- Improved product quality: By quickly identifying and removing defective containers from the production line, this technology helps maintain high product quality standards and reduces the risk of faulty products reaching consumers.
- Time savings: The automated analysis of images allows for faster inspection and detection of defects, increasing overall production efficiency.
Original Abstract Submitted
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.
