Packaging Digest is part of the Informa Markets Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them. Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.

Healthcare Packaging

AI Advances Pharmaceutical Packaging Inspection

Photo supplied by Stevanato Group Stevanato Group - Artificial Intelligence_AVI_PR-ftd.jpg
Stevanato Group’s new AI platform brings deep learning to inspection machines and brings machine data to the MS Azure cloud for those who seek to perform advanced analytics.
A new artificial intelligence (AI) and its deep learning solution for pharmaceutical visual inspection promises up to 99.9% accuracy, better detection, and reduced false rejects — plus MS Azure cloud analytics.

Stevanato Group, has launched an artificial intelligence platform for its pharmaceutical inspection systems. Using deep learning models to overcome the traditional trade-off between detection and false reject rates, the company says the solution improves detection rates and offers a “tenfold” reduction in false reject rates for up to 99.9% accuracy, both for particle inspection and cosmetic defects detection.

Raffaele Pace, engineering vice president of operations at Stevanato Group, says the AI-and-cloud enhanced platform can “substantially increase defect detection accuracy even with the most challenging drugs.” In particular, drugs in the form of suspensions or lyophilized cakes frequently challenge available vision tools, causing misinterpretations of supposed defects. Traditional systems can, for instance, misclassify cosmetic defects or air bubbles as particles. Artificial Intelligence mitigates misclassification and reduces costly re-inspection.

The company reports that this new platform includes four key features:

1. Cloud-based: Data remains online and therefore perpetually available. The certified cloud-based platform that stores images and data can work with any cloud-based system and allows operators to manage images, even if they are stored in the server.

2. Security: Compliant with US CFR 21 Part 11 and EU GMP Annex 11, the platform enables data sharing in a completely safe environment. Further, multi-factor authentication and encrypted communication ensure complete access control and data security.

3. Assistance: Continuous support is available for all platform capabilities throughout the process, assisting pharmaceutical companies with a variety of tasks, including a labeling assistant tool to optimize timing for classification and new recipe development. 

4. Monitoring: The platform features a range of statistics and visualizations (heat maps, confusion matrix, and more) for model performance evaluation. Pharma companies can track and monitor all processes through real-time reports.

Stevanato’s cloud-ward data connectivity uses a certified cloud-based platform compliant with US CFR 21 Part 11 and EU GMP Annex 11 that meets data integrity needs and offers advanced monitoring tools, such as heat maps and confusion matrix for model performance evaluation. The platform of choice: the Microsoft’s Azure platform with associated machine learning and AI features.

According to Giacomo Girotto, a project manager with the company, cited benefits in four areas for this technology in his recent presentations, including one at the virtual Pack Expo Connects event last November, titled, “Unlocking the Potential of Artificial Intelligence to Enhance Visual Inspection Performance”:

1. Increased detection rate while reducing false reject rates.
2. Reduced setup time for recipes and parameters or “parameterization.”
3. Reduction/avoidance of costly re-inspection.
4. Data monitoring, trending, and predictive solutions to further reduce defects.

Beyond the standalone machine level, adding the cloud element to the solution can help companies perform analytics top multi-machine and multi-site optimization efforts such as overall equipment effectiveness (OEE) and other key performance indicators (KPIs). The is because the AI application encompasses capture of all data logged by machine controls down to the real-time control level, local databases, and the secure cloud. This data includes product and machine identifications; recipe, batch, and quality data; timestamps; serialization IDs; and all parameters.

Hide comments


  • Allowed HTML tags: <em> <strong> <blockquote> <br> <p>

Plain text

  • No HTML tags allowed.
  • Web page addresses and e-mail addresses turn into links automatically.
  • Lines and paragraphs break automatically.