Application of deep learning convolutional neural networks for internal tablet defect detection: high accuracy, throughput, and adaptability

January 23, 2020

Xiangyu Ma (1), Nada Kittikunakorn (1), Bradley Sorman (2), Hanmi Xi (3), Antong Chen (3), Mike Marsh (4), Arthur Mongeau (4), Nicolas Piché (4), Robert O. Williams III (1), Daniel Skomski (5)

Journal of Pharmaceutical Sciences,, 109, 4, April 2020:1547-1557. DOI: 10.1016/j.xphs.2020.01.014


Convolutional neural network; Deep learning; Internal tablet defects; Automation; Oral formulation; Imaging data analysis; XRCT


Tablet defects encountered during the manufacturing of oral formulations can result in quality concerns, timeline delays, and elevated financial costs. Internal tablet cracking is not typically measured in routine inspections but can lead to batch failures such as tablet fracturing. X-ray computed tomography (XRCT) has become well-established to analyze internal cracks of oral tablets. However, XRCT normally generates very large quantities of image data (thousands of 2D slices per data set) which require a trained professional to analyze. A user-guided manual analysis is laborious, time-consuming, and subjective, which may result in a poor statistical representation and inconsistent results. In this study, we have developed an analysis program that incorporates deep learning convolutional neural networks to fully automate the XRCT image analysis of oral tablets for internal crack detection. The computer program achieves robust quantification of internal tablet cracks with an average accuracy of 94%. In addition, the deep learning tool is fully automated and achieves a throughput capable of analyzing hundreds of tablets. We have also explored the adaptability of the deep learning analysis program toward different products (e.g., different types of bottles and tablets). Finally, the deep learning tool is effectively implemented into the industrial pharmaceutical workflow.

How Our Software Was Used

Dragonfly was used for data analysis and the training of a deep learning neural network in order to distinguish each individual tablet. A second trained deep learning neural network was used to identify cracks in each tablet for quantitative crack analysis.

Author Affiliation

(1) Molecular Pharmaceutics and Drug Delivery, College of Pharmacy, The University of Texas at Austin, 2409 University Avenue, Austin, TX 78712, USA
(2) ExecuPharm, 610 Freedom Business Center Drive, Suite 200, King of Prussia, Pennsylvania 19406, USA
(3) MRL, Merck & Co., Inc., 770 Sumneytown Pike, West Point, PA 19486, USA
(4) Object Research Systems, 760 St-Paul West, Suite 101 Montreal, Quebec H3C 1M4, Canada
(5) MRL, Merck & Co., Inc., 126 E. Lincoln Ave, Rahway, NJ 07065, USA