(404b) Overall Elegance Assessment for a Solid Oral Dosage Form Using Multivariate Image Analysis and Multivariate Texture Analysis
- Conference: AIChE Annual Meeting
- Year: 2013
- Proceeding: 2013 AIChE Annual Meeting
- Group: Pharmaceutical Discovery, Development and Manufacturing Forum
Wednesday, November 6, 2013 - 8:55am-9:20am
The use of Multivariate Image Analysis (MIA) and Texture Analysis (MTA) has been proposed to analyze the elegance of materials involved in the manufacture of solid oral dosages, including the final product (García-Muñoz, Gierer2010;Garcia-Munoz, Carmody2010). This contribution discusses the application of these tools to support the design of the film coating step for a controlled release matrix tablet to assure the within-tablet color uniformity and prevent the logo erosion in the core. The embossing in the tablet required the application of additional algorithmic solutions, the fast template matching (Lewis1995) (originally applied in the production of the movie “Forrest Gump”) was used to separate the embossed logo from the rest of the tablet. Metrics were developed and correlated back to processing conditions in the film coating process. The obtained model was then used to suggest operational conditions to assure the elegance of the tablet and the lack of erosion in the face of the tablet. Additional details on the maintenance of MIA and MTA systems (not discussed in literature) are addressed, specifically dealing with changes in the lighting conditions. The application of the dynamic time warping algorithm to the 2D score histogram is proposed as a solution to the non-linear bias introduced by these changes.
García-Muñoz, S., Gierer, D. S. (2010). Coating uniformity assessment for colored immediate release tablets using multivariate image analysis.International Journal of Pharmaceutics, 395(1-2),104.
Garcia-Munoz, S., Carmody, A. (2010). Multivariate wavelet texture analysis for pharmaceutical solid product characterization.International Journal of Pharmaceutics, 398(1-2),97.
Lewis, J. (1995). Fast template matching.Vision Interface 95, Canadian Image Processing and Pattern Recognition Society, Quebec City, Canada, May 15-19,120.