1. UV imaging for the rapid at-line content determination of different colourless APIs in their tablets with artificial neural networks.
- Author
-
Ficzere, Máté, Alexandra Mészáros, Lilla, Diószegi, Anna, Bánrévi, Zoltán, Farkas, Attila, Lenk, Sándor, László Galata, Dorián, and Kristóf Nagy, Zsombor
- Subjects
- *
IMAGING systems , *ARTIFICIAL neural networks , *VALSARTAN , *TABLETING , *QUALITY control , *COMPUTER vision - Abstract
[Display omitted] • A novel high-resolution and rapid (50 ms) at-line UV imaging system was developed. • Colourless high- and non-fluorescent APIs were investigated in white tablets. • UV images correlated with the fluorescent spectra of the APIs. • Artificial neural networks were trained and optimized for API content determination. • The prediction error was 4.41% and 3.98% for amlodipine and valsartan respectively. This paper presents a novel high-resolution and rapid (50 ms) UV imaging system, which was used for at-line, non-destructive API content determination of tablets. For the experiments, amlodipine and valsartan were selected as two colourless APIs with different UV induced fluorescent properties according to the measured solid fluorescent spectra. Images were captured with a LED-based UV illumination (385–395 nm) of tablets containing amlodipine or valsartan and common tableting excipients. Blue or green colour components from the RGB colour space were extracted from the images and used as an input dataset to execute API content prediction with artificial neural networks. The traditional destructive, solution-based transmission UV measurement was applied as reference method. After the optimization of the number of hidden layer neurons it was found that the relative error of the content prediction was 4.41 % and 3.98 % in the case of amlodipine and valsartan containing tablets respectively. The results open the possibility to use the proposed UV imaging-based system as a rapid, in-line tool for 100 % API content screening in order to greatly improve pharmaceutical quality control and process understanding. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF