.png){kind=icon}
Return
Disintegration testing augmented by computer Vision technology
.png){kind=icon}
PRE
AI
DOI：10.1016/j.ijpharm.2022.121668.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Oral solid dosage forms, specifically immediate release tablets, are prevalent in the pharmaceutical industry. Disintegration testing is often the first step of commercialization and large-scale production of these dosage forms. Current disintegration testing in the pharmaceutical industry, according to United States Pharmacopeia (USP) chapter<701>, only gives information about the duration of the tablet disintegration process. This information is subjective, variable, and prone to human error due to manual or physical data collection methods via the human eye or contact disks. To lessen the data integrity risk associated with this process, efforts have been made to automate the analysis of the disintegration process using digital lens and other imaging technologies. This would provide a non-invasive method to quantitatively determine disintegration time through computer algorithms. The main challenges associated with developing such a system involve visualization of tablet pieces through cloudy and turbid liquid. The Computer Vision for Disintegration (CVD) system has been developed to be used along with traditional pharmaceutical disintegration testing devices to monitor tablet pieces and distinguish them from the surrounding liquid. The software written for CVD utilizes data captured by cameras or other lenses then uses mobile SSD and CNN, with an OpenCV and FRCNN machine learning model, to analyze and interpret the data. This technology is capable of consistently identifying tablets with >= 99.6% accuracy. Not only is the data produced by CVD more reliable, but it opens the possibility of a deeper understanding of disintegration rates and mechanisms in addition to duration.
Keywords:
Disintegration
Oral Solid Dosage Forms
Disintegration Test
Machine Learning
Neural Networks
Journal
IF:
5.2
Papers:
2.2W
Citations:
6.7W
Organization
Cited Papers
.png){kind=icon}
ShareSaveA New Apparatus for Real-Time Assessment of the Particle Size Distribution of Disintegrating Tablets
PREAI
ShareSaveShareSaveShareSaveShareSaveShareSaveShareSave
View more