Deep convolutional neural networks: Outperforming established algorithms in the evaluation of industrial optical coherence tomography (OCT) images of pharmaceutical coatings

This paper presents a novel evaluation approach for optical coherence tomography (OCT) image analysis of pharmaceutical solid dosage forms based on deep convolutional neural networks (CNNs). As a proof of concept, CNNs were applied to image data from both, in- and at-line OCT implementations, monito...

Full description

Saved in:
Bibliographic Details
Main Authors: Matthias Wolfgang (Author), Michael Weißensteiner (Author), Phillip Clarke (Author), Wen-Kai Hsiao (Author), Johannes G. Khinast (Author)
Format: Book
Published: Elsevier, 2020-12-01T00:00:00Z.
Subjects:
Online Access:Connect to this object online.
Tags: Add Tag
No Tags, Be the first to tag this record!

MARC

LEADER 00000 am a22000003u 4500
001 doaj_da47587d5baf41c3aebdec41fe3d2ef1
042 |a dc 
100 1 0 |a Matthias Wolfgang  |e author 
700 1 0 |a Michael Weißensteiner  |e author 
700 1 0 |a Phillip Clarke  |e author 
700 1 0 |a Wen-Kai Hsiao  |e author 
700 1 0 |a Johannes G. Khinast  |e author 
245 0 0 |a Deep convolutional neural networks: Outperforming established algorithms in the evaluation of industrial optical coherence tomography (OCT) images of pharmaceutical coatings 
260 |b Elsevier,   |c 2020-12-01T00:00:00Z. 
500 |a 2590-1567 
500 |a 10.1016/j.ijpx.2020.100058 
520 |a This paper presents a novel evaluation approach for optical coherence tomography (OCT) image analysis of pharmaceutical solid dosage forms based on deep convolutional neural networks (CNNs). As a proof of concept, CNNs were applied to image data from both, in- and at-line OCT implementations, monitoring film-coated tablets as well as single- and multi-layered pellets. CNN results were compared against results from established algorithms based on ellipse-fitting, as well as to human-annotated ground truth data. Performance benchmarks used include, efficiency (computation speed), sensitivity (number of detections from a defined test set) and accuracy (deviation from the reference method). The results were validated by comparing the output of several algorithms to data manually annotated by human experts and microscopy images of cross-sectional cuts of the same dosage forms as a reference method. In order to guarantee comparability for all results, the algorithms were executed on the same hardware. Since modern OCT systems must operate under real-time conditions in order to be implemented in-line into manufacturing lines, the necessary steps are discussed on how to achieve this goal without sacrificing the algorithmic performance and how to tailor a deep CNN to cope with the high amount of image noise and alterations in object appearance. The developed deep learning approach outperforms static algorithms currently available in pharma applications with respect to performance benchmarks, and represents the next level in real time evaluation of challenging industrial OCT image data. 
546 |a EN 
690 |a Convolutional neural networks (CNNs) 
690 |a Optical coherence tomography (OCT) 
690 |a Image segmentation 
690 |a Coating layer thickness 
690 |a Single- and multi-layered coatings 
690 |a Pharmacy and materia medica 
690 |a RS1-441 
655 7 |a article  |2 local 
786 0 |n International Journal of Pharmaceutics: X, Vol 2, Iss , Pp 100058- (2020) 
787 0 |n http://www.sciencedirect.com/science/article/pii/S2590156720300207 
787 0 |n https://doaj.org/toc/2590-1567 
856 4 1 |u https://doaj.org/article/da47587d5baf41c3aebdec41fe3d2ef1  |z Connect to this object online.