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...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2020-12-01
|
| Series: | International Journal of Pharmaceutics: X |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590156720300207 |
| _version_ | 1818952739125723136 |
|---|---|
| author | Matthias Wolfgang Michael Weißensteiner Phillip Clarke Wen-Kai Hsiao Johannes G. Khinast |
| author_facet | Matthias Wolfgang Michael Weißensteiner Phillip Clarke Wen-Kai Hsiao Johannes G. Khinast |
| author_sort | Matthias Wolfgang |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-12-20T09:55:10Z |
| format | Article |
| id | doaj.art-da47587d5baf41c3aebdec41fe3d2ef1 |
| institution | Directory Open Access Journal |
| issn | 2590-1567 |
| language | English |
| last_indexed | 2024-12-20T09:55:10Z |
| publishDate | 2020-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Pharmaceutics: X |
| spelling | doaj.art-da47587d5baf41c3aebdec41fe3d2ef12022-12-21T19:44:29ZengElsevierInternational Journal of Pharmaceutics: X2590-15672020-12-012100058Deep convolutional neural networks: Outperforming established algorithms in the evaluation of industrial optical coherence tomography (OCT) images of pharmaceutical coatingsMatthias Wolfgang0Michael Weißensteiner1Phillip Clarke2Wen-Kai Hsiao3Johannes G. Khinast4Research Center Pharmaceutical Engineering GmbH, Graz, AustriaResearch Center Pharmaceutical Engineering GmbH, Graz, AustriaResearch Center Pharmaceutical Engineering GmbH, Graz, AustriaResearch Center Pharmaceutical Engineering GmbH, Graz, AustriaResearch Center Pharmaceutical Engineering GmbH, Graz, Austria; Institute for Process and Particle Engineering, Graz University of Technology, Graz, Austria; Corresponding author at: Institute for Process and Particle Engineering, Graz University of Technology, Graz, Austria.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.http://www.sciencedirect.com/science/article/pii/S2590156720300207Convolutional neural networks (CNNs)Optical coherence tomography (OCT)Image segmentationCoating layer thicknessSingle- and multi-layered coatings |
| spellingShingle | Matthias Wolfgang Michael Weißensteiner Phillip Clarke Wen-Kai Hsiao Johannes G. Khinast Deep convolutional neural networks: Outperforming established algorithms in the evaluation of industrial optical coherence tomography (OCT) images of pharmaceutical coatings International Journal of Pharmaceutics: X Convolutional neural networks (CNNs) Optical coherence tomography (OCT) Image segmentation Coating layer thickness Single- and multi-layered coatings |
| title | Deep convolutional neural networks: Outperforming established algorithms in the evaluation of industrial optical coherence tomography (OCT) images of pharmaceutical coatings |
| title_full | Deep convolutional neural networks: Outperforming established algorithms in the evaluation of industrial optical coherence tomography (OCT) images of pharmaceutical coatings |
| title_fullStr | Deep convolutional neural networks: Outperforming established algorithms in the evaluation of industrial optical coherence tomography (OCT) images of pharmaceutical coatings |
| title_full_unstemmed | Deep convolutional neural networks: Outperforming established algorithms in the evaluation of industrial optical coherence tomography (OCT) images of pharmaceutical coatings |
| title_short | Deep convolutional neural networks: Outperforming established algorithms in the evaluation of industrial optical coherence tomography (OCT) images of pharmaceutical coatings |
| title_sort | deep convolutional neural networks outperforming established algorithms in the evaluation of industrial optical coherence tomography oct images of pharmaceutical coatings |
| topic | Convolutional neural networks (CNNs) Optical coherence tomography (OCT) Image segmentation Coating layer thickness Single- and multi-layered coatings |
| url | http://www.sciencedirect.com/science/article/pii/S2590156720300207 |
| work_keys_str_mv | AT matthiaswolfgang deepconvolutionalneuralnetworksoutperformingestablishedalgorithmsintheevaluationofindustrialopticalcoherencetomographyoctimagesofpharmaceuticalcoatings AT michaelweißensteiner deepconvolutionalneuralnetworksoutperformingestablishedalgorithmsintheevaluationofindustrialopticalcoherencetomographyoctimagesofpharmaceuticalcoatings AT phillipclarke deepconvolutionalneuralnetworksoutperformingestablishedalgorithmsintheevaluationofindustrialopticalcoherencetomographyoctimagesofpharmaceuticalcoatings AT wenkaihsiao deepconvolutionalneuralnetworksoutperformingestablishedalgorithmsintheevaluationofindustrialopticalcoherencetomographyoctimagesofpharmaceuticalcoatings AT johannesgkhinast deepconvolutionalneuralnetworksoutperformingestablishedalgorithmsintheevaluationofindustrialopticalcoherencetomographyoctimagesofpharmaceuticalcoatings |