Matches in SemOpenAlex for { <https://semopenalex.org/work/W4304688981> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W4304688981 endingPage "778" @default.
- W4304688981 startingPage "771" @default.
- W4304688981 abstract "Imaging is commonly used as a characterization method in the pharmaceuticals industry, including for quantifying subvisible particles in solid and liquid formulations. Extracting information beyond particle size, such as classifying morphological subpopulations, requires some type of image analysis method. Suggested methods to classify particles have been based on pre-determined morphological features or use supervised training of convolutional neural networks to learn image representations in relation to ground truth labels. Complications arising from highly complex morphologies, unforeseen classes, and time-consuming preparation of ground truth labels, are some of the challenges faced by these methods. In this work, we evaluate the application of a self-supervised contrastive learning method in studying particle images from therapeutic solutions. Unlike with supervised training, this approach does not require ground truth labels and representations are learned by comparing particle images and their augmentations. This method provides a fast and easily implementable tool of coarse screening for morphological attribute assessment. Furthermore, our analysis shows that in cases with relatively balanced datasets, a small subset of an image dataset is sufficient to train a convolutional neural network encoder capable of extracting useful image representations. It is also demonstrated that particle classes typically observed in protein solutions administered by pre-filled syringes emerge as separated clusters in the encoder's embedding space, facilitating performing tasks such as training weakly-supervised classifiers or identifying the presence of new subpopulations." @default.
- W4304688981 created "2022-10-12" @default.
- W4304688981 creator A5020279715 @default.
- W4304688981 creator A5027339969 @default.
- W4304688981 creator A5083893913 @default.
- W4304688981 date "2023-03-01" @default.
- W4304688981 modified "2023-10-14" @default.
- W4304688981 title "Evaluation of a Self-Supervised Machine Learning Method for Screening of Particulate Samples: A Case Study in Liquid Formulations" @default.
- W4304688981 cites W1974076996 @default.
- W4304688981 cites W1983542678 @default.
- W4304688981 cites W1992973370 @default.
- W4304688981 cites W1993511309 @default.
- W4304688981 cites W2011684044 @default.
- W4304688981 cites W2012557883 @default.
- W4304688981 cites W2051034485 @default.
- W4304688981 cites W2056085522 @default.
- W4304688981 cites W2061932771 @default.
- W4304688981 cites W2068162244 @default.
- W4304688981 cites W2070870412 @default.
- W4304688981 cites W2136301556 @default.
- W4304688981 cites W2566621816 @default.
- W4304688981 cites W2583922609 @default.
- W4304688981 cites W2778541577 @default.
- W4304688981 cites W2885999719 @default.
- W4304688981 cites W2936235983 @default.
- W4304688981 cites W2945303934 @default.
- W4304688981 cites W2981728535 @default.
- W4304688981 cites W3043065216 @default.
- W4304688981 cites W3043306461 @default.
- W4304688981 cites W3196354372 @default.
- W4304688981 cites W4285404729 @default.
- W4304688981 cites W4310778193 @default.
- W4304688981 doi "https://doi.org/10.1016/j.xphs.2022.10.010" @default.
- W4304688981 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36240862" @default.
- W4304688981 hasPublicationYear "2023" @default.
- W4304688981 type Work @default.
- W4304688981 citedByCount "3" @default.
- W4304688981 countsByYear W43046889812023 @default.
- W4304688981 crossrefType "journal-article" @default.
- W4304688981 hasAuthorship W4304688981A5020279715 @default.
- W4304688981 hasAuthorship W4304688981A5027339969 @default.
- W4304688981 hasAuthorship W4304688981A5083893913 @default.
- W4304688981 hasConcept C111368507 @default.
- W4304688981 hasConcept C115961682 @default.
- W4304688981 hasConcept C119857082 @default.
- W4304688981 hasConcept C124101348 @default.
- W4304688981 hasConcept C127313418 @default.
- W4304688981 hasConcept C136389625 @default.
- W4304688981 hasConcept C146849305 @default.
- W4304688981 hasConcept C153180895 @default.
- W4304688981 hasConcept C154945302 @default.
- W4304688981 hasConcept C25343380 @default.
- W4304688981 hasConcept C2778517922 @default.
- W4304688981 hasConcept C41008148 @default.
- W4304688981 hasConcept C41608201 @default.
- W4304688981 hasConcept C50644808 @default.
- W4304688981 hasConcept C81363708 @default.
- W4304688981 hasConceptScore W4304688981C111368507 @default.
- W4304688981 hasConceptScore W4304688981C115961682 @default.
- W4304688981 hasConceptScore W4304688981C119857082 @default.
- W4304688981 hasConceptScore W4304688981C124101348 @default.
- W4304688981 hasConceptScore W4304688981C127313418 @default.
- W4304688981 hasConceptScore W4304688981C136389625 @default.
- W4304688981 hasConceptScore W4304688981C146849305 @default.
- W4304688981 hasConceptScore W4304688981C153180895 @default.
- W4304688981 hasConceptScore W4304688981C154945302 @default.
- W4304688981 hasConceptScore W4304688981C25343380 @default.
- W4304688981 hasConceptScore W4304688981C2778517922 @default.
- W4304688981 hasConceptScore W4304688981C41008148 @default.
- W4304688981 hasConceptScore W4304688981C41608201 @default.
- W4304688981 hasConceptScore W4304688981C50644808 @default.
- W4304688981 hasConceptScore W4304688981C81363708 @default.
- W4304688981 hasIssue "3" @default.
- W4304688981 hasLocation W43046889811 @default.
- W4304688981 hasLocation W43046889812 @default.
- W4304688981 hasOpenAccess W4304688981 @default.
- W4304688981 hasPrimaryLocation W43046889811 @default.
- W4304688981 hasRelatedWork W2175746458 @default.
- W4304688981 hasRelatedWork W2732542196 @default.
- W4304688981 hasRelatedWork W2738221750 @default.
- W4304688981 hasRelatedWork W2760085659 @default.
- W4304688981 hasRelatedWork W2767651786 @default.
- W4304688981 hasRelatedWork W2883200793 @default.
- W4304688981 hasRelatedWork W3021430260 @default.
- W4304688981 hasRelatedWork W3027997911 @default.
- W4304688981 hasRelatedWork W3093612317 @default.
- W4304688981 hasRelatedWork W4287776258 @default.
- W4304688981 hasVolume "112" @default.
- W4304688981 isParatext "false" @default.
- W4304688981 isRetracted "false" @default.
- W4304688981 workType "article" @default.