Sub-Visible Particle Classification and Label Consistency Analysis for Flow-Imaging Microscopy Via Machine Learning Methods
Sub-visible particles can be a quality concern in pharmaceutical products, especially parenteral preparations. To quantify and characterize these particles, liquid samples may be passed through a flow-imaging microscopy instrument that also generates images of each detected particle. Machine learnin...
Saved in:
| Published in | Journal of pharmaceutical sciences Vol. 113; no. 4; pp. 880 - 890 |
|---|---|
| Main Authors | , , , , , |
| Format | Journal Article |
| Language | English |
| Published |
United States
Elsevier Inc
01.04.2024
|
| Subjects | |
| Online Access | Get full text |
| ISSN | 0022-3549 1520-6017 1520-6017 |
| DOI | 10.1016/j.xphs.2023.10.041 |
Cover
Loading…
| Abstract | Sub-visible particles can be a quality concern in pharmaceutical products, especially parenteral preparations. To quantify and characterize these particles, liquid samples may be passed through a flow-imaging microscopy instrument that also generates images of each detected particle. Machine learning techniques have increasingly been applied to this kind of data to detect changes in experimental conditions or classify specific types of particles, primarily focusing on silicone oil. That technique generally requires manual labeling of particle images by subject matter experts, a time-consuming and complex task.
In this study, we created artificial datasets of silicone oil, protein particles, and glass particles that mimicked complex datasets of particles found in biopharmaceutical products. We used unsupervised learning techniques to effectively describe particle composition by sample. We then trained independent one-class classifiers to detect specific particle populations: silicone oil and glass particles. We also studied the consistency of the particle labels used to evaluate these models. Our results show that one-class classifiers are a reasonable choice for handling heterogeneous flow-imaging microscopy data and that unsupervised learning can aid in the labeling process. However, we found agreement among experts to be rather low, especially for smaller particles (< 8 µm for our Micro-Flow Imaging data). Given the fact that particle label confidence is not usually reported in the literature, we recommend more careful assessment of this topic in the future. |
|---|---|
| AbstractList | Sub-visible particles can be a quality concern in pharmaceutical products, especially parenteral preparations. To quantify and characterize these particles, liquid samples may be passed through a flow-imaging microscopy instrument that also generates images of each detected particle. Machine learning techniques have increasingly been applied to this kind of data to detect changes in experimental conditions or classify specific types of particles, primarily focusing on silicone oil. That technique generally requires manual labeling of particle images by subject matter experts, a time-consuming and complex task.
In this study, we created artificial datasets of silicone oil, protein particles, and glass particles that mimicked complex datasets of particles found in biopharmaceutical products. We used unsupervised learning techniques to effectively describe particle composition by sample. We then trained independent one-class classifiers to detect specific particle populations: silicone oil and glass particles. We also studied the consistency of the particle labels used to evaluate these models. Our results show that one-class classifiers are a reasonable choice for handling heterogeneous flow-imaging microscopy data and that unsupervised learning can aid in the labeling process. However, we found agreement among experts to be rather low, especially for smaller particles (< 8 µm for our Micro-Flow Imaging data). Given the fact that particle label confidence is not usually reported in the literature, we recommend more careful assessment of this topic in the future. Sub-visible particles can be a quality concern in pharmaceutical products, especially parenteral preparations. To quantify and characterize these particles, liquid samples may be passed through a flow-imaging microscopy instrument that also generates images of each detected particle. Machine learning techniques have increasingly been applied to this kind of data to detect changes in experimental conditions or classify specific types of particles, primarily focusing on silicone oil. That technique generally requires manual labeling of particle images by subject matter experts, a time-consuming and complex task. In this study, we created artificial datasets of silicone oil, protein particles, and glass particles that mimicked complex datasets of particles found in biopharmaceutical products. We used unsupervised learning techniques to effectively describe particle composition by sample. We then trained independent one-class classifiers to detect specific particle populations: silicone oil and glass particles. We also studied the consistency of the particle labels used to evaluate these models. Our results show that one-class classifiers are a reasonable choice for handling heterogeneous flow-imaging microscopy data and that unsupervised learning can aid in the labeling process. However, we found agreement among experts to be rather low, especially for smaller particles (< 8 µm for our Micro-Flow Imaging data). Given the fact that particle label confidence is not usually reported in the literature, we recommend more careful assessment of this topic in the future.Sub-visible particles can be a quality concern in pharmaceutical products, especially parenteral preparations. To quantify and characterize these particles, liquid samples may be passed through a flow-imaging microscopy instrument that also generates images of each detected particle. Machine learning techniques have increasingly been applied to this kind of data to detect changes in experimental conditions or classify specific types of particles, primarily focusing on silicone oil. That technique generally requires manual labeling of particle images by subject matter experts, a time-consuming and complex task. In this study, we created artificial datasets of silicone oil, protein particles, and glass particles that mimicked complex datasets of particles found in biopharmaceutical products. We used unsupervised learning techniques to effectively describe particle composition by sample. We then trained independent one-class classifiers to detect specific particle populations: silicone oil and glass particles. We also studied the consistency of the particle labels used to evaluate these models. Our results show that one-class classifiers are a reasonable choice for handling heterogeneous flow-imaging microscopy data and that unsupervised learning can aid in the labeling process. However, we found agreement among experts to be rather low, especially for smaller particles (< 8 µm for our Micro-Flow Imaging data). Given the fact that particle label confidence is not usually reported in the literature, we recommend more careful assessment of this topic in the future. Sub-visible particles can be a quality concern in pharmaceutical products, especially parenteral preparations. To quantify and characterize these particles, liquid samples may be passed through a flow-imaging microscopy instrument that also generates images of each detected particle. Machine learning techniques have increasingly been applied to this kind of data to detect changes in experimental conditions or classify specific types of particles, primarily focusing on silicone oil. That technique generally requires manual labeling of particle images by subject matter experts, a time-consuming and complex task. In this study, we created artificial datasets of silicone oil, protein particles, and glass particles that mimicked complex datasets of particles found in biopharmaceutical products. We used unsupervised learning techniques to effectively describe particle composition by sample. We then trained independent one-class classifiers to detect specific particle populations: silicone oil and glass particles. We also studied the consistency of the particle labels used to evaluate these models. Our results show that one-class classifiers are a reasonable choice for handling heterogeneous flow-imaging microscopy data and that unsupervised learning can aid in the labeling process. However, we found agreement among experts to be rather low, especially for smaller particles (< 8 µm for our Micro-Flow Imaging data). Given the fact that particle label confidence is not usually reported in the literature, we recommend more careful assessment of this topic in the future. |
| Author | Kube, Sebastian Garidel, Patrick Nikels, Felix Lopez-del Rio, Angela Picart-Armada, Sergio Pacios-Michelena, Anabel |
| Author_xml | – sequence: 1 givenname: Angela surname: Lopez-del Rio fullname: Lopez-del Rio, Angela email: angela.lopez_del_rio@boehringer-ingelheim.com organization: Pharmaceutical Development Biologicals, Boehringer Ingelheim Pharma GmbH & Co. KG, Biberach an der Riss 88397, Federal Republic of Germany – sequence: 2 givenname: Anabel surname: Pacios-Michelena fullname: Pacios-Michelena, Anabel organization: Analytical Development Biologicals, Boehringer Ingelheim Pharma GmbH & Co. KG, Biberach an der Riss 88397, Federal Republic of Germany – sequence: 3 givenname: Sergio surname: Picart-Armada fullname: Picart-Armada, Sergio organization: Global Computational Biology and Digital Sciences, Boehringer Ingelheim Pharma GmbH & Co. KG, Biberach an der Riss 88397, Federal Republic of Germany – sequence: 4 givenname: Patrick surname: Garidel fullname: Garidel, Patrick organization: Pharmaceutical Development Biologicals, Boehringer Ingelheim Pharma GmbH & Co. KG, Biberach an der Riss 88397, Federal Republic of Germany – sequence: 5 givenname: Felix surname: Nikels fullname: Nikels, Felix organization: Analytical Development Biologicals, Boehringer Ingelheim Pharma GmbH & Co. KG, Biberach an der Riss 88397, Federal Republic of Germany – sequence: 6 givenname: Sebastian surname: Kube fullname: Kube, Sebastian email: sebastian.kube@boehringer-ingelheim.com organization: Pharmaceutical Development Biologicals, Boehringer Ingelheim Pharma GmbH & Co. KG, Biberach an der Riss 88397, Federal Republic of Germany |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/37924976$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9kUFP3DAQha0KVBbaP9BD5WMv2TqO4yRSL2gFFGlRkdpytRx7ws7Ka29tb8uKP0_CwqUHTh7PvG-kee-UHPnggZBPJZuXrJRf1_OH7SrNOePV2JgzUb4js7LmrJCsbI7IjDHOi6oW3Qk5TWnNGJOsrt-Tk6rpuOgaOSOPP3d9cYcJewf0VseMZiwWTqeEAxqdMXiqvaVL3YOji-ATpgze7Om5124__ugQIr104V9xvdH36O_pDZoYkgnbPb1DTW-0WaEHugQd_fMc8irY9IEcD9ol-PjynpHflxe_Ft-L5Y-r68X5sjBVLXNhO8NFX1pmq7rrayu5FEOljeE1H6wBDUzIVvBBdJXuZdP2Td1YxktgnbW9rs7Il8PebQx_dpCy2mAy4Jz2EHZJ8baVFe9E047Szy_SXb8Bq7YRNzru1atho6A9CKYLU4RBGczPLuWo0amSqSkbtVZTNmrKZuqN2Ywo_w993f4m9O0AwWjQX4SoksHRfrAYwWRlA76FPwFhK6m_ |
| CitedBy_id | crossref_primary_10_1016_j_xphs_2024_11_023 crossref_primary_10_1016_j_xphs_2024_08_003 crossref_primary_10_1016_j_xphs_2024_07_015 |
| Cites_doi | 10.1117/12.2654420 10.1016/j.xphs.2022.07.006 10.1016/0377-0427(87)90125-7 10.1208/s12248-019-0384-0 10.1016/j.xphs.2022.08.006 10.1201/9780429201400 10.1016/j.xphs.2020.10.044 10.2134/agronj1935.00021962002700010011x 10.1515/cdbme-2022-1051 10.1016/j.xphs.2021.02.029 10.1016/j.ejpb.2023.01.017 10.5731/pdajpst.2016.007377 10.1016/j.ijpharm.2021.120248 10.1016/j.xphs.2017.01.030 10.1016/j.xphs.2019.10.066 10.1208/s12248-010-9205-1 10.1002/jps.23479 10.1016/j.xphs.2020.07.008 10.1007/s11095-018-2421-6 10.1177/001316446002000104 10.1007/s11095-016-2079-x 10.1111/j.2517-6161.1995.tb02031.x 10.3390/app12125843 10.1002/jps.24387 10.1016/j.xphs.2022.09.015 10.1016/j.ejpb.2021.09.010 10.1016/j.ejpb.2021.07.004 10.1002/bit.27501 10.1007/BF00994018 10.1162/089976601750264965 10.1002/jps.23871 10.1016/j.xphs.2017.12.008 10.1016/j.xphs.2019.10.034 10.1016/j.xphs.2019.05.018 10.1016/j.knosys.2020.105754 10.1016/j.drudis.2015.10.020 10.4172/2329-6887.1000e128 10.1214/aoms/1177730491 |
| ContentType | Journal Article |
| Copyright | 2023 American Pharmacists Association Copyright © 2023 American Pharmacists Association. Published by Elsevier Inc. All rights reserved. |
| Copyright_xml | – notice: 2023 American Pharmacists Association – notice: Copyright © 2023 American Pharmacists Association. Published by Elsevier Inc. All rights reserved. |
| DBID | AAYXX CITATION NPM 7X8 |
| DOI | 10.1016/j.xphs.2023.10.041 |
| DatabaseName | CrossRef PubMed MEDLINE - Academic |
| DatabaseTitle | CrossRef PubMed MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic PubMed |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Pharmacy, Therapeutics, & Pharmacology |
| EISSN | 1520-6017 |
| EndPage | 890 |
| ExternalDocumentID | 37924976 10_1016_j_xphs_2023_10_041 S0022354923004719 |
| Genre | Journal Article |
| GroupedDBID | --- -~X .3N .GA .GJ .Y3 05W 0R~ 10A 1CY 1L6 1OC 1ZS 31~ 33P 36B 3O- 3WU 4.4 457 4ZD 50Y 50Z 51W 51X 52M 52N 52O 52P 52S 52T 52W 52X 53G 5GY 5RE 5VS 66C 702 7PT 8-0 8-1 8-3 8-4 8-5 8UM 930 A03 A8Z AAEVG AAHHS AAIAV AAKUH AALRI AAOIN AAONW AAXUO AAYOK AAZKR ABCQN ABEML ABFRF ABIJN ABJNI ABMAC ABMYL ABOCM ABPVW ABWRO ACBWZ ACCFJ ACGFO ACGFS ACIWK ACPRK ACSCC ACXME ACXQS ADBBV ADIZJ AEEZP AEFWE AEIMD AENEX AEQDE AEUQT AFBPY AFFNX AFRAH AFTJW AFZJQ AGHFR AI. AITUG AIWBW AJAOE AJBDE AKRWK ALAGY ALMA_UNASSIGNED_HOLDINGS AMBMR AMRAJ ATUGU AZBYB BAFTC BDRZF BNHUX BROTX BRXPI BY8 CS3 D-E D-F DCZOG DPXWK DR2 DU5 E3Z EBD EBS EJD EMB EMOBN ESTFP F00 F01 F04 F5P FDB FEDTE G-S G.N GNP GODZA H.T H.X HBH HF~ HHY HHZ HOLLA HVGLF HX~ HZ~ IX1 J0M JPC KQQ L7B LAW LC2 LC3 LH4 LP6 LP7 LSO LW6 M41 M6Q MK0 MK4 N04 N05 N9A NF~ NNB O66 O9- P2P P2X P4D Q.N Q11 QB0 QRW R.K RNS ROL RWI RX1 RYL SSZ SUPJJ SV3 UB1 UKR UNMZH V2E V8K VH1 W8V W99 WBFHL WH7 WIB WJL WQJ WRC WUP WWP WYUIH XG1 XPP XV2 Y6R YCJ ZE2 ZGI ZXP ~IA ~WT AANHP AAYWO AAYXX ACRPL ACVFH ACYXJ ADCNI ADNMO ADVLN AEUPX AFJKZ AFPUW AGCQF AGQPQ AIGII AKBMS AKYEP APXCP CITATION OIG AAMMB AEFGJ AGXDD AIDQK AIDYY EFKBS NPM 7X8 |
| ID | FETCH-LOGICAL-c356t-d9c24b1d0d359b5d6264f3acc252fdceae046842f493ab678b757d021e09ddba3 |
| ISSN | 0022-3549 1520-6017 |
| IngestDate | Fri Jul 11 07:49:02 EDT 2025 Mon Jul 21 05:58:34 EDT 2025 Tue Jul 01 02:09:41 EDT 2025 Thu Apr 24 23:08:11 EDT 2025 Sat Mar 23 16:40:54 EDT 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 4 |
| Keywords | Image analysis Therapeutic solutions Flow imaging microscopy Machine learning Particle characterization |
| Language | English |
| License | Copyright © 2023 American Pharmacists Association. Published by Elsevier Inc. All rights reserved. |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c356t-d9c24b1d0d359b5d6264f3acc252fdceae046842f493ab678b757d021e09ddba3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| PMID | 37924976 |
| PQID | 2886329478 |
| PQPubID | 23479 |
| PageCount | 11 |
| ParticipantIDs | proquest_miscellaneous_2886329478 pubmed_primary_37924976 crossref_citationtrail_10_1016_j_xphs_2023_10_041 crossref_primary_10_1016_j_xphs_2023_10_041 elsevier_sciencedirect_doi_10_1016_j_xphs_2023_10_041 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | April 2024 2024-04-00 2024-Apr 20240401 |
| PublicationDateYYYYMMDD | 2024-04-01 |
| PublicationDate_xml | – month: 04 year: 2024 text: April 2024 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | Journal of pharmaceutical sciences |
| PublicationTitleAlternate | J Pharm Sci |
| PublicationYear | 2024 |
| Publisher | Elsevier Inc |
| Publisher_xml | – name: Elsevier Inc |
| References | FDA. Questions and answers on current good manufacturing practice requirements | control of components and drug product containers and closures. Published November 16, 2022. Accessed January 3, 2023. Saggu, Patel, Koulis (bib0035) 2017; 34 Probst (bib0057) 2020; 109 (bib0001) 2022 Ratnaswamy, Hair, Li (bib0008) 2014; 103 Maddux, Daniels, Randolph (bib0015) 2017; 106 Mann, Whitney (bib0053) 1947; 18 Wang, Liaw, Chen, Su, Skomski (bib0022) 2022 Ditter, Mahler, Gohlke (bib0006) 2018; 35 Khanal, Hasan, Khanal, Linte (bib0028) 2023; 12464 Calderon CP, Daniels AL, Randolph TW. Using deep convolutional neural networks to circumvent morphological feature specification when classifying subvisible protein aggregates from micro-flow images. 2017;arXiv:1709.00152v1. arXiv preprint. Mathaes, Narhi, Hawe (bib0040) 2019; 22 Cortes, Vapnik (bib0046) 1995; 20 Salami, Wang, Skomski (bib0034) 2022 Fawaz, Schaz, Boehrer, Garidel, Blech (bib0014) 2023; 185 Daniels, Calderon, Randolph (bib0020) 2020; 117 Shibata, Terabe, Shibano (bib0025) 2022; 111 Pedregosa F, Varoquaux G, Gramfort A, et al. Scikit-learn: machine learning in python. 2012;arXiv:1201.0490v4. arXiv preprint. Grabarek, Jiskoot, Hawe, Pike-Overzet, Menzen (bib0055) 2021; 167 Sharma, King, Oma, Merchant (bib0039) 2010; 12 Gambe-Gilbuena, Shibano, Krayukhina, Torisu, Uchiyama (bib0019) 2020; 109 . Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. 2014;arXiv:1409.1556v6. arXiv preprint. Gerhardt, Nguyen, Lewus, Carpenter, Randolph (bib0036) 2015; 104 (bib0013) 2013 Schölkopf, Platt, Shawe-Taylor, Smola, Williamson (bib0047) 2001; 13 Chollet F., others. Keras. Probst, Zayats, Venkatachalam, Davidson (bib0056) 2020; 109 Rousseeuw (bib0043) 1987; 20 Song, Hu, Hamzaoui (bib0037) 2022; 111 Nishiumi, Deiringer, Krause (bib0024) 2022; 111 Cohen (bib0049) 1960; 20 Schaut, Weeks (bib0004) 2017; 71 Witeof, Daniels, Rea (bib0016) 2021; 110 Natarajan, Dhillon, Ravikumar, Tewari (bib0029) 2013; 26 Benjamini, Hochberg (bib0045) 1995; 57 Swift R., Schaut R., Flynn C.R., Asselta R. Glass containers for parenteral products. In: Nema S., Ludwig J.D., eds. Parenteral Medications. 4th ed. CRC Press. Calderon, Daniels, Randolph (bib0018) 2018; 107 (bib0003) 2021 Jiao, Barnett, Christian (bib0038) 2020; 109 Alam, Sonbhadra, Agarwal, Nagabhushan (bib0048) 2020; 196 Grabarek, Senel, Menzen (bib0021) 2020 Schilling, Ahuja, Rettenberger, Scherr, Reischl (bib0027) 2022; 8 FAIR principles - GO FAIR. Accessed June 28, 2023. Chen, Graužinytė, der, Boll (bib0023) 2021; 110 Wei J, Zhu Z, Cheng H, Liu T, Niu G, Liu Y. Learning with noisy labels revisited: a study using real-world human annotations. 2021;arXiv:2110.12088v2. arXiv preprint. FDA. Summary of recent findings related to glass delamination. Published October 24, 2022. Accessed January 2, 2023. Fisher (bib0044) 1935; 27 Umar, Krause, Hawe, Simmel, Menzen (bib0032) 2021; 169 Deng, Dong, Socher, Li, Li (bib0042) 2009 Tawde (bib0009) 2015; 03 Patrini, Rozza, Menon, Nock, Qu (bib0031) 2017 Long, Ma, Sheng (bib0033) 2022; 12 Song H, Kim M, Park D, Shin Y, Lee JG. Learning from noisy labels with deep neural networks: a survey. 2020;arXiv:2007.08199v7. arXiv preprint. Ebbers, de, Hoefnagel, Nibbeling, Mantel-Teeuwisse (bib0010) 2016; 21 Ma, Ashraf, Srinivasan (bib0007) 2021; 596 Abadi M, Agarwal A, Barham P, et al. TensorFlow: large-scale machine learning on heterogeneous distributed systems. 2016;arXiv:1603.04467v2. arXiv preprint (bib0002) 2021 Zölls, Gregoritza, Tantipolphan (bib0054) 2013; 102 Natarajan (10.1016/j.xphs.2023.10.041_bib0029) 2013; 26 Ma (10.1016/j.xphs.2023.10.041_bib0007) 2021; 596 10.1016/j.xphs.2023.10.041_bib0041 Rousseeuw (10.1016/j.xphs.2023.10.041_bib0043) 1987; 20 Khanal (10.1016/j.xphs.2023.10.041_bib0028) 2023; 12464 Tawde (10.1016/j.xphs.2023.10.041_bib0009) 2015; 03 Schilling (10.1016/j.xphs.2023.10.041_bib0027) 2022; 8 Daniels (10.1016/j.xphs.2023.10.041_bib0020) 2020; 117 Cohen (10.1016/j.xphs.2023.10.041_bib0049) 1960; 20 Mann (10.1016/j.xphs.2023.10.041_bib0053) 1947; 18 Patrini (10.1016/j.xphs.2023.10.041_bib0031) 2017 Ebbers (10.1016/j.xphs.2023.10.041_bib0010) 2016; 21 (10.1016/j.xphs.2023.10.041_bib0002) 2021 Deng (10.1016/j.xphs.2023.10.041_bib0042) 2009 Calderon (10.1016/j.xphs.2023.10.041_bib0018) 2018; 107 10.1016/j.xphs.2023.10.041_bib0050 Ratnaswamy (10.1016/j.xphs.2023.10.041_bib0008) 2014; 103 10.1016/j.xphs.2023.10.041_bib0052 Nishiumi (10.1016/j.xphs.2023.10.041_bib0024) 2022; 111 10.1016/j.xphs.2023.10.041_bib0051 10.1016/j.xphs.2023.10.041_bib0012 10.1016/j.xphs.2023.10.041_bib0011 Shibata (10.1016/j.xphs.2023.10.041_bib0025) 2022; 111 Maddux (10.1016/j.xphs.2023.10.041_bib0015) 2017; 106 Probst (10.1016/j.xphs.2023.10.041_bib0056) 2020; 109 Fawaz (10.1016/j.xphs.2023.10.041_bib0014) 2023; 185 Gambe-Gilbuena (10.1016/j.xphs.2023.10.041_bib0019) 2020; 109 Long (10.1016/j.xphs.2023.10.041_bib0033) 2022; 12 Alam (10.1016/j.xphs.2023.10.041_bib0048) 2020; 196 Saggu (10.1016/j.xphs.2023.10.041_bib0035) 2017; 34 Jiao (10.1016/j.xphs.2023.10.041_bib0038) 2020; 109 (10.1016/j.xphs.2023.10.041_bib0003) 2021 Sharma (10.1016/j.xphs.2023.10.041_bib0039) 2010; 12 10.1016/j.xphs.2023.10.041_bib0005 Probst (10.1016/j.xphs.2023.10.041_bib0057) 2020; 109 (10.1016/j.xphs.2023.10.041_bib0001) 2022 Umar (10.1016/j.xphs.2023.10.041_bib0032) 2021; 169 Mathaes (10.1016/j.xphs.2023.10.041_bib0040) 2019; 22 Schaut (10.1016/j.xphs.2023.10.041_bib0004) 2017; 71 (10.1016/j.xphs.2023.10.041_bib0013) 2013 Witeof (10.1016/j.xphs.2023.10.041_bib0016) 2021; 110 10.1016/j.xphs.2023.10.041_bib0058 Grabarek (10.1016/j.xphs.2023.10.041_bib0021) 2020 Gerhardt (10.1016/j.xphs.2023.10.041_bib0036) 2015; 104 10.1016/j.xphs.2023.10.041_bib0017 Cortes (10.1016/j.xphs.2023.10.041_bib0046) 1995; 20 10.1016/j.xphs.2023.10.041_bib0030 Song (10.1016/j.xphs.2023.10.041_bib0037) 2022; 111 Schölkopf (10.1016/j.xphs.2023.10.041_bib0047) 2001; 13 Benjamini (10.1016/j.xphs.2023.10.041_bib0045) 1995; 57 Fisher (10.1016/j.xphs.2023.10.041_bib0044) 1935; 27 Ditter (10.1016/j.xphs.2023.10.041_bib0006) 2018; 35 Grabarek (10.1016/j.xphs.2023.10.041_bib0055) 2021; 167 Salami (10.1016/j.xphs.2023.10.041_bib0034) 2022 10.1016/j.xphs.2023.10.041_bib0026 Zölls (10.1016/j.xphs.2023.10.041_bib0054) 2013; 102 Wang (10.1016/j.xphs.2023.10.041_bib0022) 2022 Chen (10.1016/j.xphs.2023.10.041_bib0023) 2021; 110 |
| References_xml | – volume: 111 start-page: 3191 year: 2022 end-page: 3194 ident: bib0037 article-title: The impact of syringe age prior to filling on migration of subvisible silicone-oil particles into drug product publication-title: J Pharm Sci – volume: 35 start-page: 146 year: 2018 ident: bib0006 article-title: Impact of vial washing and depyrogenation on surface properties and delamination risk of glass vials publication-title: Pharmaceut Res – volume: 109 start-page: 364 year: 2020 end-page: 374 ident: bib0057 article-title: Characterization of protein aggregates, silicone oil droplets, and protein-silicone interactions using imaging flow cytometry publication-title: J Pharm Sci – volume: 109 start-page: 2996 year: 2020 end-page: 3005 ident: bib0056 article-title: Advanced characterization of silicone oil droplets in protein therapeutics using artificial intelligence analysis of imaging flow cytometry data publication-title: J Pharm Sci – reference: Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. 2014;arXiv:1409.1556v6. arXiv preprint. – year: 2013 ident: bib0013 article-title: United States pharmacopoeia. USP-NF 2021 issue 1 – volume: 110 start-page: 2743 year: 2021 end-page: 2752 ident: bib0016 article-title: Machine learning and accelerated stress approaches to differentiate potential causes of aggregation in polyclonal antibody formulations during shipping publication-title: J Pharm Sci – volume: 13 start-page: 1443 year: 2001 end-page: 1471 ident: bib0047 article-title: Estimating the support of a high-dimensional distribution publication-title: Neural Comput – volume: 20 start-page: 53 year: 1987 end-page: 65 ident: bib0043 article-title: Silhouettes: a graphical aid to the interpretation and validation of cluster analysis publication-title: J Comput Appl Math – volume: 103 start-page: 1104 year: 2014 end-page: 1114 ident: bib0008 article-title: A case study of nondelamination glass dissolution resulting in visible particles: implications for neutral pH formulations publication-title: J Pharm Sci – volume: 102 start-page: 1434 year: 2013 end-page: 1446 ident: bib0054 article-title: How subvisible particles become invisible—relevance of the refractive index for protein particle analysis publication-title: J Pharm Sci – volume: 34 start-page: 479 year: 2017 end-page: 491 ident: bib0035 article-title: A random forest approach for counting silicone oil droplets and protein particles in antibody formulations using flow microscopy publication-title: Pharmaceut Res – volume: 104 start-page: 1601 year: 2015 end-page: 1609 ident: bib0036 article-title: Effect of the siliconization method on particle generation in a monoclonal antibody formulation in pre-filled syringes publication-title: J Pharm Sci – start-page: 2233 year: 2017 end-page: 2241 ident: bib0031 article-title: Making deep neural networks robust to label noise: a loss correction approach publication-title: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) – reference: Abadi M, Agarwal A, Barham P, et al. TensorFlow: large-scale machine learning on heterogeneous distributed systems. 2016;arXiv:1603.04467v2. arXiv preprint – volume: 71 start-page: 279 year: 2017 end-page: 296 ident: bib0004 article-title: Historical review of glasses used for parenteral packaging publication-title: PDA J Pharm Sci Technol – volume: 22 start-page: 1 year: 2019 ident: bib0040 article-title: Phase-appropriate application of analytical methods to monitor subvisible particles across the biotherapeutic drug product life cycle publication-title: AAPS J – volume: 8 start-page: 197 year: 2022 end-page: 200 ident: bib0027 article-title: Impact of annotation noise on histopathology nucleus segmentation publication-title: Curr Dir Biomed Eng – volume: 196 year: 2020 ident: bib0048 article-title: One-class support vector classifiers: a survey publication-title: Knowl-based Syst – volume: 18 start-page: 50 year: 1947 end-page: 60 ident: bib0053 article-title: On a test of whether one of two random variables is stochastically larger than the other publication-title: Ann Math Stat – volume: 111 start-page: 2745 year: 2022 end-page: 2757 ident: bib0025 article-title: A collaborative study on the classification of silicone oil droplets and protein particles using flow imaging method publication-title: J Pharm Sci – reference: Chollet F., others. Keras. – reference: FDA. Questions and answers on current good manufacturing practice requirements | control of components and drug product containers and closures. Published November 16, 2022. Accessed January 3, 2023. – reference: Song H, Kim M, Park D, Shin Y, Lee JG. Learning from noisy labels with deep neural networks: a survey. 2020;arXiv:2007.08199v7. arXiv preprint. – volume: 110 start-page: 1643 year: 2021 end-page: 1651 ident: bib0023 article-title: Applying pattern recognition as a robust approach for silicone oil droplet identification in flow-microscopy images of protein formulations publication-title: J Pharm Sci – volume: 185 start-page: 55 year: 2023 end-page: 70 ident: bib0014 article-title: Micro-flow imaging multi-instrument evaluation for sub-visible particle detection publication-title: Eur J Pharm Biopharm – year: 2021 ident: bib0002 article-title: United States pharmacopoeia. USP-NF 2021 Issue 1 – volume: 596 year: 2021 ident: bib0007 article-title: Microscopic evaluation of pharmaceutical glass container-formulation interactions under stressed conditions publication-title: Int J Pharmaceut – year: 2021 ident: bib0003 article-title: United States pharmacopoeia. USP-NF 2021 issue 1 – reference: Wei J, Zhu Z, Cheng H, Liu T, Niu G, Liu Y. Learning with noisy labels revisited: a study using real-world human annotations. 2021;arXiv:2110.12088v2. arXiv preprint. – volume: 107 start-page: 999 year: 2018 end-page: 1008 ident: bib0018 article-title: Deep convolutional neural network analysis of flow imaging microscopy data to classify subvisible particles in protein formulations publication-title: J Pharm Sci – year: 2022 ident: bib0034 article-title: Evaluation of a self-supervised machine learning method for screening of particulate samples: a case study in liquid formulations publication-title: J Pharm Sci – volume: 109 start-page: 614 year: 2020 end-page: 623 ident: bib0019 article-title: Automatic identification of the stress sources of protein aggregates using flow imaging microscopy images publication-title: J Pharm Sci – year: 2020 ident: bib0021 article-title: Particulate impurities in cell-based medicinal products traced by flow imaging microscopy combined with deep learning for image analysis publication-title: Cytotherapy – volume: 20 start-page: 273 year: 1995 end-page: 297 ident: bib0046 article-title: Support-vector networks publication-title: Mach Learn – volume: 109 start-page: 640 year: 2020 end-page: 645 ident: bib0038 article-title: Characterization of subvisible particles in biotherapeutic prefilled syringes: the role of polysorbate and protein on the formation of silicone oil and protein subvisible particles after drop shock publication-title: J Pharm Sci – volume: 12 start-page: 5843 year: 2022 ident: bib0033 article-title: Transfer learning analysis for subvisible particle flow imaging of pharmaceutical formulations publication-title: Appl Sci – reference: FAIR principles - GO FAIR. Accessed June 28, 2023. – volume: 106 start-page: 1239 year: 2017 end-page: 1248 ident: bib0015 article-title: Microflow imaging analyses reflect mechanisms of aggregate formation: comparing protein particle data sets using the Kullback–Leibler divergence publication-title: J Pharm Sci – volume: 169 start-page: 97 year: 2021 end-page: 102 ident: bib0032 article-title: Towards quantification and differentiation of protein aggregates and silicone oil droplets in the low micrometer and submicrometer size range by using oil-immersion flow imaging microscopy and convolutional neural networks publication-title: Eur J Pharm Biopharm – volume: 21 start-page: 536 year: 2016 end-page: 539 ident: bib0010 article-title: Characteristics of product recalls of biopharmaceuticals and small-molecule drugs in the USA publication-title: Drug Discov Today – volume: 27 start-page: 76 year: 1935 ident: bib0044 article-title: Statistical methods for research workers publication-title: Agron J – year: 2022 ident: bib0001 article-title: European pharmacopoeia – volume: 03 year: 2015 ident: bib0009 article-title: Particulate matter in injectables: main cause for recalls publication-title: J Pharmacovigil – volume: 57 start-page: 289 year: 1995 end-page: 300 ident: bib0045 article-title: Controlling the false discovery rate: a practical and powerful approach to multiple testing publication-title: J R Stat Soc Ser B Methodol – volume: 20 start-page: 37 year: 1960 end-page: 46 ident: bib0049 article-title: A coefficient of agreement for nominal scales publication-title: Educ Psychol Meas – volume: 111 start-page: 3017 year: 2022 end-page: 3028 ident: bib0024 article-title: Utility of three flow imaging microscopy instruments for image analysis in evaluating four types of subvisible particle in biopharmaceuticals publication-title: J Pharm Sci – volume: 26 year: 2013 ident: bib0029 article-title: Learning with noisy labels publication-title: Proceedings of the Advances in Neural Information Processing System – start-page: 248 year: 2009 end-page: 255 ident: bib0042 article-title: ImageNet FFL: a large-scale hierarchical image database publication-title: Proceedings of the 2009 IEEE Conference on Computer Vision Pattern Recognition – reference: . – reference: Swift R., Schaut R., Flynn C.R., Asselta R. Glass containers for parenteral products. In: Nema S., Ludwig J.D., eds. Parenteral Medications. 4th ed. CRC Press. – reference: FDA. Summary of recent findings related to glass delamination. Published October 24, 2022. Accessed January 2, 2023. – start-page: 1 year: 2022 end-page: 11 ident: bib0022 article-title: Convolutional neural networks enable highly accurate and automated subvisible particulate classification of biopharmaceuticals publication-title: Pharmaceut Res – reference: Pedregosa F, Varoquaux G, Gramfort A, et al. Scikit-learn: machine learning in python. 2012;arXiv:1201.0490v4. arXiv preprint. – reference: Calderon CP, Daniels AL, Randolph TW. Using deep convolutional neural networks to circumvent morphological feature specification when classifying subvisible protein aggregates from micro-flow images. 2017;arXiv:1709.00152v1. arXiv preprint. – volume: 12 start-page: 455 year: 2010 end-page: 464 ident: bib0039 article-title: Micro-flow imaging: flow microscopy applied to sub-visible particulate analysis in protein formulations publication-title: AAPS J – volume: 117 start-page: 3322 year: 2020 end-page: 3335 ident: bib0020 article-title: Machine learning and statistical analyses for extracting and characterizing “fingerprints” of antibody aggregation at container interfaces from flow microscopy images publication-title: Biotechnol Bioeng – volume: 12464 year: 2023 ident: bib0028 article-title: Investigating the impact of class-dependent label noise in medical image classification publication-title: Méd Imaging Image Process – volume: 167 start-page: 38 year: 2021 end-page: 47 ident: bib0055 article-title: Forced degradation of cell-based medicinal products guided by flow imaging microscopy: Explorative studies with Jurkat cells publication-title: Eur J Pharm Biopharm – ident: 10.1016/j.xphs.2023.10.041_bib0017 – volume: 12464 year: 2023 ident: 10.1016/j.xphs.2023.10.041_bib0028 article-title: Investigating the impact of class-dependent label noise in medical image classification publication-title: Méd Imaging Image Process doi: 10.1117/12.2654420 – volume: 111 start-page: 2745 issue: 10 year: 2022 ident: 10.1016/j.xphs.2023.10.041_bib0025 article-title: A collaborative study on the classification of silicone oil droplets and protein particles using flow imaging method publication-title: J Pharm Sci doi: 10.1016/j.xphs.2022.07.006 – volume: 20 start-page: 53 year: 1987 ident: 10.1016/j.xphs.2023.10.041_bib0043 article-title: Silhouettes: a graphical aid to the interpretation and validation of cluster analysis publication-title: J Comput Appl Math doi: 10.1016/0377-0427(87)90125-7 – volume: 22 start-page: 1 issue: 1 year: 2019 ident: 10.1016/j.xphs.2023.10.041_bib0040 article-title: Phase-appropriate application of analytical methods to monitor subvisible particles across the biotherapeutic drug product life cycle publication-title: AAPS J doi: 10.1208/s12248-019-0384-0 – volume: 26 year: 2013 ident: 10.1016/j.xphs.2023.10.041_bib0029 article-title: Learning with noisy labels – volume: 111 start-page: 3017 issue: 11 year: 2022 ident: 10.1016/j.xphs.2023.10.041_bib0024 article-title: Utility of three flow imaging microscopy instruments for image analysis in evaluating four types of subvisible particle in biopharmaceuticals publication-title: J Pharm Sci doi: 10.1016/j.xphs.2022.08.006 – ident: 10.1016/j.xphs.2023.10.041_bib0051 – ident: 10.1016/j.xphs.2023.10.041_bib0005 doi: 10.1201/9780429201400 – volume: 110 start-page: 1643 issue: 4 year: 2021 ident: 10.1016/j.xphs.2023.10.041_bib0023 article-title: Applying pattern recognition as a robust approach for silicone oil droplet identification in flow-microscopy images of protein formulations publication-title: J Pharm Sci doi: 10.1016/j.xphs.2020.10.044 – start-page: 248 year: 2009 ident: 10.1016/j.xphs.2023.10.041_bib0042 article-title: ImageNet FFL: a large-scale hierarchical image database – volume: 27 start-page: 76 issue: 1 year: 1935 ident: 10.1016/j.xphs.2023.10.041_bib0044 article-title: Statistical methods for research workers publication-title: Agron J doi: 10.2134/agronj1935.00021962002700010011x – volume: 8 start-page: 197 issue: 2 year: 2022 ident: 10.1016/j.xphs.2023.10.041_bib0027 article-title: Impact of annotation noise on histopathology nucleus segmentation publication-title: Curr Dir Biomed Eng doi: 10.1515/cdbme-2022-1051 – ident: 10.1016/j.xphs.2023.10.041_bib0041 – volume: 110 start-page: 2743 issue: 7 year: 2021 ident: 10.1016/j.xphs.2023.10.041_bib0016 article-title: Machine learning and accelerated stress approaches to differentiate potential causes of aggregation in polyclonal antibody formulations during shipping publication-title: J Pharm Sci doi: 10.1016/j.xphs.2021.02.029 – volume: 185 start-page: 55 year: 2023 ident: 10.1016/j.xphs.2023.10.041_bib0014 article-title: Micro-flow imaging multi-instrument evaluation for sub-visible particle detection publication-title: Eur J Pharm Biopharm doi: 10.1016/j.ejpb.2023.01.017 – year: 2022 ident: 10.1016/j.xphs.2023.10.041_bib0034 article-title: Evaluation of a self-supervised machine learning method for screening of particulate samples: a case study in liquid formulations publication-title: J Pharm Sci – volume: 71 start-page: 279 issue: 4 year: 2017 ident: 10.1016/j.xphs.2023.10.041_bib0004 article-title: Historical review of glasses used for parenteral packaging publication-title: PDA J Pharm Sci Technol doi: 10.5731/pdajpst.2016.007377 – volume: 596 year: 2021 ident: 10.1016/j.xphs.2023.10.041_bib0007 article-title: Microscopic evaluation of pharmaceutical glass container-formulation interactions under stressed conditions publication-title: Int J Pharmaceut doi: 10.1016/j.ijpharm.2021.120248 – volume: 106 start-page: 1239 issue: 5 year: 2017 ident: 10.1016/j.xphs.2023.10.041_bib0015 article-title: Microflow imaging analyses reflect mechanisms of aggregate formation: comparing protein particle data sets using the Kullback–Leibler divergence publication-title: J Pharm Sci doi: 10.1016/j.xphs.2017.01.030 – volume: 109 start-page: 640 issue: 1 year: 2020 ident: 10.1016/j.xphs.2023.10.041_bib0038 article-title: Characterization of subvisible particles in biotherapeutic prefilled syringes: the role of polysorbate and protein on the formation of silicone oil and protein subvisible particles after drop shock publication-title: J Pharm Sci doi: 10.1016/j.xphs.2019.10.066 – start-page: 1 year: 2022 ident: 10.1016/j.xphs.2023.10.041_bib0022 article-title: Convolutional neural networks enable highly accurate and automated subvisible particulate classification of biopharmaceuticals publication-title: Pharmaceut Res – volume: 12 start-page: 455 issue: 3 year: 2010 ident: 10.1016/j.xphs.2023.10.041_bib0039 article-title: Micro-flow imaging: flow microscopy applied to sub-visible particulate analysis in protein formulations publication-title: AAPS J doi: 10.1208/s12248-010-9205-1 – ident: 10.1016/j.xphs.2023.10.041_bib0052 – volume: 102 start-page: 1434 issue: 5 year: 2013 ident: 10.1016/j.xphs.2023.10.041_bib0054 article-title: How subvisible particles become invisible—relevance of the refractive index for protein particle analysis publication-title: J Pharm Sci doi: 10.1002/jps.23479 – volume: 109 start-page: 2996 issue: 10 year: 2020 ident: 10.1016/j.xphs.2023.10.041_bib0056 article-title: Advanced characterization of silicone oil droplets in protein therapeutics using artificial intelligence analysis of imaging flow cytometry data publication-title: J Pharm Sci doi: 10.1016/j.xphs.2020.07.008 – volume: 35 start-page: 146 issue: 7 year: 2018 ident: 10.1016/j.xphs.2023.10.041_bib0006 article-title: Impact of vial washing and depyrogenation on surface properties and delamination risk of glass vials publication-title: Pharmaceut Res doi: 10.1007/s11095-018-2421-6 – volume: 20 start-page: 37 issue: 1 year: 1960 ident: 10.1016/j.xphs.2023.10.041_bib0049 article-title: A coefficient of agreement for nominal scales publication-title: Educ Psychol Meas doi: 10.1177/001316446002000104 – volume: 34 start-page: 479 issue: 2 year: 2017 ident: 10.1016/j.xphs.2023.10.041_bib0035 article-title: A random forest approach for counting silicone oil droplets and protein particles in antibody formulations using flow microscopy publication-title: Pharmaceut Res doi: 10.1007/s11095-016-2079-x – volume: 57 start-page: 289 issue: 1 year: 1995 ident: 10.1016/j.xphs.2023.10.041_bib0045 article-title: Controlling the false discovery rate: a practical and powerful approach to multiple testing publication-title: J R Stat Soc Ser B Methodol doi: 10.1111/j.2517-6161.1995.tb02031.x – ident: 10.1016/j.xphs.2023.10.041_bib0011 – volume: 12 start-page: 5843 issue: 12 year: 2022 ident: 10.1016/j.xphs.2023.10.041_bib0033 article-title: Transfer learning analysis for subvisible particle flow imaging of pharmaceutical formulations publication-title: Appl Sci doi: 10.3390/app12125843 – volume: 104 start-page: 1601 issue: 5 year: 2015 ident: 10.1016/j.xphs.2023.10.041_bib0036 article-title: Effect of the siliconization method on particle generation in a monoclonal antibody formulation in pre-filled syringes publication-title: J Pharm Sci doi: 10.1002/jps.24387 – volume: 111 start-page: 3191 issue: 12 year: 2022 ident: 10.1016/j.xphs.2023.10.041_bib0037 article-title: The impact of syringe age prior to filling on migration of subvisible silicone-oil particles into drug product publication-title: J Pharm Sci doi: 10.1016/j.xphs.2022.09.015 – year: 2020 ident: 10.1016/j.xphs.2023.10.041_bib0021 article-title: Particulate impurities in cell-based medicinal products traced by flow imaging microscopy combined with deep learning for image analysis publication-title: Cytotherapy – volume: 169 start-page: 97 year: 2021 ident: 10.1016/j.xphs.2023.10.041_bib0032 article-title: Towards quantification and differentiation of protein aggregates and silicone oil droplets in the low micrometer and submicrometer size range by using oil-immersion flow imaging microscopy and convolutional neural networks publication-title: Eur J Pharm Biopharm doi: 10.1016/j.ejpb.2021.09.010 – volume: 167 start-page: 38 year: 2021 ident: 10.1016/j.xphs.2023.10.041_bib0055 article-title: Forced degradation of cell-based medicinal products guided by flow imaging microscopy: Explorative studies with Jurkat cells publication-title: Eur J Pharm Biopharm doi: 10.1016/j.ejpb.2021.07.004 – volume: 117 start-page: 3322 issue: 11 year: 2020 ident: 10.1016/j.xphs.2023.10.041_bib0020 article-title: Machine learning and statistical analyses for extracting and characterizing “fingerprints” of antibody aggregation at container interfaces from flow microscopy images publication-title: Biotechnol Bioeng doi: 10.1002/bit.27501 – volume: 20 start-page: 273 issue: 3 year: 1995 ident: 10.1016/j.xphs.2023.10.041_bib0046 article-title: Support-vector networks publication-title: Mach Learn doi: 10.1007/BF00994018 – volume: 13 start-page: 1443 issue: 7 year: 2001 ident: 10.1016/j.xphs.2023.10.041_bib0047 article-title: Estimating the support of a high-dimensional distribution publication-title: Neural Comput doi: 10.1162/089976601750264965 – year: 2021 ident: 10.1016/j.xphs.2023.10.041_bib0002 – volume: 103 start-page: 1104 issue: 4 year: 2014 ident: 10.1016/j.xphs.2023.10.041_bib0008 article-title: A case study of nondelamination glass dissolution resulting in visible particles: implications for neutral pH formulations publication-title: J Pharm Sci doi: 10.1002/jps.23871 – ident: 10.1016/j.xphs.2023.10.041_bib0030 – volume: 107 start-page: 999 issue: 4 year: 2018 ident: 10.1016/j.xphs.2023.10.041_bib0018 article-title: Deep convolutional neural network analysis of flow imaging microscopy data to classify subvisible particles in protein formulations publication-title: J Pharm Sci doi: 10.1016/j.xphs.2017.12.008 – year: 2013 ident: 10.1016/j.xphs.2023.10.041_bib0013 – year: 2022 ident: 10.1016/j.xphs.2023.10.041_bib0001 – ident: 10.1016/j.xphs.2023.10.041_bib0012 – volume: 109 start-page: 614 issue: 1 year: 2020 ident: 10.1016/j.xphs.2023.10.041_bib0019 article-title: Automatic identification of the stress sources of protein aggregates using flow imaging microscopy images publication-title: J Pharm Sci doi: 10.1016/j.xphs.2019.10.034 – start-page: 2233 year: 2017 ident: 10.1016/j.xphs.2023.10.041_bib0031 article-title: Making deep neural networks robust to label noise: a loss correction approach – ident: 10.1016/j.xphs.2023.10.041_bib0058 – volume: 109 start-page: 364 issue: 1 year: 2020 ident: 10.1016/j.xphs.2023.10.041_bib0057 article-title: Characterization of protein aggregates, silicone oil droplets, and protein-silicone interactions using imaging flow cytometry publication-title: J Pharm Sci doi: 10.1016/j.xphs.2019.05.018 – volume: 196 year: 2020 ident: 10.1016/j.xphs.2023.10.041_bib0048 article-title: One-class support vector classifiers: a survey publication-title: Knowl-based Syst doi: 10.1016/j.knosys.2020.105754 – volume: 21 start-page: 536 issue: 4 year: 2016 ident: 10.1016/j.xphs.2023.10.041_bib0010 article-title: Characteristics of product recalls of biopharmaceuticals and small-molecule drugs in the USA publication-title: Drug Discov Today doi: 10.1016/j.drudis.2015.10.020 – ident: 10.1016/j.xphs.2023.10.041_bib0026 – ident: 10.1016/j.xphs.2023.10.041_bib0050 – year: 2021 ident: 10.1016/j.xphs.2023.10.041_bib0003 – volume: 03 issue: 01 year: 2015 ident: 10.1016/j.xphs.2023.10.041_bib0009 article-title: Particulate matter in injectables: main cause for recalls publication-title: J Pharmacovigil doi: 10.4172/2329-6887.1000e128 – volume: 18 start-page: 50 issue: 1 year: 1947 ident: 10.1016/j.xphs.2023.10.041_bib0053 article-title: On a test of whether one of two random variables is stochastically larger than the other publication-title: Ann Math Stat doi: 10.1214/aoms/1177730491 |
| SSID | ssj0006055 |
| Score | 2.4484556 |
| Snippet | Sub-visible particles can be a quality concern in pharmaceutical products, especially parenteral preparations. To quantify and characterize these particles,... |
| SourceID | proquest pubmed crossref elsevier |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 880 |
| SubjectTerms | Flow imaging microscopy Image analysis Machine learning Particle characterization Therapeutic solutions |
| Title | Sub-Visible Particle Classification and Label Consistency Analysis for Flow-Imaging Microscopy Via Machine Learning Methods |
| URI | https://dx.doi.org/10.1016/j.xphs.2023.10.041 https://www.ncbi.nlm.nih.gov/pubmed/37924976 https://www.proquest.com/docview/2886329478 |
| Volume | 113 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1bb9MwFLbKkNBeEHfKABkJ7WVzlSXO7RExpoE6VE3dtLcojp2to2urNdXo-EX8S87JcS4bdAJeoirOxer32T7H-c45jL2PnCwPtJOB5RbkQuaOESryjJCu46U6LGtso9ria7B_JL-c-Cedzs-WamlRqF52_ce4kv9BFc4Brhgl-w_I1g-FE_Ab8IUjIAzHv8IYRr04HgGpxwZMQWqnMpcoACJocWO8nyozptqc86KMtaxzkaDKcG88vRKfL6he0QEq9DBWZbl1PEqxMNEZGqL9agvloCw5PV9h1M7ObmyR2_W1ttv705m5FrvQmcMRxdegprZeGVAhOJ0LkqcailaDnipTy0AG8NjLQgA9U102w1x3SlKyUkUEnr8m3QHVHvjW3tVw22IYY2di9GsdCuysp2qKW7WclK2JN6J6UL8tCLQ3cd77PiuTs7teD7V8lGurxZDZRUkRL0R3NLyVm5tWe9t0j913wSPBYhm7h02mMvAKfRuTRfLB2y9cZw-qR6wygVa5OKWpM3zEHlo4-Qci1GPWMZMnbHNA0C63-bCJ2Ztv800-aNKfL5-yHy1W8oqV_CYrObCSl6zkLVbyipUcWMnbrOQNKzmwkltW8oqV3LLyGTva-zT8uC9siQ-ReX5QCB1nrlQ72tGeHytfg3stcy_NMtd3c52Z1DgSvxTnMvZSBYaVCv1Qg11qnFhrlXrP2dpkOjEvGVe-ysEMC7WRSkoTprk0QWTCwGS5CXTQZTvVv55kNv89lmEZJ5XQ8TxB0BIEDc8BaF22Vd8zo-wvd17tV2AmdnyRXZoAG--8712FfAKTO36xSydmuoCLoijw3FiGUZe9IErU_ajY9GplywZbb4bWa7ZWXC7MGzChC_W2JO8vFPPMcA |
| linkProvider | Wiley-Blackwell |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Sub-Visible+Particle+Classification+and+Label+Consistency+Analysis+for+Flow-Imaging+Microscopy+Via+Machine+Learning+Methods&rft.jtitle=Journal+of+pharmaceutical+sciences&rft.au=Lopez-Del+Rio%2C+Angela&rft.au=Pacios-Michelena%2C+Anabel&rft.au=Picart-Armada%2C+Sergio&rft.au=Garidel%2C+Patrick&rft.date=2024-04-01&rft.eissn=1520-6017&rft.volume=113&rft.issue=4&rft.spage=880&rft_id=info:doi/10.1016%2Fj.xphs.2023.10.041&rft_id=info%3Apmid%2F37924976&rft.externalDocID=37924976 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0022-3549&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0022-3549&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0022-3549&client=summon |