{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T12:50:49Z","timestamp":1784119849377,"version":"3.55.0"},"reference-count":35,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2022,8,24]],"date-time":"2022-08-24T00:00:00Z","timestamp":1661299200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Hallym University Research Fund","award":["HURF-2020-14"],"award-info":[{"award-number":["HURF-2020-14"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:sec id=\"sec001\">\n<jats:title>Background<\/jats:title>\n<jats:p>Protein electrophoresis (PEP) is an important tool in supporting the analytical characterization of protein status in diseases related to monoclonal components, inflammation, and antibody deficiency. Here, we developed a deep learning-based PEP classification algorithm to supplement the labor-intensive PEP interpretation and enhance inter-observer reliability.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec002\">\n<jats:title>Methods<\/jats:title>\n<jats:p>A total of 2,578 gel images and densitogram PEP images from January 2018 to July 2019 were split into training (80%), validation (10%), and test (10.0%) sets. The PEP images were assessed based on six major findings (acute-phase protein, monoclonal gammopathy, polyclonal gammopathy, hypoproteinemia, nephrotic syndrome, and normal). The images underwent processing, including color-to-grayscale and histogram equalization, and were input into neural networks.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec003\">\n<jats:title>Results<\/jats:title>\n<jats:p>Using densitogram PEP images, the area under the receiver operating characteristic curve (AUROC) for each diagnosis ranged from 0.873 to 0.989, and the accuracy for classifying all the findings ranged from 85.2% to 96.9%. For gel images, the AUROC ranged from 0.763 to 0.965, and the accuracy ranged from 82.0% to 94.5%.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec004\">\n<jats:title>Conclusions<\/jats:title>\n<jats:p>The deep learning algorithm demonstrated good performance in classifying PEP images. It is expected to be useful as an auxiliary tool for screening the results and helpful in environments where specialists are scarce.<\/jats:p>\n<\/jats:sec>","DOI":"10.1371\/journal.pone.0273284","type":"journal-article","created":{"date-parts":[[2022,8,24]],"date-time":"2022-08-24T17:32:22Z","timestamp":1661362342000},"page":"e0273284","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":10,"title":["Development and validation of a deep learning-based protein electrophoresis classification algorithm"],"prefix":"10.1371","volume":"17","author":[{"given":"Nuri","family":"Lee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seri","family":"Jeong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kibum","family":"Jeon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5056-9033","authenticated-orcid":true,"given":"Wonkeun","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2775-2128","authenticated-orcid":true,"given":"Min-Jeong","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2022,8,24]]},"reference":[{"issue":"10","key":"pone.0273284.ref001","doi-asserted-by":"crossref","first-page":"1458","DOI":"10.1515\/CCLM.2008.284","article-title":"An expert system for the classification of serum protein electrophoresis patterns","volume":"46","author":"S Altinier","year":"2008","journal-title":"Clinical chemistry and laboratory medicine"},{"issue":"1","key":"pone.0273284.ref002","first-page":"105","volume":"71","author":"T O\u2019Connell","year":"2005","journal-title":"Understanding and interpreting the serum protein electrophoresis"},{"issue":"2","key":"pone.0273284.ref003","doi-asserted-by":"crossref","first-page":"C18","DOI":"10.12968\/hmed.2017.78.2.C18","article-title":"Clinical use and interpretation of serum protein electrophoresis and adjunct assays","volume":"78","author":"AY Lee","year":"2017","journal-title":"British journal of hospital medicine (London, England: 2005)"},{"key":"pone.0273284.ref004","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1016\/j.clinbiochem.2017.09.017","article-title":"Peaks and tails: Evaluation of irregularities in capillary serum protein electrophoresis","volume":"51","author":"A Regeniter","year":"2018","journal-title":"Clinical biochemistry"},{"issue":"6","key":"pone.0273284.ref005","doi-asserted-by":"crossref","first-page":"907","DOI":"10.1515\/cclm-2015-0580","article-title":"Laboratory testing requirements for diagnosis and follow-up of multiple myeloma and related plasma cell dyscrasias","volume":"54","author":"MA Willrich","year":"2016","journal-title":"Clinical chemistry and laboratory medicine"},{"issue":"8","key":"pone.0273284.ref006","doi-asserted-by":"crossref","first-page":"1230","DOI":"10.1093\/clinchem\/46.8.1230","article-title":"Understanding and identifying monoclonal gammopathies","volume":"46","author":"M Attaelmannan","year":"2000","journal-title":"Clinical chemistry"},{"issue":"1","key":"pone.0273284.ref007","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3109\/10408367909105852","article-title":"Plasma protein patterns in health and disease","volume":"11","author":"LM Killingsworth","year":"1979","journal-title":"CRC critical reviews in clinical laboratory sciences"},{"issue":"1","key":"pone.0273284.ref008","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1016\/S0272-6386(99)70119-8","article-title":"Role of urine and serum protein electrophoresis in evaluation of nephrotic-range proteinuria","volume":"34","author":"ST Chew","year":"1999","journal-title":"American journal of kidney diseases: the official journal of the National Kidney Foundation"},{"issue":"6","key":"pone.0273284.ref009","doi-asserted-by":"crossref","first-page":"1085","DOI":"10.1515\/cclm-2015-1023","article-title":"Monoclonal antibody therapeutics as potential interferences on protein electrophoresis and immunofixation","volume":"54","author":"MA Willrich","year":"2016","journal-title":"Clinical chemistry and laboratory medicine"},{"issue":"16\u201317","key":"pone.0273284.ref010","doi-asserted-by":"crossref","first-page":"1776","DOI":"10.1016\/j.clinbiochem.2013.07.010","article-title":"Challenges in identifying some IgM monoclonal proteins by capillary serum protein electrophoresis","volume":"46","author":"D Bailey","year":"2013","journal-title":"Clinical biochemistry"},{"key":"pone.0273284.ref011","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1016\/j.clinbiochem.2017.08.013","article-title":"Recognition and management of common, rare, and novel serum protein electrophoresis and immunofixation interferences","volume":"51","author":"CR McCudden","year":"2018","journal-title":"Clinical biochemistry"},{"issue":"6","key":"pone.0273284.ref012","doi-asserted-by":"crossref","first-page":"1095","DOI":"10.1515\/cclm-2015-1031","article-title":"Monitoring multiple myeloma patients treated with daratumumab: teasing out monoclonal antibody interference","volume":"54","author":"C McCudden","year":"2016","journal-title":"Clinical chemistry and laboratory medicine"},{"issue":"8","key":"pone.0273284.ref013","doi-asserted-by":"crossref","first-page":"e179","DOI":"10.1515\/cclm-2018-1121","article-title":"Serum protein electrophoresis and complement deficiencies: a veteran but very versatile test in clinical laboratories","volume":"57","author":"C Franco-Jarava","year":"2019","journal-title":"Clinical chemistry and laboratory medicine"},{"issue":"1","key":"pone.0273284.ref014","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1002\/jcla.21641","article-title":"High false-positive rate for monoclonal gammopathy using capillary electrophoresis (CAPILLARYS 2) alone","volume":"28","author":"RS Huang","year":"2014","journal-title":"Journal of clinical laboratory analysis"},{"issue":"8","key":"pone.0273284.ref015","doi-asserted-by":"crossref","first-page":"1183","DOI":"10.1515\/CCLM.2008.221","article-title":"Computer-assisted detection of monoclonal components: results from the multicenter study for the evaluation of CASPER (Computer Assisted Serum Protein Electrophoresis Recognizer) algorithm","volume":"46","author":"A Ognibene","year":"2008","journal-title":"Clinical chemistry and laboratory medicine"},{"issue":"12","key":"pone.0273284.ref016","doi-asserted-by":"crossref","first-page":"1451","DOI":"10.1515\/CCLM.2004.271","article-title":"Artificial neural network-based algorithm for the evaluation of serum protein capillary electrophoresis","volume":"42","author":"A Ognibene","year":"2004","journal-title":"Clinical chemistry and laboratory medicine"},{"issue":"5","key":"pone.0273284.ref017","first-page":"670","article-title":"Enhancing the Role of the Medical Technologist in Serum Protein Electrophoresis Interpretation: A Pattern Recognition Approach to Identifying Obvious and Potentially Significant Subtle Alterations","volume":"50","author":"SL Strobel","year":"2020","journal-title":"Annals of clinical and laboratory science"},{"key":"pone.0273284.ref018","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"G Litjens","year":"2017","journal-title":"Medical image analysis"},{"issue":"11","key":"pone.0273284.ref019","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1007\/s10916-018-1088-1","article-title":"Medical Image Analysis using Convolutional Neural Networks: A Review","volume":"42","author":"SM Anwar","year":"2018","journal-title":"Journal of medical systems"},{"issue":"1","key":"pone.0273284.ref020","doi-asserted-by":"crossref","first-page":"11399","DOI":"10.1038\/s41598-019-47765-6","article-title":"DeepInsight: A methodology to transform a non-image data to an image for convolution neural network architecture","volume":"9","author":"A Sharma","year":"2019","journal-title":"Scientific reports"},{"issue":"6","key":"pone.0273284.ref021","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbab297","article-title":"DeepFeature: feature selection in nonimage data using convolutional neural network","volume":"22","author":"A Sharma","year":"2021","journal-title":"Briefings in bioinformatics"},{"issue":"Pt 3","key":"pone.0273284.ref022","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1258\/acb.2011.011158","article-title":"Recommendations for standardized reporting of protein electrophoresis in Australia and New Zealand","volume":"49","author":"J Tate","year":"2012","journal-title":"Annals of clinical biochemistry"},{"issue":"24","key":"pone.0273284.ref023","doi-asserted-by":"crossref","first-page":"e171","DOI":"10.3346\/jkms.2020.35.e171","article-title":"Drawing Guidelines for Receiver Operating Characteristic Curve in Preparation of Manuscripts","volume":"35","author":"J Kim","year":"2020","journal-title":"Journal of Korean medical science"},{"key":"pone.0273284.ref024","article-title":"Convolutional Networks with Dense Connectivity","author":"G Huang","year":"2019","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"issue":"3","key":"pone.0273284.ref025","first-page":"211","volume":"115","author":"O Russakovsky","year":"2015","journal-title":"Imagenet large scale visual recognition challenge"},{"key":"pone.0273284.ref026","article-title":"editors. Rethinking the inception architecture for computer vision","author":"C Szegedy","year":"2016","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"pone.0273284.ref027","doi-asserted-by":"crossref","unstructured":"Chollet F, editor Xception: Deep learning with depthwise separable convolutions. Proceedings of the IEEE conference on computer vision and pattern recognition; 2017.","DOI":"10.1109\/CVPR.2017.195"},{"key":"pone.0273284.ref028","article-title":"editors. Learning deep features for discriminative localization","author":"B Zhou","year":"2016","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"issue":"9","key":"pone.0273284.ref029","doi-asserted-by":"crossref","first-page":"e367","DOI":"10.1515\/cclm-2021-0146","article-title":"Use of Neurosoft expert system improves turnaround time in a laboratory section specialized in protein diagnostics: a two-year experience","volume":"59","author":"F Borrillo","year":"2021","journal-title":"Clinical chemistry and laboratory medicine"},{"issue":"10","key":"pone.0273284.ref030","doi-asserted-by":"crossref","first-page":"1406","DOI":"10.1093\/clinchem\/hvab133","article-title":"Achieving Expert-Level Interpretation of Serum Protein Electrophoresis through Deep Learning Driven by Human Reasoning","volume":"67","author":"F Chabrun","year":"2021","journal-title":"Clinical chemistry"},{"issue":"9","key":"pone.0273284.ref031","doi-asserted-by":"crossref","first-page":"1686","DOI":"10.1016\/j.ajpath.2019.05.007","article-title":"Pathology Image Analysis Using Segmentation Deep Learning Algorithms","volume":"189","author":"S Wang","year":"2019","journal-title":"The American journal of pathology"},{"key":"pone.0273284.ref032","doi-asserted-by":"crossref","first-page":"171","DOI":"10.3389\/fncel.2020.00171","article-title":"Convolutional Neural Networks Can Predict Retinal Differentiation in Retinal Organoids","volume":"14","author":"E Kegeles","year":"2020","journal-title":"Frontiers in cellular neuroscience"},{"issue":"45","key":"pone.0273284.ref033","doi-asserted-by":"crossref","first-page":"e23154","DOI":"10.1097\/MD.0000000000023154","article-title":"AML, ALL, and CML classification and diagnosis based on bone marrow cell morphology combined with convolutional neural network: A STARD compliant diagnosis research","volume":"99","author":"F Huang","year":"2020","journal-title":"Medicine"},{"issue":"9","key":"pone.0273284.ref034","doi-asserted-by":"crossref","first-page":"1221","DOI":"10.1001\/jamaoncol.2018.2128","article-title":"Global Burden of Multiple Myeloma: A Systematic Analysis for the Global Burden of Disease Study 2016","volume":"4","author":"AJ Cowan","year":"2018","journal-title":"JAMA oncology"},{"key":"pone.0273284.ref035","doi-asserted-by":"crossref","first-page":"573","DOI":"10.1016\/j.cca.2020.07.051","article-title":"Vertical cutoff methods in serum protein electrophoresis for the measurement of monoclonal protein concentrations: Which is best?","volume":"510","author":"MC C\u00e1rdenas Fern\u00e1ndez","year":"2020","journal-title":"Clinica chimica acta; international journal of clinical chemistry"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0273284","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,24]],"date-time":"2022-08-24T17:33:09Z","timestamp":1661362389000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0273284"}},"subtitle":[],"editor":[{"given":"Swakkhar","family":"Shatabda","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2022,8,24]]},"references-count":35,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2022,8,24]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0273284","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8,24]]}}}