{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T17:08:02Z","timestamp":1778778482253,"version":"3.51.4"},"reference-count":47,"publisher":"IOP Publishing","issue":"1","license":[{"start":{"date-parts":[[2022,12,21]],"date-time":"2022-12-21T00:00:00Z","timestamp":1671580800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2022,12,21]],"date-time":"2022-12-21T00:00:00Z","timestamp":1671580800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100007065","name":"Nvidia","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100007065","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"crossref","award":["R01DK128120201"],"award-info":[{"award-number":["R01DK128120201"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Brain Tumor SPORE","award":["P50CA127001-07"],"award-info":[{"award-number":["P50CA127001-07"]}]},{"DOI":"10.13039\/100007270","name":"University of Michigan","doi-asserted-by":"crossref","award":["PODS Grant"],"award-info":[{"award-number":["PODS Grant"]}],"id":[{"id":"10.13039\/100007270","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100007313","name":"University of Texas MD Anderson Cancer Center","doi-asserted-by":"crossref","award":["Institutional Research Grant"],"award-info":[{"award-number":["Institutional Research Grant"]}],"id":[{"id":"10.13039\/100007313","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Center for Radiation Oncology","award":["Research Pilot Grant"],"award-info":[{"award-number":["Research Pilot Grant"]}]},{"name":"National Cancer Institute","award":["R37-CA214955"],"award-info":[{"award-number":["R37-CA214955"]}]},{"DOI":"10.13039\/100000048","name":"American Cancer Society","doi-asserted-by":"crossref","award":["RSG-16-005-01"],"award-info":[{"award-number":["RSG-16-005-01"]}],"id":[{"id":"10.13039\/100000048","id-type":"DOI","asserted-by":"crossref"}]},{"name":"NCI","award":["P30 CA016672"],"award-info":[{"award-number":["P30 CA016672"]}]},{"name":"CCSG Bioinformatics Shared Resource 5","award":["P30 CA046592"],"award-info":[{"award-number":["P30 CA046592"]}]},{"name":"Agilent Technologies"},{"name":"Center for Radiation Oncology","award":["Research Pilot Grant"],"award-info":[{"award-number":["Research Pilot Grant"]}]},{"name":"NIH NCI U01","award":["CA196403"],"award-info":[{"award-number":["CA196403"]}]},{"DOI":"10.13039\/100004917","name":"Cancer Prevention and Research Institute of Texas","doi-asserted-by":"crossref","award":["RP110532"],"award-info":[{"award-number":["RP110532"]}],"id":[{"id":"10.13039\/100004917","id-type":"DOI","asserted-by":"crossref"}]},{"name":"University of Michigan Precision Health"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Phys. Med. Biol."],"published-print":{"date-parts":[[2023,1,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    <jats:italic>Objective.<\/jats:italic>\n                    Histology image analysis is a crucial diagnostic step in staging and treatment planning, especially for cancerous lesions. With the increasing adoption of computational methods for image analysis, significant strides are being made to improve the performance metrics of image segmentation and classification frameworks. However, many developed frameworks effectively function as black boxes, granting minimal context to the decision-making process. Thus, there is a need to develop methods that offer reasonable discriminatory power and a biologically-informed intuition to the decision-making process.\n                    <jats:italic>Approach.<\/jats:italic>\n                    In this study, we utilized and modified a discriminative feature-based dictionary learning (DFDL) paradigm to generate a classification framework that allows for discrimination between two distinct clinical histologies. This framework allows us (i) to discriminate between 2 clinically distinct diseases or histologies and (ii) provides interpretable group-specific representative dictionary image patches, or \u2018atoms\u2019, generated during classifier training. This implementation is performed on multiplexed immunofluorescence images from two separate patient cohorts- a pancreatic cohort consisting of cancerous and non-cancerous tissues and a metastatic non-small cell lung cancer (mNSCLC) cohort of responders and non-responders to an immunotherapeutic treatment regimen. The analysis was done at both the image-level and subject-level. Five cell types were selected, namely, epithelial cells, cytotoxic lymphocytes, antigen presenting cells, HelperT cells, and T-regulatory cells, as our phenotypes of interest.\n                    <jats:italic>Results.<\/jats:italic>\n                    We showed that DFDL had significant discriminant capabilities for both the pancreatic pathologies cohort (subject-level AUC-0.8878) and the mNSCLC immunotherapy response cohort (subject-level AUC-0.7221). The secondary analysis also showed that more than 50% of the obtained dictionary atoms from the classifier contained biologically relevant information.\n                    <jats:italic>Significance.<\/jats:italic>\n                    Our method shows that the generated dictionary features can help distinguish patients presenting two different histologies with strong sensitivity and specificity metrics. These features allow for an additional layer of model interpretability, a highly desirable element in clinical applications for identifying novel biological phenomena.\n                  <\/jats:p>","DOI":"10.1088\/1361-6560\/aca86a","type":"journal-article","created":{"date-parts":[[2022,12,2]],"date-time":"2022-12-02T17:36:05Z","timestamp":1670002565000},"page":"014002","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Towards the characterization of the tumor microenvironment through dictionary learning-based interpretable classification of multiplexed immunofluorescence images"],"prefix":"10.1088","volume":"68","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5114-9778","authenticated-orcid":false,"given":"Santhoshi N","family":"Krishnan","sequence":"first","affiliation":[{"name":"Rice University"},{"name":"University of Michigan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1675-8874","authenticated-orcid":false,"given":"Souptik","family":"Barua","sequence":"additional","affiliation":[{"name":"Rice University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Timothy L","family":"Frankel","sequence":"additional","affiliation":[{"name":"University of Michigan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arvind","family":"Rao","sequence":"additional","affiliation":[{"name":"Rice University"},{"name":"University of Michigan"},{"name":"University of Michigan"},{"name":"University of Michigan"},{"name":"University of Michigan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2022,12,21]]},"reference":[{"key":"pmbaca86abib1","doi-asserted-by":"publisher","first-page":"4311","DOI":"10.1109\/TSP.2006.881199","type":"journal-article","article-title":"RMK-SVD: An algorithm for designing overcomplete dictionaries for sparse representation","volume":"54","author":"Aharon","year":"2006","journal-title":"IEEE Trans. Signal Process."},{"key":"pmbaca86abib2","doi-asserted-by":"publisher","DOI":"10.1109\/icip.2014.7025561","type":"other","article-title":"Brain tumor classification using sparse coding and dictionary learning","author":"Al-Shaikhli","year":"2014"},{"key":"pmbaca86abib3","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1038\/s41568-018-0081-9","type":"journal-article","article-title":"The lung microenvironment: an important regulator of tumour growth and metastasis","volume":"19","author":"Altorki","year":"2018","journal-title":"Nat. Rev. Cancer"},{"key":"pmbaca86abib4","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1016\/j.bspc.2019.04.032","type":"journal-article","article-title":"Integrating imaging and OMICS DATA: a review","volume":"52","author":"Antonelli","year":"2019","journal-title":"Biomed. Signal Process. Control"},{"key":"pmbaca86abib5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v012.i06","type":"journal-article","article-title":"spatstat: an R package for analyzing spatial point patterns","volume":"12","author":"Baddeley","year":"2005","journal-title":"J. Statistical Software"},{"key":"pmbaca86abib6","doi-asserted-by":"publisher","DOI":"10.1109\/wacv.2016.7477561","type":"other","article-title":"Direct face detection and video reconstruction from event cameras","author":"Barua","year":"2016"},{"key":"pmbaca86abib7","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1016\/j.lungcan.2018.01.022","type":"journal-article","article-title":"Spatial interaction of tumor cells and regulatory T cells correlates with survival in non-small cell lung cancer","volume":"117","author":"Barua","year":"2018","journal-title":"Lung Cancer"},{"key":"pmbaca86abib8","doi-asserted-by":"publisher","DOI":"10.1177\/1176935118782880","type":"journal-article","article-title":"A functional spatial analysis platform for discovery of immunological interactions predictive of low-grade to high-grade transition of pancreatic intraductal papillary mucinous neoplasms","volume":"17","author":"Barua","year":"2018","journal-title":"Cancer Informatics"},{"key":"pmbaca86abib9","doi-asserted-by":"publisher","first-page":"687","DOI":"10.1126\/science.1198704","type":"journal-article","article-title":"Single-cell mass cytometry of differential immune and drug responses across a human hematopoietic continuum","volume":"332","author":"Bendall","year":"2011","journal-title":"Science"},{"key":"pmbaca86abib10","article-title":"pracma: Practical Numerical Math Functions. R package version 2.3.3","author":"Borchers","year":"2021","type":"journal-article"},{"key":"pmbaca86abib11","doi-asserted-by":"publisher","first-page":"1145","DOI":"10.1016\/S0031-3203(96)00142-2","type":"journal-article","article-title":"The use of the area under the ROC curve in the evaluation of machine learning algorithms","volume":"30","author":"Bradley","year":"1997","journal-title":"Pattern Recognit."},{"key":"pmbaca86abib12","article-title":"Data-driven representation learning from histopathology image databases to support digital pathology analysis","author":"Cruz","year":"2015","type":"other"},{"key":"pmbaca86abib13","doi-asserted-by":"publisher","first-page":"138","DOI":"10.2307\/2347366","type":"journal-article","article-title":"A kernel method for smoothing point process data","volume":"34","author":"Diggle","year":"1985","journal-title":"Appl. Stat."},{"key":"pmbaca86abib14","author":"Everitt","year":"2011","type":"book"},{"key":"pmbaca86abib15","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1186\/s13000-020-01003-0","type":"journal-article","article-title":"Deep learning-based image analysis methods for Brightfield-acquired multiplex immunohistochemistry images","volume":"15","author":"Fassler","year":"2020","journal-title":"Diagnostic Pathology"},{"key":"pmbaca86abib16","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2018.01044","type":"journal-article","article-title":"Pancreatic ductal adenocarcinoma: A strong imbalance of good and bad immunological cops in the tumor microenvironment","volume":"9","author":"Foucher","year":"2018","journal-title":"Frontiers Immunology"},{"key":"pmbaca86abib17","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1186\/s13045-021-01103-4","type":"journal-article","article-title":"Spatial architecture of the immune microenvironment orchestrates tumor immunity and therapeutic response","volume":"14","author":"Fu","year":"2021","journal-title":"J. Hematology amp; Oncol."},{"key":"pmbaca86abib18","doi-asserted-by":"publisher","first-page":"2078","DOI":"10.1056\/NEJMoa1801005","type":"journal-article","article-title":"Pembrolizumab plus chemotherapy in metastatic non-small-cell lung cancer","volume":"378","author":"Gandhi","year":"2018","journal-title":"New Engl. J. Med."},{"key":"pmbaca86abib19","author":"Hainmueller","year":"2017","journal-title":"KRLS: Kernel-Based Regularized Least Squares. R package version 1.0-0","type":"journal-article"},{"key":"pmbaca86abib20","doi-asserted-by":"publisher","first-page":"757","DOI":"10.1016\/j.celrep.2017.06.079","type":"report","article-title":"An atlas of human regulatory T helper-like cells reveals features of th2-like Tregs that support a tumorigenic environment","author":"Halim","year":"2017"},{"key":"pmbaca86abib21","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1038\/labinvest.2014.155","type":"journal-article","article-title":"Mapping spatial heterogeneity in the tumor microenvironment: A new era for digital pathology","volume":"95","author":"Heindl","year":"2015","journal-title":"Lab. Invest."},{"key":"pmbaca86abib22","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-06602-z","type":"journal-article","article-title":"GaWRDenMap: A quantitative framework to study the local variation in cell-cell interactions in pancreatic disease subtypes","volume":"12","author":"Krishnan","year":"2022","journal-title":"Sci. Rep."},{"key":"pmbaca86abib23","doi-asserted-by":"publisher","first-page":"2821","DOI":"10.1245\/s10434-019-07508-3","type":"journal-article","article-title":"Mathematical modeling of the metastatic colorectal cancer microenvironment defines the importance of cytotoxic lymphocyte infiltration and presence of PD-L1 on antigen presenting cells","volume":"26","author":"Lazarus","year":"2019","journal-title":"Ann Surg. Oncol."},{"key":"pmbaca86abib24","doi-asserted-by":"publisher","first-page":"e121932","DOI":"10.1172\/jci.insight.121932","type":"journal-article","article-title":"Spatial and phenotypic immune profiling of metastatic colon cancer","volume":"3","author":"Lazarus","year":"2018","journal-title":"JCI Insight"},{"key":"pmbaca86abib25","doi-asserted-by":"publisher","first-page":"7","DOI":"10.2217\/iim.09.9","type":"journal-article","article-title":"Digital pathology image analysis: opportunities and challenges","volume":"1","author":"Madabhushi","year":"2009","journal-title":"Imaging in Medicine"},{"key":"pmbaca86abib26","type":"other"},{"key":"pmbaca86abib27","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1158\/1078-0432.CCR-14-0990","type":"journal-article","article-title":"Imaging intratumor heterogeneity: Role in therapy response, resistance, and clinical outcome","volume":"21","author":"O\u2019Connor","year":"2014","journal-title":"Clin. Cancer Res."},{"key":"pmbaca86abib28","type":"web-resource"},{"key":"pmbaca86abib29","type":"web-resource"},{"key":"pmbaca86abib30","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2010.5539964","type":"other","article-title":"Classification and clustering via dictionary learning with structured incoherence and shared features","author":"Ramirez","year":"2010"},{"key":"pmbaca86abib31","doi-asserted-by":"publisher","first-page":"1823","DOI":"10.1056\/NEJMoa1606774","type":"journal-article","article-title":"Pembrolizumab versus chemotherapy for PD-L1-positive non-small-cell lung cancer","volume":"375","author":"Reck","year":"2016","journal-title":"New Engl. J. Med."},{"key":"pmbaca86abib32","doi-asserted-by":"publisher","DOI":"10.1117\/12.2043935","type":"other","article-title":"A discriminant multi-scale histopathology descriptor using dictionary learning","author":"Romo","year":"2014"},{"key":"pmbaca86abib33","type":"web-resource"},{"key":"pmbaca86abib34","doi-asserted-by":"publisher","DOI":"10.1109\/i2ct42659.2018.9058133","type":"other","article-title":"Sparse representation based class level dictionary learning approach for Histopathology Image Classification","author":"Shirale","year":"2018"},{"key":"pmbaca86abib35","type":"web-resource"},{"key":"pmbaca86abib36","doi-asserted-by":"publisher","DOI":"10.1109\/isbi.2013.6556675","type":"other","article-title":"Shirc: A simultaneous sparsity model for histopathological image representation and classification","author":"Srinivas","year":"2013"},{"key":"pmbaca86abib37","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/bs.mie.2019.07.039","type":"journal-article","article-title":"Characterization of the immune microenvironment of NSCLC by Multispectral Analysis of multiplex immunofluorescence images","volume":"635","author":"Surace","year":"2020","journal-title":"Methods Enzymol."},{"key":"pmbaca86abib38","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1002\/cac2.12023","type":"journal-article","article-title":"Overview of multiplex immunohistochemistry\/ immunofluorescence techniques in the era of cancer immunotherapy","volume":"40","author":"Tan","year":"2020","journal-title":"Cancer Commun."},{"key":"pmbaca86abib39","type":"journal-article","article-title":"tseries: time series analysis and computational finance","author":"Trapletti","year":"2022","journal-title":"R package version 0.10-50"},{"key":"pmbaca86abib40","doi-asserted-by":"publisher","first-page":"5160","DOI":"10.1109\/TIP.2017.2729885","type":"journal-article","article-title":"Fast low-rank shared dictionary learning for image classification","volume":"26","author":"Vu","year":"2017","journal-title":"IEEE Trans. Image Process."},{"key":"pmbaca86abib41","doi-asserted-by":"publisher","DOI":"10.1109\/isbi.2015.7164037","type":"other","article-title":"DFDL: Discriminative feature-oriented dictionary learning for Histopathological Image Classification","author":"Vu","year":"2015"},{"key":"pmbaca86abib42","doi-asserted-by":"publisher","first-page":"738","DOI":"10.1109\/TMI.2015.2493530","type":"journal-article","article-title":"Histopathological image classification using discriminative feature-oriented dictionary learning","volume":"35","author":"Vu","year":"2016","journal-title":"IEEE Trans. Med. Imaging"},{"key":"pmbaca86abib43","author":"Whittaker","year":"2009","type":"book"},{"key":"pmbaca86abib44","author":"Wiegand","year":"2014","type":"book"},{"key":"pmbaca86abib45","doi-asserted-by":"publisher","first-page":"157ra143","DOI":"10.1126\/scitranslmed.3004330","type":"journal-article","article-title":"Quantitative image analysis of cellular heterogeneity in breast tumors complements genomic profiling","volume":"4","author":"Yuan","year":"2012","journal-title":"Sci. Transl. Med."},{"key":"pmbaca86abib46","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1007\/s11831-019-09383-3","type":"journal-article","article-title":"A survey of dictionary learning in Medical Image Analysis and its application for glaucoma diagnosis","volume":"28","author":"Zhao","year":"2019","journal-title":"Arch. Comput. Meth. Eng."},{"key":"pmbaca86abib47","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1016\/j.jvcir.2018.06.001","type":"journal-article","article-title":"Multiple disjoint dictionaries for representation of histopathology images","volume":"55","author":"Zhu","year":"2018","journal-title":"J. Visual Commun. Image Represent."}],"container-title":["Physics in Medicine &amp; Biology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aca86a","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aca86a\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aca86a","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aca86a\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aca86a\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aca86a\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aca86a\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aca86a\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T16:11:25Z","timestamp":1778775085000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aca86a"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,21]]},"references-count":47,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,12,21]]},"published-print":{"date-parts":[[2023,1,7]]}},"URL":"https:\/\/doi.org\/10.1088\/1361-6560\/aca86a","relation":{},"ISSN":["0031-9155","1361-6560"],"issn-type":[{"value":"0031-9155","type":"print"},{"value":"1361-6560","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,21]]},"assertion":[{"value":"Towards the characterization of the tumor microenvironment through dictionary learning-based interpretable classification of multiplexed immunofluorescence images","name":"article_title","label":"Article Title"},{"value":"Physics in Medicine & Biology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2022 The Author(s). Published on behalf of Institute of Physics and Engineering in Medicine by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2022-06-01","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2022-12-02","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2022-12-21","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}