{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T03:57:26Z","timestamp":1760241446045,"version":"build-2065373602"},"reference-count":53,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2018,2,26]],"date-time":"2018-02-26T00:00:00Z","timestamp":1519603200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>Indirect Immuno-Fluorescence (IIF) microscopy imaging of human epithelial (HEp-2) cells is a popular method for diagnosing autoimmune diseases. Considering large data volumes, computer-aided diagnosis (CAD) systems, based on image-based classification, can help in terms of time, effort, and reliability of diagnosis. Such approaches are based on extracting some representative features from the images. This work explores the selection of the most distinctive features for HEp-2 cell images using various feature selection (FS) methods. Considering that there is no single universally optimal feature selection technique, we also propose hybridization of one class of FS methods (filter methods). Furthermore, the notion of variable importance for ranking features, provided by another type of approaches (embedded methods such as Random forest, Random uniform forest) is exploited to select a good subset of features from a large set, such that addition of new features does not increase classification accuracy. In this work, we have also, with great consideration, designed class-specific features to capture morphological visual traits of the cell patterns. We perform various experiments and discussions to demonstrate the effectiveness of FS methods along with proposed and a standard feature set. We achieve state-of-the-art performance even with small number of features, obtained after the feature selection.<\/jats:p>","DOI":"10.3390\/jimaging4030046","type":"journal-article","created":{"date-parts":[[2018,2,27]],"date-time":"2018-02-27T03:36:12Z","timestamp":1519702572000},"page":"46","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Feature Importance for Human Epithelial (HEp-2) Cell Image Classification"],"prefix":"10.3390","volume":"4","author":[{"given":"Vibha","family":"Gupta","sequence":"first","affiliation":[{"name":"School of Computing and Electrical Engineering, Indian Institute of Technology Mandi, Himachal Pradesh-17005, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arnav","family":"Bhavsar","sequence":"additional","affiliation":[{"name":"School of Computing and Electrical Engineering, Indian Institute of Technology Mandi, Himachal Pradesh-17005, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2018,2,26]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"166","DOI":"10.1111\/j.1749-6632.2009.04735.x","article-title":"Autoantibody Detection Using Indirect Immunofluorescence on HEp-2 Cells","volume":"1173","author":"Sack","year":"2009","journal-title":"Ann. N. Y. Acad. Sci."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"324","DOI":"10.4049\/jimmunol.80.4.324","article-title":"Interaction of nuclei and globulin from lupus erythematosis serum demonstrated with fluorescent antibody","volume":"80","author":"Friou","year":"1958","journal-title":"J. Immunol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1878","DOI":"10.1109\/TMI.2013.2268163","article-title":"Benchmarking HEp-2 cells classification methods","volume":"32","author":"Foggia","year":"2013","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1016\/j.jaut.2010.06.019","article-title":"Antinuclear antibodies: A contemporary nomenclature using HEp-2 cells","volume":"35","author":"Wiik","year":"2010","journal-title":"J. Autoimmun."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1746-1596-4-1","article-title":"Antinuclear antibodies and their detection methods in diagnosis of connective tissue diseases: A journey revisited","volume":"4","author":"Kumar","year":"2009","journal-title":"Diagn. Pathol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1016\/j.artmed.2015.08.001","article-title":"Benchmarking human epithelial type 2 interphase cells classification methods on a very large dataset","volume":"65","author":"Hobson","year":"2015","journal-title":"Artif. Intell. Med."},{"key":"ref_7","unstructured":"Hobson, P., Percannella, G., Vento, M., and Wiliem, A. (2013, January 15\u201318). Competition on cells classification by fluorescent image analysis. Proceedings of the 20th IEEE International Conference on Image Processing (ICIP), Melbourne, Australia."},{"key":"ref_8","unstructured":"Bradwell, A., Hughes, R.S., and Harden, E. (1995). Atlas of Hep-2 Patterns and Laboratory Techniques, Binding Site."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Foggia, P., Percannella, G., Soda, P., and Vento, M. (2010, January 12\u201315). Early experiences in mitotic cells recognition on HEp-2 slides. Proceedings of the 2010 IEEE 23rd International Symposium on Computer-Based Medical Systems (CBMS), Perth, Australia.","DOI":"10.1109\/CBMS.2010.6042611"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1016\/j.patrec.2014.03.011","article-title":"Mitotic cells recognition in HEp-2 images","volume":"45","author":"Iannello","year":"2014","journal-title":"Pattern Recognit. Lett."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Ensafi, S., Lu, S., Kassim, A.A., and Tan, C.L. (2014, January 24). A bag of words based approach for classification of hep-2 cell images. Proceedings of the 2014 1st Workshop on Pattern Recognition Techniques for Indirect Immunofluorescence Images (I3A), Stockholm, Sweden.","DOI":"10.1109\/I3A.2014.12"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"2409","DOI":"10.1016\/j.patcog.2013.09.021","article-title":"Efficient k-NN based HEp-2 cells classifier","volume":"47","author":"Stoklasa","year":"2014","journal-title":"Pattern Recognit."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Gupta, V., Gupta, K., Bhavsar, A., and Sao, A.K. (2016, January 25\u201327). Hierarchical classification of HEp-2 cell images using class-specific features. Proceedings of the European Workshop on Visual Information Processing (EUVIP 2016), Marseille, France.","DOI":"10.1109\/EUVIP.2016.7764585"},{"key":"ref_14","unstructured":"Strandmark, P., Ul\u00e9n, J., and Kahl, F. (2012, January 11\u201315). Hep-2 staining pattern classification. Proceedings of the 2012 21st International Conference on Pattern Recognition (ICPR), Tsukuba, Japan."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1016\/S0004-3702(97)00063-5","article-title":"Selection of relevant features and examples in machine learning","volume":"97","author":"Blum","year":"1997","journal-title":"Artif. Intell."},{"key":"ref_16","first-page":"1371","article-title":"Overfitting in making comparisons between variable selection methods","volume":"3","author":"Reunanen","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref_17","unstructured":"Liu, H., and Setiono, R. (1995, January 5\u20138). Chi2: Feature selection and discretization of numeric attributes. Proceedings of the Seventh International Conference on Tools with Artificial Intelligence, Herndon, VA, USA."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1100","DOI":"10.1109\/T-C.1971.223410","article-title":"A direct method of nonparametric measurement selection","volume":"100","author":"Whitney","year":"1971","journal-title":"IEEE Trans. Comput."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Roffo, G., Melzi, S., and Cristani, M. (2015, January 7\u201313). Infinite Feature Selection. Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), Washington, DC, USA.","DOI":"10.1109\/ICCV.2015.478"},{"key":"ref_21","unstructured":"Yang, Y., Shen, H.T., Ma, Z., Huang, Z., and Zhou, X. (2011, January 16\u201322). L2,1-norm Regularized Discriminative Feature Selection for Unsupervised Learning. Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence (IJCAI\u201911)\u2014Volume Volume Two, Barcelona, Spain."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Cai, D., Zhang, C., and He, X. (2010, January 24\u201328). Unsupervised feature selection for multi-cluster data. Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Washington, DC, USA.","DOI":"10.1145\/1835804.1835848"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1084","DOI":"10.1093\/bioinformatics\/bti108","article-title":"Identifying differentially expressed genes from microarray experiments via statistic synthesis","volume":"21","author":"Yang","year":"2004","journal-title":"Bioinformatics"},{"key":"ref_24","unstructured":"Ciss, S. (2015). Variable Importance in Random Uniform Forests."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"922","DOI":"10.1007\/978-3-319-60964-5_80","article-title":"Random Forest-Based Feature Importance for HEp-2 Cell Image Classification","volume":"Volume 723","author":"Gupta","year":"2017","journal-title":"Proceedings of the Annual Conference on Medical Image Understanding and Analysis"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1016\/S0933-3657(02)00057-X","article-title":"Mining knowledge for HEp-2 cell image classification","volume":"26","author":"Perner","year":"2002","journal-title":"Artif. Intell. Med."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Huang, Y.C., Hsieh, T.Y., Chang, C.Y., Cheng, W.T., Lin, Y.C., and Huang, Y.L. (2012, January 19\u201321). HEp-2 cell images classification based on textural and statistic features using self-organizing map. Proceedings of the Asian Conference on Intelligent Information and Database Systems, Kaohsiung, Taiwan.","DOI":"10.1007\/978-3-642-28490-8_55"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Hsieh, T.Y., Huang, Y.C., Chung, C.W., and Huang, Y.L. (2009, January 8\u201310). HEp-2 cell classification in indirect immunofluorescence images. Proceedings of the 7th International Conference on Information, Communications and Signal Processing ( ICICS), Macau, China.","DOI":"10.1109\/ICICS.2009.5397624"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"2305","DOI":"10.1016\/j.patcog.2014.01.010","article-title":"Pattern recognition in stained HEp-2 cells: Where are we now?","volume":"47","author":"Foggia","year":"2014","journal-title":"Pattern Recognit."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Prasath, V., Kassim, Y., Oraibi, Z.A., Guiriec, J.B., Hafiane, A., Seetharaman, G., and Palaniappan, K. (2016, January 4\u20138). HEp-2 cell classification and segmentation using motif texture patterns and spatial features with random forests. Proceedings of the 23th International Conference on Pattern Recognition (ICPR), Cancun, Mexico.","DOI":"10.1109\/ICPR.2016.7899614"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Li, B.H., Zhang, J., and Zheng, W.S. (2015, January 3\u20136). HEp-2 cells staining patterns classification via wavelet scattering network and random forest. Proceedings of the 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR), Kuala Lumpur, Malaysia.","DOI":"10.1109\/ACPR.2015.7486535"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Agrawal, P., Vatsa, M., and Singh, R. (2013, January 22). HEp-2 cell image classification: A comparative analysis. Proceedings of the International Workshop on Machine Learning in Medical Imaging, Nagoya, Japan.","DOI":"10.1007\/978-3-319-02267-3_25"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1016\/j.patcog.2015.09.015","article-title":"An automated pattern recognition system for classifying indirect immunofluorescence images of HEp-2 cells and specimens","volume":"51","author":"Manivannan","year":"2016","journal-title":"Pattern Recognit."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Gao, Z., Wang, L., Zhou, L., and Zhang, J. (arXiv, 2015). Hep-2 cell image classification with deep convolutional neural networks, arXiv.","DOI":"10.1109\/I3A.2014.15"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1016\/j.patrec.2016.07.013","article-title":"HEp-2 staining pattern recognition at cell and specimen levels: Datasets, algorithms and results","volume":"82","author":"Hobson","year":"2016","journal-title":"Pattern Recognit. Lett."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.patrec.2016.06.013","article-title":"Computer aided diagnosis for anti-nuclear antibodies HEp-2 images: progress and challenges","volume":"82","author":"Hobson","year":"2016","journal-title":"Pattern Recognit. Lett."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Gragnaniello, D., Sansone, C., and Verdoliva, L. (2014, January 24). Biologically-inspired dense local descriptor for indirect immunofluorescence image classification. Proceedings of the 2014 1st Workshop on Pattern Recognition Techniques for Indirect Immunofluorescence Images (I3A), Stockholm, Sweden.","DOI":"10.1109\/I3A.2014.19"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Moorthy, K., and Mohamad, M.S. (2012). Random forest for gene selection and microarray data classification. Knowledge Technology, Springer.","DOI":"10.1007\/978-3-642-32826-8_18"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Paul, A., Dey, A., Mukherjee, D.P., Sivaswamy, J., and Tourani, V. (2015, January 5\u20139). Regenerative Random Forest with Automatic Feature Selection to Detect Mitosis in Histopathological Breast Cancer Images. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany.","DOI":"10.1007\/978-3-319-24571-3_12"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"551","DOI":"10.4236\/jbise.2013.65070","article-title":"Random forest classifier combined with feature selection for breast cancer diagnosis and prognostic","volume":"6","author":"Nguyen","year":"2013","journal-title":"J. Biomed. Sci. Eng."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Hariharan, S., Tirodkar, S., De, S., and Bhattacharya, A. (2014, January 13\u201318). Variable importance and random forest classification using RADARSAT-2 PolSAR data. Proceedings of the 2014 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Quebec City, QC, Canada.","DOI":"10.1109\/IGARSS.2014.6946649"},{"key":"ref_42","first-page":"1157","article-title":"An introduction to variable and feature selection","volume":"3","author":"Guyon","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1016\/j.compeleceng.2013.11.024","article-title":"A survey on feature selection methods","volume":"40","author":"Chandrashekar","year":"2014","journal-title":"Comput. Electr. Eng."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"258","DOI":"10.1016\/j.dss.2010.08.028","article-title":"Combining multiple feature selection methods for stock prediction: Union, intersection, and multi-intersection approaches","volume":"50","author":"Tsai","year":"2010","journal-title":"Decis. Support Syst."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Al-Thubaity, A., Abanumay, N., Al-Jerayyed, S., Alrukban, A., and Mannaa, Z. (2013, January 1\u20133). The effect of combining different feature selection methods on arabic text classification. Proceedings of the 2013 14th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel\/Distributed Computing (SNPD), Honolulu, HI, USA.","DOI":"10.1109\/SNPD.2013.89"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2017\/9838169","article-title":"New Hybrid Features Selection Method: A Case Study on Websites Phishing","volume":"2017","author":"Rajab","year":"2017","journal-title":"Secur. Commun. Netw."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1016\/j.csl.2013.11.004","article-title":"Feature selection methods and their combinations in high- dimensional classification of speaker likability, intelligibility and personality traits","volume":"29","author":"Pohjalainen","year":"2015","journal-title":"Comput. Speech Lang."},{"key":"ref_48","unstructured":"Doan, S., and Horiguchi, S. (2004, January 5\u20138). An efficient feature selection using multi-criteria in text categorization. Proceedings of the 2004 Fourth International Conference on Hybrid Intelligent Systems (HIS\u201904), Kitakyushu, Japan."},{"key":"ref_49","unstructured":"Cover, T.M., and Thomas, J.A. (1991). Elements of Information Theory, Wiley."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"R\u00e4s\u00e4nen, O., and Pohjalainen, J. (2013, January 25\u201329). Random subset feature selection in automatic recognition of developmental disorders, affective states, and level of conflict from speech. Proceedings of the INTERSPEECH, Lyon, France.","DOI":"10.21437\/Interspeech.2013-69"},{"key":"ref_51","unstructured":"Strobl, C., and Zeileis, A. (2018, February 14). Danger: High power!\u2014Exploring the Statistical Properties of a Test for Random Forest Variable Importance. Available online: https:\/\/epub.ub.uni-muenchen.de\/2111\/."},{"key":"ref_52","unstructured":"Segal, M.R. (2004). Machine Learning Benchmarks and Random Forest Regression, Center for Bioinformatics & Molecular Biostatistics."},{"key":"ref_53","unstructured":"Liu, H., and Motoda, H. (2012). Feature Selection for Knowledge Discovery and Data Mining, Springer Science & Business Media."}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/4\/3\/46\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T14:56:32Z","timestamp":1760194592000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/4\/3\/46"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,2,26]]},"references-count":53,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2018,3]]}},"alternative-id":["jimaging4030046"],"URL":"https:\/\/doi.org\/10.3390\/jimaging4030046","relation":{},"ISSN":["2313-433X"],"issn-type":[{"type":"electronic","value":"2313-433X"}],"subject":[],"published":{"date-parts":[[2018,2,26]]}}}