{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T17:18:29Z","timestamp":1769879909309,"version":"3.49.0"},"reference-count":42,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2021,6,10]],"date-time":"2021-06-10T00:00:00Z","timestamp":1623283200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The early detection of melanoma is the most efficient way to reduce its mortality rate. Dermatologists achieve this task with the help of dermoscopy, a non-invasive tool allowing the visualization of patterns of skin lesions. Computer-aided diagnosis (CAD) systems developed on dermoscopic images are needed to assist dermatologists. These systems rely mainly on multiclass classification approaches. However, the multiclass classification of skin lesions by an automated system remains a challenging task. Decomposing a multiclass problem into a binary problem can reduce the complexity of the initial problem and increase the overall performance. This paper proposes a CAD system to classify dermoscopic images into three diagnosis classes: melanoma, nevi, and seborrheic keratosis. We introduce a novel ensemble scheme of convolutional neural networks (CNNs), inspired by decomposition and ensemble methods, to improve the performance of the CAD system. Unlike conventional ensemble methods, we use a directed acyclic graph to aggregate binary CNNs for the melanoma detection task. On the ISIC 2018 public dataset, our method achieves the best balanced accuracy (76.6%) among multiclass CNNs, an ensemble of multiclass CNNs with classical aggregation methods, and other related works. Our results reveal that the directed acyclic graph is a meaningful approach to develop a reliable and robust automated diagnosis system for the multiclass classification of dermoscopic images.<\/jats:p>","DOI":"10.3390\/s21123999","type":"journal-article","created":{"date-parts":[[2021,6,9]],"date-time":"2021-06-09T22:18:29Z","timestamp":1623277109000},"page":"3999","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":26,"title":["Ensemble Method of Convolutional Neural Networks with Directed Acyclic Graph Using Dermoscopic Images: Melanoma Detection Application"],"prefix":"10.3390","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3897-5693","authenticated-orcid":false,"given":"Arthur Cartel","family":"Foahom Gouabou","sequence":"first","affiliation":[{"name":"Laboratoire d\u2019Informatique et Syst\u00e8mes, Aix-Marseille University, 163 Avenue de Luminy, CEDEX 09, 13288 Marseille, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1875-7111","authenticated-orcid":false,"given":"Jean-Luc","family":"Damoiseaux","sequence":"additional","affiliation":[{"name":"Laboratoire d\u2019Informatique et Syst\u00e8mes, Aix-Marseille University, 163 Avenue de Luminy, CEDEX 09, 13288 Marseille, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8747-5011","authenticated-orcid":false,"given":"Jilliana","family":"Monnier","sequence":"additional","affiliation":[{"name":"Laboratoire d\u2019Informatique et Syst\u00e8mes, Aix-Marseille University, 163 Avenue de Luminy, CEDEX 09, 13288 Marseille, France"},{"name":"Centre de Recherche en Cancerologie de Marseille (CRCM), 27 Boulevard Lei Roure, 13009 Marseille, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1728-3532","authenticated-orcid":false,"given":"Rabah","family":"Iguernaissi","sequence":"additional","affiliation":[{"name":"Laboratoire d\u2019Informatique et Syst\u00e8mes, Aix-Marseille University, 163 Avenue de Luminy, CEDEX 09, 13288 Marseille, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abdellatif","family":"Moudafi","sequence":"additional","affiliation":[{"name":"Laboratoire d\u2019Informatique et Syst\u00e8mes, Aix-Marseille University, 163 Avenue de Luminy, CEDEX 09, 13288 Marseille, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9233-0020","authenticated-orcid":false,"given":"Djamal","family":"Merad","sequence":"additional","affiliation":[{"name":"Laboratoire d\u2019Informatique et Syst\u00e8mes, Aix-Marseille University, 163 Avenue de Luminy, CEDEX 09, 13288 Marseille, France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2021,6,10]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Leiter, U., Keim, U., and Garbe, C. (2020). Epidemiology of skin cancer: Update 2019. Sunlight, Vitamin D and Skin Cancer, Springer.","DOI":"10.1007\/978-3-030-46227-7_6"},{"key":"ref_2","first-page":"1397","article-title":"Early detection of melanoma. Discussing a new approach","volume":"57","author":"Grob","year":"2007","journal-title":"Rev. Prat."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1556","DOI":"10.1001\/archderm.138.12.1556","article-title":"Dermoscopy of pigmented seborrheic keratosis: A morphological study","volume":"138","author":"Braun","year":"2002","journal-title":"Arch. Dermatol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1068","DOI":"10.1016\/j.jaad.2010.03.039","article-title":"Diagnostic accuracy of dermatoscopy for melanocytic and nonmelanocytic pigmented lesions","volume":"64","author":"Rosendahl","year":"2011","journal-title":"J. Am. Acad. Dermatol."},{"key":"ref_5","unstructured":"Codella, N., Rotemberg, V., Tschandl, P., Celebi, M.E., Dusza, S., Gutman, D., Helba, B., Kalloo, A., Liopyris, K., and Marchetti, M. (2019). Skin lesion analysis toward melanoma detection 2018: A challenge hosted by the international skin imaging collaboration (isic). arXiv."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1001\/jamadermatol.2016.5500","article-title":"Ugly duckling sign as a major factor of efficiency in melanoma detection","volume":"153","author":"Wazaefi","year":"2017","journal-title":"JAMA Dermatol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1158","DOI":"10.1016\/j.jaad.2019.12.063","article-title":"Meta-analysis of number needed to treat for diagnosis of melanoma by clinical setting","volume":"82","author":"Petty","year":"2020","journal-title":"J. Am. Acad. Dermatol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"409","DOI":"10.1016\/j.det.2017.06.001","article-title":"Clinical Diagnosis of Skin Cancer: Enhancing Inspection and Early Recognition","volume":"35","author":"Glazer","year":"2017","journal-title":"Dermatol. Clin."},{"key":"ref_9","unstructured":"Mullani, N.A. (2006). Dermoscopy Epiluminescence Device Employing cross and Parallel Polarization. (7,006,223), U.S. Patent."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1016\/S1470-2045(00)00422-8","article-title":"Dermoscopy of pigmented skin lesions\u2014A valuable tool for early","volume":"2","author":"Argenziano","year":"2001","journal-title":"Lancet Oncol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1211","DOI":"10.1001\/archderm.142.9.1211","article-title":"Why perform dermoscopy? The evidence for its role in the routine management of pigmented skin lesions","volume":"142","author":"Menzies","year":"2006","journal-title":"Arch. Dermatol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"717","DOI":"10.1016\/j.jaad.2015.01.025","article-title":"Early detection of melanoma: Reviewing the ABCDEs","volume":"72","author":"Tsao","year":"2015","journal-title":"J. Am. Acad. Dermatol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"362","DOI":"10.1016\/j.compmedimag.2007.01.003","article-title":"A methodological approach to the classification of dermoscopy images","volume":"31","author":"Celebi","year":"2007","journal-title":"Comput. Med. Imaging Graph."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"A10","DOI":"10.1097\/00008390-200408000-00037","article-title":"21 Randomized assessment of strategies for self-detection in the general population: Failure of ABCD, success of cognitive approach","volume":"14","author":"Girardi","year":"2004","journal-title":"Melanoma Res."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1038\/nature21056","article-title":"Dermatologist-level classification of skin cancer with deep neural networks","volume":"542","author":"Esteva","year":"2017","journal-title":"Nature"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"938","DOI":"10.1016\/S1470-2045(19)30333-X","article-title":"Comparison of the accuracy of human readers versus machine-learning algorithms for pigmented skin lesion classification: An open, web-based, international, diagnostic study","volume":"20","author":"Tschandl","year":"2019","journal-title":"Lancet Oncol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1016\/j.jbi.2018.08.006","article-title":"Skin lesion classification with ensembles of deep convolutional neural networks","volume":"86","author":"Harangi","year":"2018","journal-title":"J. Biomed. Inform."},{"key":"ref_18","unstructured":"Pacheco, A.G.C., Ali, A.R., and Trappenberg, T. (2019). Skin cancer detection based on deep learning and entropy to detect outlier samples. arXiv."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"105475","DOI":"10.1016\/j.cmpb.2020.105475","article-title":"Transfer learning using a multi-scale and multi-network ensemble for skin lesion classification","volume":"193","author":"Mahbod","year":"2020","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Mahbod, A., Schaefer, G., Wang, C., Ecker, R., and Ellinge, I. (2019, January 12\u201317). Skin lesion classification using hybrid deep neural networks. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK.","DOI":"10.1109\/ICASSP.2019.8683352"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Aldwgeri, A., and Abubacker, N.F. (2019, January 19\u201321). Ensemble of Deep Convolutional Neural Network for Skin Lesion Classification in Dermoscopy Images. Proceedings of the International Visual Informatics Conference, Bangi, Malaysia.","DOI":"10.1007\/978-3-030-34032-2_20"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"5:1","DOI":"10.1147\/JRD.2017.2708299","article-title":"Deep learning ensembles for melanoma recognition in dermoscopy images","volume":"61","author":"Codella","year":"2017","journal-title":"IBM J. Res. Dev."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Shahin, A.H., Kamal, A., and Elattar, M.A. (2018, January 20\u201322). Deep Ensemble Learning for Skin Lesion Classification from Dermoscopic Images. Proceedings of the Cairo International Biomedical Engineering Conference (CIBEC), Cairo, Egypt.","DOI":"10.1109\/CIBEC.2018.8641815"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"100864","DOI":"10.1016\/j.mex.2020.100864","article-title":"Skin lesion classification using ensembles of multi-resolution EfficientNets with meta data","volume":"7","author":"Gessert","year":"2020","journal-title":"MethodsX"},{"key":"ref_25","unstructured":"De Vries, T., and Ramachandram, D. (2017). Skin lesion classification using deep multi-scale convolutional neural networks. arXiv."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1761","DOI":"10.1016\/j.patcog.2011.01.017","article-title":"An overview of ensemble methods for binary classifiers in multi-class problems: Experimental study on one-vs-one and one-vs-all schemes","volume":"44","author":"Galar","year":"2011","journal-title":"Pattern Recognit."},{"key":"ref_27","first-page":"547","article-title":"Large margin dags for multiclass classification","volume":"12","author":"Platt","year":"1999","journal-title":"Nips"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"679","DOI":"10.1067\/mjd.2003.281","article-title":"Dermoscopy of pigmented skin lesions: Results of a consensus meeting via the Internet","volume":"48","author":"Argenziano","year":"2003","journal-title":"J. Am. Acad. Dermatol."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Perez, F., Vasconcelos, C., Avila, S., and Valle, E. (2018). Data augmentation for skin lesion analysis. OR 2.0 Context-Aware Operating Theaters, Computer Assisted Robotic Endoscopy, Clinical Image-Based Procedures, and Skin Image Analysis, Springer.","DOI":"10.1007\/978-3-030-01201-4_33"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"2207","DOI":"10.1109\/TIP.2007.901808","article-title":"Edge-based color constancy","volume":"16","author":"Gevers","year":"2007","journal-title":"IEEE Trans. Image Process."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"2475","DOI":"10.1109\/TIP.2011.2118224","article-title":"Computational color constancy: Survey and experiments","volume":"20","author":"Gijsenij","year":"2011","journal-title":"IEEE Trans. Image Process."},{"key":"ref_32","first-page":"1146","article-title":"Improving dermoscopy image classification using color constancy","volume":"19","author":"Barata","year":"2014","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_33","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_35","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."},{"key":"ref_36","first-page":"3772","article-title":"Analysis of multiclass support vector machines","volume":"21","author":"Abe","year":"2003","journal-title":"Thyroid"},{"key":"ref_37","unstructured":"Takahashi, F., and Abe, S. (2003). Optimizing directed acyclic graph support vector machines. Artif. Neural Netw. Pattern Recognit. ANNPR, 166\u2013173."},{"key":"ref_38","unstructured":"Tan, M., and Le, Q. (2019, January 9\u201315). Efficientnet: Rethinking model scaling for convolutional neural networks. Proceedings of the International Conference on Machine Learning, Long Beach, CA, USA."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., and Sun, G. (2018, January 18\u201322). Squeeze-and-excitation networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref_40","unstructured":"Selvaraju, R.R., Das, A., Vedantam, R., Cogswell, M., Parikh, D., and Batra, D. (2016). Grad-CAM: Why did you say that?. arXiv."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"107413","DOI":"10.1016\/j.patcog.2020.107413","article-title":"Explainable skin lesion diagnosis using taxonomies","volume":"110","author":"Barata","year":"2021","journal-title":"Pattern Recognit."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Barata, C., and Marques, J.S. (2019, January 8\u201311). Deep learning for skin cancer diagnosis with hierarchical architectures. Proceedings of the IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), Venice, Italy.","DOI":"10.1109\/ISBI.2019.8759561"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/12\/3999\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:12:42Z","timestamp":1760163162000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/12\/3999"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,10]]},"references-count":42,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2021,6]]}},"alternative-id":["s21123999"],"URL":"https:\/\/doi.org\/10.3390\/s21123999","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6,10]]}}}