{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T16:14:42Z","timestamp":1784391282605,"version":"3.55.0"},"reference-count":29,"publisher":"Public Library of Science (PLoS)","issue":"4","license":[{"start":{"date-parts":[[2024,4,16]],"date-time":"2024-04-16T00:00:00Z","timestamp":1713225600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>It is well known that the performance of any classification model is effective if the dataset used for the training process and the test process satisfy some specific requirements. In other words, the more the dataset size is large, balanced, and representative, the more one can trust the proposed model\u2019s effectiveness and, consequently, the obtained results. Unfortunately, large-size anonymous datasets are generally not publicly available in biomedical applications, especially those dealing with pathological human face images. This concern makes using deep-learning-based approaches challenging to deploy and difficult to reproduce or verify some published results. In this paper, we propose an efficient method to generate a realistic anonymous synthetic dataset of human faces, focusing on attributes related to acne disorders at three distinct levels of severity (Mild, Moderate, and Severe). Notably, our approach initiates from a small dataset of facial acne images, leveraging generative techniques to augment and diversify the dataset, ensuring comprehensive coverage of acne severity levels while maintaining anonymity and realism in the synthetic data. Therefore, a specific hierarchy StyleGAN-based algorithm trained at distinct levels is considered. Moreover, the utilization of generative adversarial networks for augmentation offers a means to circumvent potential privacy or legal concerns associated with acquiring medical datasets. This is attributed to the synthetic nature of the generated data, where no actual subjects are present, thereby ensuring compliance with privacy regulations and legal considerations. To evaluate the performance of the proposed scheme, we consider a CNN-based classification system, trained using the generated synthetic acneic face images and tested using authentic face images. Consequently, we show that an accuracy of 97.6% is achieved using InceptionResNetv2. As a result, this work allows the scientific community to employ the generated synthetic dataset for any data processing application without restrictions on legal or ethical concerns. Moreover, this approach can also be extended to other applications requiring the generation of synthetic medical images.<\/jats:p>","DOI":"10.1371\/journal.pone.0297958","type":"journal-article","created":{"date-parts":[[2024,4,16]],"date-time":"2024-04-16T17:27:29Z","timestamp":1713288449000},"page":"e0297958","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":13,"title":["Generative adversarial networks for anonymous acneic face dataset generation"],"prefix":"10.1371","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3015-847X","authenticated-orcid":true,"given":"Hazem","family":"Zein","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Samer","family":"Chantaf","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"R\u00e9gis","family":"Fournier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amine","family":"Nait-Ali","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2024,4,16]]},"reference":[{"key":"pone.0297958.ref001","article-title":"The Global Burden of Skin Disease in 2010: An Analysis of the Prevalence and Impact of Skin Conditions","volume":"134","author":"Roderick Hay","year":"2013","journal-title":"The Journal of investigative dermatology"},{"issue":"5","key":"pone.0297958.ref002","doi-asserted-by":"crossref","first-page":"472","DOI":"10.1001\/jamadermatol.2016.6032","article-title":"Analysis of Trends in Geographic Distribution of US Dermatology Workforce Density","volume":"153","author":"AM Glazer","year":"2017","journal-title":"JAMA Dermatol"},{"key":"pone.0297958.ref003","volume-title":"OR 2.0 Context-Aware Operating Theaters, Computer Assisted Robotic Endoscopy, Clinical Image-Based Procedures, and Skin Image Analysis. CARE CLIP OR 2.0 ISIC 2018 2018 2018 2018. Lecture Notes in Computer Science()","author":"C. Baur","year":"2018"},{"key":"pone.0297958.ref004","first-page":"155","volume-title":"Proceedings of the Machine Learning for Health NeurIPS Workshop","author":"A. Ghorbani","year":"2020"},{"key":"pone.0297958.ref005","unstructured":"Xiang, Alec, and Fei Wang. \u201cTowards Interpretable Skin Lesion Classification with Deep Learning Models.\u201d AMIA \u2026 Annual SymposiumProceedings. AMIA Symposium, vol. 2019, Mar. 2020, pp. 1246\u20131255."},{"key":"pone.0297958.ref006","first-page":"203","author":"Masum Shah Junayed","year":"2019","journal-title":"AcneNet\u2014A Deep CNN Based Classification Approach for Acne Classes"},{"key":"pone.0297958.ref007","first-page":"1","article-title":"Studies on Different CNN Algorithms for Face Skin Disease Classification Based on Clinical Images","author":"Zhe Wu","year":"2019","journal-title":"IEEE Access"},{"issue":"8","key":"pone.0297958.ref008","doi-asserted-by":"crossref","first-page":"2852","DOI":"10.3390\/s21082852","article-title":"Classification of Skin Disease Using Deep Learning Neural Networks with MobileNet V2 and LSTM","volume":"21","author":"PN Srinivasu","year":"2021","journal-title":"Sensors (Basel)"},{"key":"pone.0297958.ref009","doi-asserted-by":"crossref","first-page":"8659","DOI":"10.1109\/ACCESS.2021.3049600","article-title":"Dermoscopy Image Classification Based on StyleGAN and DenseNet201","volume":"9","author":"C. Zhao","year":"2021","journal-title":"IEEE Access"},{"key":"pone.0297958.ref010","doi-asserted-by":"crossref","first-page":"6145","DOI":"10.3390\/s22166145","article-title":"Deep Convolutional Generative Adversarial Networks to Enhance Artificial Intelligence in Healthcare: A Skin Cancer Application","volume":"22","author":"M. La Salvia","year":"2022","journal-title":"Sensors"},{"key":"pone.0297958.ref011","author":"Saad Albawi","year":"2017","journal-title":"Understanding of a Convolutional Neural Network"},{"key":"pone.0297958.ref012","author":"C Szegedy","year":"2016","journal-title":"Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning"},{"key":"pone.0297958.ref013","first-page":"630","volume":"9908","author":"Kaiming He","year":"2016","journal-title":"Identity Mappings in Deep Residual Networks"},{"key":"pone.0297958.ref014","article-title":"Generative Adversarial Networks","volume":"3","author":"Ian Goodfellow","year":"2014","journal-title":"Advances in Neural Information Processing Systems"},{"key":"pone.0297958.ref015","doi-asserted-by":"crossref","unstructured":"Karras, Tero, et al. \u201cA Style-Based Generator Architecture for Generative Adversarial Networks.\u201d ArXiv.org, 2018, arxiv.org\/abs\/1812.04948.","DOI":"10.1109\/CVPR.2019.00453"},{"key":"pone.0297958.ref016","unstructured":"Karras, Tero, et al. \u201cAnalyzing and Improving the Image Quality of StyleGAN.\u201d ArXiv:1912.04958 [Cs, Eess, Stat], 23 Mar. 2020, arxiv.org\/abs\/1912.04958."},{"key":"pone.0297958.ref017","doi-asserted-by":"crossref","unstructured":"Z. Wu, D. Lischinski and E. Shechtman, \u201cStyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation,\u201d 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA, 2021, pp. 12858\u201312867.","DOI":"10.1109\/CVPR46437.2021.01267"},{"key":"pone.0297958.ref018","unstructured":"Voynov, A., & Babenko, A. (2020). Unsupervised Discovery of Interpretable Directions in the GAN Latent Space. In Proceedings of the 37th International Conference on Machine Learning (pp. 9786\u20139796). PMLR."},{"key":"pone.0297958.ref019","unstructured":"Andrew Brock, Jeff Donahue, Karen Simonyan: \u201cLarge Scale GAN Training for High Fidelity Natural Image Synthesis\u201d, 2018; arXiv:1809.11096."},{"key":"pone.0297958.ref020","unstructured":"Alec Radford, Luke Metz, Soumith Chintala: \u201cUnsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks\u201d, 2015; arXiv:1511.06434."},{"key":"pone.0297958.ref021","author":"J. D. Curt\u00f3","year":"2017","journal-title":"High-resolution Deep Convolutional Generative Adversarial Networks"},{"key":"pone.0297958.ref022","volume-title":"Advances in Neural Information Processing Systems","author":"E. Denton","year":"2015"},{"key":"pone.0297958.ref023","article-title":"Joint Acne Image Grading and Counting via Label Distribution Learning","author":"Xiaoping Wu","year":"2019","journal-title":"IEEE Xplore"},{"key":"pone.0297958.ref024","unstructured":"Li, Xiaoming, et al. \u201cBlind Face Restoration via Deep Multi-Scale Component Dictionaries.\u201d ArXiv:2008.00418 [Cs], 2 Aug. 2020, arxiv.org\/abs\/2008.00418."},{"issue":"8","key":"pone.0297958.ref025","doi-asserted-by":"crossref","first-page":"1497","DOI":"10.3390\/sym13081497","article-title":"StyleGANs and Transfer Learning for Generating Synthetic Images in Industrial Applications","volume":"13","author":"Harold Achicanoy","year":"2021","journal-title":"Symmetry"},{"key":"pone.0297958.ref026","unstructured":"Heusel, Martin, et al. \u201cGANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium.\u201d ArXiv:1706.08500 [Cs, Stat], 12 Jan. 2018, arxiv.org\/abs\/1706.08500"},{"key":"pone.0297958.ref027","doi-asserted-by":"crossref","first-page":"01","DOI":"10.5121\/ijdkp.2015.5201","article-title":"A Review on Evaluation Metrics for Data Classification Evaluations","volume":"5","author":"Mohammad Hossin","year":"2015","journal-title":"International Journal of Data Mining & Knowledge Management Process"},{"key":"pone.0297958.ref028","doi-asserted-by":"crossref","unstructured":"N. Bonettini, E. D. Cannas, S. Mandelli, L. Bondi, P. Bestagini and S. Tubaro, \u201cVideo Face Manipulation Detection Through Ensemble of CNNs,\u201d 2020 25th International Conference on Pattern Recognition (ICPR), Milan, Italy, 2021, pp. 5012\u20135019.","DOI":"10.1109\/ICPR48806.2021.9412711"},{"key":"pone.0297958.ref029","article-title":"A global perspective on the epidemiology of acne","volume":"172","author":"J.K.L. Tan","year":"2015","journal-title":"British Journal of Dermatology"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0297958","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,16]],"date-time":"2024-04-16T17:27:45Z","timestamp":1713288465000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0297958"}},"subtitle":[],"editor":[{"given":"Jude","family":"Hemanth","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,4,16]]},"references-count":29,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2024,4,16]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0297958","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,16]]}}}