FACES: A Deep-Learning-Based Parametric Model to Improve Rosacea Diagnoses
Open accessAbstract
Rosacea is a chronic inflammatory skin disorder that causes visible blood vessels and redness on the nose, chin, cheeks, and forehead. However, visual assessment, the current standard method used to identify rosacea, is often subjective among clinicians and results in high variation. Recent advances in artificial intelligence have allowed for the effective detection of various skin diseases with high accuracy and consistency. In this study, we develop a new methodology, coined “five accurate CNNs-based evaluation system (FACES)”, to identify and classify rosacea more efficiently. First, 19 CNN-based models that have been widely used for image classification were trained and tested via training and validation data sets. Next, the five best performing models were selected based on accuracy, which served as a weight value for FACES. At the same time, we also applied a majority rule to five selected models to detect rosacea. The results exhibited that the performance of FACES was superior to that of the five individual CNN-based models and the majority rule in terms of accuracy, sensitivity, specificity, and precision. In particular, the accuracy and sensitivity of FACES were the highest, and the specificity and precision were higher than most of the individual models. To improve the performance of our system, future studies must consider patient details, such as age, gender, and race, and perform comparison tests between our model system and clinicians.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Image-based deep learning models such as RosNet and FACES have been developed to classify rosacea.
“A few studies developed image-based deep learning models to classify rosacea, such as RosNet (adapted from Inception-ResNet-v2) and FACES (an ensemble deep learning model) (Binol et al, 2020; Park et al, 2023).”
From Artificial intelligence–enabled precision medicine for inflammatory skin diseases (2026) · cites this paper as Park et al, 2023
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · see citing works
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562 · see citing works
Dermatologist-level classification of skin cancer with deep neural networks
Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017) · Nature · doi:10.1038/nature21056 · Cited by 14,362 · see citing works
ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
Ma, N., Zhang, X., Zheng, H.-T., & Sun, J. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01264-9_8 · Cited by 7,356 · cited 1× · see citing works
“All of the selected 5 methods are CNN models that take a linear O(n) time, where n is the number of input pixels [39].”
MethodWilkin, J. K., Dahl, M. V., Detmar, M. J., Drake, L. A., Feinstein, A. R., Odom, R. B., & Powell, F. C. (2002) · Journal of the American Academy of Dermatology · doi:10.1067/mjd.2002.120625 · Cited by 913 · see citing works
A transfer convolutional neural network for fault diagnosis based on ResNet-50
Wen, L., Li, X., & Gao, L. (2019) · Neural Computing and Applications · doi:10.1007/s00521-019-04097-w · Cited by 774 · see citing works
Gallo, R. L., Granstein, R. D., Kang, S., Mannis, M. J., Steinhoff, M. S., Tan, J. K. L., & Thiboutot, D. M. (2017) · Journal of the American Academy of Dermatology · doi:10.1016/j.jaad.2017.08.037 · Cited by 513 · see citing works
Skin Cancer Classification Using Convolutional Neural Networks: Systematic Review
Brinker, T. J., Hekler, A., Utikal, J. S., Grabe, N., Schadendorf, D., Klode, J., Berking, C., Steeb, T., Enk, A. H., & Kalle, C. V. (2018) · Journal of Medical Internet Research · doi:10.2196/11936 · Cited by 504 · see citing works
Deep Learning, Sparse Coding, and SVM for Melanoma Recognition in Dermoscopy Images
Codella, N., Cai, J., Abedini, M., Garnavi, R., Halpern, A. C., & Smith, J. R. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24888-2_15 · Cited by 400 · see citing works
Two, A. M., Wu, W., Gallo, R. L., & Hata, T. R. (2015) · Journal of the American Academy of Dermatology · doi:10.1016/j.jaad.2014.08.028 · Cited by 380 · see citing works
Fujisawa, Y., Otomo, Y., Ogata, Y., Nakamura, Y., Fujita, R., Ishitsuka, Y., Watanabe, R., Okiyama, N., Ohara, K., & Fujimoto, M. (2018) · British Journal of Dermatology · doi:10.1111/bjd.16924 · Cited by 316 · see citing works
Skin Cancer Classification using Deep Learning and Transfer Learning
Hosny, K. M., Kassem, M. A. A., & Foaud, M. M. (2018) · Cairo International Biomedical Engineering Conference · doi:10.1109/cibec.2018.8641762 · Cited by 293 · see citing works
Kadampur, M. A., & Alriyaee, S. (2019) · Informatics in Medicine Unlocked · doi:10.1016/j.imu.2019.100282 · Cited by 257 · see citing works
Melanoma diagnosis using deep learning techniques on dermatoscopic images
Jojoa, M., Caballero, L., García-Zapirain, B., & Percybrooks, W. (2021) · BMC Medical Imaging · doi:10.1186/s12880-020-00534-8 · Cited by 244 · see citing works
Phillips, M. R., Marsden, H., Jaffe, W., Matin, R., Wali, G. N., Greenhalgh, J., McGrath, E., James, R., Ladoyanni, E., Bewley, A., et al. (2019) · JAMA Network Open · doi:10.1001/jamanetworkopen.2019.13436 · Cited by 231 · see citing works
Rosacea: Epidemiology, pathogenesis, and treatment
Rainer, B. M., Kang, S., & Chien, A. L.-L. (2017) · Dermato-Endocrinology · doi:10.1080/19381980.2017.1361574 · Cited by 225 · see citing works
Self-citationRecent advances in understanding and managing rosacea
Buddenkotte, J., & Steinhoff, M. S. (2018) · F1000Research · doi:10.12688/f1000research.16537.1 · Cited by 221 · see citing works
Deep Learning–Based Methods for Automatic Diagnosis of Skin Lesions
El-Khatib, H., Popescu, D., & Ichim, L. (2020) · Sensors · doi:10.3390/s20061753 · Cited by 159 · see citing works
Brinker, T. J., Hekler, A., Hauschild, A., Berking, C., Schilling, B., Enk, A. H., Haferkamp, S., Karoglan, A., von Kalle, C., Weichenthal, M., et al. (2019) · European Journal of Cancer · doi:10.1016/j.ejca.2018.12.016 · Cited by 157 · see citing works
Multi-view classification with convolutional neural networks
Seeland, M., & Mäder, P. (2021) · PLoS ONE · doi:10.1371/journal.pone.0245230 · Cited by 145 · see citing works
Systematic review of machine learning for diagnosis and prognosis in dermatology
Thomsen, K. G., Iversen, L., Titlestad, T. L., & Winther, O. (2019) · Journal of Dermatological Treatment · doi:10.1080/09546634.2019.1682500 · Cited by 101 · see citing works
Deep learning based classification of facial dermatological disorders
Göçeri, E. (2020) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2020.104118 · Cited by 97 · see citing works
Data augmentation in dermatology image recognition using machine learning
Aggarwal, S. L. P. (2019) · Skin Research and Technology · doi:10.1111/srt.12726 · Cited by 80 · see citing works
Epidemiology of rosacea: updated data
Chosidow, O., & Cribier, B. J. (2011) · Annales de Dermatologie et de Vénéréologie · doi:10.1016/s0151-9638(11)70087-4 · Cited by 75 · see citing works
Deep Learning for Diagnostic Binary Classification of Multiple-Lesion Skin Diseases
Thomsen, K. G., Christensen, A. L., Iversen, L., Lomholt, H. B., & Winther, O. (2020) · Frontiers in Medicine · doi:10.3389/fmed.2020.574329 · Cited by 68 · see citing works
Rosacea in skin of color: not a rare diagnosis
Al‐Dabagh, A., Davis, S., McMichael, A. J., & Feldman, S. R. (2014) · Dermatology Online Journal · doi:10.5070/d32010024262 · Cited by 65 · see citing works
Epidemiological features of rosacea in Changsha, China: A population‐based, cross‐sectional study
Li, J., Wang, B., Deng, Y., Shi, W., Jian, D., Liu, F., Huang, Y., Tang, Y., Zhao, Z., Huang, X., et al. (2020) · The Journal of Dermatology · doi:10.1111/1346-8138.15301 · Cited by 59 · see citing works
Zhao, Z., Wu, C.-M., Zhang, S., He, F., Liu, F., Wang, B., Huang, Y., Shi, W., Jian, D., Xie, H., et al. (2021) · JMIR Medical Informatics · doi:10.2196/23415 · Cited by 58 · cited 1× · see citing works
“However, it is often difficult to distinguish one type from another [7].”
BackgroundSkin Disease Diagnosis from Photographs Using Deep Learning
Göçeri, E. (2019) · Lecture notes in computational vision and biomechanics · doi:10.1007/978-3-030-32040-9_25 · Cited by 57 · see citing works
Ros‐NET: A deep convolutional neural network for automatic identification of rosacea lesions
Binol, H., Plotner, A., Sopkovich, J., Kaffenberger, B., Niazi, M. K. K., & Gurcan, M. N. (2020) · Skin Research and Technology · doi:10.1111/srt.12817 · Cited by 56 · see citing works
Epidemiology of rosacea in a population‐based study of 161,269 German employees
Hilbring, C., Augustin, M., Kirsten, N., & Mohr, N. (2021) · International Journal of Dermatology · doi:10.1111/ijd.15989 · Cited by 47 · see citing works
Guarino, A., Malandrino, D., & Zaccagnino, R. (2021) · Computer Networks · doi:10.1016/j.comnet.2021.108614 · Cited by 44 · see citing works
Elgendi, M., Nasir, M. U., Tang, Q., Fletcher, R., Howard, N., Menon, C., Ward, R. K., Parker, W., & Nicolaou, S. (2020) · Frontiers in Medicine · doi:10.3389/fmed.2020.00550 · Cited by 42 · see citing works
Tozour, J. N., Bandremer, S., Patberg, E. T., Zavala, J., Akerman, M. B., Chavez, M., Mann, D. M., Testa, P. A., Vintzileos, A. M., & Heo, H. J. (2021) · American Journal of Obstetrics & Gynecology MFM · doi:10.1016/j.ajogmf.2021.100469 · Cited by 40 · see citing works
Zhou, M., Xie, H., Cheng, L. Z., & Li, J. (2016) · Pakistan Journal of Medical Sciences · doi:10.12669/pjms.326.11236 · Cited by 38 · see citing works
Aractingi, S., & Pellacani, G. (2019) · European Journal of Dermatology · doi:10.1684/ejd.2019.3538 · Cited by 36 · see citing works
Gupta, A. K., & Lynch, L. E. (2004) · PubMed · Cited by 26 · see citing works
Segmentation of Acne Vulgaris Lesions
Ramli, R., Malik, A. S., Hani, A. F. M., & Yap, F. B. (2011) · International Conference on Digital Image Computing: Techniques and Applications (DICTA) · doi:10.1109/dicta.2011.63 · Cited by 17 · see citing works
Update on rosacea classification and its controversies.
Wang, Y. A., & James, W. D. (2019) · PubMed · Cited by 16 · see citing works
Content-based image retrieval using Group Normalized-Inception-Darknet-53
Pathak, D., & Raju, U. S. N. (2021) · International Journal of Multimedia Information Retrieval · doi:10.1007/s13735-021-00215-4 · Cited by 12 · see citing works
Automated Detection of Facial Disorders (ADFD): a novel approach based-on digital photographs
Göçeri, E., & Günay, M. (2017) · Computer Methods in Biomechanics and Biomedical Engineering Imaging & Visualization · doi:10.1080/21681163.2017.1317292 · Cited by 10 · see citing works
Binol, H., Niazi, M. K. K., Plotner, A. N., Sopkovich, J. A., Kaffenberger, B. H., & Gürcan, M. N. (2020) · SPIE Medical Imaging: Computer-Aided Diagnosis · doi:10.1117/12.2549392 · Cited by 10 · see citing works
Flagged first, then by citations
Research works printed but not linked: 2
- Odom, R. The Nosology of Rosacea. Cutis 2004, 74, 5-8.
- Wilkin, J.; Dahl, M.; Detmar, M.; Drake, L.; Feinstein, A.; Odom, R.; Powell, F. Standard Classification of Rosacea: Report of the National Rosacea Society Expert Committee on the Classification and Staging of Rosacea. J. Am. Acad. Dermatol. 2002, 46, 584-587.
Cited by
Sorted by citations
A survey on computer vision approaches for automated classification of skin diseases
Gupta, P., Nirmal, J. H., & Mehendale, N. D. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-19301-w · Cited by 24 · see citing works
Deep learning models for cancer stem cell detection: a brief review
Chen, J., Xu, L., Li, X., & Park, S. (2023) · Frontiers in Immunology · doi:10.3389/fimmu.2023.1214425 · Cited by 19 · see citing works
Self-citationImproved CNN architecture for automated classification of skin diseases
Deepak, G. D., Bhat, S. K., & Gupta, A. (2024) · Computer Methods in Biomechanics and Biomedical Engineering Imaging & Visualization · doi:10.1080/21681163.2024.2420727 · Cited by 14 · see citing works
High-throughput platform for label-free sorting of 3D spheroids using deep learning
da Silva, C. S., Boos, J. A., Goldowsky, J., Blache, M. L., Schmid, N., Heinemann, T., Netsch, C., Luongo, F., Pasche, S., Weder, G., et al. (2024) · Frontiers in Bioengineering and Biotechnology · doi:10.3389/fbioe.2024.1432737 · Cited by 9 · see citing works
Artificial intelligence–enabled precision medicine for inflammatory skin diseases
Tang, A. S., Wei, M. L., Haemel, A., La, C., Sirota, M., & Lee, E. Y. (2026) · Journal of Investigative Dermatology · doi:10.1016/j.jid.2025.10.596 · Cited by 6 · see citing works
Predicting Prognosis of Early-Stage Mycosis Fungoides with Utilization of Machine Learning
Mendi, B. İ., Sanlı, H. E., İnsel, M. A., Bayındır, B., & Atak, M. F. (2024) · Life · doi:10.3390/life14111371 · Cited by 4 · see citing works
Artificial intelligence in cellular senescence research: a narrative review
Lee, C., Yaganapu, A., Singam, A., Fikru, S., Rahmani, R., Zheng, J., Kang, M., & Park, S. (2025) · Aging advances. · doi:10.4103/agingadv.agingadv-d-25-00011 · Cited by 3 · see citing works
Self-citationArtificial intelligence-enabled precision medicine for inflammatory skin diseasesPreprint
Tang, A., Wei, M. L., Haemel, A. K., La, C., Sirota, M., & Lee, E. Y. (2025) · PubMed · doi:10.48550/arxiv.2505.09527 · Cited by 5 · see citing works
Comparison and detection of skin disease to improve accuracy using ANN and SVM
Basha, S. S., & Baskar, R. (2025) · AIP conference proceedings · doi:10.1063/5.0265714
Wang, Y., Luo, H., Song, D., Duan, M., Han, Y., Wang, W., Feng, Y., & Jiang, X. L. (2026) · Dermatology · doi:10.1159/000550245
AI-Powered Approach to Rosacea
Kyrmanidou, E., & Lazaridou, E. (2026) · Springer eBooks · doi:10.1007/978-3-032-15614-3_12
Convolutional Neural Networks for Skin Disease Analysis and Treatment Decision Support System
Selçuk, K., Taşkıran, I., Alkaddour, M. H. S., Türk, A., & Baykara, M. (2026) · International Symposium on AI-Driven Engineering Systems (ISADES) · doi:10.1109/isades69945.2026.11608061
- Authors
- Park, S., Chien, A. L., Lin, B., & Li, K.
- Affiliations
- University of Nevada, Las Vegas (US)
- Johns Hopkins University (US)
- Corresponding author
- Park, Seungman
- Venue
- Applied Sciences
- Publisher
- MDPI AG
- Published
- 2023-01-11
- Volume
- 13
- Issue
- 2
- Pages
- 970
- ISSN
- 2076-3417 (ISSN-L)
- PMC
- PMC10817774
- OpenAlex
- W4315574576
- Cited by
- 12
- References
- 42
- Citations by year
- 2026: 4 · 2025: 3 · 2024: 4 · 2023: 1
- FWCI
- 3.31
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Applied Sciences (publishedVersion, cc-by)
- PubMed (publishedVersion)
- PubMed Central (acceptedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Institute on Aging of the National Institutes of Health (K25AG070286)
- Topics
- Health Sciences › Medicine › Dermatology › Acne and Rosacea Treatments and Effects
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Health Sciences › Medicine › Oncology › Cutaneous Melanoma Detection and Management
- Keywords
- rosacea, skin disease classification, convolutional neural networks, ensemble learning, majority voting, dermatological image analysis, automated diagnosis, face
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
