{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T13:03:13Z","timestamp":1792069393586,"version":"4.4.0"},"reference-count":17,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2025,8,13]],"date-time":"2025-08-13T00:00:00Z","timestamp":1755043200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2024YFA1108200"],"award-info":[{"award-number":["2024YFA1108200"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,29]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Nasolabial-fold (NLF) severity is a key indicator of facial aging and a frequent target in aesthetic treatments. The Wrinkle Severity Rating Scale (WSRS) is widely used for clinical grading but remains inherently subjective and vulnerable to inter-observer variability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>The authors of this study aim to develop and validate DeepFold, a deep learning\u2013based ensemble model for automated, objective, and clinically interpretable grading of NLF severity based on the WSRS.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A dataset of 6718 facial images was constructed, including 1718 images from clinical outpatients and 5000 from the CelebA dataset. All images were split into left and right halves and annotated independently by 3 senior plastic surgeons using the WSRS. ResNet-50 served as the base model architecture, and an ensemble strategy was applied using majority voting over 3 independently trained networks. Model training used focal loss to address class imbalance and was conducted in PyTorch with early stopping based on validation loss. Performance was assessed using accuracy, F1 score, and confusion matrix analysis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The DeepFold ensemble model achieved a validation accuracy and F1 score of 0.917, outperforming individual baseline models such as ResNet-50 (accuracy: 0.904) and SeResNet-50 (accuracy: 0.882). Ensemble strategies reduced prediction variance and enhanced model robustness under class imbalance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>DeepFold provides a reliable and standardized approach to NLF severity assessment, offering potential clinical value in aesthetic evaluation, treatment planning, and outcome monitoring.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/asj\/sjaf161","type":"journal-article","created":{"date-parts":[[2025,8,13]],"date-time":"2025-08-13T05:22:08Z","timestamp":1755062528000},"page":"130-136","source":"Crossref","is-referenced-by-count":3,"title":["A Deep Learning\u2013Based Ensemble Model for Automated Nasolabial-Fold Severity Grading"],"prefix":"10.1093","volume":"46","author":[{"given":"Hengqing","family":"Cui","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziqi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0879-2415","authenticated-orcid":false,"given":"Haiyan","family":"Cui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,8,13]]},"reference":[{"key":"2026012908470506400_sjaf161-B1","doi-asserted-by":"publisher","first-page":"3568","DOI":"10.1007\/s00266-024-04070-6","article-title":"Understanding the interplay between skin, fascia, and muscles of the midface in facial aging","volume":"48","author":"Frank","year":"2024","journal-title":"Aesthetic Plast Surg"},{"key":"2026012908470506400_sjaf161-B2","doi-asserted-by":"publisher","first-page":"1043","DOI":"10.1093\/asj\/sjy096","article-title":"Calvarial volume loss and facial aging: a computed tomographic (CT)-based study","volume":"38","author":"Cotofana","year":"2018","journal-title":"Aesthet Surg J"},{"key":"2026012908470506400_sjaf161-B3","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1111\/jocd.13486","article-title":"Quantitative evaluation of rejuvenation treatment of nasolabial fold wrinkles by regression model and 3D photography","volume":"20","author":"Fang","year":"2021","journal-title":"J Cosmet Dermatol"},{"key":"2026012908470506400_sjaf161-B4","doi-asserted-by":"publisher","first-page":"1221","DOI":"10.1007\/s00266-020-02050-0","article-title":"Effectiveness and long-acting of the hyaluronic acid injected into the nasolabial fold measured through magnetic resonance imaging","volume":"45","author":"Abramo","year":"2021","journal-title":"Aesthetic Plast Surg"},{"key":"2026012908470506400_sjaf161-B5","doi-asserted-by":"publisher","first-page":"1796","DOI":"10.1007\/s00266-023-03600-y","article-title":"Safety and efficacy of poly-l-lactic acid filler (Gana V vs. Sculptra) injection for correction of the nasolabial fold: a double-blind, non-inferiority, randomized, split-face controlled trial","volume":"47","author":"Han","year":"2023","journal-title":"Aesthetic Plast Surg"},{"key":"2026012908470506400_sjaf161-B6","doi-asserted-by":"publisher","first-page":"NP87","DOI":"10.1093\/asj\/sjad169","article-title":"Effect of a new hyaluronic acid hydrogel dermal filler cross-linked with lysine amino acid for skin augmentation and rejuvenation","volume":"44","author":"Guo","year":"2023","journal-title":"Aesthet Surg J"},{"key":"2026012908470506400_sjaf161-B7","doi-asserted-by":"publisher","first-page":"2190829","DOI":"10.1080\/09546634.2023.2190829","article-title":"Safety and efficacy of hyaluronic acid injectable filler in the treatment of nasolabial fold wrinkle: a randomized, double-blind, self-controlled clinical trial","volume":"34","author":"Li","year":"2023","journal-title":"J Dermatolog Treat"},{"key":"2026012908470506400_sjaf161-B8","doi-asserted-by":"publisher","first-page":"703","DOI":"10.1038\/s41571-019-0252-y","article-title":"Artificial intelligence in digital pathology\u2014new tools for diagnosis and precision oncology","volume":"16","author":"Bera","year":"2019","journal-title":"Nat Rev Clin Oncol"},{"key":"2026012908470506400_sjaf161-B9","doi-asserted-by":"publisher","first-page":"500","DOI":"10.1038\/s41568-018-0016-5","article-title":"Artificial intelligence in radiology","volume":"18","author":"Hosny","year":"2018","journal-title":"Nat Rev Cancer"},{"key":"2026012908470506400_sjaf161-B10","doi-asserted-by":"publisher","first-page":"2552","DOI":"10.1007\/s00266-023-03615-5","article-title":"How brow rotation affects emotional expression utilizing artificial intelligence","volume":"47","author":"Zhu","year":"2023","journal-title":"Aesthetic Plast Surg"},{"key":"2026012908470506400_sjaf161-B11","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1016\/j.bjps.2023.07.017","article-title":"Estimating apparent age using artificial intelligence: quantifying the effect of blepharoplasty","volume":"85","author":"Goodyear","year":"2023","journal-title":"J Plast Reconstr Aesthet Surg"},{"key":"2026012908470506400_sjaf161-B12","author":"Liu"},{"key":"2026012908470506400_sjaf161-B13","doi-asserted-by":"publisher","first-page":"49","DOI":"10.2165\/00128071-200405010-00007","article-title":"The wrinkle severity rating scale: a validation study","volume":"5","author":"Day","year":"2004","journal-title":"Am J Clin Dermatol"},{"key":"2026012908470506400_sjaf161-B14","first-page":"8024","volume-title":"Advances in Neural Information Processing Systems (NeurIPS 2019)","author":"Paszke","year":"2019"},{"key":"2026012908470506400_sjaf161-B15","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1016\/j.bjps.2025.02.014","article-title":"Can AI-assisted objective facial attractiveness scoring systems replace manual aesthetic evaluations? A comparative analysis of human and machine ratings","volume":"104","author":"Wang","year":"2025","journal-title":"J Plast Reconstr Aesthet Surg"},{"key":"2026012908470506400_sjaf161-B16","doi-asserted-by":"publisher","first-page":"4110","DOI":"10.1111\/jocd.16481","article-title":"AI assistance in aesthetic medicine\u2014a consensus on objective medical standards","volume":"23","author":"Frank","year":"2024","journal-title":"J Cosmet Dermatol"},{"key":"2026012908470506400_sjaf161-B17","doi-asserted-by":"publisher","first-page":"3572","DOI":"10.1007\/s00266-025-04746-7","article-title":"Artificial intelligence in facial measurement: a new era of symmetry and proportions analysis","volume":"49","author":"Ali","year":"2025","journal-title":"Aesthetic Plast Surg"}],"container-title":["Aesthetic Surgery Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/asj\/advance-article-pdf\/doi\/10.1093\/asj\/sjaf161\/64030888\/sjaf161.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/asj\/article-pdf\/46\/2\/130\/64030888\/sjaf161.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/asj\/article-pdf\/46\/2\/130\/64030888\/sjaf161.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T13:47:14Z","timestamp":1769694434000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/asj\/article\/46\/2\/130\/8232888"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,13]]},"references-count":17,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,8,13]]},"published-print":{"date-parts":[[2026,1,29]]}},"URL":"https:\/\/doi.org\/10.1093\/asj\/sjaf161","relation":{},"ISSN":["1090-820X","1527-330X"],"issn-type":[{"value":"1090-820X","type":"print"},{"value":"1527-330X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,2]]},"published":{"date-parts":[[2025,8,13]]}}}