{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T18:23:57Z","timestamp":1773771837464,"version":"3.50.1"},"reference-count":34,"publisher":"Association for Computing Machinery (ACM)","issue":"2","funder":[{"DOI":"10.13039\/501100020874","name":"Faculty of Information and Communication Technology, Mahidol University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100020874","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Mahidol University Central Institutional Review Board","award":["MU-CIRB 2023\/146.1809"],"award-info":[{"award-number":["MU-CIRB 2023\/146.1809"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Comput. Healthcare"],"published-print":{"date-parts":[[2026,4,30]]},"abstract":"<jats:p>This study introduces a novel approach to enhance acne severity classification by leveraging cross-dataset training within a Label Distribution Learning (LDL) framework. Traditional acne grading methods are often subjective and inconsistent, while automated systems struggle to generalize across diverse datasets, limiting their real-world applicability. This research addresses this challenge by integrating data from multiple sources (Acne04 and AcneSCU) to train a robust model capable of accurately classifying acne severity despite variations in image quality, lighting, and skin tone. We explore the impact of different backbone architectures (ResNet50, EfficientNet B7, and BEiT) within the LDL framework, which is specifically designed to handle the inherent ambiguity in acne severity labeling. Our results demonstrate that cross-dataset training within the LDL framework significantly improves generalization performance compared to models trained on individual datasets. Additionally, results demonstrate that integrating EfficientNet B7 and BEiT enhances the model\u2019s accuracy and robustness. This novel approach offers a promising solution for developing scalable and reliable automated acne grading systems suitable for telemedicine and dermatology applications, ultimately aiding dermatologists in providing more precise and personalized treatment plans.<\/jats:p>","DOI":"10.1145\/3793540","type":"journal-article","created":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T14:47:32Z","timestamp":1769179652000},"page":"1-19","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["XD-LDL: Improving Generalization in Acne Severity Classification via Cross-Dataset Label Distribution Learning"],"prefix":"10.1145","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6472-8426","authenticated-orcid":false,"given":"Sirawich","family":"Vachmanus","sequence":"first","affiliation":[{"name":"Faculty of Information and Communication Technology, Mahidol University, Salaya, Thailand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1654-9706","authenticated-orcid":false,"given":"Teerapong","family":"Rattananukrom","sequence":"additional","affiliation":[{"name":"Division of Dermatology, Department of Medicine, Faculty of Medicine Ramathibodi Hospital, Mahidol University, Bangkok, Thailand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5201-5699","authenticated-orcid":false,"given":"Suppawong","family":"Tuarob","sequence":"additional","affiliation":[{"name":"Faculty of Information and Communication Technology, Mahidol University, Salaya, Thailand"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,3,17]]},"reference":[{"key":"e_1_3_1_2_2","unstructured":"GitHub. 2019. Zllrunning\/face-parsing.PyTorch: Using modified BiSeNet for face parsing in PyTorch. Retrieved October 31 2023 from https:\/\/github.com\/zllrunning\/face-parsing.PyTorch"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10243158"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.4108\/eetpht.9.4039"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-15655-9"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-025-03051-2"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.34218\/IJARET.11.10.2020.122"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1002\/ima.23121"},{"key":"e_1_3_1_9_2","unstructured":"Hangbo Bao Li Dong Songhao Piao and Furu Wei. 2021. BEiT: BERT pre-training of image transformers. arXiv:2106.08254. Retrieved from https:\/\/arxiv.org\/abs\/2106.08254"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2017.2689998"},{"key":"e_1_3_1_11_2","doi-asserted-by":"crossref","unstructured":"Nils Gessert Maximilian Nielsen Mohsin Shaikh Ren\u00e9 Werner and Alexander Schlaefer. 2019. Skin lesion classification using ensembles of multi-resolution EfficientNets with meta data. arXiv:1910.03910. Retrieved from http:\/\/arxiv.org\/abs\/1910.03910","DOI":"10.1016\/j.mex.2020.100864"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00144"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1346-8138.2008.00462.x"},{"key":"e_1_3_1_14_2","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2015. Deep residual learning for image recognition. arXiv:1512.03385. Retrieved from http:\/\/arxiv.org\/abs\/1512.03385"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0217293"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3138021"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00372"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11036-020-01550-2"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00559"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM52615.2021.9669431"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/AIMLA59606.2024.10531439"},{"key":"e_1_3_1_22_2","doi-asserted-by":"crossref","unstructured":"Sergio Nava-Mu\u00f1oz Mario Graff Guerrero and Hugo Jair Escalante. 2023. Comparison of classifiers in challenge scheme. arXiv:2305.10452. Retrieved from https:\/\/arxiv.org\/abs\/2305.10452","DOI":"10.1007\/978-3-031-33783-3_9"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2019.101765"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ceh.2023.08.002"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.14569\/IJACSA.2024.0150668"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/C2I454156.2021.9689338"},{"key":"e_1_3_1_27_2","first-page":"6105","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan and Quoc Le. 2019. EfficientNet: Rethinking model scaling for convolutional neural networks. In Proceedings of the International Conference on Machine Learning. PMLR, 6105\u20136114."},{"key":"e_1_3_1_28_2","unstructured":"Jessica Velasco Cherry Pascion Jean Wilmar Alberio Jonathan Apuang John Stephen Cruz Mark Angelo Gomez Benjamin Molina Jr. Lyndon Tuala August Thio-Ac and Romeo Jorda Jr. 2019. A smartphone-based skin disease classification using MobileNet CNN. arXiv:1911.07929. Retrieved from https:\/\/arxiv.org\/abs\/1911.07929"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1186\/s13244-021-01100-8"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12020438"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01074"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3154403"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2023.3304727"},{"key":"e_1_3_1_34_2","unstructured":"Jianwei Zhang Lei Zhang Junyou Wang Xin-Tong Wei Jiaqi Li Xiangjian Jiang and Dan Du. 2022. Learning high-quality proposals for acne detection. arxiv:2207.03674. Retrieved from https:\/\/arxiv.org\/abs\/2207.03674"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1186\/s13550-022-00881-3"}],"container-title":["ACM Transactions on Computing for Healthcare"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3793540","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T15:10:33Z","timestamp":1773760233000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3793540"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,17]]},"references-count":34,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,4,30]]}},"alternative-id":["10.1145\/3793540"],"URL":"https:\/\/doi.org\/10.1145\/3793540","relation":{},"ISSN":["2691-1957","2637-8051"],"issn-type":[{"value":"2691-1957","type":"print"},{"value":"2637-8051","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,17]]},"assertion":[{"value":"2025-02-24","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-15","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}