EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

AI‐assisted diagnosis of nail unit melanoma and melanonychia using a clinical deep learning model

Yusung Chu iD, Sejung Yang, Jin-Woong Jung, Jun Young Kim, Joon-Goon Kim, Hae June Sung iD, Byungho Oh iD

JDDG: Journal der Deutschen Dermatologischen Gesellschaft · 24.07.2026

DOI: 10.1111/ddg.70347 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JDDG: Journal der Deutschen Dermatologischen Gesellschaft, online erschienen am 24.07.2026. Verfasst von Yusung Chu und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Precision Medicine, Yonsei University Wonju College of Medicine, Wonju-si, Gangwon-do, Republic of Korea. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Yonsei University College of Medicine, National Research Foundation of Korea (NRF).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background and objectives Nail unit melanoma (NUM) is a rare but potentially fatal malignancy often misdiagnosed as melanonychia. Because biopsy may cause permanent nail dystrophy, accurate noninvasive diagnosis is essential. This study aimed to develop and validate an artificial intelligence model to distinguish NUM from benign melanonychia using clinical images and to assess its diagnostic utility through human comparison and external validation. Patients and Methods Clinical images from 172 patients with melanonychia and 122 patients with NUM were retrospectively collected. Pediatric melanonychia was excluded to minimize diagnostic ambiguity. Three convolutional neural networks (CNNs) were trained and validated with patient‐wise splits. Human validation involved 40 representative images assessed by dermatologists, residents, and non‐medical participants, with and without CNN assistance.

Results

ResNet‐50 achieved the highest sensitivity (87.2 %). DenseNet‐121 achieved the highest AUROC (area under the receiver operating characteristic curve) (0.954). CNN assistance improved the diagnostic accuracy of all human raters (accuracy increased from 70.0 % to 80.8 %), with dermatology residents showing the largest gain.

Conclusions

The proposed CNN‐based models demonstrated robust performance in differentiating NUM from melanonychia and improved diagnostic accuracy and agreement among human evaluators. While not intended to replace clinical judgment, this approach shows promise as a supportive screening tool in clinical settings, warranting further validation in larger, multi‐institutional, and multi‐ethnic cohorts.

Schlagwörter

Stichwörter der Autor:innen

AI‐assisted diagnosisdeep learningmelanonychianail unit melanoma

Autor:innen und Institutionen

  • Department of Precision Medicine, Yonsei University Wonju College of Medicine, Wonju-si, Gangwon-do, Republic of Korea.
  • Department of Medical Informatics and Biostatistics, Graduate School, Yonsei University, Wonju-si, Gangwon-do, Republic of Korea.
  • Department of Dermatology, School of Medicine & Institute for Medical Science, Keimyung University, Daegu, South Korea.
  • Department of Dermatology, School of Medicine, Kyungpook National University, Daegu, South Korea.
  • Department of Dermatology, Yeungnam University College of Medicine, Daegu, Republic of Korea.
  • Department of Dermatology, Severance Hospital, Cutaneous Biology Research Institute, Yonsei University College of Medicine, Seoul, South Korea.

ORCID-Profile: Yusung Chu, Hae June Sung, Byungho Oh

Förderung

  • Yonsei University College of Medicine
  • National Research Foundation of Korea (NRF)

Zitieren

APA

Chu, Y., Yang, S., Jung, J. W., Kim, J. Y., Kim, J. G., Sung, H. J., & Oh, B. (2026). AI‐assisted diagnosis of nail unit melanoma and melanonychia using a clinical deep learning model. JDDG: Journal der Deutschen Dermatologischen Gesellschaft. https://doi.org/10.1111/ddg.70347

Vancouver

Chu Y, Yang S, Jung JW, Kim JY, Kim JG, Sung HJ, et al. AI‐assisted diagnosis of nail unit melanoma and melanonychia using a clinical deep learning model. JDDG: Journal der Deutschen Dermatologischen Gesellschaft. 2026. doi:10.1111/ddg.70347

BibTeX
@article{Chu2026,
  author = {Chu, Yusung and Yang, Sejung and Jung, Jin-Woong and Kim, Jun Young and Kim, Joon-Goon and Sung, Hae June and Oh, Byungho},
  title = {AI‐assisted diagnosis of nail unit melanoma and melanonychia using a clinical deep learning model},
  journal = {JDDG: Journal der Deutschen Dermatologischen Gesellschaft},
  year = {2026},
  doi = {10.1111/ddg.70347}
}
Kostenlos starten →