Comparative and complementary diagnostic value of dermatoscopy and clinical close-up photography in skin cancer diagnosis: A study from the MILK10k dataset - 22/04/26

Doi : 10.1016/j.jaad.2026.03.069

Christoph Müller, MD ^a,^⁎ , Anna Wolber, MD ^a, Aimilios Lallas, MD ^b, Giuseppe Argenziano, MD ^c, Iris Zalaudek, MD ^d, H. Peter Soyer, MD ^e,^f, Susana Puig, MD ^g, Bengu Nisa Akay, MD ^h, Ana Maria Forsea, MD ^i,^j, Josep Malvehy, MD ^k, Ashfaq Marghoob, MD ^l, Zoe Apalla, MD ^m, Cliff Rosendahl, MD ⁿ, Konstantinos Liopyris, MD ^o, Ofer Reiter, MD ^p, Caterina Longo, MD ^q, Philipp Tschandl, MD ^a,^r, Harald Kittler, MD ^a,^r

^a Department of Dermatology, Medical University of Vienna, Vienna, Austria

^b First Department of Dermatology, School of Medicine, Faculty of Health Sciences, Aristotle University, Thessaloniki, Greece

^c Dermatology Unit, University of Campania "Luigi Vanvitelli", Naples, Italy

^d Department of Dermatology, Medical University of Trieste, Trieste, Italy

^e Frazer Institute, The University of Queensland, Dermatology Research Centre, Brisbane, Queensland, Australia

^f Department of Dermatology, Princess Alexandra Hospital, Brisbane, Australia

^g Melanoma Unit, Dermatology Department, Hospital Clínic de Barcelona, IDIBAPS, Universitat de Barcelona, Barcelona, Spain

^h Department of Dermatology, Faculty of Medicine, Ankara University, Ankara, Turkey

ⁱ Department of Oncologic Dermatology, Carol Davila University of Medicine and Pharmacy Bucharest, Elias University Hospital Bucharest, Bucharest, Romania

^j Health and Medical University Potsdam, Potsdam, Germany

^k Dermatology Department, Hospital Clínic de Barcelona, University of Barcelona, IDIBAPS, CIBER de enfermedades raras, Instituto Carlos III, Barcelona, Spain

^l Memorial Sloan Kettering Cancer Center, Hauppauge, New York

^m Second Department of Dermatology, Aristotle University, Thessaloniki, Greece

ⁿ Mayne Academy of General Practice, Medical School, The University of Queensland, Brisbane, Queensland, Australia

^o Department of Dermatology, Andreas Syngros Hospital of Venereal and Dermatological Diseases, University of Athens, Athens, Greece

^p Dermatology Division, Rabin Medical Center, Petach Tikva, and Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel

^q Department of Dermatology, University of Modena and Reggio Emilia, Modena, Italy

^r Comprehensive Center for Artificial Intelligence in Medicine, Medical University of Vienna, Vienna, Austria

^∗ Correspondence to: Christoph Müller, MD, Department of Dermatology, Medical University of Vienna, Währinger Gürtel 18-20, Vienna, 1090, Austria. Department of Dermatology Medical University of Vienna Währinger Gürtel 18-20 Vienna 1090 Austria

Sous presse. Épreuves corrigées par l'auteur. Disponible en ligne depuis le Wednesday 22 April 2026
Cet article a été publié dans un numéro de la revue, cliquez ici pour y accéder

Abstract

Background

While dermatoscopy's added value to clinical imaging is known, the standalone value of dermatoscopy and clinical images remains unclear.

Objective

To quantify the standalone and complementary value of dermatoscopy and clinical close-up imaging across lesion types and reader expertise.

Methods

In an online reader study, 283 participants diagnosed 1567 paired images (clinical close-up/dermatoscopic) of skin cancers and mimics. The presentation order was randomized. Diagnostic accuracy, sensitivity, and specificity were compared. The effects of modality, reader expertise, and presentation order were analyzed using a generalized linear mixed model.

Results

Dermatoscopy alone showed higher sensitivity (85.0% vs 74.2%) but lower specificity (66.8% vs 71.9%) compared with clinical close-up images alone. It improved accuracy for melanoma and basal cell carcinoma, but not for nevi. Adding either modality increased the odds of a correct diagnosis. Dermatoscopy raised the odds by 52% (OR = 1.52; 95% CI: 1.36-1.70; P < .001), while clinical close-ups increased the odds by 40% (OR = 1.40; 95% CI: 1.20-1.61; P < .001).

Limitations

Image-based evaluation simulated teledermatology rather than face-to-face assessment; potential selection and verification bias cannot be excluded.

Conclusion

Dermatoscopy alone yields higher sensitivity for malignant lesions but lower specificity for nevi than clinical close-up images. The latter provides complementary diagnostic cues, underscoring the value of integrating both modalities for optimal assessment.

Le texte complet de cet article est disponible en PDF.

Key words : dermatoscopy, diagnostic accuracy, diagnostic modality, sensitivity, skin cancer, specificity

Abbreviations used : IDS, OR

Plan

Ethical considerations

Statistics

Results

Participants

Comparative diagnostic accuracy of image modalities

Complementary diagnostic value of each modality

Order effects

Generalized linear mixed model

Discussion

Conclusion

Limitations

	Funding sources: None.
	Patient consent: As the study involved no direct interventions with patients and only anonymized image data were used, patient consent was not required.
	IRB approval status: Reviewed and approved by the Ethics Committee of the Medical University of Vienna, Vienna, Austria, approval number 14488/ .