Supporting diagnosis of melanoma

Supporting diagnosis of melanoma

Dermatofluoroscopy is a novel method for early diagnosis of malignant melanoma in vivo offering doctors and patients reliable, fast and painless diagnostic support.

The patented technology allows for selective excitation of melanin fluorescence in the skin. The magnosco machine-learning algorithm analyze the fluorescence-dominated signals to generate a score as decision support for dermatologists.

magnosco DermaFC, in which the method is used, is used for study purposes only.

Evidence-based and objective method

The calibration and validation of DermaFC was carried out as part of a three-year, multi-centre clinical trial at the University Hospital of Tübingen, the University Hospital of Heidelberg and the Charité Berlin.

We are working on continuous improvement of dermatofluoroscopy method through participation in clinical trials and scientific conferences.

The latest study results can be found here:

Characteristic spectral signals

Under normal excitation conditions, ultra-weak melanin fluorescence is completely surpassed by the autofluorescence of other endogenous fluorophores in the skin such as NADH coenzyme, tryptophan, flavins or lipofuscins. With help of stepwise two-photon absorption, melanin can be selectively excited and its fluorescence becomes visible.


In the dermatofluoroscopy, melanocytes of healthy skin, melanocytes of nevi and, melanocytes of melanoma exhibit characteristic fluorescence spectra, allowing for reliable differentiation between benign and malignant tissue.


Method of Dermatofluoroscopy

The basis for the excitation of melanin is the stepwise two-photon absorption. For this purpose, nanosecond laser pulses are focused in the epidermis at 800 nm and the resulting melanin fluorescence is detected in the range of approx. 385 - 785 nm.

Using this excitation method, the lesion is scanned point by point.

Acceptance & Accuracy

A "high" to "very high" level of patient acceptance and trust in dermatofluoroscopy was found in 74 % of responders

- C. Fink, 'Patient acceptance and trust in automated computer-assisted diagnosis of melanoma with dermatofluoroscopy.' Deutsche Dermatologische Ges. (2018)

The scoring algorithm revealed a sensitivity of 91.7% and a specificity of 83.0% in diagnosing malignant melanoma. Using additionally the image segmentation for normalization of lesions' region of interest, a further improvement of sensitivity of 95.8% was achieved, with a corresponding specificity of 80.9%.

- L. Szyc, 'Diagnostic Performance of a Support Vector Machine for Dermatofluoroscopic Melanoma Recognition: The Results of the Retrospective Clinical Study on 214 Pigmented Skin Lesions. Diagnostics (2019)