Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Jul 18:104:adv40023.
doi: 10.2340/actadv.v104.40023.

Performance of a Machine Learning Algorithm on Lesions with a High Preoperative Suspicion of Invasive Melanoma

Filippos Giannopoulos  1 , Martin Gillstedt  2 , Sofia Lindskogen  3 , John Paoli  2 , Sam Polesie  2
Affiliations

Performance of a Machine Learning Algorithm on Lesions with a High Preoperative Suspicion of Invasive Melanoma

Filippos Giannopoulos et al. Acta Derm Venereol. .
No abstract available

PubMed Disclaimer

Figures

Fig. 1
Fig. 1
Receiver operating characteristic curves (ROC). The figure displays the ROC curves for the 2 respective image sets. The HPSI test set consisted of dermoscopic images of histopathologically confirmed melanomas that received the HPSI label (n=184, 119 invasive melanomas and 65 melanoma in situ). The All-melanoma test set comprised all dermoscopic images of melanomas with a histopathological verification regardless of the HPSI label (n=476; 169 invasive melanomas and 307 MIS). HPSIM: lesions with a high preoperative suspicion of being invasive melanomas.
Fig. 2
Fig. 2
Violin plots. The violin plots demonstrate the distinct difference of the sigmoid output between the HPSI melanoma in situ and all melanoma in situ (MIS) lesions. This illustrates that the HPSI melanoma in situ lesions were generally more challenging to diagnose and classify by both the dermatologists and the CNN. CNN: convolutional neural network; HPSIM: lesions with a high preoperative suspicion of being invasive melanomas.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Polesie S, Gillstedt M, Kittler H, Rinner C, Tschandl P, Paoli J. Assessment of melanoma thickness based on dermoscopy images: an open, web-based, international, diagnostic study. J Eur Acad Dermatol Venereol 2022; 36: 2002-2007. 10.1111/jdv.18436 - DOI - PMC - PubMed
    1. Polesie S, Jergeus E, Gillstedt M, Ceder H, Dahlen Gyllencreutz J, Fougelberg J, et al. . Can dermoscopy be used to predict if a melanoma is in situ or invasive? Dermatol Pract Concept 2021; 11: e2021079. 10.5826/dpc.1103a79 - DOI - PMC - PubMed
    1. Polesie S, Sundback L, Gillstedt M, Ceder H, Dahlen Gyllencreutz J, Fougelberg J, et al. . Interobserver agreement on dermoscopic features and their associations with in situ and invasive cutaneous melanomas. Acta Derm Venereol 2021; 101: adv00570. 10.2340/actadv.v101.281 - DOI - PMC - PubMed
    1. Swedish guidelines for malignant melanoma [in Swedish], Version 6.0, last updated: December 14, 2021: Available from: https://kunskapsbanken.cancercentrum.se/globalassets/cancerdiagnoser/hud...
    1. Gillstedt M, Hedlund E, Paoli J, Polesie S. Discrimination between invasive and in situ melanomas using a convolutional neural network. J Am Acad Dermatol 2022; 86: 647-649. 10.1016/j.jaad.2021.02.012 - DOI - PubMed

LinkOut - more resources