Reducing the Impact of Confounding Factors on Skin Cancer Classification via Image Segmentation: Technical Model Study

• Egile Nagusiak: Maron, Roman C (Egilea), Hekler, Achim (Egilea), Krieghoff-Henning, Eva (Egilea), Schmitt, Max (Egilea), Schlager, Justin G (Egilea), Utikal, Jochen S (Egilea), Brinker, Titus J (Egilea)
• Formatua: Liburua
• Argitaratua: JMIR Publications, 2021-03-01T00:00:00Z.
• Gaiak: article
• Sarrera elektronikoa: Connect to this object online.

BackgroundStudies have shown that artificial intelligence achieves similar or better performance than dermatologists in specific dermoscopic image classification tasks. However, artificial intelligence is susceptible to the influence of confounding factors within images (eg, skin markings), which ca...