collaborators

4 papers

eess.IV2024

Clinical Melanoma Diagnosis with Artificial Intelligence: Insights from a Prospective Multicenter Study

Lukas Heinlein, Roman C. Maron, Achim Hekler +27

Early detection of melanoma, a potentially lethal type of skin cancer with high prevalence worldwide, improves patient prognosis. In retrospective studies, artificial intelligence…

cs.CV2023

Mitigating the Influence of Domain Shift in Skin Lesion Classification: A Benchmark Study of Unsupervised Domain Adaptation Methods on Dermoscopic Images

Sireesha Chamarthi, Katharina Fogelberg, Roman C. Maron +2

The potential of deep neural networks in skin lesion classification has already been demonstrated to be on-par if not superior to the dermatologists diagnosis. However, the perform…

eess.IV2023

Using Multiple Dermoscopic Photographs of One Lesion Improves Melanoma Classification via Deep Learning: A Prognostic Diagnostic Accuracy Study

Achim Hekler, Roman C. Maron, Sarah Haggenmüller +28

Background: Convolutional neural network (CNN)-based melanoma classifiers face several challenges that limit their usefulness in clinical practice. Objective: To investigate the im…

cs.CV2023

Domain shifts in dermoscopic skin cancer datasets: Evaluation of essential limitations for clinical translation

Katharina Fogelberg, Sireesha Chamarthi, Roman C. Maron +2

The limited ability of Convolutional Neural Networks to generalize to images from previously unseen domains is a major limitation, in particular, for safety-critical clinical tasks…