AI to support the early diagnosis of Systemic Sclerosis (SSc)

We recently published a joint work with the Department of Rheumatology, University Hospital of Zurich, the Department of Quantitative Biomedicine, and the Department of Rheumatology and Immunology, University Hospital Bern. The study assessed the capacity of AI to detect patterns of microangiopathy in nailfold capillaroscopy (NFC) images of patients with Systemic Sclerosis (SSc). We used local registers from the University Hospital Zurich and ‘off-the-shelf’ artificial intelligence models (ViT). In their editorial Maurizio Cutolo, Emanuele Gotelli and Vanessa Smith conclude, “the ViT is welcome and seems to represent a further valid system for an early and fast reading of the NFC images/morphological biomarkers in SSc, reaching for the first time the fusion of EULAR-validated algorithms for the delineation of the scleroderma pattern from the non-scleroderma pattern and artificial intelligence.

Zoo visit and Christmas dinner

Last week, our Lab went to the Zoo of Zurich and had a nice Christmas dinner with Fondue at “Chäsalp”. First, we spent the afternoon in the zoo where we could observe many interesting animals. Queen of animals Fun fact: Penguins are not able to pick up fish from the ground by themselves A hungry tiger A super cute red panda After the zoo visit, we went to the near located restaurant “Chäsalp” from where we had a nice view over the city.

Lab Outing: Küsnacht walk

A late autumn "hike".

Interpretable Machine Learning

How can we better understand what our models are telling us?