Physicians use their clinical experience to identify patterns (such as symptoms) that are common among a group of patients, leading to treatment strategies. However, rather than having to base judgement on few patients, digital medical information allows the inspection of data from thousands if not Millions of patients at the same time. In…
The progression of multiple sclerosis (MS) is characterized by the evolution of brain lesions. Traditionally, neuroradiologists need to manually track and compare a large number of lesions in MRI images over multiple exams. Novel AI methods support this process, by automating the detection, localization, and quantification of lesions. WebJazz is a web application that makes…
To start the design of an orthosis or of a prosthesis, orthopedists commonly use plaster casting to acquire the patient’s limb shape. The rest of the design workflow is so far already digital. However, the limb shape acquisition is still analog, wet, inaccurate and time consuming. The Swiss startup BellwaldTec…
The use of many anticancer drugs is problematic due to severe adverse effects. While the recent clinical launch of several kinase inhibitors led to tremendous progress, these targeted agents tend to be of non-specific nature within the kinase target class. A future strategy will be the development of nanocarrier-based systems…
Early and accurate disease diagnosis is crucial for stopping disease progression and identifying appropriate treatments, but precise diagnosis of autoimmune disease is notoriously challenging due to the non-specific symptoms: it can take 4 to 5 years and multiple visits to various physicians. However, an early and precise disease diagnosis is…
In today’s intensive care units (ICUs), biosensors collect up to 100 GB of data per patient every day. These vast amounts of data are only valuable if they lead to better patient outcomes. The following questions arise:How can medical staff gain insights from this data?How can risk constellations be identified as early as…
Model-based signal processing approaches often form the missing link between raw sensor data and sophisticated machine learning methods. To provide state-of-the-art algorithms in this area, FHNW/HLS recently launched the open source project lmlib.ch. In this presentation we will give a short insight into the project with some…