Interstitial lung disease (ILD) is a group of more than 200 chronic lung disorders characterized by inflammation and scarring of the lung tissue that leads to respiratory failure. ILD accounts for 15% of all cases seen by pulmonologists and can be caused by autoimmune disease, genetic abnormalities, infections, drugs or long-term exposure to hazardous materials. Although ILD is a heterogeneous group of histologically distinct diseases, most of these exhibit similar clinical presentations and their diagnosis often presents a diagnostic dilemma.
To this end, we investigate AI- and computer vision-based algorithms for the analysis of imaging, clinical /biochemical and other disease-related data for diagnosis and management of ILDs. More specifically, algorithmic approaches for the fully automatic segmentation of lung and anatomical structures of the lung cavity, the segmentation and characterization of lung pathological tissue, and the calculation of disease distributions are introduced and continuously validated within the framework of research trials. The image analysis results along with the additional disease-related information are further analysed not only in order to support the faster diagnosis, but also for the more efficient disease management in the sense of treatment selections and disease progression.
We aim to improve COVID-19 patient care by using imaging and medical disease-related data from Swiss medical centers along with artificial intelligence (AI) algorithms, and particularly deep learning methodologies. Scope is to develop a decision support system to allow the early detection of the disease, to improve the distinction of COVID-19 from other types of pneumonias and proceed to assessment of the disease’s severity.
The research is carried out within the framework of the INTACT research project, supported by Bern University Hospital, “Inselspital”, the Swiss National Science Foundation (SNSF), Stiftung Lindenhof Bern, Roche and Hasler Stiftung.