In many medical fields, such as burn medicine, chronic wound management, forensics, etc., the affected body surface of patients is an essential diagnostic factor – a documentation of the course of treatment is essential. For example, the success of a therapeutic approach in chronic wound management can only be assessed by the temporal course of wound size and position.

In the research focus, virtual 3-dimensional patient avatars are created which correspond as closely as possible to the real patients. The avatars are used for objective diagnostics and medical documentation. The technical basis for this is a platform-independent and generic implementation that can be used in many medical fields.

The visualization and interaction of/with the avatars is carried out on consumer hardware such as smartphones, tablets or PCs. Image data are used for shape and pose adaptation by means of modern machine-learning methods. Even though a 3D scan would certainly have certain advantages in terms of accuracy, additional hardware is deliberately not used here to ensure a high degree of acceptance and penetration.

A further research aspect is the demand for a preferably automated transfer of data from the real world to the patient’s avatar. These include dermatological situations, burns, wounds, X-rays, etc.

References