Ahmet Ekin (Philips Senior Scientist - Project Manager)
Octavian Soldea (Postdoc Sabanci University)
Devrim Unay (Philips)
Gokhan Uzunbas (alumni)
Patient-to-patient search, which can be defined as comparing multiple patients and retrieving relevant cases among them, should especially help the medical expert in diagnosis of diseases whose causes and progress have not yet been completely unraveled, and diseases that affect large number of patients such as Alzheimer’s and Parkinson’s.
To this end, in the framework of the IRonDB Project we developed a Patient Search tool, where the user can load a patient’s image data, defines search parameters such as region-of-interest and image feature type selection, and the system sorts and visualizes the cases in the OASIS database according to visual similarity.
The following two images show snapshots of the input and output panes of the Patient Search tool for a retrieval example.