University of Southern California
Computer-aided Diagnosis (CAD)
Bone Age Assessment
Data Grid
RT Informatics
Informatics Beyond Radiology

A Multimedia Electronic Patient Record System (ePR) for a Randomized Controlled Trial of Rehabilitation Dose Optimization after Stroke


Imaging studies have been used widely across the healthcare enterprise including imaging-based clinical trials. The objective of the DOSE Optimization Stroke Evaluation Clinical Trial is to determine prospectively the optimal dose of therapy that will lead to further improvements of upper extremity use for individual patients who have had a stroke.
To facilitate the data entry and data management for DOSE trial and provide a platform for the development of the data mining tools, we design and implement a clinical trial-oriented ePR system.

The DOSE trial aims to recruit 60 subjects. Each subject is recruited, enrolled, and randomized into the trial and undergo 10 months of therapy A variety of data will be collected including:

  • Rehabilitation evaluation and clinical test data in forms
  • MRI studies with DTI
  • Transcranial magnetic stimulation (TMS) sensor data

As shown in Figure 1, the workflow for each participant of the DOSE clinical trial has three major stages: enrollment, participation and follow-up.

Figure 1 Workflow of the DOSE Clinical Trial


As shown in figure 2, the system is comprised of a database, a file storage system, a web server, a web based graphical user interface, and decision-support tools. The data mining & computational models are still under development. Data flow includes the demographic data, treatment records, screening and evaluation data, MRI studies and TMS data. The system can support PC, laptop and mobile devices or iPad.

Figure 2 System Architecture


The system has been developed at IPILab, USC and was implemented in the DOSE clinical trial. Figure 3 is a screenshot of the GUI application. The first arrow shows the timeline status with an overview progress of the trial for the specific trial subject. The second arrow shows the forms required in each stage. Figure 5 is an integrated DICOM viewer with measurement tools, ROI tools and annotation tools. The screen shot shows a measurement.

Figure 3 Subject Overview    Figure 4 DICOM Viewer

Copyright 2005-2013.  Image Processing and Informatics Lab, 1042 Downey Way. Denney Research Center (DRB) 264 Los Angeles, CA 90089-1111   Phone: 213.821.8395 Fax: 213.743.2962