Defining cutting-edge imaging informatics
Dr. Erickson's lab creates new informatics tools that can clearly and concisely extract and convey the wealth of information in medical images to improve patient outcomes. In this example, an informatics tool reads the image to measure fat under the skin and around the internal organs. It also measures the muscles of the abdomen. These measurements help predict people's risk of getting several diseases, including cardiovascular disease.
Overview
Mayo Clinic's Radiology Informatics Lab, directed by Bradley J. Erickson, M.D., Ph.D., adds value to medical imaging by designing tools that:
- Help extract quantitative and diagnostic information, including subtle textures, that humans can't perceive.
- Optimize the creation and quality of medical images, including deep-learning-based reconstruction.
- Improve the workflow for planning, executing and reporting medical imaging.
The lab's original work focused on brain cancer. Now its main research focus is creating image-derived biomarkers of diseases. The lab works on a wide range of diseases and medical images from the Mayo Clinic Department of Radiology and other image-producing departments.
RIL-Contour annotation software
Main view of the open-source annotation software RIL-Contour, which includes classic annotation tools plus a deep-learning model
The Radiology Informatics Lab has created an image annotation tool called RIL-Contour. It allows users to divide medical images quickly and easily into parts. Imaging experts call this "segmentation." RIL-Contour has advanced image processing tools for segmentation. It can use external deep-learning tools that can produce segmentations. It also allows users to refine these segmentations. Users define the structure of labels, including RadLex labels that allow interoperability.
The lab also has created a data management tool called PESSCARA. This tool can accept Digital Imaging and Communications in Medicine (DICOM) images, remove protected health information and perform complex workflows. These workflows may include steps completed by humans, algorithms or both. PESSCARA also supports sophisticated versioning and is integrated with high-performance computing environments.
Related publications:
Affiliations
Dr. Erickson's Radiology Informatics Lab is affiliated with several Mayo Clinic research areas: