MIT & MITM 12/18cp Projects
Lossless Compression of Dual-Modality Medical Images
This project will develop a tool to compress and uncompress dual-modality PET-CT volumes, aiming to reduce the space requirement for PET-CT data achieve while keeping all useful information.
Dual modality PET-CT imaging offers aligned anatomical (CT) and functional (PET) imaging data for a patient in a single scanning session, and therefore, is now a routine diagnostic tool in major health centers around the world. However, the data acquired by PET-CT scanner is very huge. Take the Biograph LSO Duo PET/CT scanner installed in the Department of PET and Nuclear Medicine at Royal Prince Alfred Hospital for example, a whole-body scan using this machine will produce two 3D data volumes of size up to 400 MB. The data volume will become even larger for new scanners with higher resolution. Therefore, it is worthwhile to develop lossless compression algorithms for dual-modality medical images.
This project aims to develop a toolbox for compressing and uncompressing dual-modality medical images. We expect that the outcome of this project can be used in medical data achieve and related research. Students involved in the projects will have the opportunity to work in RPA hospital for a certain period of time depending on the progress and necessarily. By finishing this project, students will learn some technologies in medical imaging, and digital image processing and be more experienced in programming and problem solving.
Keywords: Medical image analyse, image compression, PET-CT imaging
Supervisors: Dr. Tom Cai, Dr. Yong Xia
Research Locations: Level 3, School of IT building J12