Application
Software to perform attenuation correction in quantitative PET imaging.
Key Benefits
- Improves quantification accuracy and reliability.
- Applicable to PET data collected on hybrid platform (PET/CT or PET/MRI).
- Reduced radiation exposure.
- No need of additional scans.
Market Summary
Positron-Emission Tomography (PET) is a nuclear medicine functional imaging technique that is used to observe metabolic processes in the body as an aid to the diagnosis of disease. However, most of signal is lost because of their absorption in the body, depending on the size of the body in the field of view. This loss of detection is called attenuation and leads to severe artifacts in PET image, unless it is corrected during image reconstruction. Attenuation correction (AC) is an essential component of PET reconstruction that improves visual interpretation, and more importantly, enables absolute quantification. The Gold standard AC used consists in combining a CT (Computed Tomography) scanner with the PET scanner. However, limitations persist including propagation of CT-based artefacts and spatial inconsistencies such as PET-to-CT misalignment. In addition, concerns remain regarding the potential hazards of radiation exposures, especially CT doses and excessive exposures on pediatric patients receiving sequential scans. Therefore, techniques that offer high quality PET without the uncertainty of PET-to-CT misalignment are needed for more accurate AC and treatment of cancers.
Technical Summary
Emory inventors have created a deep learning-based method to perform whole-body PET attenuation correction. This system was tested using a total of 60 sets of whole-body PET/CT. The synthetic CT images generated with the proposed method demonstrate great resemblance to true CT images. These images not only recover lung, soft tissue and bony structures such as humerus and femur, but also demonstrate good contrast on fat and soft tissues around extremities.
Developmental Stage
The system was tested using real patients’ data and demonstrated excellent PET quantification accuracy.
Publications
Dong, X. et al. (2019). Phys. Med. Biol., 64(21), 215016.
Dong, X. et al. (2019). Phys. Med. Biol.
