Memorial Sloan Kettering Cancer Center researchers found that a new deep learning approach called DeepPET was 108 times and three times faster in reconstructing high-quality PET images, compared with standard ordered subset expectation maximization and filtered back-projection, respectively. The technique, described in the journal Medical Image Analysis, "should lead to higher patient throughput, as well as more reliable and faster diagnoses and treatment decisions, and thus better care for cancer patients," and may also be used in other modalities such as SPECT, researchers wrote.
New deep learning technique tied to faster PET image reconstruction
Sign up for SNMMI SmartBrief
Nuclear medicine and molecular imaging news
Get the intelligence you need: news and information that is changing your industry today, hand-curated by our professional editors from thousands of sources and delivered straight to your inbox.