Utilizing a 3D deep learning reconstruction to improve pediatric abdominal 3D LAVA-Flex image quality

Motivation: Fat suppressed T1 images, such as LAVA-FLEX, are routinely used in pediatric abdominal imaging, but can suffer for SNR and IQ issues. Goal(s): Our goal was to validate application of 3D deep learning to 3D LAVA-FLEX via image quality assessment and noise characterization. Approach: DL and conventionally reconstructed images were assessed by two radiologists and noise characteristics were evaluated by calculation of total variation and number of detected edges. Results: The radiologists preferred DL in a majority of cases (>80%), with noticeably lower noise and improved sharpness in DL images. Impact: The application of DL to routine pediatric 3D LAVA-FLEX imaging provides enhanced diagnostic quality, and has the potential to improve pediatric patient care.