Deep Learning Artificial Intelligence for Single Photon Emission Computed Tomography: A Comprehensive Overview and Future Perspectives

The application of deep learning (DL) artificial intelligence techniques within the realm of medical imaging, particularly in nuclear medicine, has emerged as a vibrant area of investigation in recent years. Single photon emission computed tomography (SPECT), a crucial branch of nuclear medicine imaging, furnishes clinicians with valuable functional information, distinctively contributing to diagnostic accuracy. This paper systematically reviews the principal research directions, significance, and current state-of-the-art applications of DL in SPECT, pinpointing existing limitations in current studies. Furthermore, it provides a forward-looking outlook on prospective avenues of inquiry in this rapidly evolving field.