The Role of Artificial Intelligence in Advancing Theranostics Dosimetry for Cancer Therapy: a Review.

Abstract

Cancer treatment has greatly benefited from advancements in radiopharmaceutical therapy, which requires precise dosimetry to enhance therapeutic efficacy and minimize risks to healthy tissues. This review investigated the role of artificial intelligence (AI) in theranostic radiopharmaceutical dosimetry, focusing on image quality enhancement, dose estimation, and organ segmentation. An in-depth review of the literature was conducted using targeted keywords searches in Google Scholar, PubMed, and Scopus. Selected studies were evaluated for their methodologies and outcomes. Traditional dosimetry techniques such as organ-level and voxel-based methods are discussed. Deep learning (DL) models based on U-Net, generative adversarial networks, and hybrid transformer networks for image synthesis and generation, image quality improvement, organ segmentation, and radiation dose estimation are reviewed and discussed. While DL shows great potential for enhancing dosimetry accuracy and efficiency, challenges such as the need for accurate dose estimation from theranostic pairs, lack of imaging data, and modeling of radionuclide decay chains must be addressed using DL models. In addition, the optimization and standardization of DL and AI models is crucial for ensuring clinical reliability and should be given high priority to support their effective integration into clinical practice.