Retrospective evaluation of the clinical utility of reconstructed computed tomography images using artificial intelligence in the oral and maxillofacial region

This study aimed to utilize artificial intelligence (AI) to transform medical images stored in the picture archiving and communication system (PACS) from 3 mm slices to 1 mm slices and assess the accuracy of the reconstructions. Using original 1.0 mm CT slices from 30 patients, they were reformatted to 3.0 mm and then reconstructed back to 1.0 mm with AI. When compared, AI-constructed images displayed significantly smaller discrepancies from original images than the 3.0 mm rough images, especially in hard and soft tissue landmarks. This suggests that AI can enhance image accuracy, with errors less than 1.0 mm. Historically, PACS has stored thicker slices due to storage constraints, but the surgical precision required in fields like oral and maxillofacial surgery makes finer slices essential. The study utilized AVIEW1.0, a smart slicer from Coreline soft, as the AI source for reconstructions. Overall, the AI technique could optimize PACS storage efficiency and improve the utility of CT data.