Comparative analysis of iterative vs AI-based reconstruction algorithms in CT imaging for total body assessment: Objective and subjective clinical analysis

• Published in: Physica medica Vol. 136; p. 105034
• Main Authors: Tucciariello, Raffaele Maria, Botte, Manuela, Calice, Giovanni, Cammarota, Aldo, Cammarota, Flavia, Capasso, Mariagrazia, Nardo, Giuseppina Di, Lancellotti, Maria Imma, Palmese, Valentina Pirozzi, Sarno, Antonio, Villonio, Antonio, Bianculli, Antonella
• Format: Journal Article
• Language: English
• Published: Italy Elsevier Ltd 01.08.2025
• Subjects: Algorithms; Artificial Intelligence; Artificial intelligence algorithms; Brain - diagnostic imaging; Computed tomography; CT image reconstruction; Humans; Image Processing, Computer-Assisted - methods; Image quality; Iterative algorithms; Oncology imaging; Phantoms, Imaging; Radiologists’ reporting; Signal-To-Noise Ratio; Tomography, X-Ray Computed; Whole Body Imaging - methods; Image quality; Oncology imaging; Computed tomography; CT image reconstruction; Artificial intelligence algorithms; Iterative algorithms; Radiologists’ reporting
• ISSN: 1120-1797; 1724-191X; 1724-191X
• DOI: 10.1016/j.ejmp.2025.105034

•AI and iterative methods complement each other but need careful clinical integration.•Radiologists noted key anatomical challenges in algorithms performance evaluation.•The study stresses harmonizing phantom data with radiologists’ clinical evaluations.•Critical analysis ensures AI doesn’t compromise diagnostic image interpretability. This study evaluates the performance of Iterative and AI-based Reconstruction algorithms in CT imaging for brain, chest, and upper abdomen assessments. Using a 320-slice CT scanner, phantom images were analysed through quantitative metrics such as Noise, Contrast-to-Noise-Ratio and Target Transfer Function. Additionally, five radiologists performed subjective evaluations on real patient images by scoring clinical parameters related to anatomical structures across the three body sites. The study aimed to relate results obtained with the typical approach related to parameters involved in medical physics using a Catphan physical phantom, with the evaluations assigned by the radiologists to the clinical parameters chosen in this study, and to determine whether the physical approach alone can ensure the implementation of new procedures and the optimization in clinical practice. AI-based algorithms demonstrated superior performance in chest and abdominal imaging, enhancing parenchymal and vascular detail with notable reductions in noise. However, their performance in brain imaging was less effective, as the aggressive noise reduction led to excessive smoothing, which affected diagnostic interpretability. Iterative reconstruction methods provided balanced results for brain imaging, preserving structural details and maintaining diagnostic clarity. The findings emphasize the need for region-specific optimization of reconstruction protocols. While AI-based methods can complement traditional IR techniques, they should not be assumed to inherently improve outcomes. A critical and cautious introduction of AI-based techniques is essential, ensuring radiologists adapt effectively without compromising diagnostic accuracy.