Construction and benchmarking of the AFISMI water-filled CT phantom against the ACR, AAPM and Catphan 600 phantoms using automated image quality analysis with IndoQCT.

Routine computed tomography (CT) quality control (QC) is used to verify adequate image quality, support radiation-dose optimisation, and identify changes in scanner performance. Commonly used test objects include the ACR CT Phantom, the AAPM CT Performance Phantom, and the Catphan 600. The AFISMI CT Phantom is a locally manufacturable, water-filled prototype developed for routine constancy testing. This study provides preliminary single-scanner benchmarking of the AFISMI phantom using the IndoQCT automated analysis platform. The AFISMI phantom comprises a hollow polymethyl methacrylate (PMMA) shell (16 cm diameter and 10 cm length), a nominal 1.0-mm aluminium sheet fixed at 45° for slice-thickness measurement, and acrylic and Teflon inserts. Each phantom was scanned in three separate acquisitions on a Philips Ingenuity 128 CT scanner using 120 kVp, 300 mAs, a 5.0-mm slice thickness, and a 200-mm field of view; each acquisition was analysed independently. IndoQCT assessed uniformity in homogeneous water-filled or water-equivalent regions, Hounsfield unit (HU) accuracy, noise power spectrum (NPS), modulation transfer function (MTF), slice thickness, and signal-difference-to-noise ratio (SDNR). Raw-noise magnitude was not analysed separately because it is not included in the Indonesian national CT Compliance Test protocol used to define the QC scope. Under the tested scan and reconstruction conditions, the AFISMI phantom produced broadly comparable results for uniformity, water CT-number accuracy, MTF, and slice-thickness measurement relative to the commercial reference phantoms. NPS magnitude and shape differed among the phantoms. The AFISMI phantom had a higher mean SDNR than the AAPM phantom under the tested conditions, but this result cannot be used to claim better low-contrast performance because phantom geometry, target contrast, and background materials differed. Scalar outcomes are reported as mean ± standard deviation from three acquisitions and compared descriptively; no inferential statistical tests were performed. The AFISMI phantom and IndoQCT showed feasibility for automated CT constancy measurements under the tested single-scanner conditions. The findings represent preliminary benchmarking rather than independent validation or evidence of comparative advantage. Longitudinal baseline testing, multi-scanner evaluation, production-unit reproducibility assessment, and formal cost analysis are required before broad QA applicability or economic advantage can be established.