Automatic exposure control (AEC) systems have been developed by computed tomography (CT) manufacturers to improve the consistency of image quality among patients and to control the absorbed dose. Since a multichannel helical CT scan may easily increase individual radiation doses, this technical improvement is of special interest in children who are particularly sensitive to ionizing radiation, but little information is currently available regarding the precise performance of these systems on small patients. Our objective was to assess an AEC system on pediatric dose phantoms by studying the impact of phantom transmission and acquisition parameters on tube current modulation, on the resulting absorbed dose and on image quality. We used a four-channel CT scan working with a patient-size and z -axis-based AEC system designed to achieve a constant noise within the reconstructed images by automatically adjusting the tube current during acquisition. The study was performed with six cylindrical poly(methylmethacrylate) (PMMA) phantoms of variable diameters (10- 32 cm) and one 5 years of age equivalent pediatric anthropomorphic phantom. After a single scan projection radiograph (SPR), helical acquisitions were performed and images were reconstructed with a standard convolution kernel. Tube current modulation was studied with variable SPR settings (tube angle, mA, kVp) and helical parameters (6- 20 HU noise indices, 80- 140 kVp tube potential, 0.8- 4 s. tube rotation time, 5- 20 mm x-ray beam thickness, 0.75-1.5 pitch, 1.25- 10 mm image thickness, variable acquisition, and reconstruction fields of view). CT dose indices (CTDIvol) were measured, and the image quality criterion used was the standard deviation of the CT number measured in reconstructed images of PMMA material. Observed tube current levels were compared to the expected values from Brooks and Di Chiro's [R.A. Brooks and G.D. Chiro, Med. Phys. 3, 237-240 (1976)] model and calculated values (product of a reference value multiplied by a dose ratio measured with thermoluminescent dosimeters). Our study demonstrates that this AEC system accurately modulates the tube current according to phantom size and transmission to achieve a stable image noise. The system accurately controls the tube current when changing tube rotation time, tube potential, or image thickness, with minimal variations of the resulting noise. Nevertheless, CT users should be aware of possible changes of tube current and resulting dose and quality according to several parameters: the tube angle and tube potential used for SPR, the x-ray beam thickness (tube current decreases and image noise increases when doubling x-ray beam thickness), the pitch value (a pitch decrease leads to a higher dose but also to a higher noise), and the acquisition field of view (FOV) (tube current is lower when using the small acquisition FOV compared to the large one, but the use of small acquisition FOV at 120 kVp leads to a peculiar increase of tube current and CTDIvol). © 2007 American Association of Physicists in Medicine.