Radiation exposure from computerized tomography and risk of childhood leukemia: Finnish register-based case-control study of childhood leukemia (FRECCLE)

Abstract

The only well-established risk factors for childhood leukemia are high-dose ionizing radiation and Down syndrome. Computerized tomography is a common source of low-dose radiation. In this study, we examined the magnitude of the risk of childhood leukemia after pediatric computed tomography examinations. We evaluated the association of computed tomography scans with risk of childhood leukemia in a nationwide register-based case-control study. Cases (n=1,093) were identified from the population-based Finnish Cancer Registry and three controls, matched by gender and age, were randomly selected for each case from the Population Registry. Information was also obtained on birth weight, maternal smoking, parental socioeconomic status and background gamma radiation. Data on computed tomography scans were collected from the ten largest hospitals in Finland, covering approximately 87% of all pediatric computed tomography scans. Red bone marrow doses were estimated with NCICT dose calculation software. The data were analyzed using exact conditional logistic regression analysis. A total of 15 cases (1.4%) and ten controls (0.3%) had undergone one or more computed tomography scans, excluding a 2-year latency period. For one or more computed tomography scans, we observed an odds ratio of 2.82 (95% confidence interval: 1.05 - 7.56). Cumulative red bone marrow dose from computed tomography scans showed an excess odds ratio of 0.13 (95% confidence interval: 0.02 - 0.26) per mGy. Our results are consistent with the notion that even low doses of ionizing radiation observably increase the risk of childhood leukemia. However, the observed risk estimates are somewhat higher than those in earlier studies, probably due to random error, although unknown predisposing factors cannot be ruled out.

Figure 1.

Flow chart depicting the selection of study subjects. The flow of cases is represented on a white background and the controls on a light gray background. The necessary exclusions are shown in red boxes. Dashed lines represent the linking of the study subjects with the CT scans collected.

Figure 2.

Flow chart linking the collected computed tomography scans to the study subjects The flow of the CT scans is represented on a white background and the CT scans to different body parts on a light gray background. The necessary exclusions are shown in red boxes.

Figure 3.

Histograms of (A) the ages of the subjects at the time of computed tomography scan and (B) the cumulative doses received by the subjects, calculated with NCICT.

Figure 4.

Dose-response curve of cumulative red bone marrow dose from pediatric computed tomography scans and childhood leukemia. The point estimates with 95% confidence intervals are for the three dose index levels and the fitted curve is for the cumulative RBM dose calculated with NCICT. The shaded area represents the 95% confidence interval for the continuous dose-response. The vertical axis is on a binary logarithm scale.