Strong Correlation among Three Biodosimetry Techniques Following Exposures to Ionizing Radiation

A machine learning method for improving the accuracy of radiation biodosimetry by combining data from the dicentric chromosomes and micronucleus assays

A large-scale malicious or accidental radiological event can expose vast numbers of people to ionizing radiation. The dicentric chromosome (DCA) and cytokinesis-block micronucleus (CBMN) assays are well-established biodosimetry methods for estimating individual absorbed doses after radiation exposure. Here we used machine learning (ML) to test the hypothesis that combining automated DCA and CBMN assays will improve dose reconstruction accuracy, compared with using either cytogenetic assay alone. We analyzed 1349 blood sample aliquots from 155 donors of different ages (3-69 years) and sexes (49.1% males), ex vivo irradiated with 0-8 Gy at dose rates from 0.08 Gy/day to ≥ 600 Gy/s. We compared the performances of several state-of-the-art ensemble ML methods and found that random forest generated the best results, with R² for actual vs. reconstructed doses on a testing data subset = 0.845, and mean absolute error = 0.628 Gy. The most important predictor variables were CBMN and DCA frequencies, and age. Removing CBMN or DCA data from the model significantly increased squared errors on testing data (p-values 3.4 × 10^-8 and 1.1 × 10^-6, respectively). These findings demonstrate the promising potential of combining CBMN and DCA assay data to reconstruct radiation doses in realistic scenarios of heterogeneous populations exposed to a mass-casualty radiological event.

Cytogenetic Damage of Human Lymphocytes in Humanized Mice Exposed to Neutrons and X Rays 24 h After Exposure

Detonation of an improvised nuclear device highlights the need to understand the risk of mixed radiation exposure as prompt radiation exposure could produce significant neutron and gamma exposures. Although the neutron component may be a relatively small percentage of the total absorbed dose, the large relative biological effectiveness (RBE) can induce larger biological DNA damage and cell killing. The objective of this study was to use a hematopoietically humanized mouse model to measure chromosomal DNA damage in human lymphocytes 24 h after in vivo exposure to neutrons (0.3 Gy) and X rays (1 Gy). The human dicentric and cytokinesis-block micronucleus assays were performed to measure chromosomal aberrations in human lymphocytes in vivo from the blood and spleen, respectively. The mBAND assay based on fluorescent in situ hybridization labeling was used to detect neutron-induced chromosome 1 inversions in the blood lymphocytes of the neutron-irradiated mice. Cytogenetics endpoints, dicentrics and micronuclei showed that there was no significant difference in yields between the 2 irradiation types at the doses tested, indicating that neutron-induced chromosomal DNA damage in vivo was more biologically effective (RBE ∼3.3) compared to X rays. The mBAND assay, which is considered a specific biomarker of high-LET neutron exposure, confirmed the presence of clustered DNA damage in the neutron-irradiated mice but not in the X-irradiated mice, 24 h after exposure.

Machine learning methodology for high throughput personalized neutron dose reconstruction in mixed neutron + photon exposures

We implemented machine learning in the radiation biodosimetry field to quantitatively reconstruct neutron doses in mixed neutron + photon exposures, which are expected in improvised nuclear device detonations. Such individualized reconstructions are crucial for triage and treatment because neutrons are more biologically damaging than photons. We used a high-throughput micronucleus assay with automated scanning/imaging on lymphocytes from human blood ex-vivo irradiated with 44 different combinations of 0-4 Gy neutrons and 0-15 Gy photons (542 blood samples), which include reanalysis of past experiments. We developed several metrics that describe micronuclei/cell probability distributions in binucleated cells, and used them as predictors in random forest (RF) and XGboost machine learning analyses to reconstruct the neutron dose in each sample. The probability of "overfitting" was minimized by training both algorithms with repeated cross-validation on a randomly-selected subset of the data, and measuring performance on the rest. RF achieved the best performance. Mean R² for actual vs. reconstructed neutron doses over 300 random training/testing splits was 0.869 (range 0.761 to 0.919) and root mean squared error was 0.239 (0.195 to 0.351) Gy. These results demonstrate the promising potential of machine learning to reconstruct the neutron dose component in clinically-relevant complex radiation exposure scenarios.

Meeting radiation dosimetry capacity requirements of population-scale exposures by geostatistical sampling

BACKGROUND

Accurate radiation dose estimates are critical for determining eligibility for therapies by timely triaging of exposed individuals after large-scale radiation events. However, the universal assessment of a large population subjected to a nuclear spill incident or detonation is not feasible. Even with high-throughput dosimetry analysis, test volumes far exceed the capacities of first responders to measure radiation exposures directly, or to acquire and process samples for follow-on biodosimetry testing.

AIM

To significantly reduce data acquisition and processing requirements for triaging of treatment-eligible exposures in population-scale radiation incidents.

METHODS

Physical radiation plumes modelled nuclear detonation scenarios of simulated exposures at 22 US locations. Models assumed only location of the epicenter and historical, prevailing wind directions/speeds. The spatial boundaries of graduated radiation exposures were determined by targeted, multistep geostatistical analysis of small population samples. Initially, locations proximate to these sites were randomly sampled (generally 0.1% of population). Empirical Bayesian kriging established radiation dose contour levels circumscribing these sites. Densification of each plume identified critical locations for additional sampling. After repeated kriging and densification, overlapping grids between each pair of contours of successive plumes were compared based on their diagonal Bray-Curtis distances and root-mean-square deviations, which provided criteria (<10% difference) to discontinue sampling.

RESULTS/CONCLUSIONS

We modeled 30 scenarios, including 22 urban/high-density and 2 rural/low-density scenarios under various weather conditions. Multiple (3-10) rounds of sampling and kriging were required for the dosimetry maps to converge, requiring between 58 and 347 samples for different scenarios. On average, 70±10% of locations where populations are expected to receive an exposure ≥2Gy were identified. Under sub-optimal sampling conditions, the number of iterations and samples were increased, and accuracy was reduced. Geostatistical mapping limits the number of required dose assessments, the time required, and radiation exposure to first responders. Geostatistical analysis will expedite triaging of acute radiation exposure in population-scale nuclear events.

A High Throughput Approach to Reconstruct Partial-Body and Neutron Radiation Exposures on an Individual Basis

Biodosimetry-based individualized reconstruction of complex irradiation scenarios (partial-body shielding and/or neutron + photon mixtures) can improve treatment decisions after mass-casualty radiation-related incidents. We used a high-throughput micronucleus assay with automated scanning and imaging software on ex-vivo irradiated human lymphocytes to: a) reconstruct partial-body and/or neutron exposure, and b) estimate separately the photon and neutron doses in a mixed exposure. The mechanistic background is that, compared with total-body photon irradiations, neutrons produce more heavily-damaged lymphocytes with multiple micronuclei/binucleated cell, whereas partial-body exposures produce fewer such lymphocytes. To utilize these differences for biodosimetry, we developed metrics that describe micronuclei distributions in binucleated cells and serve as predictors in machine learning or parametric analyses of the following scenarios: (A) Homogeneous gamma-irradiation, mimicking total-body exposures, vs. mixtures of irradiated blood with unirradiated blood, mimicking partial-body exposures. (B) X rays vs. various neutron + photon mixtures. The results showed high accuracies of scenario and dose reconstructions. Specifically, receiver operating characteristic curve areas (AUC) for sample classification by exposure type reached 0.931 and 0.916 in scenarios A and B, respectively. R² for actual vs. reconstructed doses in these scenarios reached 0.87 and 0.77, respectively. These encouraging findings demonstrate a proof-of-principle for the proposed approach of high-throughput reconstruction of clinically-relevant complex radiation exposure scenarios.

Dose Estimation Curves Following In Vitro X-ray Irradiation Using Blood From Four Healthy Korean Individuals

Cytogenetic dosimetry is useful for evaluating the absorbed dose of ionizing radiation based on analysis of radiation-induced chromosomal aberrations. We created two types of in vitro dose-response calibration curves for dicentric chromosomes (DC) and translocations (TR) induced by X-ray irradiation, using an electron linear accelerator, which is the most frequently used medical device in radiotherapy. We irradiated samples from four healthy Korean individuals and compared the resultant curves between individuals. Aberration yields were studied in a total of 31,800 and 31,725 metaphases for DC and TR, respectively, obtained from 11 X-ray irradiation dose-points (0, 0.05, 0.1, 0.25, 0.5, 0.75, 1, 2, 3, 4, and 5 Gy). The dose-response relationship followed a linear-quadratic equation, Y=C+αD+βD², with the coefficients C=0.0011 for DC and 0.0015 for TR, α=0.0119 for DC and 0.0048 for TR, and β=0.0617 for DC and 0.0237 for TR. Correlation coefficients between irradiation doses and chromosomal aberrations were 0.971 for DC and 0.6 for TR, indicating a very strong and a moderate correlation, respectively. This is the first study implementing cytogenetic dosimetry following exposure to ionizing X-radiation.

A comparison of estimates of doses to radiotherapy patients obtained with the dicentric chromosome analysis and the γ-H2AX assay: Relevance to radiation triage

The γ-H2AX assay was investigated as an alternative to the time-consuming dicentric chromosome assay (DCA). Radiation doses to 25 radiotherapy patients were estimated in parallel by DCA and the γ-H2AX assay. The γ-H2AX assay yielded doses in line with the calculated equivalent whole body doses in 92% of the patients, whereas the success rate of DCA was only 76%. The result shows that the γ-H2AX assay can be effectively used as a rapid and more precise alternative to DCA.