Sam J. Weisenthal BA, Abstract Co-Author: Nothing to Disclose

Ari Seff, Abstract Co-Author: Nothing to Disclose

Xiao Zhang PhD, Abstract Co-Author: Nothing to Disclose

Ronald M. Summers MD, PhD, Presenter: Royalties, iCAD, Inc Research funded, iCAD, Inc Stockholder, Johnson & Johnson Grant, Viatronix, Inc

Les Roger Folio DO, MPH, Abstract Co-Author: Nothing to Disclose

Jianhua Yao PhD, Abstract Co-Author: Royalties, iCAD, Inc

To detect anomalous radiation events by taking into account exam-specific clinical characteristics, we implement a statistical method for context-dependent CT radiation sentinel event detection directly from DICOM header data that is size and exam-specific rather than a general threshold for all exams/ patient sizes.

Patient and scanner parameters (study description, scan length, dose length product (DLP), patient age, scanner model) were obtained with an automatic Radiation Exposure Extraction Engine (RE3) for all CT chest abdomen and pelvis exams in January and February 2014 (n=892). BMI data was acquired from RIS. A multivariable regression was applied with scanner model, age, BMI, BMI*scan length, height and weight as predictors for DLP. Using leave-one-out cross validation, we predict a DLP for each exam. All exams with observed DLPs greater than two standard deviations (95th percentile) from the mean residual were flagged. All studies were also analyzed with a simple thresholding model to identify exams with DLPs over two standard deviations above the mean of all exams. Exams flagged by the context-dependent and independent methods were checked for factors in patient weight and multi-phase exams.

Our multivariable regression model detected 18 anomalous exams with a mean DLP of 2678 mGy*cm (1350 to 4101). The context-independent thresholding detected 43 with a mean DLP of 2765 mGy*cm (2206 to 4101). 11 exams were detected by both methods. The average BMI for exams detected by only our context-dependent model (n=7) was 25.6 ±6.5 kg/m2, and that of those only by the thresholding model (n=32) was 36.9±5.2 kg/m2 (mostly obese patients). The average number of acquisitions for exams detected only by our context-dependent model was 1.6 ± 0.8 passes and that of the thresholding model was 2.7±0.58 passes (mostly multi-phase exams).

We present a context-dependent CT radiation anomaly detection method using exam-specific variables. Our model takes into account clinical context and therefore detects patient-specific outliers missed by simple thresholding, but does not falsely flag exams that would be detected by simple thresholding due to high exposure from patient weight and multiple phases.

Contextual sentinel event detection allows for earlier detection of individual or systemic excessive radiation exposures. 

Weisenthal, S, Seff, A, Zhang, X, Summers, R, Folio, L, Yao, J, Contextual CT Radiation Exposure Sentinel Event Detection.  Radiological Society of North America 2014 Scientific Assembly and Annual Meeting, - ,Chicago IL. http://archive.rsna.org/2014/14015274.html