Accuracy of automated patient positioning in CT using a 3D camera for body contour detection

Abstract

ObjectiveTo assess the accuracy of a 3D camera for body contour detection and patient positioning in CT compared to routine manual positioning by radiographers.Methods and materialsFour hundred twenty-three patients that underwent CT of the head, thorax, and/or abdomen on a scanner with manual table height selection and 254 patients on a scanner with table height suggestion by a 3D camera were retrospectively included. Within the camera group, table height suggestion was based on infrared body contour detection and fitting of a scalable patient model to the 3D data. Proper positioning was defined as the ideal table height at which the scanner isocenter coincides with the patient’s isocenter. Patient isocenter was computed by automatic skin contour extraction in each axial image and averaged over all images. Table heights suggested by the camera and selected by the radiographer were compared with the ideal height.ResultsMedian (interquartile range) absolute table height deviation in millimeter was 12.0 (21.6) for abdomen, 12.2 (12.0) for head, 13.4 (17.6) for thorax-abdomen, and 14.7 (17.3) for thorax CT scans positioned by radiographers. The deviation was significantly less (p < 0.01) for the 3D camera at 6.3 (6.9) for abdomen, 9.5 (6.8) for head, 6.0 (6.1) for thorax-abdomen, and 5.4 (6.4) mm for thorax.ConclusionA 3D camera for body contour detection allows for accurate patient positioning, thereby outperforming manual positioning done by radiographers, resulting in significantly smaller deviations from the ideal table height. However, radiographers remain indispensable when the system fails or in challenging cases.Key Points • A 3D camera for body contour detection allows for accurate patient positioning. • A 3D camera outperformed radiographers in patient positioning in CT. • Deviation from ideal table height was more extreme for patients positioned by radiographers for all body parts.

Automated patient positioning in CT using a 3D camera for body contour detection: accuracy in pediatric patients

“…We found that positioning with the 3D camera of pediatric patients without a fixation aid allows for more accurate patient positioning than manual positioning by radiographers. This outcome is similar to the findings in adult patients [10,11].…”

“…If Avatar fitting is not possible, then the isocenter curve is automatically obtained as the geometric center between the camera depth data and the central part of the scanner table. This is the same fallback as described before [11]. For adult patients, the camera images are processed by an algorithm [12], as described in detail before [10,11].…”

“…This is the same fallback as described before [11]. For adult patients, the camera images are processed by an algorithm [12], as described in detail before [10,11]. However, the algorithm installed on the scanner that was used in the (adult) reference study was not optimized for pediatric patients.…”

Review of Artificial Intelligence Techniques in Imaging Data Acquisition, Segmentation, and Diagnosis for COVID-19

“…ISO-centering refers to aligning the target body region of the subject, so that the center of the target body region overlaps with the scanner ISO center and thus the overall imaging quality is optimal. Studies have shown that, with better ISO-centering, radiation dosage can be reduced while maintaining similar imaging quality [42]. In order to align the target body region to the ISO center, and given that anatomical keypoints usually represent only a very sparse sampling of the full 3D mesh in the 3D space (defining the digital human body), Georgakis et al [43] propose to recover human mesh from a single monocular RGB image using a parametric human model SMPL [44].…”

Use of artificial intelligence in computed tomography dose optimisation

“…portion of the body to be scanned and the current height of the table, the system automatically moves the table vertically to position the patient such that the majority of the scanned anatomy is located at the isocentre (Saltybaeva et al, 2018;Booij et al, 2019). Table 1 summarises the results of a study by Saltybaeva et al (2018), demonstrating that the average and maximal errors are decreased substantially using this AI algorithm to centre the patient automatically.…”