Purpose: The aim of this study was to develop an efficient CT scan range estimation method that is based on the analysis of image data itself instead of metadata analysis. This makes it possible to quantitatively compare the scan range of two studies.
Methods: In our study, 3D stacks are first projected to 2D coronal images via a ray casting-like process. Trained 2D body part classifiers are then used to recognize different body parts in the projected image. The detected candidate regions go into a structure grouping process to eliminate false-positive detections. Finally, the scale and position of the patient relative to the projected figure are estimated based on the detected body parts via a structural voting. The start and end lines of the CT scan are projected to a standard human figure. The position readout is normalized so that the bottom of the feet represents 0.0, and the top of the head is 1.0.
Results: Classifiers for 18 body parts were trained using 184 CT scans. The final application was tested on 136 randomly selected heterogeneous CT scans. Ground truth was generated by asking two human observers to mark the start and end positions of each scan on the standard human figure. When compared with the human observers, the mean absolute error of the proposed method is 1.2% (max: 3.5%) and 1.6% (max: 5.4%) for the start and end positions, respectively.
Conclusion: We proposed a scan range estimation method using multiple body parts detection and relative structure position analysis. In our preliminary tests, the proposed method delivered promising results.
Keywords: Body parts detection; Image classification; Machine learning; Pictorial structures; Scan range estimation; Structural voting.