We have clinically evaluated the accuracy of an automatic patient-positioning system based on the image correlation of two edge images in radiotherapy. Ninetysix head & neck images from eight patients undergoing proton therapy were compared with a digitally reconstructed radiograph (DRR) of planning CT. Two edge images, a reference image and a test image, were extracted by applying a Canny edge detector algorithm to a DRR and a 2D X-ray image, respectively, of each patient before positioning. In a simulation using a humanoid phantom, performed to verify the effectiveness of the proposed method, no registration errorswere observed for given ranges of rotation, pitch, and translation in the x, y, and z directions. For real patients, however, there were discrepancies between the automatic positioning method andmanual positioning by physicians or technicians.Using edged head coronal- and sagittal-viewimages, the average differences in registration between these two methods for the x, y, and z directions were 0.11 cm, 0.09 cm and 0.11 cm, respectively, whereas the maximum discrepancies were 0.34 cm, 0.38 cm, and 0.50 cm, respectively. For rotation and pitch, the average registration errors were 0.95° and 1.00°, respectively, and the maximum errors were 3.6° and 2.3°, respectively. The proposed automatic patient-positioning system based on edge image comparison was relatively accurate for head and neck patients. However, image deformation during treatmentmay render the automatic method less accurate, since the test image many differ significantly from the reference image.
- Automated object detection
- Digital image processing
ASJC Scopus subject areas
- Radiological and Ultrasound Technology
- Radiology Nuclear Medicine and imaging
- Computer Science Applications