Robust calculation of the midsagittal plane in CT scans using the Kullback–Leibler’s measure

• Published in: International journal for computer assisted radiology and surgery Vol. 4; no. 6; pp. 535 - 547
• Main Authors: Puspitasari, Fiftarina, Volkau, Ihar, Ambrosius, Wojciech, Nowinski, Wieslaw L.
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer-Verlag 01.11.2009
• Subjects: Algorithms; Brain - anatomy & histology; Brain - diagnostic imaging; Computer Imaging; Computer Science; Health Informatics; Humans; Imaging; Medicine; Medicine & Public Health; Pattern Recognition and Graphics; Radiology; Review Article; Surgery; Tomography, X-Ray Computed - methods; Vision; CT; Stroke; Midsagittal plane; Symmetry
• ISSN: 1861-6410; 1861-6429; 1861-6429
• DOI: 10.1007/s11548-009-0366-2

Objective The identification of the interhemispheric fissure (IF) is important in clinical applications for brain landmark identification, registration, symmetry assessment, and pathology detection. The IF is usually approximated by the midsagittal plane (MSP) separating the brain into two hemispheres. We present a fast accurate, automatic, and robust algorithm for finding the MSP for CT scans acquired in emergency room (ER) with a large slice thickness, high partial volume effect, and substantial head tilt. Materials and methods An earlier algorithm for MSP identification from MRI using the Kullback–Leibler’s measure was extended for CT by estimating patient’s head orientation using model fitting, image processing, and atlas-based techniques. The new algorithm was validated on 208 clinical scans acquired mainly in the ER with slice thickness ranging from 1.5 to 6 mm and severe head tilt. Results The algorithm worked robustly for all 208 cases. An angular discrepancy (°) and maximum distance (mm) between the calculated MSP and ground truth have the mean value (SD) 0.0258° (0.9541°) and 0.1472 (0.7373) mm, respectively. In average, the algorithm takes 10 s to process of a typical CT case. Conclusion The proposed algorithm is robust to head rotation, and correctly identifies the MSP for a standard clinical CT scan with a large slice thickness. It has been applied in our several CT stroke CAD systems.