Automatic Segmentation of Ventricular Cerebrospinal Fluid from Ischemic Stroke CT Images

• Published in: Neuroinformatics (Totowa, N.J.) Vol. 10; no. 2; pp. 159 - 172
• Main Authors: Poh, L. E., Gupta, V., Johnson, A., Kazmierski, R., Nowinski, W. L.
• Format: Journal Article
• Language: English
• Published: New York Springer-Verlag 01-04-2012; Springer Nature B.V
• Subjects: Algorithms; Bioinformatics; Biomedical and Life Sciences; Biomedicine; Brain Ischemia - cerebrospinal fluid; Brain Ischemia - complications; Brain Ischemia - diagnostic imaging; Cerebral Ventriculography - methods; Cerebrospinal fluid; Computational Biology/Bioinformatics; Computed tomography; Computer Appl. in Life Sciences; Fourth Ventricle - diagnostic imaging; Humans; Image processing; Image Processing, Computer-Assisted; Ischemia; Magnetic Resonance Imaging; Neurology; Neurosciences; Original Article; Reproducibility of Results; Scaling; Segmentation; Stroke; Stroke - cerebrospinal fluid; Stroke - diagnostic imaging; Stroke - etiology; Tomography, X-Ray Computed; Ventricles (cerebral); CT; Stroke; Segmentation; Ventriclular system; Registration
• ISSN: 1539-2791; 1559-0089
• DOI: 10.1007/s12021-011-9135-9

Accurate segmentation of ventricular cerebrospinal fluid (CSF) regions in stroke CT images is important in assessing stroke patients. Manual segmentation is subjective, time consuming and error prone. There are currently no methods dedicated to extracting ventricular CSF regions in stroke CT images. 102 ischemic stroke CT scans (slice thickness between 3 and 6 mm, voxel size in the axial plane between 0.390 and 0.498 mm) were acquired. An automated template-based algorithm is proposed to extract ventricular CSF regions which accounts for the presence of ischemic infarct regions, image noise, and variations in orientation. First, template VT
2
is registered to the scan using landmark-based piecewise linear scaling and then template VT
1
is used to further refine the registration by partial segmentation of the fourth ventricle. A region of interest (ROI) is found using the registered VT
2
. Automated thresholding is then applied to the ROI and the artifacts are removed in the final phase. Sensitivity, dice similarity coefficient, volume error, conformity and sensibility of segmentation results were 0.74 ± 0.12, 0.8 ± 0.09, 0.16 ± 0.11, 0.45 ± 0.39, 0.88 ± 0.09, respectively. The processing time for a 512 × 512 × 30 CT scan takes less than 30 s on a 2.49 GHz dual core processor PC with 4 GB RAM. Experiments with clinical stroke CT scans showed that the proposed algorithm can generate acceptable results in the presence of noise, size variations and orientation differences of ventricular systems and in the presence of ischemic infarcts.