Automated Detection of Regions of Interest for Brain Perfusion MR Images




Perfusion-weighted magnetic resonance imaging, Abnormal brain scans, Region of interest, Segmentation, Thresh-olding


Background. Images with abnormal brain anatomy produce problems for automatic segmentation techniques, and as a result poor ROI detection affects both quantitative measurements and visual assessment of perfusion data.

Objective. This paper presents a new approach for fully automated and relatively accurate ROI detection from dynamic susceptibility contrast perfusion magnetic resonance and can therefore be applied excellently in the perfusion analysis.

Methods. In the proposed approach the segmentation output is a binary mask of perfusion ROI that has zero values for air pixels, pixels that represent non-brain tissues, and cerebrospinal fluid pixels. The process of binary mask producing starts with extracting low intensity pixels by thresholding, which subsequently correspond to zero values of the mask. Optimal low-threshold value is solved by obtaining intensity pixels information from the approximate anatomical brain location. Holes filling algorithm and binary region growing algorithm are used to remove falsely detected regions and produce region of only brain tissues. Further, CSF pixels extraction is provided by thresholding of high intensity pixels from region of only brain tissues. Each time-point image of the perfusion sequence is used for adjustment of CSF pixels location.

Results. The segmentation results were compared with the manual segmentation performed by experienced radiologists, considered as the reference standard for evaluation of proposed approach. On average of 120 images the segmentation results have a good agreement with the reference standard with a Dice Index of 0.9576 ± 0.013 (sensitivity and specificity are 0.9931 ± 0.0053 and 0.9730 ± 0.0111 respectively). All detected perfusion ROIs were deemed by two experienced radiologists as satisfactory enough for clinical use.

Conclusions. The results show that proposed approach is suitable to be used for perfusion ROI detection from DSC head scans. Segmentation tool based on the proposed approach can be implemented as a part of any automatic brain image processing system for clinical use.

Author Biography

Svitlana M. Alkhimova, Igor Sikorsky Kyiv Polytechnic Institute

Светлана Николаевна Алхимова


G.-H. Jahng et al., “Perfusion magnetic resonance imaging: A comprehensive update on principles and techniques”, Korean J. Radiol., vol. 15, no. 5, pp. 554–577, 2014. doi: 10.3348/kjr.2014.15.5.554

S.M. Alkhimova, “Detection of perfusion ROI as a quality control in perfusion analysis”, in Proc. Science, Research, Deve­lopment. Technics and Technology, Berlin, Germany, Jan 30, 2018, pp. 57–59.

S.M. Alkhimova and O.S. Zheleznyi, “Automatizations problem for region of interest detection in perfusion magnetic resonanse imaging”, in Proc. Modern Directions of Theoretical and Applied Researches ‘2015, Odesa, Ukraine, March 17–19, 2015, vol. 1, no. 4, pp. 90–93 (in Ukrainian).

I. Galinovic et al., “Automated vs manual delineations of regions of interest- a comparison in commercially available perfusion MRI software”, BMC Med. Imag., vol. 12, no. 16, pp. 1–3, 2012. doi: 10.1186/1471-2342-12-16

P. Kalavathi and V.S. Prasath, “Methods on skull stripping of MRI head scan Images – A review”, J. Digit. Imag., vol. 29, pp. 365–379, 2016. doi: 10.1007/s10278-015-9847-8

I. Despotović et al., “MRI segmentation of the human brain: challenges, methods, and applications”, Comput. Math. Methods. Med., vol. 2015, pp. 1–23, 2015. doi: 10.1155/2015/450341

S. Rajagopalan et al., “Robust fast automatic skull stripping of MRI-T2 data”, Proc. SPIE, vol. 5747, pp. 485–495. 2005. doi: 10.1117/12.594651

L. Li et al., “Improved method for automatic identification of lung regions on chest radiographs”, Academic Radiology, vol. 8, no. 7, pp. 629–638, 2001. doi: 10.1016/S1076-6332(03)80688-8

B. Clangphukhieo et al., “Segmenting the ventricle from CT brain image using gray-level co-occurrence matrices (GLCMs)”, in World Congress on Engineering, 2014, pp. 585–589.

K. Somasundaram and T. Kalaiselvi, “A method for filling holes in objects of medical images using region labeling and run length encoding schemes”, in National Conference on Image Processing (NCIMP), 2010, pp. 110–115.

W. Burger and M.J. Burge, Principles of Digital Image Processing Core Algorithms. London, UK: Springer-Verlag, 2009. doi: 10.1007/978-1-84800-195-4.

Y.-H. Kao et al., “Removal of CSF pixels on brain MR perfusion images using first several images and Otsu's thresholding technique”, Magnetic Resonance in Medicine, vol. 64, no. 3, pp. 743–748, 2010. doi: 10.1002/mrm.22402