Abstract
Objective
Accurate and rapid quantification of infarcts from DWI scans is critical in acute ischemic stroke. Acquisition artifacts lead to hyperintense regions in DWI MR scans resulting in false positives. Discriminating infarcts and artifacts helps in reducing infarct segmentation errors.
Materials and Methods
An algorithm based on two-dimensional symmetry of artifacts about the midsagittal plane and three-dimensional spatial coherence of infarct regions is proposed to characterize and separate infarcts from artifacts. The two dimensional symmetry is quantified by propagating Poisson errors in the intensity space of each pixel, and distant and spatially incoherent regions in a volume are considered as artifacts. The combination of two criteria enhances the confidence in the decision whether a hyperintense region is an infarct or artifact. The validity of the proposed algorithm is demonstrated using 51 cases.
Results
The improvement in results is demonstrated in three situations: (1) automatic infarct slice identification resulting in an average increase in (specificity, Dice Statistical Index (DSI)) by (15.2%, 6.9%) while the sensitivity decrease is by only 1.5% and (2) automatic infarct segmentation using two different algorithms: first resulting in an average DSI increase by 7.6% and second by 5.1%. On a matlab platform, the processing time is < 1 s.
Conclusions
The proposed algorithm is useful as a fast post-processing tool to reduce artifacts in infarct processing applications.
Similar content being viewed by others
References
Bevington PR (1969) Data reduction and error analysis for the physical sciences. McGraw-Hill, Inc., New York, pp 77
Jammal G, Bijaoui A (1999) Denoising and deconvolution in nuclear medicine. Int Conf Image Process 3: 896–900
Nowak RD (1999) Wavelet-based Rician noise removal for magnetic resonance imaging. IEEE Trans Image Process 10(8): 1408–1419
Thacker NA, Pokric M, Williamson DC (2004) Noise filtering and testing illustrated using a multi-dimensional partial volume model of MR data. In: Proceedings of BMVC, Kingston, pp 909–919
Lin W, Wehrli FW, Song HK (2005) Correcting bulk in-plane motion artifacts in MRI using the point spread function. MedImg September 24(9): 1170–1176
Huo Z, Giger ML, Vyborny CJ, Wolverton DE, Schmidt RA, Doi K (1998) Automated computerized classification of malignant and benign mass lesions on digitized mammograms. Acad Radiol 5: 155–168
Uehara M, Saita S, Kubo M, Kawata Y, Niki N, Nishitani H, Tominaga K, Moriyama N (2005) A computer aidied diagnosis for osteoporosis using multi slice CT images. RSNA 816
Park H, Bland PH, Meyer CR (2003) Construction of an abdominal probabilistic atlas and its application in segmentation. IEEE Trans Med Imaging 22: 483–492
Yoshida H, Näppi J, MacEneaney P, Rubin DT, Dachman AH (2002) Computer-aided diagnosis scheme for detection of polyps at CT colonography. Radiographics 22: 963–979
Nowinski WL, Qian G, Bhanu Prakash KN, Volkau I, Thirunavuukarasuu A., Hu Q, Ananthasubramaniam A, Liu J, Gupta V, Ng TT, Leong WK, Beauchamp NJ (2007) A CAD system for acute ischemic stroke image processing. Int J Comput Assist Radiol Surg 2(Suppl 1): 220–222
Nowinski WL, Qian G, Leong WK, Liu J, Kazmierski R, Urbanik A (2007) A Stroke CAD in the ER. 93 Radiological Society of North America Scientific Assembly and Annual Meeting Program 2007, Chicago, USA, 25–30 November 2007, p 837
Nowinski WL, Qian G, Bhanu Prakash KN, Volkau I, Bilello M, Beauchamp NJ (2006) A CAD system for stroke MR and CT. 92 Radiological Society of North America Scientific Assembly and Annual Meeting Program 2006, Chicago, USA, 25 November–1 December 2006, p 789
Nowinski WL, Qian GY, Bhanu Prakash KN, Volkau I, Thirunavuukarasuu A, Beauchamp NJ, Runge VW, Ananthasubramaniam A, Liu J, Qiao Y, Hu Q, Bilello M (2005) Atlas-assisted MR stroke image interpretation by using anatomical and blood supply territories atlases. Program 91st Radiological Society of North America Scientific Assembly and Annual Meeting RSNA 2005, Chicago, Illinois, USA, 27 November–2 December 2005, p 857
Gupta V, Bhanu Prakash KN, Nowinski WL (2008) Automatic and rapid identification of infarct slices and hemisphere in DWI scans. Acad Radiol 15: 24–39
Bhanu Prakash KN, Gupta V, Bilello M, Beauchamp NJ, Nowinski WL (2006) Identification, segmentation and image property study of acute infarcts in diffusion-weighted images by using a probabilistic neural network and adaptive gaussian mixture model. Acad Radiol 13: 1474–1484
Bhanu Prakash KN, Gupta V, Nowinski WL (2006): Segmenting infarct in diffusion weighted imaging volumes. Patent application PCT/SG2006/000292, filed 3 October 2006
Bhanu Prakash KN, Gupta V, Nowinski WL (2007) Automatic segmentation of infarct region in diffusion weighted images using modified Laws textural masks. Stroke (submitted)
Nowinski WL, Bhanu Prakash KN, Volkau I, Ananthasubramaniam A, Beauchamp NJ (2006) Rapid and automatic calculation of the MSP in magnetic resonance diffusion and perfusion images. Acad Radiol 13(5): 652–663
Mandel J (1984) The Statistical analysis of experimental data. Courier Dover Publications, New York, p 72
Haralick RM, Shapiro LG(1992). Computer and robot vision, Vol. I, Addison-Wesley, Reading, pp 158–205
Boomgaard vanden R, Balen van R (1992) Image transforms using bitmapped binary images. Comput Vis Graphics Image Process Graphical Models Image Processing 54(3): 254–258
Sedgewick R, Algorithms in C, 3rd edn. Addison-Wesley, Reading, pp 11–20
Zou KH, Warfield SK, Bharatha A, Tempany CMC, Kaus M, Haker S, Wells WM III, Jolesz FA, Kikinis R (2004) Statistical validation of image segmentation quality based on spatial overlap index. Acad Radiol 11: 178–189
Menezes MN, Ay H, Zhu MW, Lopez CJ, Singhal AB, Karonen JO, Aronen HJ, Liu Y, Nuutinen J, Koroshetz WJ, Sorensen AG (2007) The real estate factor: quantifying the impact of infarct location on stroke severity. Stroke 38: 194–197
Bang OY, Lee PH, Heo KG, Joo US, Yoon SR, Kim SY (2005) Specific DWI lesion pattern predict progosis after acute ischaemic stroke within MCA territory. J Neurol Neurosurg Psychiatry 76: 1222–1228
Toga AW, Thompson PM (2003) Mapping brain asymmetry. Nat Rev Neurosci 4(1): 37–48
Chen D, Li L, Yoon D, Lee JH, Liang Z (2001) Renormalization method for inhomogeneity correction of MR images. In: Proceedings of SPIE, Med. imaging: image processing, Sonka M, Hanson KM (eds) vol 4322, p 939–942
Bammer R, Markl M, Barnett A, Acar B, Alley MT, Pelc NJ, Glover GH, Moseley ME (2003) Analysis and generalized correction of the effect of spatial gradient field distortions in diffusion-weighted imaging. Magn Res Med 3(20): 560–569
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Gupta, V., Prakash, K.B. & Nowinski, W.L. Towards discrimination of infarcts from artifacts in DWI scans. Int J CARS 2, 385–395 (2008). https://doi.org/10.1007/s11548-008-0148-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11548-008-0148-2