IIAE CONFERENCE SYSTEM, The 1st IEEE/IIAE International Conference on Intelligent Systems and Image Processing 2013 (ICISIP2013)

Font Size: 
Automatic Correction of Intensity Inhomogeneities from Transmission Distribution in Medical Images
Huimin Lu, Yujie Li, Shiyuan Yang, Seiichi Serikawa

Last modified: 2013-10-01

Abstract


The field of image processing has made significant progress in the quantitative analysis of biomedical images over the last 30 years. Scientists are collecting large amount of electron microscopy image data to gain a better understanding of neuron organization. However, many of the image data are distorted by artificial light intensity inhomogeneity, such as magnetic resonance imaging (MRI), computed tomography (CT), X-ray, transmission electron microscopy (TEM), etc. In this paper, we propose a novel automatically non-uniformity correction method, which can estimate the illumination field using image intensity gradients and spatial information. The proposed method is very fast to compute, and the result is better than the state-of-the-art methods. Based on the intensity gradients in medical images, we proposed a non-parametric approach for the automatic illumination correction. The experiments demonstrate that the proposed method is not only faster, but also can eliminate the non-uniformity well.

Keywords


Intensity correction, Transmission distribution, Medical images analysis

References


(1) Vovk U, Pernus F, Lika B: A review of methods forcorrection of intensity inhomogeneity in MRI. IEEETrans. on Medical Imaging 2007, 26(3):405-421

(2) Lixiong L, Qi Z, Min W, Wu L, Fei S: Adaptivesegmentation of magnetic resonance images withintensity inhomogeneity using level set method.Magnetic Resonance Imaging 2013, 31(4):567-574

(3) Yining Z, Mengliu Z, Hongwei L, Peng Z: Micro-CTartefacts reduction based on detector random shiftingand fast data inpainting. Medical Physics 2013,40(3):031114

(4) Irarrazabal P, Meyer CH, Nishimura DG, Macovski A:Inhomogeneity correction using an estimated linearfield map. Magnetic Resonance in Medicine 1996,35(2):278-282

(5) Likar B, Viergever MA, Pernus F: Retrospectivecorrection of MR intensity inhomogeneity byinformation minimization. IEEE Trans. on MedicalImaging 2001, 20(12):1398-1410

(6) Yuanjie Z, Vanderbeek B, Rui X, Daniel E, StambolianD, Maguire M, Obrien J, Gee J: Retrospectiveillumination correction of retinal fundus images fromgradient distribution sparsity. Proc. of 9th IEEEInternational Symposium on Biomedical Imaging 2012,972-975

(7) Styner M, Brechbuhler C, Szekely G, Gerig G:Parametric estimate of intensity inhomogeneitiesapplied to MRI. IEEE Trans. on Medical Imaging 2000,19(3):153-165

(8) Vovk U, Pernus F, Likar B: MRI intensityinhomogeneity correction by combining intensity andspatial information. Physics in Medicine and Biology2004, 49(17):4119-4133

(9) Srinivasa N, Shree N: Interactive (De) Weathering ofand image using physical models. Proc. of IEEEWorkshop on Color and Photometric Methods inComputer Vision 2003

(10) Paris S, Durand F: A fast approximation of the bilateralfilter using a signal processing approach. InternationalJournal of Computer Vision 2009, 81(1):24-52


Full Text: PDF