ABSTRACT
Focal cortical dysplasia (FCD) is the most common factor leading to intractable epilepsy. It is helpful for doctors to automatically detect the FCD lesion before the operation. In this study, two methods to detect and locate the lesion are proposed. The first method is based on the symmetrical characteristics of the brain image, and can approximately detect abnormal areas caused by FCD in Magnetic Resonance (MR) images. The second method involves detecting local highlighted areas in MR images based on the expectation-maximization (EM) algorithm. The two methods were applied to 15 specific MR images of 9 epileptic patients. The recognition accuracy of the symmetrical feature algorithm and EM algorithm was 80 % (12/15) and 100% (15/15), respectively, and the detection accuracy of the combination of two algorithms is 80%. The symmetrical feature algorithm can be applied to any of the axial or coronal MR images of the modality, and the EM algorithm is suitable for detecting the local hyperintense of the MR image. The two methods were able to detect lesion areas in MR images and achieve desirable results.
- Taylor D C, Falconer M A, Bruton C J, et al. Focal dysplasia of the cerebral cortex in epilepsy[J]. Journal of Neurology Neurosurgery & Psychiatry, 1971, 34(4):369--387.Google ScholarCross Ref
- Kabat J, Król P. Focal cortical dysplasia - review[J]. Polish Journal of Radiology, 2012, 77(2):35--43.Google ScholarCross Ref
- Tassi L, Colombo N, Garbelli R, et al. Focal cortical dysplasia: neuropathological subtypes, EEG, neuroimaging and surgical outcome[J]. Brain A Journal of Neurology, 2002, 125(Pt 8):1719--1732.Google ScholarCross Ref
- Palmini A, Najm I, Avanzini G, et al. Terminology and classification of the cortical dysplasias[J]. Neurology, 2004, 62(6 Suppl 3):S2-8.Google ScholarCross Ref
- Kassubek J, Huppertz H J, Spreer J, et al. Detection and localization of focal cortical dysplasia by voxel-based 3-D MRI analysis.[J]. Epilepsia, 2002, 43(6):596--602.Google ScholarCross Ref
- Huppertz H J, Grimm C, Fauser S, et al. Enhanced visualization of blurred gray-white matter junctions in focal cortical dysplasia by voxel-based 3D MRI analysis.[J]. Epilepsy Research, 2005, 67(1-2):35.Google ScholarCross Ref
- Colliot O, Bernasconi N, Khalili N, et al. Individual voxel-based analysis of gray matter in focal cortical dysplasia[J]. Neuroimage, 2006, 29(1):162--171.Google ScholarCross Ref
- Besson, Pierre, Bernasconi, et al. Surface-Based Texture and Morphological Analysis Detects Subtle Cortical Dysplasia[M]// Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2008. Springer Berlin Heidelberg, 2008:645--52.Google Scholar
- Bernasconi A, Antel S B, Collins D L, et al. Texture analysis and morphological processing of magnetic resonance imaging assist detection of focal cortical dysplasia in extra-temporal partial epilepsy[J]. Annals of Neurology, 2001, 49(6):770--775.Google ScholarCross Ref
- Antel S B, Collins D L, Bernasconi N, et al. Automated detection of focal cortical dysplasia lesions using computational models of their MRI characteristics and texture analysis[J]. Neuroimage, 2003, 19(4):1748--1759.Google ScholarCross Ref
- Antel S B, Bernasconi A, Bernasconi N, et al. Computational models of MRI characteristics of focal cortical dysplasia improve lesion detection[J]. Neuroimage, 2002, 17(4):1755--1760.Google ScholarCross Ref
- Barkovich AJ, Kuzniecky RI, Jackson GD, Guerrini R, Dobyns WB. Classification system for malformations of cortical development: Update. Neurology.2001; 57(12):2168--78.Google Scholar
- http://radiopaedia.org/cases/focal-cortical-dysplasia-type-iib: Case courtesy of A.Prof Frank Gaillard, Radiopaedia.org, rID: 5561Google Scholar
- http://radiopaedia.org/cases/focal-cortical-dysplasia-5: Case courtesy of Dr Ahmed Abd Rabou, Radiopaedia.org, rID: 39848Google Scholar
- Chan T F, Vese L A. Active contours without edges[J]. IEEE Press, 2001, 10(2):266--277.Google ScholarDigital Library
- Khotanlou H, Colliot O, Bloch I. Automatic Brain Tumor Segmentation Using Symmetry Analysis and Deformable Models[M]// Advances In Pattern Recognition. 2014:198--202.Google Scholar
- Khotanlou H, Colliot O, Atif J, et al. 3D brain tumor segmentation in MRI using fuzzy classification, symmetry analysis and spatially constrained deformable models[J]. Fuzzy Sets & Systems, 2009, 160(10):1457--1473.Google ScholarDigital Library
- Dvorak P, Kropatsch W, Bartusek K. Automatic detection of brain tumors in MR images[C]. International Conference on Telecommunications and Signal Processing. IEEE, 2013:577--580.Google Scholar
- Saha B N, Ray N, Greiner R, et al. Quick detection of brain tumors and edemas: A bounding box method using symmetry[J]. Comput Med Imaging Graph, 2012, 36(2):95--107.Google ScholarCross Ref
- DEMPSTER, A. Maximum likelihood from incomplete data via the EM algorithm[J]. Journal of the Royal Statistical Society, 1977, 39(1):1--38.Google Scholar
Index Terms
- Detection of Focal Cortical Dysplasia lesions in MR images
Recommendations
Enhance the Focal Cortical Dysplasia Lesions in a MR-negative Image: A Case Study
ICDSP '20: Proceedings of the 2020 4th International Conference on Digital Signal ProcessingFocal cortical dysplasia (FCD) is one of the malformations of cortical development and one of the common causes of intractable epilepsy. The method of image post-processing can enhance the lesion area of the magnetic resonance (MR) image, help doctors ...
MTN-Net: A Multi-Task Network for Detection and Segmentation of Thyroid Nodules in Ultrasound Images
Knowledge Science, Engineering and ManagementAbstractAutomatic detection and segmentation of thyroid nodules is crucial for the identification of benign and malignant nodules in computer-aided diagnosis (CAD) systems. However, the diverse sizes of thyroid nodules in ultrasound images, nodules with ...
Detection and Removal of Scratches in Images
MIKE 2013: Proceedings of the First International Conference on Mining Intelligence and Knowledge Exploration - Volume 8284In this paper a detection/restoration method to detect and remove line scratches in still images, regardless of their orientation, colour, and shape is presented. In this work the two properties of scratches are considered namely: scratches have high ...
Comments