Özet:

Brain magnetic resonance imaging (MRI) images support important information about brain diseases for physicians. Morphological alterations in brain tissues indicate the probable existence of a disease in many cases. Proper estimation of these tissues, measuring their sizes, and analyzing their image patterns are parts of the diagnosis process. Therefore, the interpretability and perceptibility level of the MRI image is valuable for physicians. In this paper, a new image contrast enhancement algorithm based on linear combinations is presented. The proposed algorithm is focused on improving the interpretability and perceptibility of the image information. An MRI image is presented to the algorithm, which generates a set of images from this MRI image. After this step, the algorithm uses the linear combination technique for combining the image set to generate a final image. Linear combination coefficients are generated using the artificial bee colony algorithm. The algorithm is evaluated by 4 different global image enhancement evaluation techniques: contrast improvement ratio (CIR), enhancement measurement error (EME), absolute mean brightness error (AMBE), and peak-signal-to-noise ratio (PSNR). During the evaluation process, 2 case studies are performed. The first case study is performed with 3 different image sets (T1, T2, and proton density) presented to the algorithm. These sets are obtained from the Brainweb simulated MRI database. The algorithm shows the best performance on the T1 image set with 5.844 CIR, 6.217 EME, 15.045 AMBE, and 22.150 dB PSNR scores as average values. The second case study is also performed with 3 different image sets (T1-fast low-angle shot sequence, T1-magnetization-prepared rapid acquired gradient-echoes (MP-RAGE), and T2) obtained from the The Multimedia Digital Archiving Systempublic community database. The algorithm performs best with the T1-MP-RAGE modality images with 6.983 CIR, 17.326 EME, 3.514 AMBE, and 30.157 dB PSNR scores as average values. In addition, this algorithm can be used for classification tasks with proper linear combination coefficients, for instance, segmentation of the white matter regions in brain MRI images.

Anahtar Kelimeler: