BazTech - Yadda

1

Multi-channeled MR brain image segmentation: A new automated approach combining BAT and clustering technique for better identification of heterogeneous tumors

Alagarsamy Saravanan, Kamatchi Kartheeban, Govindaraj Vishnuvarthanan, Zhang Y. D., Thiyagarajan Arunprasath

Biocybernetics and Biomedical Engineering

|

2019

|

Vol. 39, no. 4

1005--1035

EN

Segregation of tumor region in brain MR image is a prominent task that instantly provides easier tumor diagnosis, which leads to effective radiotherapy planning. For decades together, several segmentation methods for a brain tumor have been presented and until now, enhanced tumor segmentation procedure tends to be a challenging task because, MR images are mostly inbred with varied tumor dimensions of disproportioned boundaries. To address this issue, we develop an improved brain image segmentation technique called BAT based Interval Type-2 Fuzzy C-Means (BAT-IT2FCM) clustering. The BAT algorithm is utilized to find out the optimal cluster location from which the clustering operation by Interval Type-2 Fuzzy C-Means (IT2FCM) is performed. The optimal cluster location pointed/identified by the BAT algorithm helps in easing the clustering operation performed by IT2FCM algorithm, and thereby reducing computational complexity. The efficient outcome from BAT-IT2FCM methodology was affirmed using the performance metrics such as computational time, Peak Signal to Noise Ratio, Mean Squared Error, Jaccard Tanimoto Co-efficient Index and Dice Overlap Index. Also, segmentation results of clinical brain MR images produced by the proposed methodology were evaluated with the support from radiologists (Gold Standard). The suggested BAT based fuzzy related clustering produces sensitivity and specificity values of 98.56 ± 1.2 and 97.67 ± 1.3, respectively, which are better than the existing techniques used for brain image segmentation. Heterogeneous tumor types of different grade levels and tissue structures present in the brain MR slices of three different axes are precisely segmented by the proposed methodology for better visualization of oncologists.

2

Zastosowanie algorytmu BAT w optymalizacji obliczeń adaptacyjnego regulatora stanu układu dwumasowego

Kamiński M.

Przegląd Elektrotechniczny

|

2017

|

R. 93, nr 1

300--304

PL

W publikacji analizowany jest regulator stanu, którego parametry podlegają adaptacji zgodnie z regułą Widrowa-Hoffa. Stały współczynnik wykorzystywany przy wyznaczaniu poprawek regulatora stanu wyznaczono za pomocą algorytmu BAT. Sterowanym obiektem jest układ dwumasowy. Przedstawiono analizę właściwości dynamicznych struktury sterowania, wykonano badania dla znamionowych oraz zmodyfikowanych parametrów obiektu, a także porównano działanie klasycznego oraz adaptacyjnego regulatora stanu. Zaprojektowany regulator zaimplementowano w karcie dSPACE1103, a następnie przeprowadzono testy na stanowisku laboratoryjnym.

EN

In article adaptive state space controller is analyzed. Parameters are recalculated according to Widrow-Hoff rule. Inside adaptation algorithm, the constant value of learning rate is selected using BAT algorithm. The plant used in control structure is two-mass system. Dynamical properties of proposed controller are considered. Results are prepared for nominal and disturbed parameters of the plant. Comparison between classical and adaptive controller is also presented. Designed controller has been implemented in dSPACE1103 card, then experiment was prepared.

3

Bat optimization based neuron model of stochastic resonance for the enhancement of MR images

Singh M., Verma A., Sharma N.

Biocybernetics and Biomedical Engineering

|

2017

|

Vol. 37, no. 1

124--134

EN

Stochastic resonance (SR) performs the enhancement of the low in contrast image with the help of noise. The present paper proposes a modified neuron model based stochastic resonance approach applied for the enhancement of T1 weighted, T2 weighted, fluid-attenuated inversion recovery (FLAIR) and diffusion-weighted imaging (DWI) sequences of magnetic resonance imaging. Multi objective bat algorithm has been applied to tune the parameters of the modified neuron model for the maximization of two competitive image performance indices contrast enhancement factor (F) and mean opinion score (MOS). The quality of processed image depends on the choice of these image performance indices rather the selection of SR parameters. The proposed approach performs well on enhancement of magnetic resonance (MR) images, as a result there is improvement in the gray-white matter differentiation and has been found helpful in the better diagnosis of MR images.