Naslov
An Adaptive Method Based on the Improved LPA-ICI Algorithm for MRI Enhancement

Autori
Lerga, Jonatan ; Mandić, Ivica ; Peić, Hajdi ; Brščić, Dražen

Izvornik
Imaging science journal (1368-2199) 66 (2018), 6; 372-381

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
Adaptive filtering ; Intersection of confidence interval (ICI) algorithm ; Relative intersection of confidence intervals (RICI) ; Image denoising ; Magnetic resonance imaging (MRI)

Sažetak
Nowadays, various diseases can be diagnosed in their early stages using benefits of medical imaging for analyzing internal anatomical structures of the human body. However, medical images are susceptible to noise which is introduced in both acquisition and transmission processes. In this paper, we propose an adaptive data-driven image denoising algorithm based on an improvement of the intersection of confidence intervals (ICI) algorithm, called relative intersection of confidence intervals (RICI) algorithm. The 2D mask of the adaptive size and shape is calculated for each image pixel independently, and then utilized in the design of the 2D local polynomial approximation (LPA) filters for noise removal. Denoising performances, in terms of the peak signal-to- noise ratio (PSNR), are compared to the original ICI based method, as well as to the fixed sized filtering. The proposed adaptive RICI based denoising method outperformed the original ICI based method by up to 1.32 dB, and the fixed size filtering by up to 6.48 dB. Furthermore, since the denoising of each image pixel is done locally and independently, the method is easy to parallelize in order to reduce its execution time.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA