An adaptive method based on the improved LPA-ICI algorithm for MRI enhancement

ABSTRACT

Various diseases are diagnosed using medical imaging used for analysing internal anatomical structures. However, medical images are susceptible to noise introduced in both acquisition and transmission processes. We propose an adaptive data-driven image denoising algorithm based on an improvement of the intersection of confidence intervals (ICI), called relative ICI (RICI) algorithm. The 2D mask of the adaptive size and shape is calculated for each image pixel independently, and utilized in the design of the 2D local polynomial approximation (LPA) filters. Denoising performances, in terms of the PSNR, are compared to the original ICI-based method, as well as to the fixed sized filtering. The proposed adaptive RICI-based denoising 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.

KEYWORDS:

• Adaptive filtering
• intersection of confidence intervals
• relative intersection of confidence intervals
• local polynomial approximation
• image enhancement
• image denoising
• medical imaging
• magnetic resonance imaging

Disclosure statement

No potential conflict of interest was reported by the authors.

Notes on contributors

Jonatan Lerga, Head of the Laboratory for Application of Information Technologies at the Faculty of Engineering, University of Rijeka, Croatia, received his MS degree in Electrical Engineering from the Faculty of Engineering, University of Rijeka, in 2006, and the PhD degree from the Faculty of Electrical Engineering and Computing, University of Zagreb, Croatia in 2011. Since 2007, he has been with the Faculty of Engineering, University of Rijeka. In 2012, he received the Award of the Croatian Academy of Engineering for his scientific achievements, as well as the annual award of the City of Rijeka in 2015 and annual award of the Primorje-Gorski Kotar County in 2018. He also received annual awards from the Foundation of the University of Rijeka in 2008 and 2010. His main research interests are statistical signal processing, time-frequency signal analysis, image and video processing, and biomedical signal processing.

Ivica Mandić, Information System Developer at Hrvatski telekom, received his Master’s degree in Computing from the Faculty of Engineering, University of Rijeka, Croatia, in April 2018. Since 2017, he worked as Software Developer for desktop applications used in maritime affairs. Following that, since 2018, he has been with Hrvatski Telekom, a company in the Deutsche Telekom group, as Information System Developer.

Hajdi Peić, former student at the Faculty of Engineering, University of Rijeka, Croatia, received her master’s degree in Computing from the Faculty of Engineering, University of Rijeka, in April 2018. Since then, she has been a part of the team in one of the Kirey Group companies with branch office in Rijeka, Croatia, taking the position of the software application tester.

Drazen Brščić received his BSc and MSc degrees in electrical engineering from the University of Zagreb, Croatia, in 2000 and 2004, respectively, and the Dr. Eng. degree in electrical engineering from The University of Tokyo, Japan in 2008. From 2008 to 2010 he worked as a postdoctoral researcher at the Technische Universität München, Germany. In 2011 he joined ATR Intelligent Robotics and Communication Laboratories in Kyoto, Japan, as research scientist. Since 2016 he is working as a assistant professor at the Faculty of Engineering, University of Rijeka. His research interests include person tracking, mobile robotics and human-robot interaction.

ORCID

Jonatan Lerga http://orcid.org/0000-0002-4058-8449