A Hardware Implementation of a Brain Inspired Filter for Image Processing

A cognitive image processing implementation for pattern-matching execution is proposed in this paper. It is based on the learning process of the human vision as an edge-enhancing filter for medical images. We set up an experiment to test its impact on the performance of decision-making algorithm working on brain magnetic resonance data. The execution times of similar filters can become unpractical on real 3-D or higher dimensional data, if implemented on a CPU. An innovative and high-performance embedded system for real-time pattern matching was developed. The design uses field-programmable gate arrays and the powerful associative memory chip (an ASIC) to achieve real-time performance and requires a training phase and a data acquisition phase. It is a very compact implementation that improves execution time <inline-formula> <tex-math notation="LaTeX">$\times 1000$ </tex-math></inline-formula> for the training phase and <inline-formula> <tex-math notation="LaTeX">$\times 100$ </tex-math></inline-formula> for the data acquisition phase for 2-D black and white images compared to a last generation i7 CPU. The implementation of this edge-enhancing filter is expected to positively impact on medical devices for real-time diagnosis (e.g., diagnostic ultrasound) and for image processing steps in medical image analysis where computing power is a limiting factor.

[1]  M. Tosetti,et al.  Ultra-High-Field MR Imaging in Polymicrogyria and Epilepsy , 2015, American Journal of Neuroradiology.

[2]  Mohd Fauzi Bin Othman,et al.  An overview of MRI brain classification using FPGA implementation , 2010, 2010 IEEE Symposium on Industrial Electronics and Applications (ISIEA).

[3]  Alexandre Yakovlev,et al.  Performance efficient FPGA implementation of parallel 2-D MRI image filtering algorithms using Xilinx system generator , 2010, 2010 7th International Symposium on Communication Systems, Networks & Digital Signal Processing (CSNDSP 2010).

[4]  G. Aad,et al.  The ATLAS Experiment at the CERN Large Hadron Collide , 2008 .

[5]  G. Punzi,et al.  Information and Perception of Meaningful Patterns , 2013, PloS one.

[6]  V. Kasik,et al.  FPGA in technical resources of medical imaging , 2013, 2013 IEEE 11th International Symposium on Applied Machine Intelligence and Informatics (SAMI).

[7]  Abraham Lempel,et al.  A universal algorithm for sequential data compression , 1977, IEEE Trans. Inf. Theory.

[8]  P. Luciano,et al.  Highly Parallelized Pattern Matching Hardware for Fast Tracking at Hadron Colliders , 2016, IEEE Transactions on Nuclear Science.

[9]  D. Magalotti,et al.  The FastTracker Real Time Processor and Its Impact on Muon Isolation, Tau and b-Jet Online Selections at ATLAS , 2012, IEEE Transactions on Nuclear Science.

[10]  W. H. Smith,et al.  Triggering at LHC experiments , 2002 .

[11]  A. Goshaw.  The ATLAS Experiment at the CERN Large Hadron Collider , 2008 .

[12]  Volkmar Schulz,et al.  FPGA-based singles and coincidences processing pipeline for integrated digital PET/MR detectors , 2012, 2012 IEEE Nuclear Science Symposium and Medical Imaging Conference Record (NSS/MIC).

[13]  Monica Borda,et al.  Fundamentals in Information Theory and Coding , 2011 .

[14]  P. Luciano,et al.  A Multi-Core FPGA-Based 2D-Clustering Implementation for Real-Time Image Processing , 2014, IEEE Transactions on Nuclear Science.

[15]  Stamatios Gkaitatzis,et al.  High Performance Embedded System for Real-Time Pattern Matching , 2017 .

[16]  Spiridon Nikolaidis,et al.  Real-Time Machine Vision FPGA Implementation for Microfluidic Monitoring on Lab-on-Chips , 2014, IEEE Transactions on Biomedical Circuits and Systems.

[17]  Mauro Dell'Orso,et al.  VLSI STRUCTURES FOR TRACK FINDING , 1989 .

[18]  Alberto Annovi,et al.  Characterisation of an Associative Memory Chip for high-energy physics experiments , 2014, 2014 IEEE International Instrumentation and Measurement Technology Conference (I2MTC) Proceedings.

[19]  Piergiorgio Cerello,et al.  Predictive Models Based on Support Vector Machines: Whole‐Brain versus Regional Analysis of Structural MRI in the Alzheimer's Disease , 2015, Journal of neuroimaging : official journal of the American Society of Neuroimaging.