Determinant and Exchange Algorithms for Observation Subset Selection

In many applications involving image reconstruction, signal observation time is limited. This emphasizes the requirement for optimal observation selection algorithms. A selection criterion using the trace of a matrix forms the basis of two existing algorithms, the Sequential Backward Selection and Sequential Forward Selection algorithms. Neither is optimal although both generally perform well. Here we introduce a trace row-exchange criterion to further improve the quality of the selected subset and introduce another observation selection criterion based upon the determinant of a matrix.

[1]  L. Ganesan,et al.  Orthogonal Moments Based Texture Analysis of CT Liver Images , 2007 .

[2]  Nicholas D. Blakeley.  Sampling strategies and reconstruction techniques for magnetic resonance imaging , 2003 .

[3]  Martin J. Graves,et al.  MRI from Picture to Proton , 2017 .

[4]  P J Bones,et al.  Efficient frequency-domain sample selection for recovering limited-support images. , 2003, Journal of the Optical Society of America. A, Optics, image science, and vision.

[5]  Philip J. Bones,et al.  Improved matrix inversion in image plane parallel MRI. , 2009, Magnetic resonance imaging.

[6]  Manu Parmar,et al.  A perceptually based design methodology for color filter arrays [image reconstruction] , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[7]  W. Marsden.  I and J , 2012 .

[8]  Cai Chang,et al.  Classifying Uterine Myoma and Adenomyosis Based on Ultrasound Image Fractal and Texture Features , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[9]  Jing-Huei Lee,et al.  Fast spectroscopic imaging using online optimal sparse k‐space acquisition and projections onto convex sets reconstruction , 2006, Magnetic resonance in medicine.

[10]  Borut Marincek,et al.  How does MRI work? , 2003, Springer Berlin Heidelberg.

[11]  Sheng-Chih Yang,et al.  Comparative Evaluation of classifiers and Feature Selection Methods for Mass Screening in Digitized Mammograms , 2006, 2006 IEEE/NLM Life Science Systems and Applications Workshop.

[12]  Larry P. Heck,et al.  Selection of observations in signal reconstruction , 1995, IEEE Trans. Signal Process..

[13]  Yun Gao,et al.  Optimal k-space sampling in MRSI for images with a limited region of support , 2000, IEEE Transactions on Medical Imaging.

[14]  N. Kumaravel,et al.  Comparison of Feature Selection Techniques for Detection of Malignant Tumor in Brain Images , 2005, 2005 Annual IEEE India Conference - Indicon.

[15]  Stanley J. Reeves,et al.  Sequential algorithms for observation selection , 1999, IEEE Trans. Signal Process..

[16]  Yun Gao,et al.  Sequential forward sample selection in array-based image formation , 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

[17]  Alicia Troncoso Lora,et al.  Detection of Microcalcifications in Mammographies Based on Linear Pixel Prediction and Support-Vector Machines , 2007, Twentieth IEEE International Symposium on Computer-Based Medical Systems (CBMS'07).

[18]  Zhe Zhao,et al.  New results on observation selection in signal reconstruction , 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

[19]  Yun Gao,et al.  Efficient computation for sequential forward observation selection in image reconstruction , 1998, Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269).

[20]  Farzad Kamalabadi,et al.  Optimal Sensor Array Configuration in Remote Image Formation , 2008, IEEE Transactions on Image Processing.

[21]  Jie Yang,et al.  Degree prediction of malignancy in brain glioma using support vector machines , 2006, Comput. Biol. Medicine.