Patolojik Görüntülerin Sıkıştırılmış Algılamasında Ölçüm Matrisi ve Geri Çatma Algoritmalarının Etkileri
Year 2020,
Volume: 8 Issue: 1, 880 - 890, 31.01.2020
Esra Şengün Ermeydan
,
Ali Değirmenci
,
İlyas Çankaya
,
Fazlı Erdoğan
Abstract
Bu çalışmada, patolojik görüntülerin
sıkıştırılmış algılama tabanlı tek piksel mikroskop ile alınıp, görüntünün geri
çatılması ile ilgili benzetimler yapılmıştır. Sıkıştırılmış algılamada, ölçüm
matrisi olarak elemanları bağımsız ve aynı şekilde dağıtılan Gaussian
ve Bernoulli matrisler kullanılmıştır. Geri çatma algoritması olarak da konveks
optimizasyon tabanlı hem Toplam Varyasyon (TV) minimizasyonunun hem de L1 norm
minimizasyonunun performansları incelenmiştir. Yapılan benzetimler sonucunda,
1:8 sıkıştırma oranında dahi patolojik görüntülerin geri çatılabildiği
gösterilmiştir. Geri çatılan görüntülerin orijinal görüntü ile benzerlik
endeksleri karşılaştırıldığında, özellikle yüksek sıkıştırma oranında TV
minimizasyonu daha başarılı sonuçlar vermiştir. Hem Gaussian hem de Bernoulli rasgele
ölçüm matrisleri ile patolojik görüntülerin geri çatılabildiği gösterilmiştir. Sonuç
olarak sıkıştırılmış algılama tabanlı tek piksel mikroskop tasarımlarında
Bernoulli ölçüm matrisinin kullanılması önerilmiştir.
Supporting Institution
Ankara Yıldırım Beyazıt Üniversitesi
Thanks
TEŞEKKÜR: Bu çalışma Ankara Yıldırım Beyazıt Üniversitesi Bilimsel Araştırma Projeleri tarafından desteklenmiştir (Proje no: 4981).
References
- [1] D. L. Donoho, “Compressed sensing,” IEEE Trans. Inform. Theory, c.52, ss.1289–1306, 2006.
- [2] E. Candès, J. Romberg ve T. Tao, “Robust uncertainty principles: Exact signal reconstruction from highly incomplete Fourier information,” IEEE Trans. Inform. Theory, c.52, ss.489-509, 2006.
- [3] E. Candès, J. Romberg ve T. Tao, "Stable signal recovery from incomplete and inaccurate measurements," Comm. Pure Appl. Math., c. 59, s. 8, ss. 1207-1223, 2006.
- [4] E. Candès ve T. Tao, "Decoding by linear programming," IEEE Trans. Inf. Theory, c. 51, s. 12, ss. 4203-4215, 2005.
- [5] M. Lustig, D. Donoho ve J. M. Pauly, “Sparse MRI: The application of compressed sensing for rapid MR imaging”. Magnetic Resonance in Medicine, c.58, s. 6, ss. 1182–1195, 2007.
- [6] M.F. Duarte ve Y. C. Eldar, “Structured Compressed Sensing: From Theory to Applications,” IEEE Transactions on Signal Processing, c.59, s.9, ss. 4053–4085, DOI: 10.1109/TSP.2011.2161982, 2011.
- [7] FDA Clears Compressed Sensing MRI Acceleration Technology From Siemens Healthineers, (2017, 12 Şubat). [Online]. Erişim: https://www.healthimaging.com/topics/imaging/fda-clears-compressed-sensing-mri-acceleration-technology-siemens-healthineers .
- [8] C.G. Graff ve E.Y. Sidky. “Compressive sensing in medical imaging,” Applied optics, c.54, s.8, ss. C23-C44, 2015.
- [9] A. Malthe-Sørenssen, “Medical radiation may be reduced to one-sixth” Apollon Research Magazine, 2015.
- [10] Compressive Sensing Could Dramatically Reduce Time to Process Complex Clinical Laboratory Tests Involving Huge Amounts of Data and Lower the Cost of Tests, (2015, 16 Eylül). [Online]. Erişim: https://www.darkdaily.com/compressive-sensing-could-dramatically-reduce-time-to-process-complex-clinical-laboratory-tests-involving-huge-amounts-of-data-and-lower-the-cost-of-tests-916/#ixzz3sRuYQJI4 .
- [11] M. F. Duarte, M. A. Davenport, D. Takhar, J. N. Laska, T. Sun, K. F. Kelly ve R. G. Baraniuk, “Single-Pixel Imaging via Compressive Sampling,” IEEE Signal Processing Magazine, March 2008.
- [12] N. Radwell, K. J. Mitchell, G. M. Gibson, M. P. Edgar, R. Bowman ve M. J. Padgett, “Single-pixel infrared and visible microscope,” Optica 1, ss.285-289, 2014.
- [13] Y. Liu, J. Suo, Y. Zhang ve Q. Dai, “Single-pixel phase and fluorescence microscope,” Optics Express, c. 26, ss. 32451-32462, 2018.
- [14] A.D. Rodríguez, P. Clemente, E. Tajahuerce ve J. Lancis, “Dual-mode optical microscope based on single-pixel imaging,” Optics and Lasers in Engineering, c. 82, ss. 87-94, ISSN 0143-8166, https://doi.org/10.1016/j.optlaseng.2016.02.004, 2016.
- [15] B. Kashin, “The widths of certain finite dimensional sets and classes of smooth functions,” Izvestia, c. 41, ss. 334–351, 1977.
- [16] A. Garnaev ve E. D. Gluskin, “The widths of Euclidean balls,” Doklady An. SSSR, c.277, ss. 1048–1052, 1984.
- [17] C. Li, W. Yin , H. Jiang ve Y. Zhang. “An efficient augmented Lagrangian method with applications to total variation minimization,” Computational Optimization and Applications, c.56, s.3, ss. 507–530, ISSN:1573-2894,DOI:10.1007/s10589-013-9576-1, 2013.
- [18] ℓ1-magic: Recovery of Sparse Signals via Convex Programming, (2005). [Online]. Erişim: https://statweb.stanford.edu/~candes/l1magic/ .
- [19] E. van den Berg ve M. P. Friedlander, “Probing the Pareto frontier for basis pursuit solutions,” SIAM J. on Scientific Computing, c.31, s.2, ss.890-912, Kasım 2008.
- [20] D. A. Gutman, J. Cobb, D. Somanna, Y. Park, F. Wang, T. Kurc, J. H. Saltz, D. J. Brat ve L. A. D. Cooper, “Cancer Digital Slide Archive: an informatics resource to support integrated in silico analysis of TCGA pathology data,” J Am Med Inform Assoc, c.20, ss.1091–1098, 2013.
- [21] W. Zhou, A. C. Bovik, H. R. Sheikh ve E. P. Simoncelli. “Image Qualifty Assessment: From Error Visibility to Structural Similarity,” IEEE Transactions on Image Processing. c. 13, s. 4, ss. 600–612, Nisan 2004.
- [22] R. Reisenhofer, S. Bosse, G. Kutyniok ve T. Wiegand, “A Haar Wavelet-Based Perceptual Similarity Index for Image Quality Assessment,” Signal Processing: Image Communication, c. 61, ss. 33-43, doi:10.1016/j.image.2017.11.001, 2018.
- [23] B. Roman, A. C. Hansen ve B. Adcock, (2014). “On asymptotic structure in compressed sensing,” CoRR, abs/1406.4178, 2014.
Year 2020,
Volume: 8 Issue: 1, 880 - 890, 31.01.2020
Esra Şengün Ermeydan
,
Ali Değirmenci
,
İlyas Çankaya
,
Fazlı Erdoğan
References
- [1] D. L. Donoho, “Compressed sensing,” IEEE Trans. Inform. Theory, c.52, ss.1289–1306, 2006.
- [2] E. Candès, J. Romberg ve T. Tao, “Robust uncertainty principles: Exact signal reconstruction from highly incomplete Fourier information,” IEEE Trans. Inform. Theory, c.52, ss.489-509, 2006.
- [3] E. Candès, J. Romberg ve T. Tao, "Stable signal recovery from incomplete and inaccurate measurements," Comm. Pure Appl. Math., c. 59, s. 8, ss. 1207-1223, 2006.
- [4] E. Candès ve T. Tao, "Decoding by linear programming," IEEE Trans. Inf. Theory, c. 51, s. 12, ss. 4203-4215, 2005.
- [5] M. Lustig, D. Donoho ve J. M. Pauly, “Sparse MRI: The application of compressed sensing for rapid MR imaging”. Magnetic Resonance in Medicine, c.58, s. 6, ss. 1182–1195, 2007.
- [6] M.F. Duarte ve Y. C. Eldar, “Structured Compressed Sensing: From Theory to Applications,” IEEE Transactions on Signal Processing, c.59, s.9, ss. 4053–4085, DOI: 10.1109/TSP.2011.2161982, 2011.
- [7] FDA Clears Compressed Sensing MRI Acceleration Technology From Siemens Healthineers, (2017, 12 Şubat). [Online]. Erişim: https://www.healthimaging.com/topics/imaging/fda-clears-compressed-sensing-mri-acceleration-technology-siemens-healthineers .
- [8] C.G. Graff ve E.Y. Sidky. “Compressive sensing in medical imaging,” Applied optics, c.54, s.8, ss. C23-C44, 2015.
- [9] A. Malthe-Sørenssen, “Medical radiation may be reduced to one-sixth” Apollon Research Magazine, 2015.
- [10] Compressive Sensing Could Dramatically Reduce Time to Process Complex Clinical Laboratory Tests Involving Huge Amounts of Data and Lower the Cost of Tests, (2015, 16 Eylül). [Online]. Erişim: https://www.darkdaily.com/compressive-sensing-could-dramatically-reduce-time-to-process-complex-clinical-laboratory-tests-involving-huge-amounts-of-data-and-lower-the-cost-of-tests-916/#ixzz3sRuYQJI4 .
- [11] M. F. Duarte, M. A. Davenport, D. Takhar, J. N. Laska, T. Sun, K. F. Kelly ve R. G. Baraniuk, “Single-Pixel Imaging via Compressive Sampling,” IEEE Signal Processing Magazine, March 2008.
- [12] N. Radwell, K. J. Mitchell, G. M. Gibson, M. P. Edgar, R. Bowman ve M. J. Padgett, “Single-pixel infrared and visible microscope,” Optica 1, ss.285-289, 2014.
- [13] Y. Liu, J. Suo, Y. Zhang ve Q. Dai, “Single-pixel phase and fluorescence microscope,” Optics Express, c. 26, ss. 32451-32462, 2018.
- [14] A.D. Rodríguez, P. Clemente, E. Tajahuerce ve J. Lancis, “Dual-mode optical microscope based on single-pixel imaging,” Optics and Lasers in Engineering, c. 82, ss. 87-94, ISSN 0143-8166, https://doi.org/10.1016/j.optlaseng.2016.02.004, 2016.
- [15] B. Kashin, “The widths of certain finite dimensional sets and classes of smooth functions,” Izvestia, c. 41, ss. 334–351, 1977.
- [16] A. Garnaev ve E. D. Gluskin, “The widths of Euclidean balls,” Doklady An. SSSR, c.277, ss. 1048–1052, 1984.
- [17] C. Li, W. Yin , H. Jiang ve Y. Zhang. “An efficient augmented Lagrangian method with applications to total variation minimization,” Computational Optimization and Applications, c.56, s.3, ss. 507–530, ISSN:1573-2894,DOI:10.1007/s10589-013-9576-1, 2013.
- [18] ℓ1-magic: Recovery of Sparse Signals via Convex Programming, (2005). [Online]. Erişim: https://statweb.stanford.edu/~candes/l1magic/ .
- [19] E. van den Berg ve M. P. Friedlander, “Probing the Pareto frontier for basis pursuit solutions,” SIAM J. on Scientific Computing, c.31, s.2, ss.890-912, Kasım 2008.
- [20] D. A. Gutman, J. Cobb, D. Somanna, Y. Park, F. Wang, T. Kurc, J. H. Saltz, D. J. Brat ve L. A. D. Cooper, “Cancer Digital Slide Archive: an informatics resource to support integrated in silico analysis of TCGA pathology data,” J Am Med Inform Assoc, c.20, ss.1091–1098, 2013.
- [21] W. Zhou, A. C. Bovik, H. R. Sheikh ve E. P. Simoncelli. “Image Qualifty Assessment: From Error Visibility to Structural Similarity,” IEEE Transactions on Image Processing. c. 13, s. 4, ss. 600–612, Nisan 2004.
- [22] R. Reisenhofer, S. Bosse, G. Kutyniok ve T. Wiegand, “A Haar Wavelet-Based Perceptual Similarity Index for Image Quality Assessment,” Signal Processing: Image Communication, c. 61, ss. 33-43, doi:10.1016/j.image.2017.11.001, 2018.
- [23] B. Roman, A. C. Hansen ve B. Adcock, (2014). “On asymptotic structure in compressed sensing,” CoRR, abs/1406.4178, 2014.