Digital Pathology Image Reconstruction with Alternating Direction Method of Multipliers using Wavelet, Contourlet and Shearlet Transforms

Year 2024, Volume: 19 Issue: 1, 169 - 178, 28.03.2024

Esra Şengün Ermeydan İlyas Çankaya

https://doi.org/10.55525/tjst.1367366

Abstract

Digital pathology refers to image-based environment in which acquisition, extraction and interpretation of pathology information is supported by computational techniques. It has a huge potential to facilitate the diagnostic process, however, big data size and necessity of large storage areas are challenging. Therefore, in this research, Compressed Sensing (CS) scheme is studied with digital pathology images in order to reduce the amount of data for reconstruction. CS requires the sparsity of signals for a successful recovery which means that different sparsifying bases can alter the final performance. Wavelet, Contourlet and Shearlet Transforms are investigated to sparsify the digital pathology images, it is seen that Contourlet Transform is superior. Alternating Direction Method of Multipliers (ADMM) is chosen for reconstruction since it is a robust and fast convex optimization method. Despite the fact that digital pathology images are less sparse than classical images, CS reconstruction is satisfactory, which emphasizes the potential of CS for digital pathology. This study can be pioneering in the field of CS with digital pathology so it can encourage further studies of CS based imaging with different type of microscopes or at different wavelengths.

Keywords

Compressed Sensing, Digital Pathology, Wavelet Transform, Contourlet Transform, Shearlet Transform

Supporting Institution

Ankara Yıldırım Beyazıt Üniversitesi

Project Number

AYBU-2018-BAP-4981

Thanks

This study is partially funded under the Ankara Yıldırım Beyazıt University's Projects Office Grant No. AYBU-2018-BAP-4981 about compressive sensing of digital pathology images. Open source convex optimization toolbox UNLocBoX is utilized for ADMM based reconstruction. The results shown here are in part based upon data generated by the TCGA Research Network: https://www.cancer.gov/tcga.

Dalgacık, Contourlet ve Shearlet Dönüşümleri Kullanılarak Çarpanların Alternatif Yön Yöntemi ile Dijital Patoloji Görüntüsü Geriçatılması

Abstract

Dijital patoloji, patoloji bilgilerinin elde edilmesi, çıkarılması ve yorumlanmasının hesaplamalı tekniklerle desteklendiği görüntü tabanlı ortamı ifade eder. Teşhis sürecini kolaylaştırma açısından büyük bir potansiyele sahiptir ancak büyük veri boyutu ve geniş depolama alanlarının gerekliliği zorlayıcıdır. Bu nedenle, bu araştırmada, yeniden yapılandırma için veri miktarını azaltmak amacıyla Sıkıştırılmış Algılama (CS) şeması dijital patoloji görüntüleri ile incelenmiştir. CS, başarılı bir kurtarma için sinyallerin seyrekliğini gerektirir; bu, farklı seyrekleştirici bazların nihai performansı değiştirebileceği anlamına gelir. Dijital patoloji görüntülerini seyrekleştirmek için Dalgacık, Contourlet ve Shearlet Dönüşümleri incelenmiştir, Contourlet Dönüşümünün üstün olduğu görülmüştür. Geriçatma için Alternatif Yön Çarpan Yöntemi (ADMM) sağlam ve hızlı bir dışbükey optimizasyon yöntemi olduğundan seçilmiştir. Dijital patoloji görüntülerinin klasik görüntülere göre daha az seyrek olmasına rağmen CS geriçatması tatmin edicidir, bu da CS'nin dijital patoloji için potansiyelini vurgulamaktadır. Bu çalışma, dijital patoloji ile CS alanında öncü olabilir ve farklı tipte mikroskoplarla veya farklı dalga boylarında CS tabanlı görüntülemeye yönelik daha ileri çalışmaları teşvik edebilir.

Keywords

Sıkıştırılmış Algılama, Dijital Patoloji, Dalgacık Dönüşümü, Contourlet Dönüşümü, Shearlet Dönüşümü

Project Number

AYBU-2018-BAP-4981

References

• Jahn S, Plass M, and Moinfar F. “Digital Pathology: Advantages, Limitations and Emerging Perspectives,” J. Clin. Med., vol. 9, p. 3697, Nov. 2020, doi: 10.3390/jcm9113697.
• Elgendi M, Fletcher RR, Abbott D, Zheng D, Kyriacou P, and Menon C, “Editorial: Mobile and wearable systems for health monitoring,” Front. Digit. Health, vol. 5, 2023, doi: 10.3389/fdgth.2023.1196103.
• Freire D, de Faria P, Travençolo B, and Zanchetta do Nascimento M. “Automated detection of tumor regions from oral histological whole slide images using fully convolutional neural networks,” Biomed. Signal Process. Control, vol. 69, p. 102921, Aug. 2021, doi: 10.1016/j.bspc.2021.102921.
• Joshi B, “Digital Pathology Market Size, Share, Trends Analysis Report by Application (Academic Research, Disease Diagnosis), by Product (Software, Device), by End-use (Diagnostic Labs, Hospitals), and Segment Forecasts, 2022-2030.” 2022.
• Shannon CE, “A Mathematical Theory of Communication,” Bell Syst. Tech. J., vol. 27, no. 3, pp. 379–423, 1948, doi: https://doi.org/10.1002/j.1538-7305.1948.tb01338.x.
• Taubman D and Marcellin M. JPEG2000 Imae Compression Fundamentals, Standards and Practice. Springer Publishing Company, Incorporated, 2013.
• Donoho DL, “Compressed sensing,” IEEE Trans. Inf. Theory, vol. 52, no. 4, pp. 1289–1306, 2006, doi: 10.1109/TIT.2006.871582.
• Candes EJ, , and Tao T. “Stable signal recovery from incomplete and inaccurate measurements,” Commun. Pure Appl. Math., vol. 59, no. 8, pp. 1207–1223, 2006, doi: https://doi.org/10.1002/cpa.20124.
• Candes EJ, J. R Romberg JK, and Tao T. “Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information,” IEEE Trans. Inf. Theory, vol. 52, no. 2, pp. 489–509, 2006, doi: 10.1109/TIT.2005.862083.
• Graff C and Sidky E. “Compressive sensing in medical imaging,” Appl. Opt., vol. 54, pp. C23-44, Mar. 2015, doi: 10.1364/AO.54.000C23.
• Lustig M, Donoho D, and Pauly JM, “Sparse MRI: The application of compressed sensing for rapid MR imaging,” Magn. Reson. Med., vol. 58, no. 6, pp. 1182–1195, 2007, doi: https://doi.org/10.1002/mrm.21391.
• Bell J. “FDA Clears Compressed Sensing MRI Acceleration Technology From Siemens Healthineers.” 2017.
• Radwell N, Mitchell K, Gibson G, Edgar M, Bowman R, and Padgett M. “Single-pixel infrared and visible microscope,” Optica, vol. 1, pp. 285–289, Oct. 2014, doi: 10.1364/OPTICA.1.000285.
• Hahamovich E, Monin S, Hazan Y, and Rosenthal A. “Single pixel imaging at megahertz switching rates via cyclic Hadamard masks,” Nat. Commun., vol. 12, Jul. 2021, doi: 10.1038/s41467-021-24850-x.
• Calisesi G. et al., “Compressed sensing in fluorescence microscopy,” Prog. Biophys. Mol. Biol., vol. 168, pp. 66–80, 2022, doi: https://doi.org/10.1016/j.pbiomolbio.2021.06.004.
• Binev P, Dahmen W, DeVore R, Lamby P, Savu D, and Sharpley R. “Compressed Sensing and Electron Microscopy,” in Modeling Nanoscale Imaging in Electron Microscopy, T. Vogt, W. Dahmen, and P. Binev, Eds., Boston, MA: Springer US, 2012, pp. 73–126. doi: 10.1007/978-1-4614-2191-7_4.
• Pavillon N, and Smith NI. “Compressed sensing laser scanning microscopy,” Opt Express, vol. 24, no. 26, pp. 30038–30052, Dec. 2016, doi: 10.1364/OE.24.030038.
• Boyd S, Parikh N, Chu E, Peleato B, and Eckstein J. “Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers,” Found. Trends Mach. Learn., vol. 3, pp. 1–122, Jan. 2011, doi: 10.1561/2200000016.
• Şengün Ermeydan E, Değirmenci A, Çankaya I, and Erdoğan F. “The Effects of Measurement Matrix and Reconstruction Algorithms on Compressed Sensing of Pathology Images,” Düzce Üniversitesi Bilim Ve Teknol. Derg., vol. 8, no. 1, pp. 880–890, 2020, doi: 10.29130/dubited.626880.
• Wang Z, Bovik AC, Sheikh HR, and Simoncelli EP. “Image quality assessment: from error visibility to structural similarity,” IEEE Trans. Image Process., vol. 13, no. 4, pp. 600–612, 2004, doi: 10.1109/TIP.2003.819861.
• Reisenhofer R, Bosse S, Kutyniok G, and Wiegand T. “A Haar wavelet-based perceptual similarity index for image quality assessment,” Signal Process. Image Commun., vol. 61, pp. 33–43, 2018, doi: https://doi.org/10.1016/j.image.2017.11.001.
• Candes EJ, “The restricted isometry property and its implications for compressed sensing,” Comptes Rendus Math., vol. 346, no. 9, pp. 589–592, 2008, doi: https://doi.org/10.1016/j.crma.2008.03.014.
• Baraniuk R, Davenport M, DeVore R, and Wakin M. “A Simple Proof of the Restricted Isometry Property for Random Matrices,” Constr. Approx., vol. 28, pp. 253–263, Dec. 2008, doi: 10.1007/s00365-007-9003-x.
• Daubechies I. Ten Lectures on Wavelets. USA: Society for Industrial and Applied Mathematics, 1992.
• Do MN and Vetterli M. “The contourlet transform: an efficient directional multiresolution image representation,” IEEE Trans. Image Process., vol. 14, no. 12, pp. 2091–2106, 2005, doi: 10.1109/TIP.2005.859376.
• Kutyniok G and Sauer T. “Adaptive Directional Subdivision Schemes and Shearlet Multiresolution Analysis,” SIAM J. Math. Anal., vol. 41, pp. 1436–1471, Jan. 2009, doi: 10.1137/08072276X.
• Mallat SG, “A theory for multiresolution signal decomposition: the wavelet representation,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 11, no. 7, pp. 674–693, 1989, doi: 10.1109/34.192463.
• Meyer Y. Wavelets and Operators, vol. 1. in Cambridge Studies in Advanced Mathematics, vol. 1. Cambridge University Press, 1993. doi: 10.1017/CBO9780511623820.
• Gonzalez RC and Woods RE. Digital image processing. Upper Saddle River, N.J.: Prentice Hall, 2008. . Available: http://www.amazon.com/Digital-Image-Processing-3rd-Edition/dp/013168728X
• Bauschke HH, Burachik RS, Combettes PL, Elser V, Luke DR, and Wolkowicz H. Fixed-Point Algorithms for Inverse Problems in Science and Engineering. Springer Publishing Company, Incorporated, 2013.
• Gutman DA et al. “Cancer digital slide archive: An informatics resource to support integrated in silico analysis of TCGA pathology data,” J. Am. Med. Inform. Assoc. JAMIA, vol. 20, no. 6, pp. 1091–1098, 2013, doi: 10.1136/amiajnl-2012-001469.