NUMERICAL ERROR ANALYSIS FOR CONFIGURABLE CELL SEGMENTATION PROBLEM

Yıl 2019, Cilt: 20 , 193 - 205, 16.12.2019

Nataliya Bilous Oleg Hramm İryna Ahekian Abed Thamer Khudhaır Ludmila Illyashenko Alexander Nerukh

https://doi.org/10.18038/estubtda.650048

Öz

The current intense interest in gold
nanoparticles is due to their Surface Plasmon Resonances (SPR) that depend
strongly on the shape and size of the nanoparticles. As the SPR wavelength and
resonantly enhanced absorption and scattering properties also depend on the
dielectric medium in which gold nanoparticles are embedded, and also depend on
the way of their clustering, they are useful to design novel nanodevices, in
particular when it is based on ideas taken from nature. With purpose to select
the most promising configurations for novel nanodevice design in this work the
method of cell recognition and evaluation of its efficiency is proposed. Exist
different methods to produce microscopic images, they can be obtained for
different types of cells in different environments. Due to this fact, the
recognition algorithms are needed. All methods have their advantages and
disadvantages and may work well only under certain conditions. Therefore, it is
useful for each specific task to implement a separate algorithm that will be
effective for the existing set of images, and take into account the
peculiarities of these images. The task of this work is not only to develop
flexible and customizable algorithm, that can be configured to segment cells on
different types of images, but also provide numerical error analysis corresponding
to each step of algorithm. As a result, a solution is developed, that has many
customizable parameters to optimize the result for a specific data set and
specific accuracy. In addition, this it is resistant to a lot of noise and
artifacts, that can occur on images, such as uneven background, small debris,
loss of focus when shooting. Numerical error analysis allows getting form of
cell segmentation more precisely to be reproduced for novel nanostructured
device design

Anahtar Kelimeler

Cells recognition, Segmentation, Watershed; Hough transform

Kaynakça

• [1] Shim H, Allabergenov B, Kim J, Noh H.Y, Lyu H.-K, Lee M.-J, Choi B. Highly Bright Flexible Electroluminescent Devices with Retroreflective Electrodes, Advanced Materials Technologies 2017; 2(9): 1700040. DOI: 10.1002/admt.201700040
• [2] Liapis A.C, Rahman A, Black C.T. Self-assembled nanotextures impart broadband transparency to glass windows and solar cell encapsulants, Appl. Phys. Lett. 2017; 111: 183901. https://doi.org/10.1063/1.500096
• [3] Law J. B. K, Ng A.M.H, He A.Y, Low H.Y., Bioinspired Ultrahigh Water Pinning Nanostructures, Langmuir 2014; 30(1): 325–331, DOI: 10.1021/la4034996.
• [4] Podsiadlo P, Liu Z, Paterson D, Messersmith P. B, Kotov N.A, Fusion of Seashell Nacre and Marine Bioadhesive Analogs: High-Strength Nanocomposite by Layer-by-Layer Assembly of Clay and L-3,4-Dihydroxyphenylalanine Polymer, Advanced Materials 2007; 19(7): 949–955. DOI: 10.1002/adma.200602706.
• [5] Davies O.G, Cox S.C, Williams R.L, Tsaroucha D, Dorrepaal R.M, Lewis M.P, Grover L.M, Annexin-enriched osteoblast-derived vesicles act as an extracellular site of mineral nucleation within developing stem cell cultures, Scientific Reports 2017; 7: 12639, doi:10.1038/s41598-017-13027-6.
• [6] Palkovic S.D, Brommer D.B, Kupwade-Patil K, Masic A., Buehler M.J, Büyüköztürk O, Roadmap across the mesoscale for durable and sustainable cement paste – A bioinspired approach, Construction and Building Materials 2016; 115: 13-31, https://doi.org/10.1016/j.conbuildmat.2016.04.020.
• [7] Peng J, Cheng Q, High-Performance Nanocomposites Inspired by Nature, Advanced Materials, 2017; 29: 1702959; DOI: 10.1002/adma.201702959.
• [8] Wong C.K, Mason A.F, Stenzel M.H, Thordarson P, Formation of non-spherical polymersomes driven by hydrophobic directional aromatic perylene interactions, Nature Communications 2017; 8: 1240; DOI:10.1038/s41467-017-01372-z.
• [9] Boyko D, Podoroznyuk A, Filatova A. The main stages of image processing in the design of biotechnical systems in medical radiology. The National Technical University - Kharkiv Polytechnic Institute 2012; 85 – 86. (in Russian).
• [10] Kovrigin A. Application of the principles of building computer vision systems in the problem of image analysis of cellular structures. Scientific Journal of KubSAU 2007; 1 – 3. (in Russian).
• [11] Tarkov М. Estimation of the number of cells on the images of cytological plant preparations. A.V. Rzhanov Institute of Semiconductor Physics 2013; 187 – 190. (in Russian).
• [12] Romero-Rondón М, Sanabria-Rosas L, Bautista-Rozo L, Mendoza-Castellanos A. Algorithm for detection of overlapped red blood cells in microscopic images of blood smears. DYNA 84; Rzhanov Institute of Semiconductor Physics 2016; 187 – 194.
• [13] Uchida S. Image processing and recognition for biological images. Dev. Growth. Differ. 2013; 55(4): 523-549.
• [14] Rivest J, Soille P, Baucher S. Morphological gradients. Journal of Electronic Imaging 1993; 2(4).
• [15] Krylov V, Shcherbakova G, Pisarenko R, Bilous N. Signal restoration by means of blind deconvolution based on optimization with wavelet transformation In: IEEE: 2016 Third International Scientific-Practical Conference Problems of Infocommunications Science and Technology (PIC S&T), October 4-6, 2016, Kharkiv, Ukraine; DOI: 10.1109/INFOCOMMST.2016.7905324.
• [16] Ablameyko S, Nedzved A. Processing of optical images of cellular structures in medicine. OIIP NAS Belarus 2005; 3: 35-55 (in Russian).
• [17] Firdousi R, Parveen S. Local Thresholding Techniques in Image Binarization. International Journal Of Engineering And Computer Science 2014; 3: 4062-4065.
• [18] Bradski G, Kaehler A. Learning OpenCV: Computer vision with the OpenCV library. O'Reilly Media San Diego, Inc., 2008.
• [19] Hramm O, Bilous N, Ahekian I. Configurable Cell Segmentation Solution Using Hough Circles Transform and Watershed Algorithm.In: 2019 IEEE 8th International Conference on Advanced Optoelectronics and Lasers (CAOL) CAOL 2019 September 6-8, 2019, Sozopol, Bulgaria, USA: IEEE, 602-605.
• [20] Image set BBBC005v1 from the Broad Bioimage Benchmark Collection. Available from: https://data.broadinstitute.org/bbbc/BBBC005/
• [21] Image set BBBC004v1 from the Broad Bioimage Benchmark Collection. Available from: https://data.broadinstitute.org/bbbc/BBBC004/
• [22] Smajic J, Hafner Ch, Raguin L, Tavzarashviki K, Mishrikey M, Comparison of numerical methods for the analysis of plasmonic structures. J. Comput. Theor. Nanoscience 2009; 6: 1-12.