Sitopatolojik Değerlendirme Süreçleri için Optimum Aralığın Korunmasıyla Yüksek Çözünürlüklü Otomatik Panoramik Görüntüleme

Öz

Mikroskop dar bir görüş alanına sahip olduğu için sitopatolojik değerlendirme süreçlerinde patologlar numunenin sadece belirli bir kısmını görebilmektedirler. Numunenin tüm alanını inceleyebilmek için mikroskop platformunu X-Y-Z yönünde hareket ettirerek numune üzerinde üç boyutlu tarama yapmaktadırlar. Yapılan çalışmada sitopatolojik değerlendirme süreçleri otomatikleştirilerek numunenin geniş görüş alanına sahip yüksek çözünürlüklü panoramik görüntüsünün elde edilmesi amaçlanmaktadır. Panoramik birleştirme sürecinin otomatikleştirilmesi için yapılan literatür çalışmalarında ortak alanlı görüntüler oluşturulurken mikroskopta var olan ve mikron cinsinden ölçülen odaklama derinliği dikkate alınmamaktadır. Bu yüzden ortak alanlı görüntüler arasında odaklama farklılıkları oluşmakta ve tarama anında bulanık görüntüler elde edilmektedir. Bu problemi çözmek için çalışmada odaklama derinliği artırılarak optimum odaklanmış ortak alanlı görüntüler oluşturulmaktadır. Önerilen yöntemin başarısının ispatı için literatürde önerilmiş 2 farklı tarama süreci kullanılarak panoramik görüntüler elde edilmiştir. Oluşturulmuş panoramik görüntüler referans görüntü gerektirmeyen metrikler kullanılarak karşılaştırılmış ve önerilen yöntemin başarısı hem sayısal hem de görsel sonuçlarla ispatlanmıştır.

Anahtar Kelimeler

• Sitopatolojik Değerlendirme,Panoramik Görüntüleme,Odaklama Derinliği,Odaklama Derinliğinin Artırılması

High Resolution Automatic Panoramic Imaging by Maintaining Optimal Range for Cytopathological Analysis

Öz

Since the microscope has a small field of view, pathologists can only see a certain part of the specimen during the cytopathological analysis process. In order to see the whole area of the sample, they scan the sample in three dimensions by moving the microscope platform in the X-Y-Z direction. The aim of the study is to obtain a high resolution panoramic image of the sample by automating the process of cytopathological analysis. Literature studies for the automation of the panoramic imaging process do not take into account the depth of focus measured in microns, which is present in the microscope, while creating images with the same field of view. This results in differences in focus between the images and during the scanning process blurred images are obtained. In order to solve this problem, the depth of focus is extended to produce optimum focused images. To evaluate the success of the proposed method, panoramic images were obtained using two different scanning processes suggested in the literature. The generated panoramic images are compared using the metrics without requiring reference image and the success of the proposed method is proved by both quantitative and visual results

Anahtar Kelimeler

• Cytopathological Analysis,Panoramic Imaging,Depth of Focus,Extended Depth of Field

Kaynakça

1. [1] Schneider T. E., Bell A. A., Meyer-Ebrecht D., Böcking A., Aach T. “Computer aided cytological cancer diagnosis: cell type classification as a step towards fully automatic cancer diagnostics on cytopathological specimens of serous effusions”, Medical Imaging, International Society for Optics and Photonics, vol.6514, pp. 6514-6524, 2007.
2. [2] Doğan H., Ekinci M., “Automatic panorama with auto-focusing based on image fusion for microscopic imaging system”, Signal, Image and Video Processing, vol. 8, pp. 5-20, 2014.
3. [3] Born M., Wolf E., “Principles of Optics (7th Ed)”, Cambridge University Press, 1999.
4. [4] Goldsmith N.T., “Deep focus; a digital image processing technique to produce improved focal depth in light microscopy”, Image Analysis – Stereology, vol. 19, pp. 163-167, 2011.
5. [5] Piccinini F., Tesei A., Zoli W., Bevilacqua A., “Extended depth of focus in optical microscopy: Assessment of existing methods and a new proposal”, Microscopy Research and Technique, vol. 75, pp. 1582-1592, 2012.
6. [6] Forster B., Van De Ville D., Berent J., Sage, D., Unser M., “Complex wavelets for extended depth-of-field: A new method for the fusion of multichannel microscopy images”, Microscopy Research and Technique, vol. 65, pp. 33–42, 2004.
7. [7] Ma B., Zimmermann T., Rohde M., Winkelbach S., He F., Lindenmaier W., Dittmar K. E., “Use of autostitch for automatic stitching of microscope images”, Micron, vol. 38, pp. 492-499, 2007.
8. [8] Yang F., Deng Z. S., Fan Q. H., “A method for fast automated microscope image stitching”, Micron, vol. 48, pp. 17-25, 2013.

9. [9] Appleton B., Bradley A. P., Wildermoth M., “Towards Optimal Image Stitching for Virtual Microscopy”, in Digital Image Computing: Techniques and Applications (DICTA'05), Queensland, Australia, 2005, pp. 44-44.
10. [10] Sun C., Beare R., Hilsenstein V., Jackway P., “Mosaicing of microscope images with global geometric and radiometric corrections”, Journal of Microscopy, vol. 224, pp. 158-165, 2006.
11. [11] Loewke K. E., Camarillo D. B., Piyawattanametha W., Mandella M. J., Contag C. H., Thrun S., Salisbury J. K.,“In vivo micro-image mosaicing” IEEE Transactions on Biomedical Engineering, vol. 58, pp. 159-171, 2011.
12. [12] Wu Y., Fang Y., Liu X., Ren X., Guo J., Yuan X., “Millimeter scale global visual field construction for atomic force microscopy based on automatic image stitching”, In Manipulation, Automation and Robotics at Small Scales (MARSS), 2017, pp. 1-5.
13. [13] Hsu W. Y., Poon W. F., Sun Y. N., “Automatic seamless mosaicing of microscopic images: enhancing appearance with colour degradation compensation and wavelet‐based blending”, Journal of Microscopy, vol. 231, pp. 408-418, 2008.
14. [14] Thévenaz P., Unser M., “User‐friendly semiautomated assembly of accurate image mosaics in microscopy”, Microscopy Research and Technique, vol. 70, pp. 135-146, 2007.
15. [15] Legesse F. B., Chernavskaia O., Heuke S., Bocklitz T., Meyer T., Popp J., Heintzmann R., “Seamless stitching of tile scan microscope images”, Journal of Microscopy, vol. 258, pp. 223-232, 2015.
16. [16] Han S., Yang J., Wan H., “An automated wide-view imaging system of pathological tissue under optical microscopy”, in Biomedical Image and Signal Processing (ICBISP), 2017, pp. 1-6.
17. [17] Forster B., Van De Ville D., Berent J., Sage D., Unser M., “Extended Depth-of-Focus for Multichannel Microscopy Images: A Complex Wavelet Approach”, in International Symposium on Biomedical Imaging: Nano to Macro, 2004, pp. 660-663.
18. [18] Choi H., Cheng S., Wu Q., Castleman K. R.,Bovik A. C., “Extended depth-of-field using adjacent plane deblurring and MPP wavelet fusion for microscope images”, in 3rd IEEE International Symposium on Biomedical Imaging: Nano to Macro, 2006, pp. 774-777.
19. [19] Tessens L., Ledda A., Pizurica A., Philips W., “Extending the Depth of Field in Microscopy Through Curvelet-Based Frequency-Adaptive Image Fusion”, in International Conference on Acoustics, Speech and Signal Processing - ICASSP ’07, 2007, pp. 861-864.
20. [20] Doğan H., Baykal E., Ekinci M., Ercin M. E., Ersöz Ş., “Optimal focusing with extended depth of focus in microscopic systems”, in 25th Signal Processing and Communications Applications Conference (SIU), Antalya, 2017, pp. 1-4.
21. [21] Li S., Kang X., Fang L., Hu J., Yin H., “Pixel-level image fusion: A survey of the state of the art”, Information Fusion, vol. 33, pp. 100-112, 2017.
22. [22] Sahu A., Bhateja V., Krishn A., Himanshi, “Medical image fusion with laplacian pyramids”, In 2014 International Conference on Medical Imaging, m-Health and Emerging Communication Systems (MedCom), 2014, pp. 448-453.
23. [23] Petrovic V.S., Xydeas C.S., “Gradient-based multiresolution image fusion”, IEEE Transactions on Image Processing, vol. 13, pp. 228-237, 2004.
24. [24] Denipote J.G., Paiva M.S.V., “A fourier transform-based approach to fusion high spatial resolution remote sensing images”, In 2008 Sixth Indian Conference on Computer Vision, Graphics Image Processing, 2008, pp. 179-186.
25. [25] Naidu V., “Discrete cosine transform-based image fusion”, Defence Science Journal, vol. 60, pp. 48-54, 2010.
26. [26] Pajares G., de la Cruz J.M., “A wavelet-based image fusion tutorial”, Pattern Recognition, vol. 37, pp. 1855-1872, 2004.
27. [27] Chai Y., Li H., Zhang X., “Multifocus image fusion based on features contrast of multiscale products in nonsubsampledcontourlet transform domain”, Optik – International Journal for Light and Electron Optics, vol. 123, pp. 569-581, 2012.
28. [28] Nejati M., Samavi S., Shirani S., “Multi-focus image fusion using dictionary-based sparse representation”, Information Fusion, vol. 25, pp. 72-84, 2015.
29. [29] Xia X., Yao Y., Liang J., Fang S., Yang Z., Cui D., “Evaluation of focus measures for the autofocus of line scan cameras”, Optik - International Journal for Light and Electron Optics, vol. 127, pp. 7762-7775, 2016.
30. [30] Krotov E.P.,“Active computervisionbycooperativefocusand stereo”, New York:Springer-Verlag, 1989.
31. [31] Kailath T., “The Divergence and Bhattacharyya Distance Measures in Signal Selection”, IEEE Transactions on Communication Technology, Vol. 15, pp. 52-60, 1967.
32. [32] Lowe D.G., “Object recognition from local scale-invariant features”, in International Conference on Computer Vision, 1999, pp. 1150-1157.
33. [33] Fischler M. A., Bolles R. C., “Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography”, Comm. of the ACM, vol. 24, pp. 381-395, 1981.
34. [34] Doğan H., Baykal E., Ekinci M., ErcinM. E.,Ersöz Ş., “Determination of optimum auto focusing function for cytopathological assessment processes”,in 2017 Medical Technologies National Congress (TIPTEKNO), Trabzon, Turkey, 2017, pp. 1-4.
35. [35] Crete-Roffet F., Dolmiere T., Ladret P., Nicolas M.,“TheBlur Effect: Perceptionand Estimation with a New No-Reference Perceptual Blur Metric”, In SPIE ElectronicImaging Symposium Conf. Human Vision and Electronic Imaging, 2007, pp. 6492-16.