SavedAdd your journal

Journals / Aquaculture Studies / 2026 / Cilt: 17 Sayı: 3

Automatic Cells Counting in Natt-Herrick Stained Fish Blood

M. Ozan İncetaş(BÜLENT ECEVİT ÜNİVERSİTESİ, MÜHENDİSLİK FAKÜLTESİ)
Erdinç Veske(Gıda Tarım ve Hayvancılık Bakanlığı, Tarımsal Araştırmalar Genel Müdürlüğü)
Nesrin Emre(Akdeniz Su Ürünleri Araştırma Enstitüsü)
Recep Demirci(GAZİ ÜNİVERSİTESİ, TEKNOLOJİ FAKÜLTESİ)
Pages
283–294
Publication Date
2017-09-01
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Consequently, an average f-score over 0.96 was achieved.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Monitoring of hematological values which provide important information about the health status of fish is considerably important in aquaculture.
📊
Key Findings & Data:The outputs generated by automatic blood cells detection algorithm in 90 images were compared with results which were obtained by means of user’s intervention.
💡
Conclusion & Impact:Consequently, an average f-score over 0.96 was achieved.
🔬Design:Araştırma Makalesi
📍Scope:Comprehensive Sample
⚙️Variables:Balık kanı · Natt-Herrick solüsyonu · Otomatik hücre sayımı

Abstract

Monitoring of hematological values which provide important information about the health status of fish is considerably important in aquaculture. One of the most commonly used methods for detecting the hematological values in fish blood is the usage of Natt-Herrick solution. Basically, in this approach, Natt-Herrick stained blood samples are examined with a microscope and the cells are counted. Nevertheless, the counting process is both tough and time-consuming. In this study, a technique in which cell counting in blood samples images is automatically performed has been presented. Natt-Herrick stained blood samples of Oncorhynchus mykiss and Sparus aurata were used for evaluation of the developed scheme. The outputs generated by automatic blood cells detection algorithm in 90 images were compared with results which were obtained by means of user’s intervention. Consequently, an average f-score over 0.96 was achieved.

Özet

Hematolojik değerlerin kontrolü balıkların sağlık durumları hakkında önemli bilgiler verdiğinden, bu kontrol balık yetiştiriciliğinde oldukça önemlidir. Hematolojik değerlerin kontrolünde en sık kullanılan yöntemlerden biri de Natt-Herrick solüsyonudur. Natt-Herrick solüsyonu yardımıyla boyanan kan örnekleri mikroskop ile incelenmekte ve hücre sayımı yapılmaktadır. Ancak bu sayım hem yorucu hem de zaman alıcıdır. Bu çalışmada kan örneklerine ait görüntüler üzerinden otomatik olarak hücre sayımı yapabilecek bir teknik sunulmuştur. Geliştirilen yöntemin değerlendirilmesinde Natt-Herrick solüsyonu ile boyanmış Gökkuşağı Alabalığı ve Çipura balıklarına ait örnekler kullanılmıştır. Bu örneklere ait 90 adet görüntüdeki kan hücrelerinin otomatik belirlenmesi sonuçları ile kullanıcılar tarafından belirlenen sonuçlarla karşılaştırılmıştır. Karşılaştırma sonucunda ortalama olarak 0,96’nın üzerinde f-skor değeri elde edilmiştir.

🔖

Cite This Article

İncetaş, M. O., Veske, E., Emre, N., Demirci, R. (2017). Automatic Cells Counting in Natt-Herrick Stained Fish Blood. Aquaculture Studies, Cilt: 17 Sayı: 3, 283–294. https://doi.org/10.17693/yunusae.v17i30729.306490

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (19)

  1. Arnold, J.E., Matsche, M.A. & Rosemary, K. (2014). Preserving whole blood in formalin extends the specimen stability period for manual cell counts for fish. Veterinary Clinical Pathology 43(4), 613–620. http://dx.doi.org/10.1111/vcp.12214
  2. Bai, X., Sun, C. & Zhou, F. (2009). Splitting touching cells based on concave points and ellipse fitting. Pattern Recognition 42(11), http://dx.doi.org/10.1016/j.patcog.2009.04.003
  3. Chetverikov, D. & Szabo, Z. (1999). A simple and efficient algorithm for detection of high curvature points in planar curves. Proceedings of the 23rd Workshop of Austrian Pattern Recognition Group. 175-184. http://dx.doi.org/10.1007/978-3-540-45179-2_91
  4. Demirci, R. (2010). Adaptive threshold selection for edge detection in colour images. IEEE 18nd Signal Processing and Communications Applications Conference (SIU), 677-679. http://dx.doi.org/10.1109/SIU.2010.5654414
  5. Fan, J., Yau, D.K.Y., Elmagarmid, A.K. & Aref, W.G. (2001). Automatic image segmentation by integrating color-edge extraction and seeded region growing. IEEE Transactions On Image Processing, 10(10), 1454-1466. http://dx.doi.org/10.1109/83.951532
  6. Gonçalves, W.N. & Bruno, O.M. (2012). Automatic system for counting cells with elliptical shape. Computer Vision and Pattern Recognition 9(1), 1-11. http://dx.doi.org/10.21528/LNLM-vol9-no1-art1
  7. Gonzalez, R.C. & Woods, R.E. (2008). Digital Image Processing, 3rd Edition. New Jersey, USA: Pearson Education Inc.
  8. Guyon, C., Bouwmans, T. & Zahzah, E.H. (2012). Robust principal component analysis for background subtraction: Systematic evaluation and comparative analysis. In P. Sanguansat (Eds.), Principal Component Analysis (pp. 223-237). Rijeka, Croatia: InTech.
  9. Halir, R. & Flusser, J. (1998). Numerically stable direct least squares fitting of ellipses. Proc. 6th International Conference in Central Europe on Computer Graphics and Visualization (WSCG). 125-132.
  10. İncetas, M.O., Demirci, R., Yavuzcan, H.G., Tanyeri, U. & Veske, E. (2014). Seeded region growing based detection of cells in fish blood stained with Natt-Herrick. IEEE 22nd Signal Processing and Communications Applications Conference (SIU), 1471-1474. http://dx.doi.org/10.1109/SIU.2014.6830518
  11. Konuk, T. (1975). Pratik Fizyoloji I. Ankara, Turkey: Ankara Üniversitesi Veteriner Fakültesi Yayınları.
  12. Leyk, S. & Boesch, R. (2010). Colors of the past: color image segmentation in historical topographic maps based on homogeneity. Geoinformatica, 14(1), 1–21. http://dx.doi.org/10.1007/s10707-008-0074-z
  13. Luskova, V. (1997). Annual cycles and normal values of hematological parameters in fishes.
  14. Acta Scientarum Naturalium Academiae Scientiarum Bohemicae Brno, 31(5): 70-78.
  15. Martin, D.R., Fowlkes, C.C. & Malik, J. (2004). Learning to detect natural image boundaries using local brightness, color and texture cues. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(5): 530-549. http://dx.doi.org/10.1109/TPAMI.2004.1273918
  16. Pavlidis, M., Futter, W. C., Katharios, P. & Divanach, P. (2007). Blood cell profile of six Mediterranean mariculture fish species. Journal of Applied Ichthyology, 23(1): 70-73. http://dx.doi.org/10.1111/j.1439-0426.2006.00771.x
  17. Qiang, J., Yang, H., Wang, H., Kpundeh, M.D. & Xu, P. (2013). Interacting effects of water temperature and dietary protein level on hematological parameters in Nile tilapia juveniles, Oreochromis niloticus (L.) and mortality under Streptococcus iniae infection. Fish & Shellfish Immunology. 34(1): 8-16. http://dx.doi.org/10.1016/j.fsi.2012.09.003
  18. Tavares - Dias, M. & Moraes, F. R. (2008). Haematological and biochemical reference intervals for farmed channel catfish. Journal of Fish Biology, 71(2): 383-388 http://dx.doi.org/10.1111/j.1095-8649.2007.01494.x
  19. Van Rijsbergen, C.J. (1979). Information Retrieval, Second Ed., London, United Kingdom: Butterworths