KUANTISASI SEL DARAH PUTIH BERTUMPUK MENGGUNAKAN ANALISIS DISTANCE MARKER

Benny Afandi, Chastine Fatichah, Nanik Suciati

Abstract


ABSTRAK

Kuantisasi sel darah putih melalui citra mikroskopis sel darah yang low-cost dan reliable masih menjadi tantangan pada banyak penelitian. Keragaman citra sel darah putihdapat mengurangi akurasi kuantisasi sel darah putih, khususnya keberadaan sel darah putih bertumpuk. Penelitian ini mengusulkan metode baru dalam mengkuantisasi sel darah putih bertumpuk menggunakan analisis distance marker. Setiap objek mempunyai marker yang merupakan local maxima dalam distance transform map. Ketika dua objek bertumpuk, marker kedua objek tetap terbentuk dan terpisah. Informasi nilai jarak marker dapat digunakan sebagai pengkuantisasi objek sel darah putih bertumpuk. Metode analisis distance marker lebih robust terhadap bentuk dan ukuran objek sel darah putih dengan tingkat akurasi mencapai 94,1%.

Kata kunci :Analisis distance marker, Citra mikroskopis sel darah, Kuantisasi sel darah putihbertumpuk.

ABSTRACT

The low-cost and reliable white blood cells quantization through a microscopic image of blood cells still a challenge in many studies. the diversity of white blood cell microscopic images can decrease the accuracy of white blood cell quantization, particularly the presence of the overlapping white blood cells. This paper proposes a novel method to quantize the overlapping white blood cells using analysis distance marker.Each object has a marker which is a local maximum in the distance transform map. When two objects overlap, the marker of both objects is still formed and separate. The information of distance marker values can be used as the overlapping white blood cells quantization. In addition, the proposed method is robust to the shape and size of the white blood cell objects with the accuracy of 94.1%.

Keywords: Analysis distance marker, blood cell microscopic image, overlapping white blood cells quantization


References


Saraswat, M. dan Arya, K. V., “Automated microscopic image analysis for leukocytes identification: a survey”. Micron (Oxford, England : 1993), Vol. 65, Hal. 20–33. 2014

Fathichah, C., Purwitasari D., Hariadi V., Effendy F., “Overlapping White Blood Cell Segmentation and Counting on Microscopic Blood Cell Images”, Int. Journal on Smart Sensing and Intelligent Systems, Vol. 7, No. 3., Hal 1271-1286, 2014.

Nazlibilek, S., Karacor, D., Ercan, T., Sazli, M. H., Kalender, O., dan Ege, Y.,“Automatic segmentation, counting, size determination and classification of white blood cells”. Measurement, Vol. 55, Hal. 58–65, 2014.

Yu. D., Pham T.D., Zhou X., “Analysis and recognition of touching cell images based on morphological structures”, Computer in Biology and Medicine, Vol. 39, Hal. 27-39, 2009.

Bai X., Sun C., Zhou F., “Splitting touching cells based on concave points and ellipse fitting”, Pattern Recognition, Vol. 42, Hal. 2434–2446, 2009.

Lin. P., Chen Y.M., He Y., Hu. G.W., “A novel matching algorithm for splitting touching rice kernels based on contour curvature analysis”, Computers and Electronics in Agriculture, Vol. 109, 124-133, 2014.

Felzenszwalb, P. dan Huttenlocher, D., “Distance Transforms of Sampled Functions”,2012.

Ghosh, M., Das,D.C., Chandan R. dan Ajoy K, “Automated leukocyte recognition using fuzzy divergence”, Micron (Oxford, England : 1993), Vol. 41 No.7, Hal. 840–6, 2010.

Scotti F, “Robust Segmentation and Measurement Techniques of White Blood Cells in Blood Microscope Images”, Instrumentation and Measurement Technology Conference, Hal. 43-48, 2006.




DOI: https://doi.org/10.21107/simantec.v5i3.2384

Refbacks

  • There are currently no refbacks.


Copyright (c) 2016 Jurnal Simantec



Indexed By