Level set analysis for leukocyte detection and tracking

被引:142
作者
Mukherjee, DP [1 ]
Ray, N
Acton, ST
机构
[1] Indian Stat Inst, Elect & Commun Sci Unit, Kolkata 700108, W Bengal, India
[2] Univ Virginia, Dept Elect & Comp Engn, Charlottesville, VA 22904 USA
关键词
cell detection; level set; tracking;
D O I
10.1109/TIP.2003.819858
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We propose a cell detection and tracking solution using image-level sets computed via threshold decomposition. In contrast to existing methods where manual initialization is required to track individual cells, the proposed approach can automatically identify and track multiple cells by exploiting the shape and intensity characteristics of the cells. The capture of the cell boundary is considered as an evolution of a closed curve that maximizes image gradient along the curve enclosing a homogeneous region. An energy functional dependent upon the gradient magnitude along the cell boundary, the region homogeneity within the cell boundary and the spatial overlap of the detected cells is minimized using a variational approach. For tracking between frames, this energy functional is modified considering the spatial and shape consistency of a cell as it moves in the video sequence. The integrated energy functional complements shape-based segmentation with a spatial consistency based tracking technique. We demonstrate that an acceptable, expedient solution of the energy functional is possible through a search of the image-level lines: boundaries of connected components within the level sets obtained by threshold decomposition. The level set analysis can also capture multiple cells in a single frame rather than iteratively computing a single active contour for each individual cell. Results of cell detection using the energy functional approach and the level set approach are presented along with the associated processing time. Results of successful tracking of rolling leukocytes from a number of digital video sequences are reported and compared with the results from a correlation tracking scheme.
引用
收藏
页码:562 / 572
页数:11
相关论文
共 18 条
[1]   Scale space classification using area morphology [J].
Acton, ST ;
Mukherjee, DP .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2000, 9 (04) :623-635
[2]   Automatic tracking of rolling leukocytes in vivo [J].
Acton, ST ;
Wethmar, K ;
Ley, K .
MICROVASCULAR RESEARCH, 2002, 63 (01) :139-148
[3]   Active contours without edges [J].
Chan, TF ;
Vese, LA .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2001, 10 (02) :266-277
[4]   FINITE-ELEMENT METHODS FOR ACTIVE CONTOUR MODELS AND BALLOONS FOR 2-D AND 3-D IMAGES [J].
COHEN, LD ;
COHEN, I .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1993, 15 (11) :1131-1147
[5]   Variation in the velocity, deformation, and adhesion energy density of leukocytes rolling within venules [J].
Damiano, ER ;
Westheider, J ;
Tozeren, A ;
Ley, K .
CIRCULATION RESEARCH, 1996, 79 (06) :1122-1130
[6]   Detection of leukocytes in contact with the vessel wall from in vivo microscope recordings using a neural network [J].
Egmont-Petersen, M ;
Schreiner, U ;
Tromp, SC ;
Lehmann, TM ;
Slaaf, DW ;
Arts, T .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2000, 47 (07) :941-951
[7]   Applying deformable templates for cell image segmentation [J].
Garrido, A ;
de la Blanca, NP .
PATTERN RECOGNITION, 2000, 33 (05) :821-832
[8]   Cloud tracking by scale space classification [J].
Mukherjee, DP ;
Acton, ST .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2002, 40 (02) :405-415
[9]   SHAPE FROM SYMMETRY - DETECTING AND EXPLOITING SYMMETRY IN AFFINE IMAGES [J].
MUKHERJEE, DP ;
ZISSERMAN, A ;
BRADY, M .
PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES, 1995, 351 (1695) :77-106
[10]   Geodesic active contours and level sets for the detection and tracking of moving objects [J].
Paragios, N ;
Deriche, R .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2000, 22 (03) :266-280