A semi-automatic method for quantification and classification of erythrocytes infected with malaria parasites in microscopic images

被引:116
作者
Diaz, Gloria [1 ]
Gonzalez, Fabio A. [1 ]
Romero, Eduardo [1 ]
机构
[1] Univ Nacl Colombia, Telemed Ctr, Fac Med, Bioingn Res Grp, Bogota, Colombia
关键词
Malaria parasites; Automatic quantification; Life stage classification; Machine learning; Plasmodium falciparum; Feature extraction; Clump splitting; Pixel color classification; Connected operators; Inclusion-Tree; Cell classification; Classifier evaluation; Multi-class classifiers; Class imbalance; SEGMENTATION; ALGORITHM; OPERATORS;
D O I
10.1016/j.jbi.2008.11.005
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Visual quantification of parasitemia in thin blood films is a very tedious, Subjective and time-consuming task. This study presents all original method for quantification and classification of erythrocytes ill stained thin blood films infected with Plasmodium falciparum. The proposed approach is composed of three main phases: a preprocessing step, which corrects luminance differences. A segmentation step that uses the normalized RGB color space for classifying pixels either as erythrocyte or background followed by in Inclusion-Tree representation that structures the pixel information into objects. from which erythrocytes are found. Finally, a two step classification process identities infected erythrocytes and differentiates the infection stage, using a trained bank of classifiers. Additionally, user intervention is allowed when the approach cannot make a proper decision. Four hundred fifty malaria images were used for training and evaluating the method. Automatic identification of infected erythrocytes showed a specificity of 99.7% and a sensitivity of 94%. The infection stage was determined with an average sensitivity of 78.8% and Average specificity of 91.2%. (C) 2008 Elsevier Inc. All rights reserved.
引用
收藏
页码:296 / 307
页数:12
相关论文
共 31 条
[1]  
[Anonymous], 1982, IMAGE ANAL MATH MORP
[2]  
[Anonymous], IMAGEVIS COMPUT
[3]  
BACON DJ, 2007, MALARIA J, P6
[4]   Multiscale connected operators [J].
Braga-Neto, U .
JOURNAL OF MATHEMATICAL IMAGING AND VISION, 2005, 22 (2-3) :199-216
[5]  
Carling A., 1992, Introducing Neural Networks
[6]   An alternative to serum for cultivation of Plasmodium falciparum in vitro [J].
Cranmer, SL ;
Magowan, C ;
Liang, J ;
Coppel, RL ;
Cooke, BM .
TRANSACTIONS OF THE ROYAL SOCIETY OF TROPICAL MEDICINE AND HYGIENE, 1997, 91 (03) :363-365
[7]   Evaluation of classifiers for an uneven class distribution problem [J].
Daskalaki, S ;
Kopanas, I ;
Avouris, N .
APPLIED ARTIFICIAL INTELLIGENCE, 2006, 20 (05) :381-417
[8]   MAXIMUM LIKELIHOOD FROM INCOMPLETE DATA VIA EM ALGORITHM [J].
DEMPSTER, AP ;
LAIRD, NM ;
RUBIN, DB .
JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-METHODOLOGICAL, 1977, 39 (01) :1-38
[9]  
DESELAERS T, 2003, FEATURES IMAGE RETRI
[10]  
DIAZ G, 2007, PROG PATTERN RECOGN, P4756