A Malaria Diagnostic Tool Based on Computer Vision Screening and Visualization of Plasmodium falciparum Candidate Areas in Digitized Blood Smears

Introduction Microscopy is the gold standard for diagnosis of malaria, however, manual evaluation of blood films is highly dependent on skilled personnel in a time-consuming, error-prone and repetitive process. In this study we propose a method using computer vision detection and visualization of only the diagnostically most relevant sample regions in digitized blood smears. Methods Giemsa-stained thin blood films with P. falciparum ring-stage trophozoites (n = 27) and uninfected controls (n = 20) were digitally scanned with an oil immersion objective (0.1 µm/pixel) to capture approximately 50,000 erythrocytes per sample. Parasite candidate regions were identified based on color and object size, followed by extraction of image features (local binary patterns, local contrast and Scale-invariant feature transform descriptors) used as input to a support vector machine classifier. The classifier was trained on digital slides from ten patients and validated on six samples. Results The diagnostic accuracy was tested on 31 samples (19 infected and 12 controls). From each digitized area of a blood smear, a panel with the 128 most probable parasite candidate regions was generated. Two expert microscopists were asked to visually inspect the panel on a tablet computer and to judge whether the patient was infected with P. falciparum. The method achieved a diagnostic sensitivity and specificity of 95% and 100% as well as 90% and 100% for the two readers respectively using the diagnostic tool. Parasitemia was separately calculated by the automated system and the correlation coefficient between manual and automated parasitemia counts was 0.97. Conclusion We developed a decision support system for detecting malaria parasites using a computer vision algorithm combined with visualization of sample areas with the highest probability of malaria infection. The system provides a novel method for blood smear screening with a significantly reduced need for visual examination and has a potential to increase the throughput in malaria diagnostics.

[1]  E. Bruck,et al.  National Committee for Clinical Laboratory Standards. , 1980, Pediatrics.

[2]  K. Kain,et al.  Impact of microscopy error on estimates of protective efficacy in malaria-prevention trials. , 2002, The Journal of infectious diseases.

[3]  Chris Drakeley,et al.  Overdiagnosis of malaria in patients with severe febrile illness in Tanzania: a prospective study , 2004, BMJ : British Medical Journal.

[4]  Chih-Jen Lin,et al.  LIBLINEAR: A Library for Large Linear Classification , 2008, J. Mach. Learn. Res..

[5]  C. Wongsrichanalai,et al.  A review of malaria diagnostic tools: microscopy and rapid diagnostic test (RDT). , 2007, The American journal of tropical medicine and hygiene.

[6]  Hongying Zhu,et al.  Cost-effective and rapid blood analysis on a cell-phone. , 2013, Lab on a chip.

[7]  Andrew G. Dempster,et al.  Analysis of infected blood cell images using morphological operators , 2002, Image Vis. Comput..

[8]  J. Isola,et al.  Web-Based Virtual Microscopy for Parasitology: A Novel Tool for Education and Quality Assurance , 2008, PLoS neglected tropical diseases.

[9]  Sissades Tongsima,et al.  An automatic device for detection and classification of malaria parasite species in thick blood film , 2012, BMC Bioinformatics.

[10]  Riku Turkki,et al.  Automated segmentation of blood cells in Giemsa stained digitized thin blood films , 2013, Diagnostic Pathology.

[11]  Organización Mundial de la Salud.  Guidelines for the treatment of malaria , 2010 .

[12]  Fabio A. González,et al.  A semi-automatic method for quantification and classification of erythrocytes infected with malaria parasites in microscopic images , 2009, J. Biomed. Informatics.

[13]  NJ White,et al.  The parasite clearance curve , 2011, Malaria Journal.

[14]  Vernon M Chinchilli,et al.  Performance of a malaria microscopy image analysis slide reading device , 2012, Malaria Journal.

[15]  J. R. Landis,et al.  The measurement of observer agreement for categorical data. , 1977, Biometrics.

[16]  D. Diallo,et al.  A “reverse pharmacology” approach for developing an anti-malarial phytomedicine , 2011, Malaria Journal.

[17]  M. Guy.  Basic malaria microscopy , 1992 .

[18]  Wendy Prudhomme O'Meara,et al.  Changes in the burden of malaria in sub-Saharan Africa. , 2010, The Lancet. Infectious diseases.

[19]  C. Wongsrichanalai,et al.  Reader technique as a source of variability in determining malaria parasite density by microscopy , 2006, Malaria Journal.

[20]  Riku Turkki,et al.  An open-source, MATLAB based annotation tool for virtual slides , 2013, Diagnostic Pathology.

[21]  A. Dempster,et al.  Computer vision for microscopy diagnosis of malaria , 2009, Malaria Journal.

[22]  M. Littrell,et al.  Monitoring fever treatment behaviour and equitable access to effective medicines in the context of initiatives to improve ACT access: baseline results and implications for programming in six African countries , 2011, Malaria Journal.

[23]  Sirish L. Shah,et al.  Automated and unsupervised detection of malarial parasites in microscopic images , 2011, Malaria Journal.

[24]  Andrew G. Dempster,et al.  Parasite detection and identification for automated thin blood film malaria diagnosis , 2010, Comput. Vis. Image Underst..

[25]  Nina Linder,et al.  On-Chip Imaging of Schistosoma haematobium Eggs in Urine for Diagnosis by Computer Vision , 2013, PLoS neglected tropical diseases.

[26]  Z. Premji,et al.  Impact of training in clinical and microscopy diagnosis of childhood malaria on antimalarial drug prescription and health outcome at primary health care level in Tanzania: A randomized controlled trial , 2008, Malaria Journal.

[27]  Steve Feng,et al.  Crowd-sourced BioGames: managing the big data problem for next-generation lab-on-a-chip platforms. , 2012, Lab on a chip.

[28]  Andrew Zisserman,et al.  Multiple kernels for object detection , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[29]  X. Su,et al.  Malaria biology and disease pathogenesis: insights for new treatments , 2013, Nature Medicine.

[30]  Andrea Vedaldi,et al.  Vlfeat: an open and portable library of computer vision algorithms , 2010, ACM Multimedia.

[31]  P. Preiser,et al.  A novel semi-automatic image processing approach to determine Plasmodium falciparum parasitemia in Giemsa-stained thin blood smears , 2008, BMC Cell Biology.

[32]  Weltgesundheitsorganisation.  World malaria report , 2005 .

[33]  Changhuei Yang,et al.  Implementation of a color-capable optofluidic microscope on a RGB CMOS color sensor chip substrate. , 2010, Lab on a chip.

[34]  John Frean,et al.  External quality assessment of national public health laboratories in Africa, 2002-2009. , 2012, Bulletin of the World Health Organization.

[35]  Clinton K. Murray,et al.  Update on Rapid Diagnostic Testing for Malaria , 2008, Clinical Microbiology Reviews.

[36]  David N Breslauer,et al.  Mobile Phone Based Clinical Microscopy for Global Health Applications , 2009, PloS one.

[37]  Matti Pietikäinen,et al.  Face Description with Local Binary Patterns: Application to Face Recognition , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[38]  Pranab K. Dutta,et al.  A Web-accessible Framework for Automated Storage with Compression and Textural Classification of Malaria Parasite Images , 2012 .

[39]  B. Bain,et al.  Diagnosis from the blood smear. , 2005, The New England journal of medicine.

[40]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[41]  Matti Pietikäinen,et al.  Identification of tumor epithelium and stroma in tissue microarrays using texture analysis , 2012, Diagnostic Pathology.

[42]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.