Parasite detection and identification for automated thin blood film malaria diagnosis


Tek F. B., Dempster A. G., Kale I.

COMPUTER VISION AND IMAGE UNDERSTANDING, vol.114, no.1, pp.21-32, 2010 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 114 Issue: 1
  • Publication Date: 2010
  • Doi Number: 10.1016/j.cviu.2009.08.003
  • Journal Name: COMPUTER VISION AND IMAGE UNDERSTANDING
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.21-32
  • Keywords: Malaria diagnosis, Microscope image analysis, Blood cell image, Parasitemia, K nearest neighbour rule, Imbalanced learning, Area granulometry, LABORATORY DIAGNOSIS, IMAGE, CLASSIFICATION, MICROSCOPY, OPERATORS, ACCURACY, SCALE, TESTS
  • Istanbul Technical University Affiliated: No

Abstract

This paper investigates automated detection and identification of malaria parasites in images of Giemsastained thin blood film specimens, The Giemsa stain highlights not only the malaria parasites but also the white blood cells, platelets, and artefacts. We propose a complete framework to extract these stained structures, determine whether they are parasites, and identify the infecting species and life-cycle stages. We investigate species and life-cycle-stage identification as multi-class classification problems in which we compare three different classification schemes and empirically show that the detection. species, and life-cycle-stage tasks can be performed in a joint classification as well as an extension to binary detection. The proposed binary parasite detector can operate at 0.1% parasitemia without any false detections and with less than 10 false detections at levels as low as 0.01%. (C) 2009 Elsevier Inc. All rights reserved.