The prognostic and diagnostic value of intraleukocytic malaria pigment in patients with severe falciparum malaria.

Severe falciparum malaria is a major cause of death in tropical countries, particularly in African children. Rapid and accurate diagnosis and prognostic assessment are critical to clinical management. In 6027 prospectively studied patients diagnosed with severe malaria we assess the prognostic value of peripheral blood film counts of malaria pigment containing polymorphonuclear leukocytes (PMNs) and monocytes.

Towards harmonization of microscopy methods for malaria clinical research studies.

Microscopy performed on stained films of peripheral blood for detection, identification and quantification of malaria parasites is an essential reference standard for clinical trials of drugs, vaccines and diagnostic tests for malaria. The value of data from such research is greatly enhanced if this reference standard is consistent across time and geography. Adherence to common standards and practices is a prerequisite to achieve this.

Deep Learning for Smartphone-Based Malaria Parasite Detection in Thick Blood Smears.

Objective: This work investigates the possibility of automated malaria parasite detection in thick blood smears with smartphones.

Methods: We have developed the first deep learning method that can detect malaria parasites in thick blood smear images and can run on smartphones. Our method consists of two processing steps.

Artemisinin Resistance and Stage Dependency of Parasite Clearance in Falciparum Malaria.

Background: Artemisinin resistance in falciparum malaria is associated with kelch13 propeller mutations, reduced ring stage parasite killing, and, consequently, slow parasite clearance. We assessed how parasite age affects parasite clearance in artemisinin resistance.

Methods: Developmental stages of Plasmodium falciparum parasites on blood films performed at hospital admission and their kelch13 genotypes were assessed for 816 patients enrolled in a multinational clinical trial of artemisinin combination therapy.

Understanding the learned behavior of customized convolutional neural networks toward malaria parasite detection in thin blood smear images.

Convolutional neural networks (CNNs) have become the architecture of choice for visual recognition tasks. However, these models are perceived as black boxes since there is a lack of understanding of the learned behavior from the underlying task of interest. This lack of transparency is a serious drawback, particularly in applications involving medical screening and diagnosis since poorly understood model behavior could adversely impact subsequent clinical decision-making.