Advances and challenges in automated malaria diagnosis using digital microscopy imaging with artificial intelligence tools: A review

Abstract

Malaria is an infectious disease caused by parasites of the genus Plasmodium spp. It is transmitted to humans by the bite of an infected female Anopheles mosquito. It is the most common disease in resource-poor settings, with 241 million malaria cases reported in 2020 according to the World Health Organization. Optical microscopy examination of blood smears is the gold standard technique for malaria diagnosis; however, it is a time-consuming method and a well-trained microscopist is needed to perform the microbiological diagnosis. New techniques based on digital imaging analysis by deep learning and artificial intelligence methods are a challenging alternative tool for the diagnosis of infectious diseases. In particular, systems based on Convolutional Neural Networks for image detection of the malaria parasites emulate the microscopy visualization of an expert. Microscope automation provides a fast and low-cost diagnosis, requiring less supervision. Smartphones are a suitable option for microscopic diagnosis, allowing image capture and software identification of parasites. In addition, image analysis techniques could be a fast and optimal solution for the diagnosis of malaria, tuberculosis, or Neglected Tropical Diseases in endemic areas with low resources. The implementation of automated diagnosis by using smartphone applications and new digital imaging technologies in low-income areas is a challenge to achieve. Moreover, automating the movement of the microscope slide and image autofocusing of the samples by hardware implementation would systemize the procedure. These new diagnostic tools would join the global effort to fight against pandemic malaria and other infectious and poverty-related diseases.

Competency of malaria laboratory diagnosis at national and provincial levels at the beginning of malaria post-elimination phase, China

“…Meanwhile, there are still two major challenges of malaria microscopy, one of which is the species identification of other Plasmodium species rather than P. falciparum , especially the misidentification between P. vivax and P. ovale [ 21 ], and the other is the unstable performance of malaria parasite counting [ 20 , 22 ]. In order to address these challenges, in addition to continuing to strengthen the competency training of microscopists, some automated systems or artificial intelligence tools are also considered to be introduced into the diagnosis of malaria [ 23 – 27 ]. Worryingly, there were still gaps in the competency of malaria microscopy in medical institutions and CDCs/IPDs below the provincial level in China [ 28 – 30 ].…”

Web Geographic Information System: A Support Tool for the Study, Evaluation, and Monitoring of Foci of Malaria Transmission in Mexico

“…The application works on mobile devices, and this makes it possible to overcome the accessibility barrier and minimize the time to start treatment [ 20 ]. There are other similar applications for the detection and classification of malaria parasite species [ 21 , 22 , 23 ]; however, given the conditions in Mexico, this option is not currently viable.…”

Systematic Review and Meta-Analysis of the Diagnostic Accuracy of Machine Learning and Deep Learning Models to Detect Malaria: A Protocol

“…In 2021, there were an estimated 247 million malaria cases and 619,000 malaria deaths globally [2]. Early and accurate diagnosis is essential both for effective management of the disease and for strong malaria surveillance [3]. However, recent evidence has identified the silent and persistent reservoir of parasites as one of the primary factors that hamper global malaria elimination efforts [4].…”

“…Over the past decade, there has been a growing body of literature on the use of ML and DL for malaria diagnosis. These studies have investigated various aspects of the diagnostic process, including the detection of malaria parasites in blood smears, the identification of infected red blood cells, and the classification of different Plasmodium species [3,[14][15][16]. However, the sensitivity and specificity of the studies is variable, and the performance of ML and DL models has not been systematically evaluated in real-world settings.…”