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

Carles Rubio Maturana; Allisson Dantas de Oliveira; Sergi Nadal; Besim Bilalli; Francesc Zarzuela Serrat; Mateu Espasa; Elena Sulleiro Igual; Mercedes Bosch; Anna Veiga Lluch; Alberto Abelló; Daniel López-Codina; Tomàs Pumarola Suñé; Elisa Sayrol Clols; Joan Joseph-Munné

doi:10.3389/fmicb.2022.1006659

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

Carles Rubio Maturana, Allisson Dantas de Oliveira, Sergi Nadal, Besim Bilalli, Francesc Zarzuela Serrat, Mateu Espasa, Elena Sulleiro Igual, Mercedes Bosch, Anna Veiga Lluch, Alberto Abelló, Daniel López-Codina, Tomàs Pumarola Suñé, Elisa Sayrol Clols, Joan Joseph-Munné

Producció científica: Contribució a revista › Article › Recerca › Avaluat per experts

75 Cites (Scopus)

Resum

La malària és una malaltia infecciosa causada per paràsits del gènere Plasmodium spp. Es transmet als humans a través de la picada d'un mosquit Anopheles femella infectat. És la malaltia més comuna en entorns amb pocs recursos, amb 241 milions de casos de malària reportats el 2020 segons l'Organització Mundial de la Salut. L'examen microscòpic òptic dels frotis sanguinis és la tècnica estàndard per al diagnòstic de la malària; tanmateix, es tracta d'un mètode que requereix molt de temps i cal un microscopista ben format per a fer el diagnòstic microbiològic. Les noves tècniques basades en l'anàlisi d'imatges digitals mitjançant aprenentatge profund i mètodes d'intel·ligència artificial són una alternativa desafiant per al diagnòstic de malalties infeccioses. En particular, els sistemes basats en xarxes neuronals convolucionals per a la detecció d'imatges dels paràsits de la malària emulen la visualització microscòpica d'un expert. L'automatització del microscopi proporciona un diagnòstic ràpid i de baix cost que requereix menys supervisió. Els telèfons intel·ligents són una opció adequada per al diagnòstic microscòpic, ja que permeten capturar imatges i identificar els paràsits mitjançant el programari. A més a més, les tècniques d'anàlisi d'imatges podrien ser una solució ràpida i òptima per al diagnòstic de la malària, la tuberculosi o malalties tropicals desateses en zones endèmiques amb pocs recursos. La implementació del diagnòstic automatitzat mitjançant aplicacions de telèfons intel·ligents i noves tecnologies d'imatge digital a les zones de baixos ingressos és un repte que cal assolir. A més a més, l'automatització del moviment de la platina del microscopi i l'enfocament automàtic de les mostres mitjançant implementacions de maquinari sistematitzaria el procediment. Aquestes eines diagnòstiques s'unirien als esforços globals per lluitar contra la malària pandèmica i altres malalties infeccioses relacionades amb la pobresa.

Idioma original	Anglès
Revista	Frontiers in Microbiology
Volum	13
DOIs	https://doi.org/10.3389/fmicb.2022.1006659
Estat de la publicació	Publicada - 2022

SDG de les Nacions Unides

Aquest resultat contribueix als següents objectius de desenvolupament sostenible.

ODG 3 – Bona salut i benestar

Accés al document

10.3389/fmicb.2022.1006659

https://ddd.uab.cat/record/281788

Altres arxius i enllaços

https://www.scopus.com/pages/publications/85143151251

Com citar-ho

Maturana, C. R., de Oliveira, A. D., Nadal, S., Bilalli, B., Serrat, F. Z., Espasa, M., Sulleiro Igual, E., Bosch, M., Lluch, A. V., Abelló, A., López-Codina, D., Pumarola Suñé, T., Clols, E. S., & Joseph-Munné, J. (2022). Advances and challenges in automated malaria diagnosis using digital microscopy imaging with artificial intelligence tools : A review. Frontiers in Microbiology, 13. https://doi.org/10.3389/fmicb.2022.1006659

@article{4168f49329ad4e06be12f577822f94e7,

title = "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.",

keywords = "Artificial intelligence, Deep learning, Digital imaging techniques, Malaria, Malaria diagnosis, Microscopic examination, Smartphone application",

author = "Maturana, \{Carles Rubio\} and \{de Oliveira\}, \{Allisson Dantas\} and Sergi Nadal and Besim Bilalli and Serrat, \{Francesc Zarzuela\} and Mateu Espasa and \{Sulleiro Igual\}, Elena and Mercedes Bosch and Lluch, \{Anna Veiga\} and Alberto Abell{\'o} and Daniel L{\'o}pez-Codina and \{Pumarola Su{\~n}{\'e}\}, Tom{\`a}s and Clols, \{Elisa Sayrol\} and Joan Joseph-Munn{\'e}",

year = "2022",

doi = "10.3389/fmicb.2022.1006659",

language = "English",

volume = "13",

journal = "Frontiers in Microbiology",

issn = "1664-302X",

}

Maturana, CR, de Oliveira, AD, Nadal, S, Bilalli, B, Serrat, FZ, Espasa, M, Sulleiro Igual, E, Bosch, M, Lluch, AV, Abelló, A, López-Codina, D, Pumarola Suñé, T, Clols, ES & Joseph-Munné, J 2022, 'Advances and challenges in automated malaria diagnosis using digital microscopy imaging with artificial intelligence tools : A review', Frontiers in Microbiology, vol. 13. https://doi.org/10.3389/fmicb.2022.1006659

TY - JOUR

T1 - Advances and challenges in automated malaria diagnosis using digital microscopy imaging with artificial intelligence tools :

T2 - A review

AU - Maturana, Carles Rubio

AU - de Oliveira, Allisson Dantas

AU - Nadal, Sergi

AU - Bilalli, Besim

AU - Serrat, Francesc Zarzuela

AU - Espasa, Mateu

AU - Sulleiro Igual, Elena

AU - Bosch, Mercedes

AU - Lluch, Anna Veiga

AU - Abelló, Alberto

AU - López-Codina, Daniel

AU - Pumarola Suñé, Tomàs

AU - Clols, Elisa Sayrol

AU - Joseph-Munné, Joan

PY - 2022

Y1 - 2022

N2 - 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.

AB - 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.

KW - Artificial intelligence

KW - Deep learning

KW - Digital imaging techniques

KW - Malaria

KW - Malaria diagnosis

KW - Microscopic examination

KW - Smartphone application

UR - https://www.scopus.com/pages/publications/85143151251

U2 - 10.3389/fmicb.2022.1006659

DO - 10.3389/fmicb.2022.1006659

M3 - Article

C2 - 36458185

SN - 1664-302X

VL - 13

JO - Frontiers in Microbiology

JF - Frontiers in Microbiology