iMAGING: a novel automated system for malaria diagnosis by using artificial intelligence tools and a universal low-cost robotized microscope
IntroductionMalaria is one of the most prevalent infectious diseases in sub-Saharan Africa, with 247 million cases reported worldwide in 2021 according to the World Health Organization. Optical microscopy remains the gold standard technique for malaria diagnosis, however, it requires expertise, is t...
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-11-01
|
| Series: | Frontiers in Microbiology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmicb.2023.1240936/full |
| _version_ | 1797460724260274176 |
|---|---|
| author | Carles Rubio Maturana Carles Rubio Maturana Allisson Dantas de Oliveira Sergi Nadal Francesc Zarzuela Serrat Elena Sulleiro Elena Sulleiro Elena Sulleiro Edurne Ruiz Besim Bilalli Anna Veiga Mateu Espasa Mateu Espasa Alberto Abelló Tomàs Pumarola Suñé Tomàs Pumarola Suñé Marta Segú Daniel López-Codina Elisa Sayrol Clols Joan Joseph-Munné |
| author_facet | Carles Rubio Maturana Carles Rubio Maturana Allisson Dantas de Oliveira Sergi Nadal Francesc Zarzuela Serrat Elena Sulleiro Elena Sulleiro Elena Sulleiro Edurne Ruiz Besim Bilalli Anna Veiga Mateu Espasa Mateu Espasa Alberto Abelló Tomàs Pumarola Suñé Tomàs Pumarola Suñé Marta Segú Daniel López-Codina Elisa Sayrol Clols Joan Joseph-Munné |
| author_sort | Carles Rubio Maturana |
| collection | DOAJ |
| description | IntroductionMalaria is one of the most prevalent infectious diseases in sub-Saharan Africa, with 247 million cases reported worldwide in 2021 according to the World Health Organization. Optical microscopy remains the gold standard technique for malaria diagnosis, however, it requires expertise, is time-consuming and difficult to reproduce. Therefore, new diagnostic techniques based on digital image analysis using artificial intelligence tools can improve diagnosis and help automate it.MethodsIn this study, a dataset of 2571 labeled thick blood smear images were created. YOLOv5x, Faster R-CNN, SSD, and RetinaNet object detection neural networks were trained on the same dataset to evaluate their performance in Plasmodium parasite detection. Attention modules were applied and compared with YOLOv5x results. To automate the entire diagnostic process, a prototype of 3D-printed pieces was designed for the robotization of conventional optical microscopy, capable of auto-focusing the sample and tracking the entire slide.ResultsComparative analysis yielded a performance for YOLOv5x on a test set of 92.10% precision, 93.50% recall, 92.79% F-score, and 94.40% mAP0.5 for leukocyte, early and mature Plasmodium trophozoites overall detection. F-score values of each category were 99.0% for leukocytes, 88.6% for early trophozoites and 87.3% for mature trophozoites detection. Attention modules performance show non-significant statistical differences when compared to YOLOv5x original trained model. The predictive models were integrated into a smartphone-computer application for the purpose of image-based diagnostics in the laboratory. The system can perform a fully automated diagnosis by the auto-focus and X-Y movements of the robotized microscope, the CNN models trained for digital image analysis, and the smartphone device. The new prototype would determine whether a Giemsa-stained thick blood smear sample is positive/negative for Plasmodium infection and its parasite levels. The whole system was integrated into the iMAGING smartphone application.ConclusionThe coalescence of the fully-automated system via auto-focus and slide movements and the autonomous detection of Plasmodium parasites in digital images with a smartphone software and AI algorithms confers the prototype the optimal features to join the global effort against malaria, neglected tropical diseases and other infectious diseases. |
| first_indexed | 2024-03-09T17:10:07Z |
| format | Article |
| id | doaj.art-32218ad0c42e4e38acb6d45a36012a74 |
| institution | Directory Open Access Journal |
| issn | 1664-302X |
| language | English |
| last_indexed | 2024-03-09T17:10:07Z |
| publishDate | 2023-11-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Microbiology |
| spelling | doaj.art-32218ad0c42e4e38acb6d45a36012a742023-11-24T14:09:24ZengFrontiers Media S.A.Frontiers in Microbiology1664-302X2023-11-011410.3389/fmicb.2023.12409361240936iMAGING: a novel automated system for malaria diagnosis by using artificial intelligence tools and a universal low-cost robotized microscopeCarles Rubio Maturana0Carles Rubio Maturana1Allisson Dantas de Oliveira2Sergi Nadal3Francesc Zarzuela Serrat4Elena Sulleiro5Elena Sulleiro6Elena Sulleiro7Edurne Ruiz8Besim Bilalli9Anna Veiga10Mateu Espasa11Mateu Espasa12Alberto Abelló13Tomàs Pumarola Suñé14Tomàs Pumarola Suñé15Marta Segú16Daniel López-Codina17Elisa Sayrol Clols18Joan Joseph-Munné19Microbiology Department, Vall d’Hebron University Hospital, Vall d’Hebron Research Institute (VHIR), Barcelona, SpainDepartment of Microbiology and Genetics, Universitat Autònoma de Barcelona (UAB), Barcelona, SpainComputational Biology and Complex Systems Group, Physics Department, Universitat Politècnica de Catalunya (UPC), Castelldefels, SpainDatabase Technologies and Information Group, Service and Information Systems Engineering Department, Universitat Politècnica de Catalunya (UPC), Barcelona, SpainMicrobiology Department, Vall d’Hebron University Hospital, Vall d’Hebron Research Institute (VHIR), Barcelona, SpainMicrobiology Department, Vall d’Hebron University Hospital, Vall d’Hebron Research Institute (VHIR), Barcelona, SpainDepartment of Microbiology and Genetics, Universitat Autònoma de Barcelona (UAB), Barcelona, SpainCIBERINFEC, ISCIII- CIBER de Enfermedades Infecciosas, Instituto de Salud Carlos III, Madrid, SpainMicrobiology Department, Vall d’Hebron University Hospital, Vall d’Hebron Research Institute (VHIR), Barcelona, SpainDatabase Technologies and Information Group, Service and Information Systems Engineering Department, Universitat Politècnica de Catalunya (UPC), Barcelona, SpainProbitas Foundation, Barcelona, SpainDepartment of Microbiology and Genetics, Universitat Autònoma de Barcelona (UAB), Barcelona, SpainClinical Laboratories, Microbiology Department, Hospital Universitari Parc Taulí, Sabadell, SpainDatabase Technologies and Information Group, Service and Information Systems Engineering Department, Universitat Politècnica de Catalunya (UPC), Barcelona, SpainMicrobiology Department, Vall d’Hebron University Hospital, Vall d’Hebron Research Institute (VHIR), Barcelona, SpainDepartment of Microbiology and Genetics, Universitat Autònoma de Barcelona (UAB), Barcelona, SpainFutbol Club Barcelona Foundation, Barcelona, SpainComputational Biology and Complex Systems Group, Physics Department, Universitat Politècnica de Catalunya (UPC), Castelldefels, SpainTecnocampus, Universitat Pompeu Fabra, Mataró, SpainMicrobiology Department, Vall d’Hebron University Hospital, Vall d’Hebron Research Institute (VHIR), Barcelona, SpainIntroductionMalaria is one of the most prevalent infectious diseases in sub-Saharan Africa, with 247 million cases reported worldwide in 2021 according to the World Health Organization. Optical microscopy remains the gold standard technique for malaria diagnosis, however, it requires expertise, is time-consuming and difficult to reproduce. Therefore, new diagnostic techniques based on digital image analysis using artificial intelligence tools can improve diagnosis and help automate it.MethodsIn this study, a dataset of 2571 labeled thick blood smear images were created. YOLOv5x, Faster R-CNN, SSD, and RetinaNet object detection neural networks were trained on the same dataset to evaluate their performance in Plasmodium parasite detection. Attention modules were applied and compared with YOLOv5x results. To automate the entire diagnostic process, a prototype of 3D-printed pieces was designed for the robotization of conventional optical microscopy, capable of auto-focusing the sample and tracking the entire slide.ResultsComparative analysis yielded a performance for YOLOv5x on a test set of 92.10% precision, 93.50% recall, 92.79% F-score, and 94.40% mAP0.5 for leukocyte, early and mature Plasmodium trophozoites overall detection. F-score values of each category were 99.0% for leukocytes, 88.6% for early trophozoites and 87.3% for mature trophozoites detection. Attention modules performance show non-significant statistical differences when compared to YOLOv5x original trained model. The predictive models were integrated into a smartphone-computer application for the purpose of image-based diagnostics in the laboratory. The system can perform a fully automated diagnosis by the auto-focus and X-Y movements of the robotized microscope, the CNN models trained for digital image analysis, and the smartphone device. The new prototype would determine whether a Giemsa-stained thick blood smear sample is positive/negative for Plasmodium infection and its parasite levels. The whole system was integrated into the iMAGING smartphone application.ConclusionThe coalescence of the fully-automated system via auto-focus and slide movements and the autonomous detection of Plasmodium parasites in digital images with a smartphone software and AI algorithms confers the prototype the optimal features to join the global effort against malaria, neglected tropical diseases and other infectious diseases.https://www.frontiersin.org/articles/10.3389/fmicb.2023.1240936/fullmalariamalaria diagnosisconvolutional neural networksartificial intelligencerobotized microscopesmartphone application |
| spellingShingle | Carles Rubio Maturana Carles Rubio Maturana Allisson Dantas de Oliveira Sergi Nadal Francesc Zarzuela Serrat Elena Sulleiro Elena Sulleiro Elena Sulleiro Edurne Ruiz Besim Bilalli Anna Veiga Mateu Espasa Mateu Espasa Alberto Abelló Tomàs Pumarola Suñé Tomàs Pumarola Suñé Marta Segú Daniel López-Codina Elisa Sayrol Clols Joan Joseph-Munné iMAGING: a novel automated system for malaria diagnosis by using artificial intelligence tools and a universal low-cost robotized microscope Frontiers in Microbiology malaria malaria diagnosis convolutional neural networks artificial intelligence robotized microscope smartphone application |
| title | iMAGING: a novel automated system for malaria diagnosis by using artificial intelligence tools and a universal low-cost robotized microscope |
| title_full | iMAGING: a novel automated system for malaria diagnosis by using artificial intelligence tools and a universal low-cost robotized microscope |
| title_fullStr | iMAGING: a novel automated system for malaria diagnosis by using artificial intelligence tools and a universal low-cost robotized microscope |
| title_full_unstemmed | iMAGING: a novel automated system for malaria diagnosis by using artificial intelligence tools and a universal low-cost robotized microscope |
| title_short | iMAGING: a novel automated system for malaria diagnosis by using artificial intelligence tools and a universal low-cost robotized microscope |
| title_sort | imaging a novel automated system for malaria diagnosis by using artificial intelligence tools and a universal low cost robotized microscope |
| topic | malaria malaria diagnosis convolutional neural networks artificial intelligence robotized microscope smartphone application |
| url | https://www.frontiersin.org/articles/10.3389/fmicb.2023.1240936/full |
| work_keys_str_mv | AT carlesrubiomaturana imaginganovelautomatedsystemformalariadiagnosisbyusingartificialintelligencetoolsandauniversallowcostrobotizedmicroscope AT carlesrubiomaturana imaginganovelautomatedsystemformalariadiagnosisbyusingartificialintelligencetoolsandauniversallowcostrobotizedmicroscope AT allissondantasdeoliveira imaginganovelautomatedsystemformalariadiagnosisbyusingartificialintelligencetoolsandauniversallowcostrobotizedmicroscope AT serginadal imaginganovelautomatedsystemformalariadiagnosisbyusingartificialintelligencetoolsandauniversallowcostrobotizedmicroscope AT francesczarzuelaserrat imaginganovelautomatedsystemformalariadiagnosisbyusingartificialintelligencetoolsandauniversallowcostrobotizedmicroscope AT elenasulleiro imaginganovelautomatedsystemformalariadiagnosisbyusingartificialintelligencetoolsandauniversallowcostrobotizedmicroscope AT elenasulleiro imaginganovelautomatedsystemformalariadiagnosisbyusingartificialintelligencetoolsandauniversallowcostrobotizedmicroscope AT elenasulleiro imaginganovelautomatedsystemformalariadiagnosisbyusingartificialintelligencetoolsandauniversallowcostrobotizedmicroscope AT edurneruiz imaginganovelautomatedsystemformalariadiagnosisbyusingartificialintelligencetoolsandauniversallowcostrobotizedmicroscope AT besimbilalli imaginganovelautomatedsystemformalariadiagnosisbyusingartificialintelligencetoolsandauniversallowcostrobotizedmicroscope AT annaveiga imaginganovelautomatedsystemformalariadiagnosisbyusingartificialintelligencetoolsandauniversallowcostrobotizedmicroscope AT mateuespasa imaginganovelautomatedsystemformalariadiagnosisbyusingartificialintelligencetoolsandauniversallowcostrobotizedmicroscope AT mateuespasa imaginganovelautomatedsystemformalariadiagnosisbyusingartificialintelligencetoolsandauniversallowcostrobotizedmicroscope AT albertoabello imaginganovelautomatedsystemformalariadiagnosisbyusingartificialintelligencetoolsandauniversallowcostrobotizedmicroscope AT tomaspumarolasune imaginganovelautomatedsystemformalariadiagnosisbyusingartificialintelligencetoolsandauniversallowcostrobotizedmicroscope AT tomaspumarolasune imaginganovelautomatedsystemformalariadiagnosisbyusingartificialintelligencetoolsandauniversallowcostrobotizedmicroscope AT martasegu imaginganovelautomatedsystemformalariadiagnosisbyusingartificialintelligencetoolsandauniversallowcostrobotizedmicroscope AT daniellopezcodina imaginganovelautomatedsystemformalariadiagnosisbyusingartificialintelligencetoolsandauniversallowcostrobotizedmicroscope AT elisasayrolclols imaginganovelautomatedsystemformalariadiagnosisbyusingartificialintelligencetoolsandauniversallowcostrobotizedmicroscope AT joanjosephmunne imaginganovelautomatedsystemformalariadiagnosisbyusingartificialintelligencetoolsandauniversallowcostrobotizedmicroscope |