Real-life evaluation of deep learning models trained on two datasets for Plasmodium falciparum detection with thin blood smear images at 500x magnification
Malaria is a fatal disease transmitted by bites from mosquito-type vectors. Biologists examined blood smears under a microscope at high magnification (1000 × ) to identify the presence of parasites in red blood cells (RBCs). Such an examination is laborious and time-consuming. Moreover, microscopist...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-01-01
|
| Series: | Informatics in Medicine Unlocked |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352914822002696 |
| _version_ | 1811185514396516352 |
|---|---|
| author | Aniss Acherar Ilhame Tantaoui Marc Thellier Alexandre Lampros Renaud Piarroux Xavier Tannier |
| author_facet | Aniss Acherar Ilhame Tantaoui Marc Thellier Alexandre Lampros Renaud Piarroux Xavier Tannier |
| author_sort | Aniss Acherar |
| collection | DOAJ |
| description | Malaria is a fatal disease transmitted by bites from mosquito-type vectors. Biologists examined blood smears under a microscope at high magnification (1000 × ) to identify the presence of parasites in red blood cells (RBCs). Such an examination is laborious and time-consuming. Moreover, microscopists sometimes have difficulty identifying parasitized RBCs due to a lack of skill or practice. Deep learning, especially convolutional neural networks (CNNs) applied for malaria diagnosis, are able to identify complex features of a large number of medical images.The proposed work focuses on the construction of a dataset of blood components images representative of the diagnostic reality captured from 202 patients at 500x magnification. We evaluated through a cross-validation study different deep learning networks for the classification of Plasmodium falciparum-infected RBCs and uninfected blood components. These models include a custom-built CNN, VGG-19, ResNet-50 and EfficientNet-B7. In addition, we conducted the same experiments on a public dataset and compared the performance of the resultant models through a patient-level inference including 200 extra patients. The models trained on our dataset show better performance in terms of generalization and achieved better accuracy, sensitivity and specificity scores of 99.7%, 77.9% and 99.8%, respectively. |
| first_indexed | 2024-04-11T13:30:42Z |
| format | Article |
| id | doaj.art-113feb3c2fbd44d1909906b445457e6e |
| institution | Directory Open Access Journal |
| issn | 2352-9148 |
| language | English |
| last_indexed | 2024-04-11T13:30:42Z |
| publishDate | 2022-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Informatics in Medicine Unlocked |
| spelling | doaj.art-113feb3c2fbd44d1909906b445457e6e2022-12-22T04:21:49ZengElsevierInformatics in Medicine Unlocked2352-91482022-01-0135101132Real-life evaluation of deep learning models trained on two datasets for Plasmodium falciparum detection with thin blood smear images at 500x magnificationAniss Acherar0Ilhame Tantaoui1Marc Thellier2Alexandre Lampros3Renaud Piarroux4Xavier Tannier5Sorbonne Université, Inserm, Institut Pierre-Louis d’Epidémiologie et de Santé Publique, IPLESP, Paris, France; Corresponding author.AP-HP, Groupe Hospitalier Pitié-Salpêtrière, Service de Parasitologie-Mycologie, Paris, FranceAP-HP, Groupe Hospitalier Pitié-Salpêtrière, Service de Parasitologie-Mycologie, Paris, FranceAP-HP, Groupe Hospitalier Pitié-Salpêtrière, Service de Parasitologie-Mycologie, Paris, FranceSorbonne Université, Inserm, Institut Pierre-Louis d’Epidémiologie et de Santé Publique, IPLESP, Paris, France; AP-HP, Groupe Hospitalier Pitié-Salpêtrière, Service de Parasitologie-Mycologie, Paris, FranceSorbonne Université, Inserm, Université Sorbonne Paris Nord, Laboratoire d’Informatique Médicale et d’Ingénierie des Connaissances pour la e-Santé, LIMICS, Paris, FranceMalaria is a fatal disease transmitted by bites from mosquito-type vectors. Biologists examined blood smears under a microscope at high magnification (1000 × ) to identify the presence of parasites in red blood cells (RBCs). Such an examination is laborious and time-consuming. Moreover, microscopists sometimes have difficulty identifying parasitized RBCs due to a lack of skill or practice. Deep learning, especially convolutional neural networks (CNNs) applied for malaria diagnosis, are able to identify complex features of a large number of medical images.The proposed work focuses on the construction of a dataset of blood components images representative of the diagnostic reality captured from 202 patients at 500x magnification. We evaluated through a cross-validation study different deep learning networks for the classification of Plasmodium falciparum-infected RBCs and uninfected blood components. These models include a custom-built CNN, VGG-19, ResNet-50 and EfficientNet-B7. In addition, we conducted the same experiments on a public dataset and compared the performance of the resultant models through a patient-level inference including 200 extra patients. The models trained on our dataset show better performance in terms of generalization and achieved better accuracy, sensitivity and specificity scores of 99.7%, 77.9% and 99.8%, respectively.http://www.sciencedirect.com/science/article/pii/S2352914822002696Malaria diagnosisThin blood smearMicroscopic imageDeep transfer learningConvolutional neural network |
| spellingShingle | Aniss Acherar Ilhame Tantaoui Marc Thellier Alexandre Lampros Renaud Piarroux Xavier Tannier Real-life evaluation of deep learning models trained on two datasets for Plasmodium falciparum detection with thin blood smear images at 500x magnification Informatics in Medicine Unlocked Malaria diagnosis Thin blood smear Microscopic image Deep transfer learning Convolutional neural network |
| title | Real-life evaluation of deep learning models trained on two datasets for Plasmodium falciparum detection with thin blood smear images at 500x magnification |
| title_full | Real-life evaluation of deep learning models trained on two datasets for Plasmodium falciparum detection with thin blood smear images at 500x magnification |
| title_fullStr | Real-life evaluation of deep learning models trained on two datasets for Plasmodium falciparum detection with thin blood smear images at 500x magnification |
| title_full_unstemmed | Real-life evaluation of deep learning models trained on two datasets for Plasmodium falciparum detection with thin blood smear images at 500x magnification |
| title_short | Real-life evaluation of deep learning models trained on two datasets for Plasmodium falciparum detection with thin blood smear images at 500x magnification |
| title_sort | real life evaluation of deep learning models trained on two datasets for plasmodium falciparum detection with thin blood smear images at 500x magnification |
| topic | Malaria diagnosis Thin blood smear Microscopic image Deep transfer learning Convolutional neural network |
| url | http://www.sciencedirect.com/science/article/pii/S2352914822002696 |
| work_keys_str_mv | AT anissacherar reallifeevaluationofdeeplearningmodelstrainedontwodatasetsforplasmodiumfalciparumdetectionwiththinbloodsmearimagesat500xmagnification AT ilhametantaoui reallifeevaluationofdeeplearningmodelstrainedontwodatasetsforplasmodiumfalciparumdetectionwiththinbloodsmearimagesat500xmagnification AT marcthellier reallifeevaluationofdeeplearningmodelstrainedontwodatasetsforplasmodiumfalciparumdetectionwiththinbloodsmearimagesat500xmagnification AT alexandrelampros reallifeevaluationofdeeplearningmodelstrainedontwodatasetsforplasmodiumfalciparumdetectionwiththinbloodsmearimagesat500xmagnification AT renaudpiarroux reallifeevaluationofdeeplearningmodelstrainedontwodatasetsforplasmodiumfalciparumdetectionwiththinbloodsmearimagesat500xmagnification AT xaviertannier reallifeevaluationofdeeplearningmodelstrainedontwodatasetsforplasmodiumfalciparumdetectionwiththinbloodsmearimagesat500xmagnification |