Diagnosing Malaria Patients with Plasmodium falciparum and vivax Using Deep Learning for Thick Smear Images

We propose a new framework, PlasmodiumVF-Net, to analyze thick smear microscopy images for a malaria diagnosis on both image and patient-level. Our framework detects whether a patient is infected, and in case of a malarial infection, reports whether the patient is infected by Plasmodium fal...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yasmin M. Kassim, Feng Yang, Hang Yu, Richard J. Maude, Stefan Jaeger
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	malaria computer-aided diagnosis biomedical image analysis deep learning ResNet50 Mask R-CNN Medicine (General) R5-920
Acceso en línea:	https://doaj.org/article/488fcf6f428349ea9297ed43bea03374
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:488fcf6f428349ea9297ed43bea03374
record_format	dspace
spelling	oai:doaj.org-article:488fcf6f428349ea9297ed43bea033742021-11-25T17:20:34ZDiagnosing Malaria Patients with <i>Plasmodium falciparum</i> and <i>vivax</i> Using Deep Learning for Thick Smear Images10.3390/diagnostics111119942075-4418https://doaj.org/article/488fcf6f428349ea9297ed43bea033742021-10-01T00:00:00Zhttps://www.mdpi.com/2075-4418/11/11/1994https://doaj.org/toc/2075-4418We propose a new framework, PlasmodiumVF-Net, to analyze thick smear microscopy images for a malaria diagnosis on both image and patient-level. Our framework detects whether a patient is infected, and in case of a malarial infection, reports whether the patient is infected by <i>Plasmodium falciparum</i> or <i>Plasmodium vivax</i>. PlasmodiumVF-Net first detects candidates for Plasmodium parasites using a Mask Regional-Convolutional Neural Network (Mask R-CNN), filters out false positives using a ResNet50 classifier, and then follows a new approach to recognize parasite species based on a score obtained from the number of detected patches and their aggregated probabilities for all of the patient images. Reporting a patient-level decision is highly challenging, and therefore reported less often in the literature, due to the small size of detected parasites, the similarity to staining artifacts, the similarity of species in different development stages, and illumination or color variations on patient-level. We use a manually annotated dataset consisting of 350 patients, with about 6000 images, which we make publicly available together with this manuscript. Our framework achieves an overall accuracy above 90% on image and patient-level.Yasmin M. KassimFeng YangHang YuRichard J. MaudeStefan JaegerMDPI AGarticlemalariacomputer-aided diagnosisbiomedical image analysisdeep learningResNet50Mask R-CNNMedicine (General)R5-920ENDiagnostics, Vol 11, Iss 1994, p 1994 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	malaria computer-aided diagnosis biomedical image analysis deep learning ResNet50 Mask R-CNN Medicine (General) R5-920
spellingShingle	malaria computer-aided diagnosis biomedical image analysis deep learning ResNet50 Mask R-CNN Medicine (General) R5-920 Yasmin M. Kassim Feng Yang Hang Yu Richard J. Maude Stefan Jaeger Diagnosing Malaria Patients with <i>Plasmodium falciparum</i> and <i>vivax</i> Using Deep Learning for Thick Smear Images
description	We propose a new framework, PlasmodiumVF-Net, to analyze thick smear microscopy images for a malaria diagnosis on both image and patient-level. Our framework detects whether a patient is infected, and in case of a malarial infection, reports whether the patient is infected by <i>Plasmodium falciparum</i> or <i>Plasmodium vivax</i>. PlasmodiumVF-Net first detects candidates for Plasmodium parasites using a Mask Regional-Convolutional Neural Network (Mask R-CNN), filters out false positives using a ResNet50 classifier, and then follows a new approach to recognize parasite species based on a score obtained from the number of detected patches and their aggregated probabilities for all of the patient images. Reporting a patient-level decision is highly challenging, and therefore reported less often in the literature, due to the small size of detected parasites, the similarity to staining artifacts, the similarity of species in different development stages, and illumination or color variations on patient-level. We use a manually annotated dataset consisting of 350 patients, with about 6000 images, which we make publicly available together with this manuscript. Our framework achieves an overall accuracy above 90% on image and patient-level.
format	article
author	Yasmin M. Kassim Feng Yang Hang Yu Richard J. Maude Stefan Jaeger
author_facet	Yasmin M. Kassim Feng Yang Hang Yu Richard J. Maude Stefan Jaeger
author_sort	Yasmin M. Kassim
title	Diagnosing Malaria Patients with <i>Plasmodium falciparum</i> and <i>vivax</i> Using Deep Learning for Thick Smear Images
title_short	Diagnosing Malaria Patients with <i>Plasmodium falciparum</i> and <i>vivax</i> Using Deep Learning for Thick Smear Images
title_full	Diagnosing Malaria Patients with <i>Plasmodium falciparum</i> and <i>vivax</i> Using Deep Learning for Thick Smear Images
title_fullStr	Diagnosing Malaria Patients with <i>Plasmodium falciparum</i> and <i>vivax</i> Using Deep Learning for Thick Smear Images
title_full_unstemmed	Diagnosing Malaria Patients with <i>Plasmodium falciparum</i> and <i>vivax</i> Using Deep Learning for Thick Smear Images
title_sort	diagnosing malaria patients with <i>plasmodium falciparum</i> and <i>vivax</i> using deep learning for thick smear images
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/488fcf6f428349ea9297ed43bea03374
work_keys_str_mv	AT yasminmkassim diagnosingmalariapatientswithiplasmodiumfalciparumiandivivaxiusingdeeplearningforthicksmearimages AT fengyang diagnosingmalariapatientswithiplasmodiumfalciparumiandivivaxiusingdeeplearningforthicksmearimages AT hangyu diagnosingmalariapatientswithiplasmodiumfalciparumiandivivaxiusingdeeplearningforthicksmearimages AT richardjmaude diagnosingmalariapatientswithiplasmodiumfalciparumiandivivaxiusingdeeplearningforthicksmearimages AT stefanjaeger diagnosingmalariapatientswithiplasmodiumfalciparumiandivivaxiusingdeeplearningforthicksmearimages
_version_	1718412468369227776

Diagnosing Malaria Patients with <i>Plasmodium falciparum</i> and <i>vivax</i> Using Deep Learning for Thick Smear Images

Ejemplares similares