Diagnosing Malaria Patients with Plasmodium falciparum and vivax Using Deep Learning for Thick Smear Images
Abstract
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 falciparum or Plasmodium vivax. 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.
- Publication Date:
- Research Org.:
- Oak Ridge Institute for Science and Education (ORISE), Oak Ridge, TN (United States)
- Sponsoring Org.:
- USDOE Office of Science (SC); National Institutes of Health (NIH)
- OSTI Identifier:
- 1828099
- Alternate Identifier(s):
- OSTI ID: 1983107
- Grant/Contract Number:
- SC0014664
- Resource Type:
- Published Article
- Journal Name:
- Diagnostics
- Additional Journal Information:
- Journal Name: Diagnostics Journal Volume: 11 Journal Issue: 11; Journal ID: ISSN 2075-4418
- Publisher:
- MDPI AG
- Country of Publication:
- Country unknown/Code not available
- Language:
- English
- Subject:
- 60 APPLIED LIFE SCIENCES; General & Internal Medicine; malaria; computer-aided diagnosis; biomedical image analysis; deep learning; ResNet50; Mask R-CNN; Plasmodium parasite; Plasmodium falciparum; Plasmodium vivax
Citation Formats
Kassim, Yasmin M., Yang, Feng, Yu, Hang, Maude, Richard J., and Jaeger, Stefan. Diagnosing Malaria Patients with Plasmodium falciparum and vivax Using Deep Learning for Thick Smear Images. Country unknown/Code not available: N. p., 2021.
Web. doi:10.3390/diagnostics11111994.
Kassim, Yasmin M., Yang, Feng, Yu, Hang, Maude, Richard J., & Jaeger, Stefan. Diagnosing Malaria Patients with Plasmodium falciparum and vivax Using Deep Learning for Thick Smear Images. Country unknown/Code not available. https://doi.org/10.3390/diagnostics11111994
Kassim, Yasmin M., Yang, Feng, Yu, Hang, Maude, Richard J., and Jaeger, Stefan. Wed .
"Diagnosing Malaria Patients with Plasmodium falciparum and vivax Using Deep Learning for Thick Smear Images". Country unknown/Code not available. https://doi.org/10.3390/diagnostics11111994.
@article{osti_1828099,
title = {Diagnosing Malaria Patients with Plasmodium falciparum and vivax Using Deep Learning for Thick Smear Images},
author = {Kassim, Yasmin M. and Yang, Feng and Yu, Hang and Maude, Richard J. and Jaeger, Stefan},
abstractNote = {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 falciparum or Plasmodium vivax. 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.},
doi = {10.3390/diagnostics11111994},
journal = {Diagnostics},
number = 11,
volume = 11,
place = {Country unknown/Code not available},
year = {Wed Oct 27 00:00:00 EDT 2021},
month = {Wed Oct 27 00:00:00 EDT 2021}
}
Free Publicly Available Full Text
Publisher's Version of Record
https://doi.org/10.3390/diagnostics11111994
https://doi.org/10.3390/diagnostics11111994
Other availability
Search WorldCat to find libraries that may hold this journal
Save to My Library
You must Sign In or Create an Account in order to save documents to your library.
Works referenced in this record:
Malaria Diagnosis: A Brief Review
journal, January 2009
- Tangpukdee, Noppadon; Duangdee, Chatnapa; Wilairatana, Polrat
- The Korean Journal of Parasitology, Vol. 47, Issue 2
Malaria parasite detection in thick blood smear microscopic images using modified YOLOV3 and YOLOV4 models
journal, March 2021
- Abdurahman, Fetulhak; Fante, Kinde Anlay; Aliy, Mohammed
- BMC Bioinformatics, Vol. 22, Issue 1
Pre-trained convolutional neural networks as feature extractors toward improved malaria parasite detection in thin blood smear images
journal, January 2018
- Rajaraman, Sivaramakrishnan; Antani, Sameer K.; Poostchi, Mahdieh
- PeerJ, Vol. 6
Performance of a fully‐automated system on a WHO malaria microscopy evaluation slide set
journal, February 2021
- Horning, Matthew P.; Delahunt, Charles B.; Bachman, Christine M.
- Malaria Journal, Vol. 20, Issue 1
Small Object Bird Detection in Infrared Drone Videos Using Mask R-CNN Deep Learning
journal, January 2020
- Kassim, Yasmin M.; Byrne, Michael E.; Burch, Cristy
- Electronic Imaging, Vol. 2020, Issue 8
Computational microscopic imaging for malaria parasite detection: a systematic review: REVIEW ON COMPUTER-AIDED MALARIA DIAGNOSIS
journal, June 2015
- Das, D. K.; Mukherjee, R.; Chakraborty, C.
- Journal of Microscopy, Vol. 260, Issue 1
Artificial Intelligence in Healthcare: Review and Prediction Case Studies
journal, March 2020
- Rong, Guoguang; Mendez, Arnaldo; Bou Assi, Elie
- Engineering, Vol. 6, Issue 3
Clustering-Based Dual Deep Learning Architecture for Detecting Red Blood Cells in Malaria Diagnostic Smears
journal, May 2021
- Kassim, Yasmin M.; Palaniappan, Kannappan; Yang, Feng
- IEEE Journal of Biomedical and Health Informatics, Vol. 25, Issue 5
Real-time Malaria Parasite Screening in Thick Blood Smears for Low-Resource Setting
journal, January 2020
- Chibuta, Samson; Acar, Aybar C.
- Journal of Digital Imaging, Vol. 33, Issue 3
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
journal, June 2017
- Ren, Shaoqing; He, Kaiming; Girshick, Ross
- IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 39, Issue 6
Update on Malaria Diagnostics and Test Utilization
journal, July 2017
- Mathison, Blaine A.; Pritt, Bobbi S.
- Journal of Clinical Microbiology, Vol. 55, Issue 7
Malaria Screener: a smartphone application for automated malaria screening
journal, November 2020
- Yu, Hang; Yang, Feng; Rajaraman, Sivaramakrishnan
- BMC Infectious Diseases, Vol. 20, Issue 1
The potential for artificial intelligence in healthcare
journal, June 2019
- Davenport, Thomas; Kalakota, Ravi
- Future Healthcare Journal, Vol. 6, Issue 2
Deep Learning in the Biomedical Applications: Recent and Future Status
journal, April 2019
- Zemouri, Ryad; Zerhouni, Noureddine; Racoceanu, Daniel
- Applied Sciences, Vol. 9, Issue 8
Blood Smear Image Based Malaria Parasite and Infected-Erythrocyte Detection and Segmentation
journal, August 2015
- Tsai, Meng-Hsiun; Yu, Shyr-Shen; Chan, Yung-Kuan
- Journal of Medical Systems, Vol. 39, Issue 10
Image analysis and machine learning for detecting malaria
journal, April 2018
- Poostchi, Mahdieh; Silamut, Kamolrat; Maude, Richard J.
- Translational Research, Vol. 194
Automatic knee meniscus tear detection and orientation classification with Mask-RCNN
journal, April 2019
- Couteaux, V.; Si-Mohamed, S.; Nempont, O.
- Diagnostic and Interventional Imaging, Vol. 100, Issue 4
Automated Detection of Malaria Parasites on Thick Blood Smears via Mobile Devices
journal, January 2016
- Rosado, Luís; Costa, José M. Correia da; Elias, Dirk
- Procedia Computer Science, Vol. 90
Two-Stage Mask-RCNN Approach for Detecting and Segmenting the Optic Nerve Head, Optic Disc, and Optic Cup in Fundus Images
journal, May 2020
- Almubarak, Haidar; Bazi, Yakoub; Alajlan, Naif
- Applied Sciences, Vol. 10, Issue 11
A Combined Algorithm for Malaria Detection from Thick Smear Blood Slides
journal, January 2015
- Chakrabortya, Kaushik
- Journal of Health & Medical Informatics, Vol. 06, Issue 01
Deep Learning for Smartphone-Based Malaria Parasite Detection in Thick Blood Smears
journal, May 2020
- Yang, Feng; Poostchi, Mahdieh; Yu, Hang
- IEEE Journal of Biomedical and Health Informatics, Vol. 24, Issue 5