ML Anthology

Computer-Automated Malaria Diagnosis and Quantitation Using Convolutional Neural Networks

Courosh Mehanian, Mayoore S. Jaiswal, Charles B. Delahunt, Clay Thompson, Matthew P. Horning, Liming Hu, Shawn K. McGuire, Travis Ostbye, Martha Mehanian, Ben Wilson, Cary R. Champlin, Earl Long, Stephane Proux, Dionicia Gamboa, Peter Chiodini, Jane Carter, Mehul Dhorda, David Isaboke, Bernhards Ogutu, Wellington Oyibo, Elizabeth Villasis, Kyaw Myo Tun, Christine Bachman, David Bell
ICCVW 2017 pp. 116-125
doi:10.1109/ICCVW.2017.22 /iccvw/2017/mehanian2017iccvw-computerautomated/

Abstract

The optical microscope remains a widely-used tool for diagnosis and quantitation of malaria. An automated system that can match the performance of well-trained technicians is motivated by a shortage of trained microscopists. We have developed a computer vision system that leverages deep learning to identify malaria parasites in micrographs of standard, field-prepared thick blood films. The prototype application diagnoses P. falciparum with sufficient accuracy to achieve competency level 1 in the World Health Organization external competency assessment, and quantitates with sufficient accuracy for use in drug resistance studies. A suite of new computer vision techniques-global white balance, adaptive nonlinear grayscale, and a novel augmentation scheme-underpin the system's state-of-the-art performance. We outline a rich, global training set; describe the algorithm in detail; argue for patient-level performance metrics for the evaluation of automated diagnosis methods; and provide results for P. falciparum.

ICCVW Semantic Scholar

Cite

Text

Mehanian et al. "Computer-Automated Malaria Diagnosis and Quantitation Using Convolutional Neural Networks." IEEE/CVF International Conference on Computer Vision Workshops, 2017. doi:10.1109/ICCVW.2017.22

Markdown

[Mehanian et al. "Computer-Automated Malaria Diagnosis and Quantitation Using Convolutional Neural Networks." IEEE/CVF International Conference on Computer Vision Workshops, 2017.](https://mlanthology.org/iccvw/2017/mehanian2017iccvw-computerautomated/) doi:10.1109/ICCVW.2017.22

BibTeX

@inproceedings{mehanian2017iccvw-computerautomated,
  title     = {{Computer-Automated Malaria Diagnosis and Quantitation Using Convolutional Neural Networks}},
  author    = {Mehanian, Courosh and Jaiswal, Mayoore S. and Delahunt, Charles B. and Thompson, Clay and Horning, Matthew P. and Hu, Liming and McGuire, Shawn K. and Ostbye, Travis and Mehanian, Martha and Wilson, Ben and Champlin, Cary R. and Long, Earl and Proux, Stephane and Gamboa, Dionicia and Chiodini, Peter and Carter, Jane and Dhorda, Mehul and Isaboke, David and Ogutu, Bernhards and Oyibo, Wellington and Villasis, Elizabeth and Tun, Kyaw Myo and Bachman, Christine and Bell, David},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2017},
  pages     = {116-125},
  doi       = {10.1109/ICCVW.2017.22},
  url       = {https://mlanthology.org/iccvw/2017/mehanian2017iccvw-computerautomated/}
}