Deep Convolutional Neural Networks for Microscopy-Based Point of Care Diagnostics

John A Quinn, Rose Nakasi, Pius K. B. Mugagga, Patrick Byanyima, William Lubega, Alfred Andama
Proceedings of the 1st Machine Learning for Healthcare Conference, PMLR 56:271-281, 2016.

Abstract

Point of care diagnostics using microscopy and computer vision methods have been applied to a number of practical problems, and are particularly relevant to low-income, high disease burden areas. However, this is subject to the limitations in sensitivity and specificity of the computer vision methods used. In general, deep learning has recently revolutionised the field of computer vision, in some cases surpassing human performance for other object recognition tasks. In this paper, we evaluate the performance of deep convolutional neural networks on three different microscopy tasks: diagnosis of malaria in thick blood smears, tuberculosis in sputum samples, and intestinal parasite eggs in stool samples. In all cases accuracy is very high and substantially better than an alternative approach more representative of traditional medical imaging techniques.

Cite this Paper

BibTeX
@InProceedings{pmlr-v56-Quinn16, title = {Deep Convolutional Neural Networks for Microscopy-Based Point of Care Diagnostics}, author = {Quinn, John A and Nakasi, Rose and Mugagga, Pius K. B. and Byanyima, Patrick and Lubega, William and Andama, Alfred}, booktitle = {Proceedings of the 1st Machine Learning for Healthcare Conference}, pages = {271--281}, year = {2016}, editor = {Doshi-Velez, Finale and Fackler, Jim and Kale, David and Wallace, Byron and Wiens, Jenna}, volume = {56}, series = {Proceedings of Machine Learning Research}, address = {Northeastern University, Boston, MA, USA}, month = {18--19 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v56/Quinn16.pdf}, url = {https://proceedings.mlr.press/v56/Quinn16.html}, abstract = {Point of care diagnostics using microscopy and computer vision methods have been applied to a number of practical problems, and are particularly relevant to low-income, high disease burden areas. However, this is subject to the limitations in sensitivity and specificity of the computer vision methods used. In general, deep learning has recently revolutionised the field of computer vision, in some cases surpassing human performance for other object recognition tasks. In this paper, we evaluate the performance of deep convolutional neural networks on three different microscopy tasks: diagnosis of malaria in thick blood smears, tuberculosis in sputum samples, and intestinal parasite eggs in stool samples. In all cases accuracy is very high and substantially better than an alternative approach more representative of traditional medical imaging techniques.} }
Endnote
%0 Conference Paper %T Deep Convolutional Neural Networks for Microscopy-Based Point of Care Diagnostics %A John A Quinn %A Rose Nakasi %A Pius K. B. Mugagga %A Patrick Byanyima %A William Lubega %A Alfred Andama %B Proceedings of the 1st Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2016 %E Finale Doshi-Velez %E Jim Fackler %E David Kale %E Byron Wallace %E Jenna Wiens %F pmlr-v56-Quinn16 %I PMLR %P 271--281 %U https://proceedings.mlr.press/v56/Quinn16.html %V 56 %X Point of care diagnostics using microscopy and computer vision methods have been applied to a number of practical problems, and are particularly relevant to low-income, high disease burden areas. However, this is subject to the limitations in sensitivity and specificity of the computer vision methods used. In general, deep learning has recently revolutionised the field of computer vision, in some cases surpassing human performance for other object recognition tasks. In this paper, we evaluate the performance of deep convolutional neural networks on three different microscopy tasks: diagnosis of malaria in thick blood smears, tuberculosis in sputum samples, and intestinal parasite eggs in stool samples. In all cases accuracy is very high and substantially better than an alternative approach more representative of traditional medical imaging techniques.
RIS
TY - CPAPER TI - Deep Convolutional Neural Networks for Microscopy-Based Point of Care Diagnostics AU - John A Quinn AU - Rose Nakasi AU - Pius K. B. Mugagga AU - Patrick Byanyima AU - William Lubega AU - Alfred Andama BT - Proceedings of the 1st Machine Learning for Healthcare Conference DA - 2016/12/10 ED - Finale Doshi-Velez ED - Jim Fackler ED - David Kale ED - Byron Wallace ED - Jenna Wiens ID - pmlr-v56-Quinn16 PB - PMLR DP - Proceedings of Machine Learning Research VL - 56 SP - 271 EP - 281 L1 - http://proceedings.mlr.press/v56/Quinn16.pdf UR - https://proceedings.mlr.press/v56/Quinn16.html AB - Point of care diagnostics using microscopy and computer vision methods have been applied to a number of practical problems, and are particularly relevant to low-income, high disease burden areas. However, this is subject to the limitations in sensitivity and specificity of the computer vision methods used. In general, deep learning has recently revolutionised the field of computer vision, in some cases surpassing human performance for other object recognition tasks. In this paper, we evaluate the performance of deep convolutional neural networks on three different microscopy tasks: diagnosis of malaria in thick blood smears, tuberculosis in sputum samples, and intestinal parasite eggs in stool samples. In all cases accuracy is very high and substantially better than an alternative approach more representative of traditional medical imaging techniques. ER -
APA
Quinn, J.A., Nakasi, R., Mugagga, P.K.B., Byanyima, P., Lubega, W. & Andama, A.. (2016). Deep Convolutional Neural Networks for Microscopy-Based Point of Care Diagnostics. Proceedings of the 1st Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 56:271-281 Available from https://proceedings.mlr.press/v56/Quinn16.html.

Related Material