Image Sequence Generation and Analysis via GRU and Attention for Trachomatous Trichiasis Classification

Juan Carlos Prieto, Hina Shah, Kasey Jones, Robert F Chew, Hashiya M. Kana, Jerusha Weaver, Rebecca M. Flueckiger, Scott McPherson, Emily W. Gower
Proceedings of the Fourth Conference on Medical Imaging with Deep Learning, PMLR 143:633-644, 2021.

Abstract

Chlamydia trachomatous is an infectious ocular condition that can cause the eyelid to turn inward so that one or more eyelashes touch the eyeball, a condition call trachomatous trichiasis (TT), which can lead to blindness. Community-based screeners are used in rural areas to identify patients with TT, who can then be referred for proper medical care. Having automatic methods to detect TT will reduce the amount of time required to train screeners and improve accuracy of detection. This paper proposes a method to automatically identify regions of an eye and identify TT, using photographs taken with smartphones in the field. The attention-based gated deep learning networks in combination with a regionidentification network can identify TT with an accuracy of 91%, sensitivity of 92% and specificity of 87%, showing that these methods have the potential to be deployed in the field.

Cite this Paper

BibTeX
@InProceedings{pmlr-v143-prieto21a, title = {Image Sequence Generation and Analysis via {GRU} and Attention for Trachomatous Trichiasis Classification}, author = {Prieto, Juan Carlos and Shah, Hina and Jones, Kasey and Chew, Robert F and Kana, Hashiya M. and Weaver, Jerusha and Flueckiger, Rebecca M. and McPherson, Scott and Gower, Emily W.}, booktitle = {Proceedings of the Fourth Conference on Medical Imaging with Deep Learning}, pages = {633--644}, year = {2021}, editor = {Heinrich, Mattias and Dou, Qi and de Bruijne, Marleen and Lellmann, Jan and Schläfer, Alexander and Ernst, Floris}, volume = {143}, series = {Proceedings of Machine Learning Research}, month = {07--09 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v143/prieto21a/prieto21a.pdf}, url = {https://proceedings.mlr.press/v143/prieto21a.html}, abstract = {Chlamydia trachomatous is an infectious ocular condition that can cause the eyelid to turn inward so that one or more eyelashes touch the eyeball, a condition call trachomatous trichiasis (TT), which can lead to blindness. Community-based screeners are used in rural areas to identify patients with TT, who can then be referred for proper medical care. Having automatic methods to detect TT will reduce the amount of time required to train screeners and improve accuracy of detection. This paper proposes a method to automatically identify regions of an eye and identify TT, using photographs taken with smartphones in the field. The attention-based gated deep learning networks in combination with a regionidentification network can identify TT with an accuracy of 91%, sensitivity of 92% and specificity of 87%, showing that these methods have the potential to be deployed in the field.} }
Endnote
%0 Conference Paper %T Image Sequence Generation and Analysis via GRU and Attention for Trachomatous Trichiasis Classification %A Juan Carlos Prieto %A Hina Shah %A Kasey Jones %A Robert F Chew %A Hashiya M. Kana %A Jerusha Weaver %A Rebecca M. Flueckiger %A Scott McPherson %A Emily W. Gower %B Proceedings of the Fourth Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2021 %E Mattias Heinrich %E Qi Dou %E Marleen de Bruijne %E Jan Lellmann %E Alexander Schläfer %E Floris Ernst %F pmlr-v143-prieto21a %I PMLR %P 633--644 %U https://proceedings.mlr.press/v143/prieto21a.html %V 143 %X Chlamydia trachomatous is an infectious ocular condition that can cause the eyelid to turn inward so that one or more eyelashes touch the eyeball, a condition call trachomatous trichiasis (TT), which can lead to blindness. Community-based screeners are used in rural areas to identify patients with TT, who can then be referred for proper medical care. Having automatic methods to detect TT will reduce the amount of time required to train screeners and improve accuracy of detection. This paper proposes a method to automatically identify regions of an eye and identify TT, using photographs taken with smartphones in the field. The attention-based gated deep learning networks in combination with a regionidentification network can identify TT with an accuracy of 91%, sensitivity of 92% and specificity of 87%, showing that these methods have the potential to be deployed in the field.
APA
Prieto, J.C., Shah, H., Jones, K., Chew, R.F., Kana, H.M., Weaver, J., Flueckiger, R.M., McPherson, S. & Gower, E.W.. (2021). Image Sequence Generation and Analysis via GRU and Attention for Trachomatous Trichiasis Classification. Proceedings of the Fourth Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 143:633-644 Available from https://proceedings.mlr.press/v143/prieto21a.html.

Related Material