A hybrid approach for incorporating deep visual features and side channel information with applications to AMD detection

Arnaldo Horta, Neil Joshi, Michael Pekala, Katia D. Pacheco, Jun Kong, Neil M Bressler, David E. Freund, Philippe Burlina

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This work investigates a hybrid method based on random forests and deep image features to combine non-visual side channel information with image data for classification. We apply this to automated retinal image analysis (ARIA) and the detection of age-related macular degeneration (AMD). For evaluation, we use a dataset collected by the National Institute of Health with over 4000 study participants. The non-visual side channel data includes information related to demographics (e.g. ethnicity), lifestyle (e.g. sunlight exposure), and prior conditions (e.g. cataracts). Our study, which compares the performance of different feature combinations, offers preliminary results that constitute a baseline for future investigations on joint deep visual and side channel feature exploitation for AMD detection. This approach could potentially be used for other medical image analysis problems.

Original languageEnglish (US)
Title of host publicationProceedings - 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages716-720
Number of pages5
Volume2018-January
ISBN (Electronic)9781538614174
DOIs
StatePublished - Jan 16 2018
Event16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017 - Cancun, Mexico
Duration: Dec 18 2017Dec 21 2017

Other

Other16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017
CountryMexico
CityCancun
Period12/18/1712/21/17

Fingerprint

Image analysis
Health

Keywords

  • age related macular degeneration
  • AMD
  • deep learning
  • non tenso features
  • side channel incorporation

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications

Cite this

Horta, A., Joshi, N., Pekala, M., Pacheco, K. D., Kong, J., Bressler, N. M., ... Burlina, P. (2018). A hybrid approach for incorporating deep visual features and side channel information with applications to AMD detection. In Proceedings - 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017 (Vol. 2018-January, pp. 716-720). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICMLA.2017.00-75

A hybrid approach for incorporating deep visual features and side channel information with applications to AMD detection. / Horta, Arnaldo; Joshi, Neil; Pekala, Michael; Pacheco, Katia D.; Kong, Jun; Bressler, Neil M; Freund, David E.; Burlina, Philippe.

Proceedings - 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. p. 716-720.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Horta, A, Joshi, N, Pekala, M, Pacheco, KD, Kong, J, Bressler, NM, Freund, DE & Burlina, P 2018, A hybrid approach for incorporating deep visual features and side channel information with applications to AMD detection. in Proceedings - 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017. vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 716-720, 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017, Cancun, Mexico, 12/18/17. https://doi.org/10.1109/ICMLA.2017.00-75
Horta A, Joshi N, Pekala M, Pacheco KD, Kong J, Bressler NM et al. A hybrid approach for incorporating deep visual features and side channel information with applications to AMD detection. In Proceedings - 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017. Vol. 2018-January. Institute of Electrical and Electronics Engineers Inc. 2018. p. 716-720 https://doi.org/10.1109/ICMLA.2017.00-75
Horta, Arnaldo ; Joshi, Neil ; Pekala, Michael ; Pacheco, Katia D. ; Kong, Jun ; Bressler, Neil M ; Freund, David E. ; Burlina, Philippe. / A hybrid approach for incorporating deep visual features and side channel information with applications to AMD detection. Proceedings - 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. pp. 716-720
@inproceedings{b94a1d72286a407aa6913b019c2539da,
title = "A hybrid approach for incorporating deep visual features and side channel information with applications to AMD detection",
abstract = "This work investigates a hybrid method based on random forests and deep image features to combine non-visual side channel information with image data for classification. We apply this to automated retinal image analysis (ARIA) and the detection of age-related macular degeneration (AMD). For evaluation, we use a dataset collected by the National Institute of Health with over 4000 study participants. The non-visual side channel data includes information related to demographics (e.g. ethnicity), lifestyle (e.g. sunlight exposure), and prior conditions (e.g. cataracts). Our study, which compares the performance of different feature combinations, offers preliminary results that constitute a baseline for future investigations on joint deep visual and side channel feature exploitation for AMD detection. This approach could potentially be used for other medical image analysis problems.",
keywords = "age related macular degeneration, AMD, deep learning, non tenso features, side channel incorporation",
author = "Arnaldo Horta and Neil Joshi and Michael Pekala and Pacheco, {Katia D.} and Jun Kong and Bressler, {Neil M} and Freund, {David E.} and Philippe Burlina",
year = "2018",
month = "1",
day = "16",
doi = "10.1109/ICMLA.2017.00-75",
language = "English (US)",
volume = "2018-January",
pages = "716--720",
booktitle = "Proceedings - 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - A hybrid approach for incorporating deep visual features and side channel information with applications to AMD detection

AU - Horta, Arnaldo

AU - Joshi, Neil

AU - Pekala, Michael

AU - Pacheco, Katia D.

AU - Kong, Jun

AU - Bressler, Neil M

AU - Freund, David E.

AU - Burlina, Philippe

PY - 2018/1/16

Y1 - 2018/1/16

N2 - This work investigates a hybrid method based on random forests and deep image features to combine non-visual side channel information with image data for classification. We apply this to automated retinal image analysis (ARIA) and the detection of age-related macular degeneration (AMD). For evaluation, we use a dataset collected by the National Institute of Health with over 4000 study participants. The non-visual side channel data includes information related to demographics (e.g. ethnicity), lifestyle (e.g. sunlight exposure), and prior conditions (e.g. cataracts). Our study, which compares the performance of different feature combinations, offers preliminary results that constitute a baseline for future investigations on joint deep visual and side channel feature exploitation for AMD detection. This approach could potentially be used for other medical image analysis problems.

AB - This work investigates a hybrid method based on random forests and deep image features to combine non-visual side channel information with image data for classification. We apply this to automated retinal image analysis (ARIA) and the detection of age-related macular degeneration (AMD). For evaluation, we use a dataset collected by the National Institute of Health with over 4000 study participants. The non-visual side channel data includes information related to demographics (e.g. ethnicity), lifestyle (e.g. sunlight exposure), and prior conditions (e.g. cataracts). Our study, which compares the performance of different feature combinations, offers preliminary results that constitute a baseline for future investigations on joint deep visual and side channel feature exploitation for AMD detection. This approach could potentially be used for other medical image analysis problems.

KW - age related macular degeneration

KW - AMD

KW - deep learning

KW - non tenso features

KW - side channel incorporation

UR - http://www.scopus.com/inward/record.url?scp=85048477311&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048477311&partnerID=8YFLogxK

U2 - 10.1109/ICMLA.2017.00-75

DO - 10.1109/ICMLA.2017.00-75

M3 - Conference contribution

AN - SCOPUS:85048477311

VL - 2018-January

SP - 716

EP - 720

BT - Proceedings - 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -