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 language | English (US) |
|---|---|
| Title of host publication | Proceedings - 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 716-720 |
| Number of pages | 5 |
| Volume | 2018-January |
| ISBN (Electronic) | 9781538614174 |
| DOIs | |
| State | Published - Jan 16 2018 |
| Event | 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017 - Cancun, Mexico Duration: Dec 18 2017 → Dec 21 2017 |
Other
| Other | 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017 |
|---|---|
| Country | Mexico |
| City | Cancun |
| Period | 12/18/17 → 12/21/17 |
Fingerprint
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
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 proceeding › Conference contribution
}
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 -