Combining efficient hand-crafted features with learned filters for fast and accurate corneal nerve fibre centreline detection

Roberto Annunziata (Lead / Corresponding author), Ahmad Kheirkhah, Pedram Hamrah, Emanuele Trucco

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

3 Citations (Scopus)

Abstract

We propose a new approach to corneal nerve fibre centreline detection for in vivo confocal microscopy images. Relying on a combination of efficient hand-crafted features and learned filters, our method offers an excellent compromise between accuracy and running time. Unlike previous solutions using sparse coding to learn small filter banks, we employ K-means to efficiently learn the high amount of filters needed to cope with the multiple challenges involved, e.g., low contrast and resolution, non-uniform illumination, tortuosity and confounding non-target structures. The use of K-means for dictionary learning allows us to learn banks of 100 filters in less than 30 seconds compared to several days needed when using sparse coding. Experimental results using a dataset including 100 images show that our approach outperforms significantly state-of-the-art methods in terms of precision-recall curves.

Original languageEnglish
Title of host publication2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
PublisherInstitute of Electrical and Electronics Engineers
Pages5655-5658
Number of pages4
ISBN (Print)9781424492718
DOIs
Publication statusPublished - 4 Nov 2015
Event37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2015 - Milan, Italy
Duration: 25 Aug 201529 Aug 2015

Conference

Conference37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2015
CountryItaly
CityMilan
Period25/08/1529/08/15

Fingerprint

Confocal microscopy
Filter banks
Glossaries
Nerve Fibers
Hand
Lighting
Fibers
Confocal Microscopy
Learning
Intravital Microscopy
Datasets

Cite this

Annunziata, R., Kheirkhah, A., Hamrah, P., & Trucco, E. (2015). Combining efficient hand-crafted features with learned filters for fast and accurate corneal nerve fibre centreline detection. In 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (pp. 5655-5658). Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/EMBC.2015.7319675
Annunziata, Roberto ; Kheirkhah, Ahmad ; Hamrah, Pedram ; Trucco, Emanuele. / Combining efficient hand-crafted features with learned filters for fast and accurate corneal nerve fibre centreline detection. 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) . Institute of Electrical and Electronics Engineers, 2015. pp. 5655-5658
@inproceedings{131b7aa32c3a4225ba2079d9d9fb2105,
title = "Combining efficient hand-crafted features with learned filters for fast and accurate corneal nerve fibre centreline detection",
abstract = "We propose a new approach to corneal nerve fibre centreline detection for in vivo confocal microscopy images. Relying on a combination of efficient hand-crafted features and learned filters, our method offers an excellent compromise between accuracy and running time. Unlike previous solutions using sparse coding to learn small filter banks, we employ K-means to efficiently learn the high amount of filters needed to cope with the multiple challenges involved, e.g., low contrast and resolution, non-uniform illumination, tortuosity and confounding non-target structures. The use of K-means for dictionary learning allows us to learn banks of 100 filters in less than 30 seconds compared to several days needed when using sparse coding. Experimental results using a dataset including 100 images show that our approach outperforms significantly state-of-the-art methods in terms of precision-recall curves.",
author = "Roberto Annunziata and Ahmad Kheirkhah and Pedram Hamrah and Emanuele Trucco",
year = "2015",
month = "11",
day = "4",
doi = "10.1109/EMBC.2015.7319675",
language = "English",
isbn = "9781424492718",
pages = "5655--5658",
booktitle = "2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)",
publisher = "Institute of Electrical and Electronics Engineers",

}

Annunziata, R, Kheirkhah, A, Hamrah, P & Trucco, E 2015, Combining efficient hand-crafted features with learned filters for fast and accurate corneal nerve fibre centreline detection. in 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) . Institute of Electrical and Electronics Engineers, pp. 5655-5658, 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2015, Milan, Italy, 25/08/15. https://doi.org/10.1109/EMBC.2015.7319675

Combining efficient hand-crafted features with learned filters for fast and accurate corneal nerve fibre centreline detection. / Annunziata, Roberto (Lead / Corresponding author); Kheirkhah, Ahmad; Hamrah, Pedram; Trucco, Emanuele.

2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) . Institute of Electrical and Electronics Engineers, 2015. p. 5655-5658.

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

TY - GEN

T1 - Combining efficient hand-crafted features with learned filters for fast and accurate corneal nerve fibre centreline detection

AU - Annunziata, Roberto

AU - Kheirkhah, Ahmad

AU - Hamrah, Pedram

AU - Trucco, Emanuele

PY - 2015/11/4

Y1 - 2015/11/4

N2 - We propose a new approach to corneal nerve fibre centreline detection for in vivo confocal microscopy images. Relying on a combination of efficient hand-crafted features and learned filters, our method offers an excellent compromise between accuracy and running time. Unlike previous solutions using sparse coding to learn small filter banks, we employ K-means to efficiently learn the high amount of filters needed to cope with the multiple challenges involved, e.g., low contrast and resolution, non-uniform illumination, tortuosity and confounding non-target structures. The use of K-means for dictionary learning allows us to learn banks of 100 filters in less than 30 seconds compared to several days needed when using sparse coding. Experimental results using a dataset including 100 images show that our approach outperforms significantly state-of-the-art methods in terms of precision-recall curves.

AB - We propose a new approach to corneal nerve fibre centreline detection for in vivo confocal microscopy images. Relying on a combination of efficient hand-crafted features and learned filters, our method offers an excellent compromise between accuracy and running time. Unlike previous solutions using sparse coding to learn small filter banks, we employ K-means to efficiently learn the high amount of filters needed to cope with the multiple challenges involved, e.g., low contrast and resolution, non-uniform illumination, tortuosity and confounding non-target structures. The use of K-means for dictionary learning allows us to learn banks of 100 filters in less than 30 seconds compared to several days needed when using sparse coding. Experimental results using a dataset including 100 images show that our approach outperforms significantly state-of-the-art methods in terms of precision-recall curves.

UR - http://www.scopus.com/inward/record.url?scp=84953257114&partnerID=8YFLogxK

U2 - 10.1109/EMBC.2015.7319675

DO - 10.1109/EMBC.2015.7319675

M3 - Conference contribution

SN - 9781424492718

SP - 5655

EP - 5658

BT - 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

PB - Institute of Electrical and Electronics Engineers

ER -

Annunziata R, Kheirkhah A, Hamrah P, Trucco E. Combining efficient hand-crafted features with learned filters for fast and accurate corneal nerve fibre centreline detection. In 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) . Institute of Electrical and Electronics Engineers. 2015. p. 5655-5658 https://doi.org/10.1109/EMBC.2015.7319675