Automatic detection of the foveal center in optical coherence tomography
We propose a method for automatic detection of the foveal center in optical coherence tomography (OCT). The method is based on a pixel-wise classification of all pixels in an OCT volume using a fully convolutional neural network (CNN) with dilated convolution filters. The CNN-architecture contains anisotropic dilated filters and a shortcut connection and has been trained using a dynamic training procedure where the network identifies its own relevant training samples. The performance of the proposed method is evaluated on a data set of 400 OCT scans of patients affected by age-related macular degeneration (AMD) at different severity levels. For 391 scans (97.75%) the method identified the foveal center with a distance to a human reference less than 750 μm, with a mean (± SD) distance of 71 μm ± 107 μm. Two independent observers also annotated the foveal center, with a mean distance to the reference of 57 μm ± 84 μm and 56 μm ± 80 μm, respectively. Furthermore, we evaluate variations to the proposed network architecture and training procedure, providing insight in the characteristics that led to the demonstrated performance of the proposed method.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2017 |
|---|---|
| Erschienen: |
2017 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:8 |
|---|---|
| Enthalten in: |
Biomedical optics express - 8(2017), 11 vom: 01. Nov., Seite 5160-5178 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Liefers, Bart [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
(100.2960) Image analysis |
|---|
| Anmerkungen: |
Date Revised 27.03.2024 published: Electronic-eCollection Citation Status PubMed-not-MEDLINE |
|---|
| doi: |
10.1364/BOE.8.005160 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM278537855 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM278537855 | ||
| 003 | DE-627 | ||
| 005 | 20240327233542.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231225s2017 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1364/BOE.8.005160 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1350.xml |
| 035 | |a (DE-627)NLM278537855 | ||
| 035 | |a (NLM)29188111 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Liefers, Bart |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Automatic detection of the foveal center in optical coherence tomography |
| 264 | 1 | |c 2017 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Revised 27.03.2024 | ||
| 500 | |a published: Electronic-eCollection | ||
| 500 | |a Citation Status PubMed-not-MEDLINE | ||
| 520 | |a We propose a method for automatic detection of the foveal center in optical coherence tomography (OCT). The method is based on a pixel-wise classification of all pixels in an OCT volume using a fully convolutional neural network (CNN) with dilated convolution filters. The CNN-architecture contains anisotropic dilated filters and a shortcut connection and has been trained using a dynamic training procedure where the network identifies its own relevant training samples. The performance of the proposed method is evaluated on a data set of 400 OCT scans of patients affected by age-related macular degeneration (AMD) at different severity levels. For 391 scans (97.75%) the method identified the foveal center with a distance to a human reference less than 750 μm, with a mean (± SD) distance of 71 μm ± 107 μm. Two independent observers also annotated the foveal center, with a mean distance to the reference of 57 μm ± 84 μm and 56 μm ± 80 μm, respectively. Furthermore, we evaluate variations to the proposed network architecture and training procedure, providing insight in the characteristics that led to the demonstrated performance of the proposed method | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a (100.2960) Image analysis | |
| 650 | 4 | |a (100.4996) Pattern recognition, neural networks | |
| 650 | 4 | |a (110.4500) Optical coherence tomography | |
| 650 | 4 | |a (170.1610) Clinical applications | |
| 650 | 4 | |a (170.4470) Ophthalmology | |
| 700 | 1 | |a Venhuizen, Freerk G |e verfasserin |4 aut | |
| 700 | 1 | |a Schreur, Vivian |e verfasserin |4 aut | |
| 700 | 1 | |a van Ginneken, Bram |e verfasserin |4 aut | |
| 700 | 1 | |a Hoyng, Carel |e verfasserin |4 aut | |
| 700 | 1 | |a Fauser, Sascha |e verfasserin |4 aut | |
| 700 | 1 | |a Theelen, Thomas |e verfasserin |4 aut | |
| 700 | 1 | |a Sánchez, Clara I |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Biomedical optics express |d 2010 |g 8(2017), 11 vom: 01. Nov., Seite 5160-5178 |w (DE-627)NLM203936965 |x 2156-7085 |7 nnns |
| 773 | 1 | 8 | |g volume:8 |g year:2017 |g number:11 |g day:01 |g month:11 |g pages:5160-5178 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1364/BOE.8.005160 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 8 |j 2017 |e 11 |b 01 |c 11 |h 5160-5178 | ||