DISCOVER : 2-D multiview summarization of Optical Coherence Tomography Angiography for automatic diabetic retinopathy diagnosis
Copyright © 2024 The Author(s). Published by Elsevier B.V. All rights reserved..
Diabetic Retinopathy (DR), an ocular complication of diabetes, is a leading cause of blindness worldwide. Traditionally, DR is monitored using Color Fundus Photography (CFP), a widespread 2-D imaging modality. However, DR classifications based on CFP have poor predictive power, resulting in suboptimal DR management. Optical Coherence Tomography Angiography (OCTA) is a recent 3-D imaging modality offering enhanced structural and functional information (blood flow) with a wider field of view. This paper investigates automatic DR severity assessment using 3-D OCTA. A straightforward solution to this task is a 3-D neural network classifier. However, 3-D architectures have numerous parameters and typically require many training samples. A lighter solution consists in using 2-D neural network classifiers processing 2-D en-face (or frontal) projections and/or 2-D cross-sectional slices. Such an approach mimics the way ophthalmologists analyze OCTA acquisitions: (1) en-face flow maps are often used to detect avascular zones and neovascularization, and (2) cross-sectional slices are commonly analyzed to detect macular edemas, for instance. However, arbitrary data reduction or selection might result in information loss. Two complementary strategies are thus proposed to optimally summarize OCTA volumes with 2-D images: (1) a parametric en-face projection optimized through deep learning and (2) a cross-sectional slice selection process controlled through gradient-based attribution. The full summarization and DR classification pipeline is trained from end to end. The automatic 2-D summary can be displayed in a viewer or printed in a report to support the decision. We show that the proposed 2-D summarization and classification pipeline outperforms direct 3-D classification with the advantage of improved interpretability.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:149 |
|---|---|
| Enthalten in: |
Artificial intelligence in medicine - 149(2024) vom: 08. März, Seite 102803 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
El Habib Daho, Mostafa [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Deep learning |
|---|
| Anmerkungen: |
Date Completed 12.03.2024 Date Revised 12.03.2024 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1016/j.artmed.2024.102803 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM369520203 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM369520203 | ||
| 003 | DE-627 | ||
| 005 | 20240312234211.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240311s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.artmed.2024.102803 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1324.xml |
| 035 | |a (DE-627)NLM369520203 | ||
| 035 | |a (NLM)38462293 | ||
| 035 | |a (PII)S0933-3657(24)00045-9 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a El Habib Daho, Mostafa |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a DISCOVER |b 2-D multiview summarization of Optical Coherence Tomography Angiography for automatic diabetic retinopathy diagnosis |
| 264 | 1 | |c 2024 | |
| 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 Completed 12.03.2024 | ||
| 500 | |a Date Revised 12.03.2024 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a Copyright © 2024 The Author(s). Published by Elsevier B.V. All rights reserved. | ||
| 520 | |a Diabetic Retinopathy (DR), an ocular complication of diabetes, is a leading cause of blindness worldwide. Traditionally, DR is monitored using Color Fundus Photography (CFP), a widespread 2-D imaging modality. However, DR classifications based on CFP have poor predictive power, resulting in suboptimal DR management. Optical Coherence Tomography Angiography (OCTA) is a recent 3-D imaging modality offering enhanced structural and functional information (blood flow) with a wider field of view. This paper investigates automatic DR severity assessment using 3-D OCTA. A straightforward solution to this task is a 3-D neural network classifier. However, 3-D architectures have numerous parameters and typically require many training samples. A lighter solution consists in using 2-D neural network classifiers processing 2-D en-face (or frontal) projections and/or 2-D cross-sectional slices. Such an approach mimics the way ophthalmologists analyze OCTA acquisitions: (1) en-face flow maps are often used to detect avascular zones and neovascularization, and (2) cross-sectional slices are commonly analyzed to detect macular edemas, for instance. However, arbitrary data reduction or selection might result in information loss. Two complementary strategies are thus proposed to optimally summarize OCTA volumes with 2-D images: (1) a parametric en-face projection optimized through deep learning and (2) a cross-sectional slice selection process controlled through gradient-based attribution. The full summarization and DR classification pipeline is trained from end to end. The automatic 2-D summary can be displayed in a viewer or printed in a report to support the decision. We show that the proposed 2-D summarization and classification pipeline outperforms direct 3-D classification with the advantage of improved interpretability | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Deep learning | |
| 650 | 4 | |a Diabetic retinopathy | |
| 650 | 4 | |a Interpretability | |
| 650 | 4 | |a Optical Coherence Tomography Angiography (OCTA) | |
| 700 | 1 | |a Li, Yihao |e verfasserin |4 aut | |
| 700 | 1 | |a Zeghlache, Rachid |e verfasserin |4 aut | |
| 700 | 1 | |a Boité, Hugo Le |e verfasserin |4 aut | |
| 700 | 1 | |a Deman, Pierre |e verfasserin |4 aut | |
| 700 | 1 | |a Borderie, Laurent |e verfasserin |4 aut | |
| 700 | 1 | |a Ren, Hugang |e verfasserin |4 aut | |
| 700 | 1 | |a Mannivanan, Niranchana |e verfasserin |4 aut | |
| 700 | 1 | |a Lepicard, Capucine |e verfasserin |4 aut | |
| 700 | 1 | |a Cochener, Béatrice |e verfasserin |4 aut | |
| 700 | 1 | |a Couturier, Aude |e verfasserin |4 aut | |
| 700 | 1 | |a Tadayoni, Ramin |e verfasserin |4 aut | |
| 700 | 1 | |a Conze, Pierre-Henri |e verfasserin |4 aut | |
| 700 | 1 | |a Lamard, Mathieu |e verfasserin |4 aut | |
| 700 | 1 | |a Quellec, Gwenolé |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Artificial intelligence in medicine |d 1995 |g 149(2024) vom: 08. März, Seite 102803 |w (DE-627)NLM075578344 |x 1873-2860 |7 nnns |
| 773 | 1 | 8 | |g volume:149 |g year:2024 |g day:08 |g month:03 |g pages:102803 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1016/j.artmed.2024.102803 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 149 |j 2024 |b 08 |c 03 |h 102803 | ||