Rotation-Oriented Collaborative Self-Supervised Learning for Retinal Disease Diagnosis
The automatic diagnosis of various conventional ophthalmic diseases from fundus images is important in clinical practice. However, developing such automatic solutions is challenging due to the requirement of a large amount of training data and the expensive annotations for medical images. This paper presents a novel self-supervised learning framework for retinal disease diagnosis to reduce the annotation efforts by learning the visual features from the unlabeled images. To achieve this, we present a rotation-oriented collaborative method that explores rotation-related and rotation-invariant features, which capture discriminative structures from fundus images and also explore the invariant property used for retinal disease classification. We evaluate the proposed method on two public benchmark datasets for retinal disease classification. The experimental results demonstrate that our method outperforms other self-supervised feature learning methods (around 4.2% area under the curve (AUC)). With a large amount of unlabeled data available, our method can surpass the supervised baseline for pathologic myopia (PM) and is very close to the supervised baseline for age-related macular degeneration (AMD), showing the potential benefit of our method in clinical practice.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2021 |
|---|---|
| Erschienen: |
2021 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:40 |
|---|---|
| Enthalten in: |
IEEE transactions on medical imaging - 40(2021), 9 vom: 23. Sept., Seite 2284-2294 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Li, Xiaomeng [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
|---|
| Anmerkungen: |
Date Completed 21.10.2021 Date Revised 21.10.2021 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1109/TMI.2021.3075244 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM324451954 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM324451954 | ||
| 003 | DE-627 | ||
| 005 | 20231225190343.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231225s2021 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1109/TMI.2021.3075244 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1081.xml |
| 035 | |a (DE-627)NLM324451954 | ||
| 035 | |a (NLM)33891550 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Li, Xiaomeng |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Rotation-Oriented Collaborative Self-Supervised Learning for Retinal Disease Diagnosis |
| 264 | 1 | |c 2021 | |
| 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 21.10.2021 | ||
| 500 | |a Date Revised 21.10.2021 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a The automatic diagnosis of various conventional ophthalmic diseases from fundus images is important in clinical practice. However, developing such automatic solutions is challenging due to the requirement of a large amount of training data and the expensive annotations for medical images. This paper presents a novel self-supervised learning framework for retinal disease diagnosis to reduce the annotation efforts by learning the visual features from the unlabeled images. To achieve this, we present a rotation-oriented collaborative method that explores rotation-related and rotation-invariant features, which capture discriminative structures from fundus images and also explore the invariant property used for retinal disease classification. We evaluate the proposed method on two public benchmark datasets for retinal disease classification. The experimental results demonstrate that our method outperforms other self-supervised feature learning methods (around 4.2% area under the curve (AUC)). With a large amount of unlabeled data available, our method can surpass the supervised baseline for pathologic myopia (PM) and is very close to the supervised baseline for age-related macular degeneration (AMD), showing the potential benefit of our method in clinical practice | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Research Support, Non-U.S. Gov't | |
| 700 | 1 | |a Hu, Xiaowei |e verfasserin |4 aut | |
| 700 | 1 | |a Qi, Xiaojuan |e verfasserin |4 aut | |
| 700 | 1 | |a Yu, Lequan |e verfasserin |4 aut | |
| 700 | 1 | |a Zhao, Wei |e verfasserin |4 aut | |
| 700 | 1 | |a Heng, Pheng-Ann |e verfasserin |4 aut | |
| 700 | 1 | |a Xing, Lei |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t IEEE transactions on medical imaging |d 1982 |g 40(2021), 9 vom: 23. Sept., Seite 2284-2294 |w (DE-627)NLM082855269 |x 1558-254X |7 nnns |
| 773 | 1 | 8 | |g volume:40 |g year:2021 |g number:9 |g day:23 |g month:09 |g pages:2284-2294 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1109/TMI.2021.3075244 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 40 |j 2021 |e 9 |b 23 |c 09 |h 2284-2294 | ||