Adaptive enhancement of cataractous retinal images for contrast standardization
Abstract Cataract affects the quality of fundus images, especially the contrast, due to lens opacity. In this paper, we propose a scheme to enhance different cataractous retinal images to the same contrast as normal images, which can automatically choose the suitable enhancement model based on cataract grading. A multi-level cataract dataset is constructed via the degradation model with quantified contrast. Then, an adaptive enhancement strategy is introduced to choose among three enhancement networks based on a blurriness classifier. The blurriness grading loss is proposed in the enhancement models to further constrain the contrast of the enhanced images. During test, the well-trained blurriness classifier can assist in the selection of enhancement networks with specific enhancement ability. Our method performs the best on the synthetic paired data on PSNR, SSIM, and FSIM and has the best PIQE and FID on 406 clinical fundus images. There is a 7.78% improvement for our method compared with the second on the introduced %$P_{h}%$ score without over-enhancement according to %$P_{oe}%$, which demonstrates that the proper enhancement by our method is close to the high-quality images. The visual evaluation on multiple clinical datasets also shows the applicability of our method for different blurriness. The proposed method can benefit clinical diagnosis and improve the performance of computer-aided algorithms such as vessel tracking and vessel segmentation..
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2023 |
|---|---|
| Erschienen: |
2023 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:62 |
|---|---|
| Enthalten in: |
Medical & biological engineering & computing - 62(2023), 2 vom: 18. Okt., Seite 357-369 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Yang, Bingyu [VerfasserIn] |
|---|
| Links: |
Volltext [lizenzpflichtig] |
|---|
| Themen: |
Adaptive enhancement |
|---|
| Anmerkungen: |
© International Federation for Medical and Biological Engineering 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. |
|---|
| doi: |
10.1007/s11517-023-02937-5 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
SPR054421772 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | SPR054421772 | ||
| 003 | DE-627 | ||
| 005 | 20240118064704.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240118s2023 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1007/s11517-023-02937-5 |2 doi | |
| 035 | |a (DE-627)SPR054421772 | ||
| 035 | |a (SPR)s11517-023-02937-5-e | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Yang, Bingyu |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Adaptive enhancement of cataractous retinal images for contrast standardization |
| 264 | 1 | |c 2023 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a © International Federation for Medical and Biological Engineering 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. | ||
| 520 | |a Abstract Cataract affects the quality of fundus images, especially the contrast, due to lens opacity. In this paper, we propose a scheme to enhance different cataractous retinal images to the same contrast as normal images, which can automatically choose the suitable enhancement model based on cataract grading. A multi-level cataract dataset is constructed via the degradation model with quantified contrast. Then, an adaptive enhancement strategy is introduced to choose among three enhancement networks based on a blurriness classifier. The blurriness grading loss is proposed in the enhancement models to further constrain the contrast of the enhanced images. During test, the well-trained blurriness classifier can assist in the selection of enhancement networks with specific enhancement ability. Our method performs the best on the synthetic paired data on PSNR, SSIM, and FSIM and has the best PIQE and FID on 406 clinical fundus images. There is a 7.78% improvement for our method compared with the second on the introduced %$P_{h}%$ score without over-enhancement according to %$P_{oe}%$, which demonstrates that the proper enhancement by our method is close to the high-quality images. The visual evaluation on multiple clinical datasets also shows the applicability of our method for different blurriness. The proposed method can benefit clinical diagnosis and improve the performance of computer-aided algorithms such as vessel tracking and vessel segmentation. | ||
| 650 | 4 | |a Retinal image enhancement |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Contrast standardization |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Blurriness grading |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Adaptive enhancement |7 (dpeaa)DE-He213 | |
| 700 | 1 | |a Cao, Lvchen |4 aut | |
| 700 | 1 | |a Zhao, He |4 aut | |
| 700 | 1 | |a Li, Huiqi |0 (orcid)0000-0002-8720-3374 |4 aut | |
| 700 | 1 | |a Liu, Hanruo |4 aut | |
| 700 | 1 | |a Wang, Ningli |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Medical & biological engineering & computing |d Cham : Springer Nature, 1963 |g 62(2023), 2 vom: 18. Okt., Seite 357-369 |w (DE-627)SPR020494920 |w (DE-600)2052667-2 |x 1741-0444 |7 nnns |
| 773 | 1 | 8 | |g volume:62 |g year:2023 |g number:2 |g day:18 |g month:10 |g pages:357-369 |
| 856 | 4 | 0 | |u https://dx.doi.org/10.1007/s11517-023-02937-5 |z lizenzpflichtig |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_SPRINGER | ||
| 951 | |a AR | ||
| 952 | |d 62 |j 2023 |e 2 |b 18 |c 10 |h 357-369 | ||