Pseudoaveraging for denoising of OCT angiography: a deep learning approach for image quality enhancement in healthy and diabetic eyes
Abstract Background This study aimed to develop a deep learning (DL) algorithm that enhances the quality of a single-frame enface OCTA scan to make it comparable to 4-frame averaged scan without the need for the repeated acquisitions required for averaging. Methods Each of the healthy eyes and eyes...
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2023-10-01
|
| Series: | International Journal of Retina and Vitreous |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40942-023-00486-5 |
| _version_ | 1797451902597726208 |
|---|---|
| author | Omar Abu-Qamar Warren Lewis Luisa S. M. Mendonca Luis De Sisternes Adam Chin A. Yasin Alibhai Isaac Gendelman Elias Reichel Stephanie Magazzeni Sophie Kubach Mary Durbin Andre J. Witkin Caroline R. Baumal Jay S. Duker Nadia K. Waheed |
| author_facet | Omar Abu-Qamar Warren Lewis Luisa S. M. Mendonca Luis De Sisternes Adam Chin A. Yasin Alibhai Isaac Gendelman Elias Reichel Stephanie Magazzeni Sophie Kubach Mary Durbin Andre J. Witkin Caroline R. Baumal Jay S. Duker Nadia K. Waheed |
| author_sort | Omar Abu-Qamar |
| collection | DOAJ |
| description | Abstract Background This study aimed to develop a deep learning (DL) algorithm that enhances the quality of a single-frame enface OCTA scan to make it comparable to 4-frame averaged scan without the need for the repeated acquisitions required for averaging. Methods Each of the healthy eyes and eyes from diabetic subjects that were prospectively enrolled in this cross-sectional study underwent four repeated 6 × 6 mm macular scans (PLEX Elite 9000 SS-OCT), and the repeated scans of each eye were co-registered to produce 4-frame averages. This prospective dataset of original (single-frame) enface scans and their corresponding averaged scans was divided into a training dataset and a validation dataset. In the training dataset, a DL algorithm (named pseudoaveraging) was trained using original scans as input and 4-frame averages as target. In the validation dataset, the pseudoaveraging algorithm was applied to single-frame scans to produce pseudoaveraged scans, and the single-frame and its corresponding averaged and pseudoaveraged scans were all qualitatively compared. In a separate retrospectively collected dataset of single-frame scans from eyes of diabetic subjects, the DL algorithm was applied, and the produced pseudoaveraged scan was qualitatively compared against its corresponding original. Results This study included 39 eyes that comprised the prospective dataset (split into 5 eyes for training and 34 eyes for validating the DL algorithm), and 105 eyes that comprised the retrospective test dataset. Of the total 144 study eyes, 58% had any level of diabetic retinopathy (with and without diabetic macular edema), and the rest were from healthy eyes or eyes of diabetic subjects but without diabetic retinopathy and without macular edema. Grading results in the validation dataset showed that the pseudoaveraged enface scan ranked best in overall scan quality, background noise reduction, and visibility of microaneurysms (p < 0.05). Averaged scan ranked best for motion artifact reduction (p < 0.05). Grading results in the test dataset showed that pseudoaveraging resulted in enhanced small vessels, reduction of background noise, and motion artifact in 100%, 82%, and 98% of scans, respectively. Rates of false-positive/-negative perfusion were zero. Conclusion Pseudoaveraging is a feasible DL approach to more efficiently improve enface OCTA scan quality without introducing notable image artifacts. |
| first_indexed | 2024-03-09T15:00:35Z |
| format | Article |
| id | doaj.art-8b14bb99d10b46659b65438cb7285055 |
| institution | Directory Open Access Journal |
| issn | 2056-9920 |
| language | English |
| last_indexed | 2024-03-09T15:00:35Z |
| publishDate | 2023-10-01 |
| publisher | BMC |
| record_format | Article |
| series | International Journal of Retina and Vitreous |
| spelling | doaj.art-8b14bb99d10b46659b65438cb72850552023-11-26T13:55:53ZengBMCInternational Journal of Retina and Vitreous2056-99202023-10-019111110.1186/s40942-023-00486-5Pseudoaveraging for denoising of OCT angiography: a deep learning approach for image quality enhancement in healthy and diabetic eyesOmar Abu-Qamar0Warren Lewis1Luisa S. M. Mendonca2Luis De Sisternes3Adam Chin4A. Yasin Alibhai5Isaac Gendelman6Elias Reichel7Stephanie Magazzeni8Sophie Kubach9Mary Durbin10Andre J. Witkin11Caroline R. Baumal12Jay S. Duker13Nadia K. Waheed14New England Eye Center, Tufts Medical CenterResearch and Development, Carl Zeiss MeditecNew England Eye Center, Tufts Medical CenterResearch and Development, Carl Zeiss MeditecNew England Eye Center, Tufts Medical Center Boston Image Reading CenterNew England Eye Center, Tufts Medical CenterNew England Eye Center, Tufts Medical CenterResearch and Development, Carl Zeiss MeditecResearch and Development, Carl Zeiss MeditecResearch and Development, Carl Zeiss MeditecNew England Eye Center, Tufts Medical CenterNew England Eye Center, Tufts Medical CenterNew England Eye Center, Tufts Medical CenterNew England Eye Center, Tufts Medical CenterAbstract Background This study aimed to develop a deep learning (DL) algorithm that enhances the quality of a single-frame enface OCTA scan to make it comparable to 4-frame averaged scan without the need for the repeated acquisitions required for averaging. Methods Each of the healthy eyes and eyes from diabetic subjects that were prospectively enrolled in this cross-sectional study underwent four repeated 6 × 6 mm macular scans (PLEX Elite 9000 SS-OCT), and the repeated scans of each eye were co-registered to produce 4-frame averages. This prospective dataset of original (single-frame) enface scans and their corresponding averaged scans was divided into a training dataset and a validation dataset. In the training dataset, a DL algorithm (named pseudoaveraging) was trained using original scans as input and 4-frame averages as target. In the validation dataset, the pseudoaveraging algorithm was applied to single-frame scans to produce pseudoaveraged scans, and the single-frame and its corresponding averaged and pseudoaveraged scans were all qualitatively compared. In a separate retrospectively collected dataset of single-frame scans from eyes of diabetic subjects, the DL algorithm was applied, and the produced pseudoaveraged scan was qualitatively compared against its corresponding original. Results This study included 39 eyes that comprised the prospective dataset (split into 5 eyes for training and 34 eyes for validating the DL algorithm), and 105 eyes that comprised the retrospective test dataset. Of the total 144 study eyes, 58% had any level of diabetic retinopathy (with and without diabetic macular edema), and the rest were from healthy eyes or eyes of diabetic subjects but without diabetic retinopathy and without macular edema. Grading results in the validation dataset showed that the pseudoaveraged enface scan ranked best in overall scan quality, background noise reduction, and visibility of microaneurysms (p < 0.05). Averaged scan ranked best for motion artifact reduction (p < 0.05). Grading results in the test dataset showed that pseudoaveraging resulted in enhanced small vessels, reduction of background noise, and motion artifact in 100%, 82%, and 98% of scans, respectively. Rates of false-positive/-negative perfusion were zero. Conclusion Pseudoaveraging is a feasible DL approach to more efficiently improve enface OCTA scan quality without introducing notable image artifacts.https://doi.org/10.1186/s40942-023-00486-5AveragingImage artifactDeep learningDenoisingDiabetic retinopathyImage quality |
| spellingShingle | Omar Abu-Qamar Warren Lewis Luisa S. M. Mendonca Luis De Sisternes Adam Chin A. Yasin Alibhai Isaac Gendelman Elias Reichel Stephanie Magazzeni Sophie Kubach Mary Durbin Andre J. Witkin Caroline R. Baumal Jay S. Duker Nadia K. Waheed Pseudoaveraging for denoising of OCT angiography: a deep learning approach for image quality enhancement in healthy and diabetic eyes International Journal of Retina and Vitreous Averaging Image artifact Deep learning Denoising Diabetic retinopathy Image quality |
| title | Pseudoaveraging for denoising of OCT angiography: a deep learning approach for image quality enhancement in healthy and diabetic eyes |
| title_full | Pseudoaveraging for denoising of OCT angiography: a deep learning approach for image quality enhancement in healthy and diabetic eyes |
| title_fullStr | Pseudoaveraging for denoising of OCT angiography: a deep learning approach for image quality enhancement in healthy and diabetic eyes |
| title_full_unstemmed | Pseudoaveraging for denoising of OCT angiography: a deep learning approach for image quality enhancement in healthy and diabetic eyes |
| title_short | Pseudoaveraging for denoising of OCT angiography: a deep learning approach for image quality enhancement in healthy and diabetic eyes |
| title_sort | pseudoaveraging for denoising of oct angiography a deep learning approach for image quality enhancement in healthy and diabetic eyes |
| topic | Averaging Image artifact Deep learning Denoising Diabetic retinopathy Image quality |
| url | https://doi.org/10.1186/s40942-023-00486-5 |
| work_keys_str_mv | AT omarabuqamar pseudoaveragingfordenoisingofoctangiographyadeeplearningapproachforimagequalityenhancementinhealthyanddiabeticeyes AT warrenlewis pseudoaveragingfordenoisingofoctangiographyadeeplearningapproachforimagequalityenhancementinhealthyanddiabeticeyes AT luisasmmendonca pseudoaveragingfordenoisingofoctangiographyadeeplearningapproachforimagequalityenhancementinhealthyanddiabeticeyes AT luisdesisternes pseudoaveragingfordenoisingofoctangiographyadeeplearningapproachforimagequalityenhancementinhealthyanddiabeticeyes AT adamchin pseudoaveragingfordenoisingofoctangiographyadeeplearningapproachforimagequalityenhancementinhealthyanddiabeticeyes AT ayasinalibhai pseudoaveragingfordenoisingofoctangiographyadeeplearningapproachforimagequalityenhancementinhealthyanddiabeticeyes AT isaacgendelman pseudoaveragingfordenoisingofoctangiographyadeeplearningapproachforimagequalityenhancementinhealthyanddiabeticeyes AT eliasreichel pseudoaveragingfordenoisingofoctangiographyadeeplearningapproachforimagequalityenhancementinhealthyanddiabeticeyes AT stephaniemagazzeni pseudoaveragingfordenoisingofoctangiographyadeeplearningapproachforimagequalityenhancementinhealthyanddiabeticeyes AT sophiekubach pseudoaveragingfordenoisingofoctangiographyadeeplearningapproachforimagequalityenhancementinhealthyanddiabeticeyes AT marydurbin pseudoaveragingfordenoisingofoctangiographyadeeplearningapproachforimagequalityenhancementinhealthyanddiabeticeyes AT andrejwitkin pseudoaveragingfordenoisingofoctangiographyadeeplearningapproachforimagequalityenhancementinhealthyanddiabeticeyes AT carolinerbaumal pseudoaveragingfordenoisingofoctangiographyadeeplearningapproachforimagequalityenhancementinhealthyanddiabeticeyes AT jaysduker pseudoaveragingfordenoisingofoctangiographyadeeplearningapproachforimagequalityenhancementinhealthyanddiabeticeyes AT nadiakwaheed pseudoaveragingfordenoisingofoctangiographyadeeplearningapproachforimagequalityenhancementinhealthyanddiabeticeyes |