Automated evaluation of retinal hyperreflective foci changes in diabetic macular edema patients before and after intravitreal injection
PurposeFast and automated reconstruction of retinal hyperreflective foci (HRF) is of great importance for many eye-related disease understanding. In this paper, we introduced a new automated framework, driven by recent advances in deep learning to automatically extract 12 three-dimensional parameter...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-10-01
|
| Series: | Frontiers in Medicine |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmed.2023.1280714/full |
| _version_ | 1797665286835404800 |
|---|---|
| author | Xingguo Wang Xingguo Wang Yanyan Zhang Yuhui Ma William Robert Kwapong Jianing Ying Jiayi Lu Jiayi Lu Shaodong Ma Qifeng Yan Quanyong Yi Yitian Zhao Yitian Zhao |
| author_facet | Xingguo Wang Xingguo Wang Yanyan Zhang Yuhui Ma William Robert Kwapong Jianing Ying Jiayi Lu Jiayi Lu Shaodong Ma Qifeng Yan Quanyong Yi Yitian Zhao Yitian Zhao |
| author_sort | Xingguo Wang |
| collection | DOAJ |
| description | PurposeFast and automated reconstruction of retinal hyperreflective foci (HRF) is of great importance for many eye-related disease understanding. In this paper, we introduced a new automated framework, driven by recent advances in deep learning to automatically extract 12 three-dimensional parameters from the segmented hyperreflective foci in optical coherence tomography (OCT).MethodsUnlike traditional convolutional neural networks, which struggle with long-range feature correlations, we introduce a spatial and channel attention module within the bottleneck layer, integrated into the nnU-Net architecture. Spatial Attention Block aggregates features across spatial locations to capture related features, while Channel Attention Block heightens channel feature contrasts. The proposed model was trained and tested on 162 retinal OCT volumes of patients with diabetic macular edema (DME), yielding robust segmentation outcomes. We further investigate HRF’s potential as a biomarker of DME.ResultsResults unveil notable discrepancies in the amount and volume of HRF subtypes. In the whole retinal layer (WR), the mean distance from HRF to the retinal pigmented epithelium was significantly reduced after treatment. In WR, the improvement in central macular thickness resulting from intravitreal injection treatment was positively correlated with the mean distance from HRF subtypes to the fovea.ConclusionOur study demonstrates the applicability of OCT for automated quantification of retinal HRF in DME patients, offering an objective, quantitative approach for clinical and research applications. |
| first_indexed | 2024-03-11T19:41:46Z |
| format | Article |
| id | doaj.art-aeda1325de4b4833a206f61c3014c03a |
| institution | Directory Open Access Journal |
| issn | 2296-858X |
| language | English |
| last_indexed | 2024-03-11T19:41:46Z |
| publishDate | 2023-10-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Medicine |
| spelling | doaj.art-aeda1325de4b4833a206f61c3014c03a2023-10-06T09:51:33ZengFrontiers Media S.A.Frontiers in Medicine2296-858X2023-10-011010.3389/fmed.2023.12807141280714Automated evaluation of retinal hyperreflective foci changes in diabetic macular edema patients before and after intravitreal injectionXingguo Wang0Xingguo Wang1Yanyan Zhang2Yuhui Ma3William Robert Kwapong4Jianing Ying5Jiayi Lu6Jiayi Lu7Shaodong Ma8Qifeng Yan9Quanyong Yi10Yitian Zhao11Yitian Zhao12Cixi Biomedical Research Institute, Wenzhou Medical University, Ningbo, ChinaInstitute of Biomedical Engineering, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo, ChinaThe Affiliated Ningbo Eye Hospital of Wenzhou Medical University, Ningbo, ChinaInstitute of Biomedical Engineering, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo, ChinaDepartment of Neurology, West China Hospital, Sichuan University, Chengdu, ChinaHealth Science Center, Ningbo University, Ningbo, ChinaCixi Biomedical Research Institute, Wenzhou Medical University, Ningbo, ChinaInstitute of Biomedical Engineering, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo, ChinaInstitute of Biomedical Engineering, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo, ChinaInstitute of Biomedical Engineering, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo, ChinaThe Affiliated Ningbo Eye Hospital of Wenzhou Medical University, Ningbo, ChinaCixi Biomedical Research Institute, Wenzhou Medical University, Ningbo, ChinaInstitute of Biomedical Engineering, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo, ChinaPurposeFast and automated reconstruction of retinal hyperreflective foci (HRF) is of great importance for many eye-related disease understanding. In this paper, we introduced a new automated framework, driven by recent advances in deep learning to automatically extract 12 three-dimensional parameters from the segmented hyperreflective foci in optical coherence tomography (OCT).MethodsUnlike traditional convolutional neural networks, which struggle with long-range feature correlations, we introduce a spatial and channel attention module within the bottleneck layer, integrated into the nnU-Net architecture. Spatial Attention Block aggregates features across spatial locations to capture related features, while Channel Attention Block heightens channel feature contrasts. The proposed model was trained and tested on 162 retinal OCT volumes of patients with diabetic macular edema (DME), yielding robust segmentation outcomes. We further investigate HRF’s potential as a biomarker of DME.ResultsResults unveil notable discrepancies in the amount and volume of HRF subtypes. In the whole retinal layer (WR), the mean distance from HRF to the retinal pigmented epithelium was significantly reduced after treatment. In WR, the improvement in central macular thickness resulting from intravitreal injection treatment was positively correlated with the mean distance from HRF subtypes to the fovea.ConclusionOur study demonstrates the applicability of OCT for automated quantification of retinal HRF in DME patients, offering an objective, quantitative approach for clinical and research applications.https://www.frontiersin.org/articles/10.3389/fmed.2023.1280714/fulldiabetic macular edemahyperreflective focioptical coherence tomographyartificial intelligencedeep learning |
| spellingShingle | Xingguo Wang Xingguo Wang Yanyan Zhang Yuhui Ma William Robert Kwapong Jianing Ying Jiayi Lu Jiayi Lu Shaodong Ma Qifeng Yan Quanyong Yi Yitian Zhao Yitian Zhao Automated evaluation of retinal hyperreflective foci changes in diabetic macular edema patients before and after intravitreal injection Frontiers in Medicine diabetic macular edema hyperreflective foci optical coherence tomography artificial intelligence deep learning |
| title | Automated evaluation of retinal hyperreflective foci changes in diabetic macular edema patients before and after intravitreal injection |
| title_full | Automated evaluation of retinal hyperreflective foci changes in diabetic macular edema patients before and after intravitreal injection |
| title_fullStr | Automated evaluation of retinal hyperreflective foci changes in diabetic macular edema patients before and after intravitreal injection |
| title_full_unstemmed | Automated evaluation of retinal hyperreflective foci changes in diabetic macular edema patients before and after intravitreal injection |
| title_short | Automated evaluation of retinal hyperreflective foci changes in diabetic macular edema patients before and after intravitreal injection |
| title_sort | automated evaluation of retinal hyperreflective foci changes in diabetic macular edema patients before and after intravitreal injection |
| topic | diabetic macular edema hyperreflective foci optical coherence tomography artificial intelligence deep learning |
| url | https://www.frontiersin.org/articles/10.3389/fmed.2023.1280714/full |
| work_keys_str_mv | AT xingguowang automatedevaluationofretinalhyperreflectivefocichangesindiabeticmacularedemapatientsbeforeandafterintravitrealinjection AT xingguowang automatedevaluationofretinalhyperreflectivefocichangesindiabeticmacularedemapatientsbeforeandafterintravitrealinjection AT yanyanzhang automatedevaluationofretinalhyperreflectivefocichangesindiabeticmacularedemapatientsbeforeandafterintravitrealinjection AT yuhuima automatedevaluationofretinalhyperreflectivefocichangesindiabeticmacularedemapatientsbeforeandafterintravitrealinjection AT williamrobertkwapong automatedevaluationofretinalhyperreflectivefocichangesindiabeticmacularedemapatientsbeforeandafterintravitrealinjection AT jianingying automatedevaluationofretinalhyperreflectivefocichangesindiabeticmacularedemapatientsbeforeandafterintravitrealinjection AT jiayilu automatedevaluationofretinalhyperreflectivefocichangesindiabeticmacularedemapatientsbeforeandafterintravitrealinjection AT jiayilu automatedevaluationofretinalhyperreflectivefocichangesindiabeticmacularedemapatientsbeforeandafterintravitrealinjection AT shaodongma automatedevaluationofretinalhyperreflectivefocichangesindiabeticmacularedemapatientsbeforeandafterintravitrealinjection AT qifengyan automatedevaluationofretinalhyperreflectivefocichangesindiabeticmacularedemapatientsbeforeandafterintravitrealinjection AT quanyongyi automatedevaluationofretinalhyperreflectivefocichangesindiabeticmacularedemapatientsbeforeandafterintravitrealinjection AT yitianzhao automatedevaluationofretinalhyperreflectivefocichangesindiabeticmacularedemapatientsbeforeandafterintravitrealinjection AT yitianzhao automatedevaluationofretinalhyperreflectivefocichangesindiabeticmacularedemapatientsbeforeandafterintravitrealinjection |