Features of CNN architectures.
<div><p>Background</p><p>Retinal problems are critical because they can cause severe vision loss if not treated. Traditional methods for diagnosing retinal disorders often rely heavily on manual interpretation of optical coherence tomography (OCT) images, which can be time-co...
محفوظ في:
| المؤلف الرئيسي: | |
|---|---|
| مؤلفون آخرون: | |
| منشور في: |
2025
|
| الموضوعات: | |
| الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
| _version_ | 1852022873923780608 |
|---|---|
| author | Gülcan Gencer (20691782) |
| author2 | Kerem Gencer (20691785) |
| author2_role | author |
| author_facet | Gülcan Gencer (20691782) Kerem Gencer (20691785) |
| author_role | author |
| dc.creator.none.fl_str_mv | Gülcan Gencer (20691782) Kerem Gencer (20691785) |
| dc.date.none.fl_str_mv | 2025-02-07T18:46:07Z |
| dc.identifier.none.fl_str_mv | 10.1371/journal.pone.0318657.t002 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/dataset/Features_of_CNN_architectures_/28372994 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Medicine Neuroscience Biotechnology Cancer Biological Sciences not elsewhere classified Information Systems not elsewhere classified provide high success produced excellent results optical coherence tomography indicate substantial promise duke &# 8217 aided diagnostic tools adaptively recalibrating per using artificial intelligence image classification tasks se blocks increase model scaling strategies model &# 8217 detecting retinal disorders dme ), drusen oct images using retinal disorders categorized using including dme classification performance proposed se hybrid se xlink "> traditional methods softmax algorithm paper offers oct images oct datasets manual interpretation known approaches findings emphasize fewer parameters early diagnosis early detection current best combined features choroidal neovascularization architectures enhances accurate detection accuracy rates |
| dc.title.none.fl_str_mv | Features of CNN architectures. |
| dc.type.none.fl_str_mv | Dataset info:eu-repo/semantics/publishedVersion dataset |
| description | <div><p>Background</p><p>Retinal problems are critical because they can cause severe vision loss if not treated. Traditional methods for diagnosing retinal disorders often rely heavily on manual interpretation of optical coherence tomography (OCT) images, which can be time-consuming and dependent on the expertise of ophthalmologists. This leads to challenges in early diagnosis, especially as retinal diseases like diabetic macular edema (DME), Drusen, and Choroidal neovascularization (CNV) become more prevalent. OCT helps ophthalmologists diagnose patients more accurately by allowing for early detection. This paper offers a hybrid SE (Squeeze-and-Excitation)-Enhanced Hybrid Model for detecting retinal disorders from OCT images, including DME, Drusen, and CNV, using artificial intelligence and deep learning.</p><p>Methods</p><p>The model integrates SE blocks with EfficientNetB0 and Xception architectures, which provide high success in image classification tasks. EfficientNetB0 achieves high accuracy with fewer parameters through model scaling strategies, while Xception offers powerful feature extraction using deep separable convolutions. The combination of these architectures enhances both the efficiency and classification performance of the model, enabling more accurate detection of retinal disorders from OCT images. Additionally, SE blocks increase the representational ability of the network by adaptively recalibrating per-channel feature responses.</p><p>Results</p><p>The combined features from EfficientNetB0 and Xception are processed via fully connected layers and categorized using the Softmax algorithm. The methodology was tested on UCSD and Duke’s OCT datasets and produced excellent results. The proposed SE-Improved Hybrid Model outperformed the current best-known approaches, with accuracy rates of 99.58% on the UCSD dataset and 99.18% on the Duke dataset.</p><p>Conclusion</p><p>These findings emphasize the model’s ability to effectively diagnose retinal disorders using OCT images and indicate substantial promise for the development of computer-aided diagnostic tools in the field of ophthalmology.</p></div> |
| eu_rights_str_mv | openAccess |
| id | Manara_aeef69c3ea3b0b187bb72dbaf41a8a67 |
| identifier_str_mv | 10.1371/journal.pone.0318657.t002 |
| network_acronym_str | Manara |
| network_name_str | ManaraRepo |
| oai_identifier_str | oai:figshare.com:article/28372994 |
| publishDate | 2025 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | Features of CNN architectures.Gülcan Gencer (20691782)Kerem Gencer (20691785)MedicineNeuroscienceBiotechnologyCancerBiological Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedprovide high successproduced excellent resultsoptical coherence tomographyindicate substantial promiseduke &# 8217aided diagnostic toolsadaptively recalibrating perusing artificial intelligenceimage classification tasksse blocks increasemodel scaling strategiesmodel &# 8217detecting retinal disordersdme ), drusenoct images usingretinal disorderscategorized usingincluding dmeclassification performanceproposed sehybrid sexlink ">traditional methodssoftmax algorithmpaper offersoct imagesoct datasetsmanual interpretationknown approachesfindings emphasizefewer parametersearly diagnosisearly detectioncurrent bestcombined featureschoroidal neovascularizationarchitectures enhancesaccurate detectionaccuracy rates<div><p>Background</p><p>Retinal problems are critical because they can cause severe vision loss if not treated. Traditional methods for diagnosing retinal disorders often rely heavily on manual interpretation of optical coherence tomography (OCT) images, which can be time-consuming and dependent on the expertise of ophthalmologists. This leads to challenges in early diagnosis, especially as retinal diseases like diabetic macular edema (DME), Drusen, and Choroidal neovascularization (CNV) become more prevalent. OCT helps ophthalmologists diagnose patients more accurately by allowing for early detection. This paper offers a hybrid SE (Squeeze-and-Excitation)-Enhanced Hybrid Model for detecting retinal disorders from OCT images, including DME, Drusen, and CNV, using artificial intelligence and deep learning.</p><p>Methods</p><p>The model integrates SE blocks with EfficientNetB0 and Xception architectures, which provide high success in image classification tasks. EfficientNetB0 achieves high accuracy with fewer parameters through model scaling strategies, while Xception offers powerful feature extraction using deep separable convolutions. The combination of these architectures enhances both the efficiency and classification performance of the model, enabling more accurate detection of retinal disorders from OCT images. Additionally, SE blocks increase the representational ability of the network by adaptively recalibrating per-channel feature responses.</p><p>Results</p><p>The combined features from EfficientNetB0 and Xception are processed via fully connected layers and categorized using the Softmax algorithm. The methodology was tested on UCSD and Duke’s OCT datasets and produced excellent results. The proposed SE-Improved Hybrid Model outperformed the current best-known approaches, with accuracy rates of 99.58% on the UCSD dataset and 99.18% on the Duke dataset.</p><p>Conclusion</p><p>These findings emphasize the model’s ability to effectively diagnose retinal disorders using OCT images and indicate substantial promise for the development of computer-aided diagnostic tools in the field of ophthalmology.</p></div>2025-02-07T18:46:07ZDatasetinfo:eu-repo/semantics/publishedVersiondataset10.1371/journal.pone.0318657.t002https://figshare.com/articles/dataset/Features_of_CNN_architectures_/28372994CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/283729942025-02-07T18:46:07Z |
| spellingShingle | Features of CNN architectures. Gülcan Gencer (20691782) Medicine Neuroscience Biotechnology Cancer Biological Sciences not elsewhere classified Information Systems not elsewhere classified provide high success produced excellent results optical coherence tomography indicate substantial promise duke &# 8217 aided diagnostic tools adaptively recalibrating per using artificial intelligence image classification tasks se blocks increase model scaling strategies model &# 8217 detecting retinal disorders dme ), drusen oct images using retinal disorders categorized using including dme classification performance proposed se hybrid se xlink "> traditional methods softmax algorithm paper offers oct images oct datasets manual interpretation known approaches findings emphasize fewer parameters early diagnosis early detection current best combined features choroidal neovascularization architectures enhances accurate detection accuracy rates |
| status_str | publishedVersion |
| title | Features of CNN architectures. |
| title_full | Features of CNN architectures. |
| title_fullStr | Features of CNN architectures. |
| title_full_unstemmed | Features of CNN architectures. |
| title_short | Features of CNN architectures. |
| title_sort | Features of CNN architectures. |
| topic | Medicine Neuroscience Biotechnology Cancer Biological Sciences not elsewhere classified Information Systems not elsewhere classified provide high success produced excellent results optical coherence tomography indicate substantial promise duke &# 8217 aided diagnostic tools adaptively recalibrating per using artificial intelligence image classification tasks se blocks increase model scaling strategies model &# 8217 detecting retinal disorders dme ), drusen oct images using retinal disorders categorized using including dme classification performance proposed se hybrid se xlink "> traditional methods softmax algorithm paper offers oct images oct datasets manual interpretation known approaches findings emphasize fewer parameters early diagnosis early detection current best combined features choroidal neovascularization architectures enhances accurate detection accuracy rates |