Application of Deep Dictionary Learning and Predefined Filters for Classification of Retinal Optical Coherence Tomography Images
In recent years, deep learning methods have excelled in Optical Coherence Tomography (OCT) image classification but demand high computational resources and extensive training data. We propose two effective methods for OCT image classification, combining the strength of deep learning with sparse repr...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10813162/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841563315994624000 |
|---|---|
| author | Fariba Shaker Zahra Baharlouei Gerlind Plonka Hossein Rabbani |
| author_facet | Fariba Shaker Zahra Baharlouei Gerlind Plonka Hossein Rabbani |
| author_sort | Fariba Shaker |
| collection | DOAJ |
| description | In recent years, deep learning methods have excelled in Optical Coherence Tomography (OCT) image classification but demand high computational resources and extensive training data. We propose two effective methods for OCT image classification, combining the strength of deep learning with sparse representation of significant image features for improved detection of retinal abnormalities. The first method, Simplified Deep Dictionary Learning (S-DDL), is based on deep dictionary learning, where the loss function enforces a sparse feature representation of input image patches before classification. The second method uses the Wavelet Scattering Transform (WST), which employs predefined filters in network layers. We compare its performance with the S-DDL method. WST is a convolutional network with predefined wavelet filters that do not need to be learned, requiring lower processing time and complexity. Both methods can be directly applied to raw image data without time-consuming pre-processing, as the first layers act like denoising filters to achieve sparse significant image structures. We assess the methods on the Optical Coherence Tomography Image Database (OCTID), consisting of 572 spectral domain OCT volumetric scans in five categories. Our proposed S-DDL and WST-based methods achieved 97.2% accuracy in diagnosing AMD, MH, and Normal categories of OCT images. Additionally, WST achieved 100% accuracy in diagnosing DR or AMD from Normal images. These results are comparable to state-of-the-art methods. Specifically, our proposed method outperforms other methods in detecting one abnormality. |
| format | Article |
| id | doaj-art-ac1ea904ce4e4ba8aa9f06751080e182 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-ac1ea904ce4e4ba8aa9f06751080e1822025-01-03T00:01:52ZengIEEEIEEE Access2169-35362025-01-011359660710.1109/ACCESS.2024.352212210813162Application of Deep Dictionary Learning and Predefined Filters for Classification of Retinal Optical Coherence Tomography ImagesFariba Shaker0Zahra Baharlouei1https://orcid.org/0000-0003-4124-2180Gerlind Plonka2https://orcid.org/0000-0002-3232-0573Hossein Rabbani3https://orcid.org/0000-0002-0551-3636Medical Image and Signal Processing Research Center, School of Advanced Technologies in Medicine, Isfahan University of Medical Sciences, Isfahan, IranMedical Image and Signal Processing Research Center, School of Advanced Technologies in Medicine, Isfahan University of Medical Sciences, Isfahan, IranInstitute for Numerical and Applied Mathematics, Georg August University of Göttingen, Göttingen, GermanyMedical Image and Signal Processing Research Center, School of Advanced Technologies in Medicine, Isfahan University of Medical Sciences, Isfahan, IranIn recent years, deep learning methods have excelled in Optical Coherence Tomography (OCT) image classification but demand high computational resources and extensive training data. We propose two effective methods for OCT image classification, combining the strength of deep learning with sparse representation of significant image features for improved detection of retinal abnormalities. The first method, Simplified Deep Dictionary Learning (S-DDL), is based on deep dictionary learning, where the loss function enforces a sparse feature representation of input image patches before classification. The second method uses the Wavelet Scattering Transform (WST), which employs predefined filters in network layers. We compare its performance with the S-DDL method. WST is a convolutional network with predefined wavelet filters that do not need to be learned, requiring lower processing time and complexity. Both methods can be directly applied to raw image data without time-consuming pre-processing, as the first layers act like denoising filters to achieve sparse significant image structures. We assess the methods on the Optical Coherence Tomography Image Database (OCTID), consisting of 572 spectral domain OCT volumetric scans in five categories. Our proposed S-DDL and WST-based methods achieved 97.2% accuracy in diagnosing AMD, MH, and Normal categories of OCT images. Additionally, WST achieved 100% accuracy in diagnosing DR or AMD from Normal images. These results are comparable to state-of-the-art methods. Specifically, our proposed method outperforms other methods in detecting one abnormality.https://ieeexplore.ieee.org/document/10813162/Deep dictionary learningoptical coherence tomography image databasewavelet scattering transform |
| spellingShingle | Fariba Shaker Zahra Baharlouei Gerlind Plonka Hossein Rabbani Application of Deep Dictionary Learning and Predefined Filters for Classification of Retinal Optical Coherence Tomography Images IEEE Access Deep dictionary learning optical coherence tomography image database wavelet scattering transform |
| title | Application of Deep Dictionary Learning and Predefined Filters for Classification of Retinal Optical Coherence Tomography Images |
| title_full | Application of Deep Dictionary Learning and Predefined Filters for Classification of Retinal Optical Coherence Tomography Images |
| title_fullStr | Application of Deep Dictionary Learning and Predefined Filters for Classification of Retinal Optical Coherence Tomography Images |
| title_full_unstemmed | Application of Deep Dictionary Learning and Predefined Filters for Classification of Retinal Optical Coherence Tomography Images |
| title_short | Application of Deep Dictionary Learning and Predefined Filters for Classification of Retinal Optical Coherence Tomography Images |
| title_sort | application of deep dictionary learning and predefined filters for classification of retinal optical coherence tomography images |
| topic | Deep dictionary learning optical coherence tomography image database wavelet scattering transform |
| url | https://ieeexplore.ieee.org/document/10813162/ |
| work_keys_str_mv | AT faribashaker applicationofdeepdictionarylearningandpredefinedfiltersforclassificationofretinalopticalcoherencetomographyimages AT zahrabaharlouei applicationofdeepdictionarylearningandpredefinedfiltersforclassificationofretinalopticalcoherencetomographyimages AT gerlindplonka applicationofdeepdictionarylearningandpredefinedfiltersforclassificationofretinalopticalcoherencetomographyimages AT hosseinrabbani applicationofdeepdictionarylearningandpredefinedfiltersforclassificationofretinalopticalcoherencetomographyimages |