Parameter-Free Matrix Decomposition for Specular Reflections Removal in Endoscopic Images
<italic>Objective:</italic> Endoscopy is a medical diagnostic procedure used to see inside the human body with the help of a camera-attached system called the endoscope. Endoscopic images and videos suffer from specular reflections (or highlight) and can have an adverse impact on the dia...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Journal of Translational Engineering in Health and Medicine |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10144758/ |
| _version_ | 1797800021113962496 |
|---|---|
| author | Jithin Joseph Sudhish N. George Kiran Raja |
| author_facet | Jithin Joseph Sudhish N. George Kiran Raja |
| author_sort | Jithin Joseph |
| collection | DOAJ |
| description | <italic>Objective:</italic> Endoscopy is a medical diagnostic procedure used to see inside the human body with the help of a camera-attached system called the endoscope. Endoscopic images and videos suffer from specular reflections (or highlight) and can have an adverse impact on the diagnostic quality of images. These scattered white regions severely affect the visual appearance of images for both endoscopists and the computer-aided diagnosis of diseases. Methods & Results: We introduce a new parameter-free matrix decomposition technique to remove the specular reflections. The proposed method decomposes the original image into a highlight-free pseudo-low-rank component and a highlight component. Along with the highlight removal, the approach also removes the boundary artifacts present around the highlight regions, unlike the previous works based on family of Robust Principal Component Analysis (RPCA). The approach is evaluated on three publicly available endoscopy datasets: Kvasir Polyp, Kvasir Normal-Pylorus and Kvasir Capsule datasets. Our evaluation is benchmarked against 4 different state-of-the-art approaches using three different well-used metrics such as Structural Similarity Index Measure (SSIM), Percentage of highlights remaining and Coefficient of Variation (CoV). Conclusions: The results show significant improvements over the compared methods on all three metrics. The approach is further validated for statistical significance where it emerges better than other state-of-the-art approaches.<italic>Clinical and Translational Impact Statement—</italic>The mathematical concepts of low rank and rank decomposition in matrix algebra are translated to remove specularities in the endoscopic images The result shows the impact of the proposed method in removing specular reflections from endoscopic images indicating improved diagnosis efficiency for both endoscopists and computer-aided diagnosis systems |
| first_indexed | 2024-03-13T04:27:43Z |
| format | Article |
| id | doaj.art-49d5415440b24d82b091ec85c2b3891d |
| institution | Directory Open Access Journal |
| issn | 2168-2372 |
| language | English |
| last_indexed | 2024-03-13T04:27:43Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Translational Engineering in Health and Medicine |
| spelling | doaj.art-49d5415440b24d82b091ec85c2b3891d2023-06-19T23:00:26ZengIEEEIEEE Journal of Translational Engineering in Health and Medicine2168-23722023-01-011136037410.1109/JTEHM.2023.328344410144758Parameter-Free Matrix Decomposition for Specular Reflections Removal in Endoscopic ImagesJithin Joseph0https://orcid.org/0000-0002-9825-9752Sudhish N. George1https://orcid.org/0000-0002-0886-9478Kiran Raja2https://orcid.org/0000-0002-9489-5161Department of Electronics and Communication Engineering, National Institute of Technology at Calicut, Kozhikode, IndiaDepartment of Electronics and Communication Engineering, National Institute of Technology at Calicut, Kozhikode, IndiaDepartment of Computer Science, Norwegian University of Science and Technology, Trondheim, Norway<italic>Objective:</italic> Endoscopy is a medical diagnostic procedure used to see inside the human body with the help of a camera-attached system called the endoscope. Endoscopic images and videos suffer from specular reflections (or highlight) and can have an adverse impact on the diagnostic quality of images. These scattered white regions severely affect the visual appearance of images for both endoscopists and the computer-aided diagnosis of diseases. Methods & Results: We introduce a new parameter-free matrix decomposition technique to remove the specular reflections. The proposed method decomposes the original image into a highlight-free pseudo-low-rank component and a highlight component. Along with the highlight removal, the approach also removes the boundary artifacts present around the highlight regions, unlike the previous works based on family of Robust Principal Component Analysis (RPCA). The approach is evaluated on three publicly available endoscopy datasets: Kvasir Polyp, Kvasir Normal-Pylorus and Kvasir Capsule datasets. Our evaluation is benchmarked against 4 different state-of-the-art approaches using three different well-used metrics such as Structural Similarity Index Measure (SSIM), Percentage of highlights remaining and Coefficient of Variation (CoV). Conclusions: The results show significant improvements over the compared methods on all three metrics. The approach is further validated for statistical significance where it emerges better than other state-of-the-art approaches.<italic>Clinical and Translational Impact Statement—</italic>The mathematical concepts of low rank and rank decomposition in matrix algebra are translated to remove specularities in the endoscopic images The result shows the impact of the proposed method in removing specular reflections from endoscopic images indicating improved diagnosis efficiency for both endoscopists and computer-aided diagnosis systemshttps://ieeexplore.ieee.org/document/10144758/Specular reflectionssingular value thresholdinglow rank and sparse decomposition |
| spellingShingle | Jithin Joseph Sudhish N. George Kiran Raja Parameter-Free Matrix Decomposition for Specular Reflections Removal in Endoscopic Images IEEE Journal of Translational Engineering in Health and Medicine Specular reflections singular value thresholding low rank and sparse decomposition |
| title | Parameter-Free Matrix Decomposition for Specular Reflections Removal in Endoscopic Images |
| title_full | Parameter-Free Matrix Decomposition for Specular Reflections Removal in Endoscopic Images |
| title_fullStr | Parameter-Free Matrix Decomposition for Specular Reflections Removal in Endoscopic Images |
| title_full_unstemmed | Parameter-Free Matrix Decomposition for Specular Reflections Removal in Endoscopic Images |
| title_short | Parameter-Free Matrix Decomposition for Specular Reflections Removal in Endoscopic Images |
| title_sort | parameter free matrix decomposition for specular reflections removal in endoscopic images |
| topic | Specular reflections singular value thresholding low rank and sparse decomposition |
| url | https://ieeexplore.ieee.org/document/10144758/ |
| work_keys_str_mv | AT jithinjoseph parameterfreematrixdecompositionforspecularreflectionsremovalinendoscopicimages AT sudhishngeorge parameterfreematrixdecompositionforspecularreflectionsremovalinendoscopicimages AT kiranraja parameterfreematrixdecompositionforspecularreflectionsremovalinendoscopicimages |