Automated assessment of the smoothness of retinal layers in optical coherence tomography images using a machine learning algorithm
Abstract Quantifying the smoothness of different layers of the retina can potentially be an important and practical biomarker in various pathologic conditions like diabetic retinopathy. The purpose of this study is to develop an automated machine learning algorithm which uses support vector regressi...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2023-02-01
|
| Series: | BMC Medical Imaging |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12880-023-00976-w |
| _version_ | 1811171514563690496 |
|---|---|
| author | Jamshid Saeidian Tahereh Mahmoudi Hamid Riazi-Esfahani Zahra Montazeriani Alireza Khodabande Mohammad Zarei Nazanin Ebrahimiadib Behzad Jafari Alireza Afzal Aghaei Hossein Azimi Elias Khalili Pour |
| author_facet | Jamshid Saeidian Tahereh Mahmoudi Hamid Riazi-Esfahani Zahra Montazeriani Alireza Khodabande Mohammad Zarei Nazanin Ebrahimiadib Behzad Jafari Alireza Afzal Aghaei Hossein Azimi Elias Khalili Pour |
| author_sort | Jamshid Saeidian |
| collection | DOAJ |
| description | Abstract Quantifying the smoothness of different layers of the retina can potentially be an important and practical biomarker in various pathologic conditions like diabetic retinopathy. The purpose of this study is to develop an automated machine learning algorithm which uses support vector regression method with wavelet kernel and automatically segments two hyperreflective retinal layers (inner plexiform layer (IPL) and outer plexiform layer (OPL)) in 50 optical coherence tomography (OCT) slabs and calculates the smoothness index (SI). The Bland–Altman plots, mean absolute error, root mean square error and signed error calculations revealed a modest discrepancy between the manual approach, used as the ground truth, and the corresponding automated segmentation of IPL/ OPL, as well as SI measurements in OCT slabs. It was concluded that the constructed algorithm may be employed as a reliable, rapid and convenient approach for segmenting IPL/OPL and calculating SI in the appropriate layers. |
| first_indexed | 2024-04-10T17:15:16Z |
| format | Article |
| id | doaj.art-868a4373826b47bf82d8e212fcde8bd8 |
| institution | Directory Open Access Journal |
| issn | 1471-2342 |
| language | English |
| last_indexed | 2024-04-10T17:15:16Z |
| publishDate | 2023-02-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Imaging |
| spelling | doaj.art-868a4373826b47bf82d8e212fcde8bd82023-02-05T12:27:10ZengBMCBMC Medical Imaging1471-23422023-02-0123111610.1186/s12880-023-00976-wAutomated assessment of the smoothness of retinal layers in optical coherence tomography images using a machine learning algorithmJamshid Saeidian0Tahereh Mahmoudi1Hamid Riazi-Esfahani2Zahra Montazeriani3Alireza Khodabande4Mohammad Zarei5Nazanin Ebrahimiadib6Behzad Jafari7Alireza Afzal Aghaei8Hossein Azimi9Elias Khalili Pour10Faculty of Mathematical Sciences and Computer, Kharazmi UniversityDepartment of Medical Physics and Biomedical Engineering, Tehran University of Medical Sciences and Research Center for Science and Technology in MedicineRetina Service, Farabi Eye Hospital, Tehran University of Medical SciencesDepartment of Medical Physics and Biomedical Engineering, Tehran University of Medical Sciences and Research Center for Science and Technology in MedicineRetina Service, Farabi Eye Hospital, Tehran University of Medical SciencesRetina Service, Farabi Eye Hospital, Tehran University of Medical SciencesRetina Service, Farabi Eye Hospital, Tehran University of Medical SciencesRetina Service, Farabi Eye Hospital, Tehran University of Medical SciencesDepartment of Computer Sciences, Faculty of Mathematical Sciences, Shahid Beheshti UniversityFaculty of Mathematical Sciences and Computer, Kharazmi UniversityRetina Service, Farabi Eye Hospital, Tehran University of Medical SciencesAbstract Quantifying the smoothness of different layers of the retina can potentially be an important and practical biomarker in various pathologic conditions like diabetic retinopathy. The purpose of this study is to develop an automated machine learning algorithm which uses support vector regression method with wavelet kernel and automatically segments two hyperreflective retinal layers (inner plexiform layer (IPL) and outer plexiform layer (OPL)) in 50 optical coherence tomography (OCT) slabs and calculates the smoothness index (SI). The Bland–Altman plots, mean absolute error, root mean square error and signed error calculations revealed a modest discrepancy between the manual approach, used as the ground truth, and the corresponding automated segmentation of IPL/ OPL, as well as SI measurements in OCT slabs. It was concluded that the constructed algorithm may be employed as a reliable, rapid and convenient approach for segmenting IPL/OPL and calculating SI in the appropriate layers.https://doi.org/10.1186/s12880-023-00976-wAutomated segmentationSupport vector regressionInner plexiform layerOuter plexiform LayerBland-Altman plotBiomarker |
| spellingShingle | Jamshid Saeidian Tahereh Mahmoudi Hamid Riazi-Esfahani Zahra Montazeriani Alireza Khodabande Mohammad Zarei Nazanin Ebrahimiadib Behzad Jafari Alireza Afzal Aghaei Hossein Azimi Elias Khalili Pour Automated assessment of the smoothness of retinal layers in optical coherence tomography images using a machine learning algorithm BMC Medical Imaging Automated segmentation Support vector regression Inner plexiform layer Outer plexiform Layer Bland-Altman plot Biomarker |
| title | Automated assessment of the smoothness of retinal layers in optical coherence tomography images using a machine learning algorithm |
| title_full | Automated assessment of the smoothness of retinal layers in optical coherence tomography images using a machine learning algorithm |
| title_fullStr | Automated assessment of the smoothness of retinal layers in optical coherence tomography images using a machine learning algorithm |
| title_full_unstemmed | Automated assessment of the smoothness of retinal layers in optical coherence tomography images using a machine learning algorithm |
| title_short | Automated assessment of the smoothness of retinal layers in optical coherence tomography images using a machine learning algorithm |
| title_sort | automated assessment of the smoothness of retinal layers in optical coherence tomography images using a machine learning algorithm |
| topic | Automated segmentation Support vector regression Inner plexiform layer Outer plexiform Layer Bland-Altman plot Biomarker |
| url | https://doi.org/10.1186/s12880-023-00976-w |
| work_keys_str_mv | AT jamshidsaeidian automatedassessmentofthesmoothnessofretinallayersinopticalcoherencetomographyimagesusingamachinelearningalgorithm AT taherehmahmoudi automatedassessmentofthesmoothnessofretinallayersinopticalcoherencetomographyimagesusingamachinelearningalgorithm AT hamidriaziesfahani automatedassessmentofthesmoothnessofretinallayersinopticalcoherencetomographyimagesusingamachinelearningalgorithm AT zahramontazeriani automatedassessmentofthesmoothnessofretinallayersinopticalcoherencetomographyimagesusingamachinelearningalgorithm AT alirezakhodabande automatedassessmentofthesmoothnessofretinallayersinopticalcoherencetomographyimagesusingamachinelearningalgorithm AT mohammadzarei automatedassessmentofthesmoothnessofretinallayersinopticalcoherencetomographyimagesusingamachinelearningalgorithm AT nazaninebrahimiadib automatedassessmentofthesmoothnessofretinallayersinopticalcoherencetomographyimagesusingamachinelearningalgorithm AT behzadjafari automatedassessmentofthesmoothnessofretinallayersinopticalcoherencetomographyimagesusingamachinelearningalgorithm AT alirezaafzalaghaei automatedassessmentofthesmoothnessofretinallayersinopticalcoherencetomographyimagesusingamachinelearningalgorithm AT hosseinazimi automatedassessmentofthesmoothnessofretinallayersinopticalcoherencetomographyimagesusingamachinelearningalgorithm AT eliaskhalilipour automatedassessmentofthesmoothnessofretinallayersinopticalcoherencetomographyimagesusingamachinelearningalgorithm |