A Transfer Learning Approach on the Optimization of Edge Detectors for Medical Images Using Particle Swarm Optimization
Edge detection is a fundamental image analysis task, as it provides insight on the content of an image. There are weaknesses in some of the edge detectors developed until now, such as disconnected edges, the impossibility to detect branching edges, or the need for a ground truth that is not always a...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-03-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/23/4/414 |
| _version_ | 1827696341082439680 |
|---|---|
| author | Delia Dumitru Laura Dioșan Anca Andreica Zoltán Bálint |
| author_facet | Delia Dumitru Laura Dioșan Anca Andreica Zoltán Bálint |
| author_sort | Delia Dumitru |
| collection | DOAJ |
| description | Edge detection is a fundamental image analysis task, as it provides insight on the content of an image. There are weaknesses in some of the edge detectors developed until now, such as disconnected edges, the impossibility to detect branching edges, or the need for a ground truth that is not always accessible. Therefore, a specialized detector that is optimized for the image particularities can help improve edge detection performance. In this paper, we apply transfer learning to optimize cellular automata (CA) rules for edge detection using particle swarm optimization (PSO). Cellular automata provide fast computation, while rule optimization provides adaptability to the properties of the target images. We use transfer learning from synthetic to medical images because expert-annotated medical data is typically difficult to obtain. We show that our method is tunable for medical images with different properties, and we show that, for more difficult edge detection tasks, batch optimization can be used to boost the quality of the edges. Our method is suitable for the identification of structures, such as cardiac cavities on medical images, and could be used as a component of an automatic radiology decision support tool. |
| first_indexed | 2024-03-10T12:45:18Z |
| format | Article |
| id | doaj.art-34d2a83adf44407088b85daecd094534 |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-03-10T12:45:18Z |
| publishDate | 2021-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-34d2a83adf44407088b85daecd0945342023-11-21T13:33:31ZengMDPI AGEntropy1099-43002021-03-0123441410.3390/e23040414A Transfer Learning Approach on the Optimization of Edge Detectors for Medical Images Using Particle Swarm OptimizationDelia Dumitru0Laura Dioșan1Anca Andreica2Zoltán Bálint3IMOGEN Research Institute, County Clinical Emergency Hospital, 400006 Cluj-Napoca, RomaniaIMOGEN Research Institute, County Clinical Emergency Hospital, 400006 Cluj-Napoca, RomaniaIMOGEN Research Institute, County Clinical Emergency Hospital, 400006 Cluj-Napoca, RomaniaIMOGEN Research Institute, County Clinical Emergency Hospital, 400006 Cluj-Napoca, RomaniaEdge detection is a fundamental image analysis task, as it provides insight on the content of an image. There are weaknesses in some of the edge detectors developed until now, such as disconnected edges, the impossibility to detect branching edges, or the need for a ground truth that is not always accessible. Therefore, a specialized detector that is optimized for the image particularities can help improve edge detection performance. In this paper, we apply transfer learning to optimize cellular automata (CA) rules for edge detection using particle swarm optimization (PSO). Cellular automata provide fast computation, while rule optimization provides adaptability to the properties of the target images. We use transfer learning from synthetic to medical images because expert-annotated medical data is typically difficult to obtain. We show that our method is tunable for medical images with different properties, and we show that, for more difficult edge detection tasks, batch optimization can be used to boost the quality of the edges. Our method is suitable for the identification of structures, such as cardiac cavities on medical images, and could be used as a component of an automatic radiology decision support tool.https://www.mdpi.com/1099-4300/23/4/414edge detectionevolutionary algorithmscellular automataparticle swarm optimizationimage processingtransfer learning |
| spellingShingle | Delia Dumitru Laura Dioșan Anca Andreica Zoltán Bálint A Transfer Learning Approach on the Optimization of Edge Detectors for Medical Images Using Particle Swarm Optimization Entropy edge detection evolutionary algorithms cellular automata particle swarm optimization image processing transfer learning |
| title | A Transfer Learning Approach on the Optimization of Edge Detectors for Medical Images Using Particle Swarm Optimization |
| title_full | A Transfer Learning Approach on the Optimization of Edge Detectors for Medical Images Using Particle Swarm Optimization |
| title_fullStr | A Transfer Learning Approach on the Optimization of Edge Detectors for Medical Images Using Particle Swarm Optimization |
| title_full_unstemmed | A Transfer Learning Approach on the Optimization of Edge Detectors for Medical Images Using Particle Swarm Optimization |
| title_short | A Transfer Learning Approach on the Optimization of Edge Detectors for Medical Images Using Particle Swarm Optimization |
| title_sort | transfer learning approach on the optimization of edge detectors for medical images using particle swarm optimization |
| topic | edge detection evolutionary algorithms cellular automata particle swarm optimization image processing transfer learning |
| url | https://www.mdpi.com/1099-4300/23/4/414 |
| work_keys_str_mv | AT deliadumitru atransferlearningapproachontheoptimizationofedgedetectorsformedicalimagesusingparticleswarmoptimization AT lauradiosan atransferlearningapproachontheoptimizationofedgedetectorsformedicalimagesusingparticleswarmoptimization AT ancaandreica atransferlearningapproachontheoptimizationofedgedetectorsformedicalimagesusingparticleswarmoptimization AT zoltanbalint atransferlearningapproachontheoptimizationofedgedetectorsformedicalimagesusingparticleswarmoptimization AT deliadumitru transferlearningapproachontheoptimizationofedgedetectorsformedicalimagesusingparticleswarmoptimization AT lauradiosan transferlearningapproachontheoptimizationofedgedetectorsformedicalimagesusingparticleswarmoptimization AT ancaandreica transferlearningapproachontheoptimizationofedgedetectorsformedicalimagesusingparticleswarmoptimization AT zoltanbalint transferlearningapproachontheoptimizationofedgedetectorsformedicalimagesusingparticleswarmoptimization |