Mixed-Sized Biomedical Image Segmentation Based on U-Net Architectures
Convolutional neural networks (CNNs) are becoming increasingly popular in medical Image Segmentation. Among them, U-Net is a widely used model that can lead to cutting-edge results for 2D biomedical Image Segmentation. However, U-Net performance can be influenced by many factors, such as the size of...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/1/329 |
| _version_ | 1797626298060767232 |
|---|---|
| author | Priscilla Benedetti Mauro Femminella Gianluca Reali |
| author_facet | Priscilla Benedetti Mauro Femminella Gianluca Reali |
| author_sort | Priscilla Benedetti |
| collection | DOAJ |
| description | Convolutional neural networks (CNNs) are becoming increasingly popular in medical Image Segmentation. Among them, U-Net is a widely used model that can lead to cutting-edge results for 2D biomedical Image Segmentation. However, U-Net performance can be influenced by many factors, such as the size of the training dataset, the performance metrics used, the quality of the images and, in particular, the shape and size of the organ to be segmented. This could entail a loss of robustness of the U-Net-based models. In this paper, the performance of the considered networks is determined by using the publicly available images from the 3D-IRCADb-01 dataset. Different organs with different features are considered. Experimental results show that the U-Net-based segmentation performance decreases when organs with sparse binary masks are considered. The solution proposed in this paper, based on automated zooming of the parts of interest, allows improving the performance of the segmentation model by up to 20% in terms of Dice coefficient metric, when very sparse segmentation images are used, without affecting the cost of the learning process. |
| first_indexed | 2024-03-11T10:08:25Z |
| format | Article |
| id | doaj.art-f1e999c7705b44e092929b0dab0d06c4 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T10:08:25Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-f1e999c7705b44e092929b0dab0d06c42023-11-16T14:55:30ZengMDPI AGApplied Sciences2076-34172022-12-0113132910.3390/app13010329Mixed-Sized Biomedical Image Segmentation Based on U-Net ArchitecturesPriscilla Benedetti0Mauro Femminella1Gianluca Reali2Department of Engineering, University of Perugia, Via G. Duranti 93, 06125 Perugia, ItalyDepartment of Engineering, University of Perugia, Via G. Duranti 93, 06125 Perugia, ItalyDepartment of Engineering, University of Perugia, Via G. Duranti 93, 06125 Perugia, ItalyConvolutional neural networks (CNNs) are becoming increasingly popular in medical Image Segmentation. Among them, U-Net is a widely used model that can lead to cutting-edge results for 2D biomedical Image Segmentation. However, U-Net performance can be influenced by many factors, such as the size of the training dataset, the performance metrics used, the quality of the images and, in particular, the shape and size of the organ to be segmented. This could entail a loss of robustness of the U-Net-based models. In this paper, the performance of the considered networks is determined by using the publicly available images from the 3D-IRCADb-01 dataset. Different organs with different features are considered. Experimental results show that the U-Net-based segmentation performance decreases when organs with sparse binary masks are considered. The solution proposed in this paper, based on automated zooming of the parts of interest, allows improving the performance of the segmentation model by up to 20% in terms of Dice coefficient metric, when very sparse segmentation images are used, without affecting the cost of the learning process.https://www.mdpi.com/2076-3417/13/1/329Image Segmentationconvolutional neural networksbiomedical image analysis |
| spellingShingle | Priscilla Benedetti Mauro Femminella Gianluca Reali Mixed-Sized Biomedical Image Segmentation Based on U-Net Architectures Applied Sciences Image Segmentation convolutional neural networks biomedical image analysis |
| title | Mixed-Sized Biomedical Image Segmentation Based on U-Net Architectures |
| title_full | Mixed-Sized Biomedical Image Segmentation Based on U-Net Architectures |
| title_fullStr | Mixed-Sized Biomedical Image Segmentation Based on U-Net Architectures |
| title_full_unstemmed | Mixed-Sized Biomedical Image Segmentation Based on U-Net Architectures |
| title_short | Mixed-Sized Biomedical Image Segmentation Based on U-Net Architectures |
| title_sort | mixed sized biomedical image segmentation based on u net architectures |
| topic | Image Segmentation convolutional neural networks biomedical image analysis |
| url | https://www.mdpi.com/2076-3417/13/1/329 |
| work_keys_str_mv | AT priscillabenedetti mixedsizedbiomedicalimagesegmentationbasedonunetarchitectures AT maurofemminella mixedsizedbiomedicalimagesegmentationbasedonunetarchitectures AT gianlucareali mixedsizedbiomedicalimagesegmentationbasedonunetarchitectures |