AID-U-Net: An Innovative Deep Convolutional Architecture for Semantic Segmentation of Biomedical Images
Semantic segmentation of biomedical images found its niche in screening and diagnostic applications. Recent methods based on deep learning convolutional neural networks have been very effective, since they are readily adaptive to biomedical applications and outperform other competitive segmentation...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/12/12/2952 |
| _version_ | 1797460643527262208 |
|---|---|
| author | Ashkan Tashk Jürgen Herp Thomas Bjørsum-Meyer Anastasios Koulaouzidis Esmaeil S. Nadimi |
| author_facet | Ashkan Tashk Jürgen Herp Thomas Bjørsum-Meyer Anastasios Koulaouzidis Esmaeil S. Nadimi |
| author_sort | Ashkan Tashk |
| collection | DOAJ |
| description | Semantic segmentation of biomedical images found its niche in screening and diagnostic applications. Recent methods based on deep learning convolutional neural networks have been very effective, since they are readily adaptive to biomedical applications and outperform other competitive segmentation methods. Inspired by the U-Net, we designed a deep learning network with an innovative architecture, hereafter referred to as AID-U-Net. Our network consists of direct contracting and expansive paths, as well as a distinguishing feature of containing sub-contracting and sub-expansive paths. The implementation results on seven totally different databases of medical images demonstrated that our proposed network outperforms the state-of-the-art solutions with no specific pre-trained backbones for both 2D and 3D biomedical image segmentation tasks. Furthermore, we showed that AID-U-Net dramatically reduces time inference and computational complexity in terms of the number of learnable parameters. The results further show that the proposed AID-U-Net can segment different medical objects, achieving an improved 2D F<sub>1</sub>-score and 3D mean BF-score of 3.82% and 2.99%, respectively. |
| first_indexed | 2024-03-09T17:07:59Z |
| format | Article |
| id | doaj.art-01133c255267413da31dcfd9fcaf65a5 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-09T17:07:59Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-01133c255267413da31dcfd9fcaf65a52023-11-24T14:16:05ZengMDPI AGDiagnostics2075-44182022-11-011212295210.3390/diagnostics12122952AID-U-Net: An Innovative Deep Convolutional Architecture for Semantic Segmentation of Biomedical ImagesAshkan Tashk0Jürgen Herp1Thomas Bjørsum-Meyer2Anastasios Koulaouzidis3Esmaeil S. Nadimi4Applied AI and Data Science (AID), Mærsk McKinney Møller Institute (MMMI), University of Southern Denmark, 5230 Odense, DenmarkApplied AI and Data Science (AID), Mærsk McKinney Møller Institute (MMMI), University of Southern Denmark, 5230 Odense, DenmarkDepartment of Surgery, Odense University Hospital, 5000 Odense, DenmarkDepartment of Surgery, Odense University Hospital, 5000 Odense, DenmarkApplied AI and Data Science (AID), Mærsk McKinney Møller Institute (MMMI), University of Southern Denmark, 5230 Odense, DenmarkSemantic segmentation of biomedical images found its niche in screening and diagnostic applications. Recent methods based on deep learning convolutional neural networks have been very effective, since they are readily adaptive to biomedical applications and outperform other competitive segmentation methods. Inspired by the U-Net, we designed a deep learning network with an innovative architecture, hereafter referred to as AID-U-Net. Our network consists of direct contracting and expansive paths, as well as a distinguishing feature of containing sub-contracting and sub-expansive paths. The implementation results on seven totally different databases of medical images demonstrated that our proposed network outperforms the state-of-the-art solutions with no specific pre-trained backbones for both 2D and 3D biomedical image segmentation tasks. Furthermore, we showed that AID-U-Net dramatically reduces time inference and computational complexity in terms of the number of learnable parameters. The results further show that the proposed AID-U-Net can segment different medical objects, achieving an improved 2D F<sub>1</sub>-score and 3D mean BF-score of 3.82% and 2.99%, respectively.https://www.mdpi.com/2075-4418/12/12/2952biomedical imagesconvolutional neural networkssemantic segmentationup and downsampling |
| spellingShingle | Ashkan Tashk Jürgen Herp Thomas Bjørsum-Meyer Anastasios Koulaouzidis Esmaeil S. Nadimi AID-U-Net: An Innovative Deep Convolutional Architecture for Semantic Segmentation of Biomedical Images Diagnostics biomedical images convolutional neural networks semantic segmentation up and downsampling |
| title | AID-U-Net: An Innovative Deep Convolutional Architecture for Semantic Segmentation of Biomedical Images |
| title_full | AID-U-Net: An Innovative Deep Convolutional Architecture for Semantic Segmentation of Biomedical Images |
| title_fullStr | AID-U-Net: An Innovative Deep Convolutional Architecture for Semantic Segmentation of Biomedical Images |
| title_full_unstemmed | AID-U-Net: An Innovative Deep Convolutional Architecture for Semantic Segmentation of Biomedical Images |
| title_short | AID-U-Net: An Innovative Deep Convolutional Architecture for Semantic Segmentation of Biomedical Images |
| title_sort | aid u net an innovative deep convolutional architecture for semantic segmentation of biomedical images |
| topic | biomedical images convolutional neural networks semantic segmentation up and downsampling |
| url | https://www.mdpi.com/2075-4418/12/12/2952 |
| work_keys_str_mv | AT ashkantashk aidunetaninnovativedeepconvolutionalarchitectureforsemanticsegmentationofbiomedicalimages AT jurgenherp aidunetaninnovativedeepconvolutionalarchitectureforsemanticsegmentationofbiomedicalimages AT thomasbjørsummeyer aidunetaninnovativedeepconvolutionalarchitectureforsemanticsegmentationofbiomedicalimages AT anastasioskoulaouzidis aidunetaninnovativedeepconvolutionalarchitectureforsemanticsegmentationofbiomedicalimages AT esmaeilsnadimi aidunetaninnovativedeepconvolutionalarchitectureforsemanticsegmentationofbiomedicalimages |