Multiscale and Hierarchical Feature-Aggregation Network for Segmenting Medical Images
We propose an encoder–decoder architecture using wide and deep convolutional layers combined with different aggregation modules for the segmentation of medical images. Initially, we obtain a rich representation of features that span from low to high levels and from small to large scales by stacking...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/9/3440 |
| _version_ | 1797502805790949376 |
|---|---|
| author | Nagaraj Yamanakkanavar Jae Young Choi Bumshik Lee |
| author_facet | Nagaraj Yamanakkanavar Jae Young Choi Bumshik Lee |
| author_sort | Nagaraj Yamanakkanavar |
| collection | DOAJ |
| description | We propose an encoder–decoder architecture using wide and deep convolutional layers combined with different aggregation modules for the segmentation of medical images. Initially, we obtain a rich representation of features that span from low to high levels and from small to large scales by stacking multiple <i>k</i> × <i>k</i> kernels, where each <i>k</i> × <i>k</i> kernel operation is split into <i>k</i> × 1 and 1 × <i>k</i> convolutions. In addition, we introduce two feature-aggregation modules—multiscale feature aggregation (<i>MFA</i>) and hierarchical feature aggregation (<i>HFA</i>)—to better fuse information across end-to-end network layers. The <i>MFA</i> module progressively aggregates features and enriches feature representation, whereas the <i>HFA</i> module merges the features iteratively and hierarchically to learn richer combinations of the feature hierarchy. Furthermore, because residual connections are advantageous for assembling very deep networks, we employ an <i>MFA</i>-based long residual connections to avoid vanishing gradients along the aggregation paths. In addition, a guided block with multilevel convolution provides effective attention to the features that were copied from the encoder to the decoder to recover spatial information. Thus, the proposed method using feature-aggregation modules combined with a guided skip connection improves the segmentation accuracy, achieving a high similarity index for ground-truth segmentation maps. Experimental results indicate that the proposed model achieves a superior segmentation performance to that obtained by conventional methods for skin-lesion segmentation, with an average accuracy score of 0.97 on the ISIC-2018, PH2, and UFBA-UESC datasets. |
| first_indexed | 2024-03-10T03:41:23Z |
| format | Article |
| id | doaj.art-bf8459ef12ed4a3d8ab96d67cbc76b6b |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T03:41:23Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-bf8459ef12ed4a3d8ab96d67cbc76b6b2023-11-23T09:18:31ZengMDPI AGSensors1424-82202022-04-01229344010.3390/s22093440Multiscale and Hierarchical Feature-Aggregation Network for Segmenting Medical ImagesNagaraj Yamanakkanavar0Jae Young Choi1Bumshik Lee2Department of Information and Communications Engineering, Chosun University, Gwangju 61452, KoreaDivision of Computer & Electronic Systems Engineering, Hankuk University of Foreign Studies, Yongin 17035, KoreaDepartment of Information and Communications Engineering, Chosun University, Gwangju 61452, KoreaWe propose an encoder–decoder architecture using wide and deep convolutional layers combined with different aggregation modules for the segmentation of medical images. Initially, we obtain a rich representation of features that span from low to high levels and from small to large scales by stacking multiple <i>k</i> × <i>k</i> kernels, where each <i>k</i> × <i>k</i> kernel operation is split into <i>k</i> × 1 and 1 × <i>k</i> convolutions. In addition, we introduce two feature-aggregation modules—multiscale feature aggregation (<i>MFA</i>) and hierarchical feature aggregation (<i>HFA</i>)—to better fuse information across end-to-end network layers. The <i>MFA</i> module progressively aggregates features and enriches feature representation, whereas the <i>HFA</i> module merges the features iteratively and hierarchically to learn richer combinations of the feature hierarchy. Furthermore, because residual connections are advantageous for assembling very deep networks, we employ an <i>MFA</i>-based long residual connections to avoid vanishing gradients along the aggregation paths. In addition, a guided block with multilevel convolution provides effective attention to the features that were copied from the encoder to the decoder to recover spatial information. Thus, the proposed method using feature-aggregation modules combined with a guided skip connection improves the segmentation accuracy, achieving a high similarity index for ground-truth segmentation maps. Experimental results indicate that the proposed model achieves a superior segmentation performance to that obtained by conventional methods for skin-lesion segmentation, with an average accuracy score of 0.97 on the ISIC-2018, PH2, and UFBA-UESC datasets.https://www.mdpi.com/1424-8220/22/9/3440convolutional neural networkmedical-image segmentationfeature fusion |
| spellingShingle | Nagaraj Yamanakkanavar Jae Young Choi Bumshik Lee Multiscale and Hierarchical Feature-Aggregation Network for Segmenting Medical Images Sensors convolutional neural network medical-image segmentation feature fusion |
| title | Multiscale and Hierarchical Feature-Aggregation Network for Segmenting Medical Images |
| title_full | Multiscale and Hierarchical Feature-Aggregation Network for Segmenting Medical Images |
| title_fullStr | Multiscale and Hierarchical Feature-Aggregation Network for Segmenting Medical Images |
| title_full_unstemmed | Multiscale and Hierarchical Feature-Aggregation Network for Segmenting Medical Images |
| title_short | Multiscale and Hierarchical Feature-Aggregation Network for Segmenting Medical Images |
| title_sort | multiscale and hierarchical feature aggregation network for segmenting medical images |
| topic | convolutional neural network medical-image segmentation feature fusion |
| url | https://www.mdpi.com/1424-8220/22/9/3440 |
| work_keys_str_mv | AT nagarajyamanakkanavar multiscaleandhierarchicalfeatureaggregationnetworkforsegmentingmedicalimages AT jaeyoungchoi multiscaleandhierarchicalfeatureaggregationnetworkforsegmentingmedicalimages AT bumshiklee multiscaleandhierarchicalfeatureaggregationnetworkforsegmentingmedicalimages |