Improved lung nodule segmentation with a squeeze excitation dilated attention based residual UNet
Abstract The diverse types and sizes, proximity to non-nodule structures, identical shape characteristics, and varying sizes of nodules make them challenging for segmentation methods. Although many efforts have been made in automatic lung nodule segmentation, most of them have not sufficiently addre...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-85199-5 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571787656822784 |
|---|---|
| author | Dhafer Alhajim Karim Ansari-Asl Gholamreza Akbarizadeh Mehdi Naderi Soorki |
| author_facet | Dhafer Alhajim Karim Ansari-Asl Gholamreza Akbarizadeh Mehdi Naderi Soorki |
| author_sort | Dhafer Alhajim |
| collection | DOAJ |
| description | Abstract The diverse types and sizes, proximity to non-nodule structures, identical shape characteristics, and varying sizes of nodules make them challenging for segmentation methods. Although many efforts have been made in automatic lung nodule segmentation, most of them have not sufficiently addressed the challenges related to the type and size of nodules, such as juxta-pleural and juxta-vascular nodules. The current research introduces a Squeeze-Excitation Dilated Attention-based Residual U-Net (SEDARU-Net) with a robust intensity normalization technique to address the challenges related to different types and sizes of lung nodules and to achieve an improved lung nodule segmentation. After preprocessing the images with the intensity normalization method and extracting the Regions of Interest by YOLOv3, they are fed into the SEDARU-Net with dilated convolutions in the encoder part. Then, the extracted features are given to the decoder part, which involves transposed convolutions, Squeeze-Excitation Dilated Residual blocks, and skip connections equipped with an Attention Gate, to decode the feature maps and construct the segmentation mask. The proposed model was evaluated using the publicly available Lung Nodule Analysis 2016 (LUNA16) dataset, achieving a Dice Similarity Coefficient of 97.86%, IoU of 96.40%, sensitivity of 96.54%, and precision of 98.84%. Finally, it was shown that each added component to the U-Net’s structure and the intensity normalization technique increased the Dice Similarity Coefficient by more than 2%. The proposed method suggests a potential clinical tool to address challenges related to the segmentation of lung nodules with different types located in the proximity of non-nodule structures. |
| format | Article |
| id | doaj-art-56389e2d502843b2bf3917eb33ff54c5 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-56389e2d502843b2bf3917eb33ff54c52025-02-02T12:17:49ZengNature PortfolioScientific Reports2045-23222025-01-0115111710.1038/s41598-025-85199-5Improved lung nodule segmentation with a squeeze excitation dilated attention based residual UNetDhafer Alhajim0Karim Ansari-Asl1Gholamreza Akbarizadeh2Mehdi Naderi Soorki3Department of Electrical Engineering, Faculty of Engineering, Shahid Chamran University of AhvazDepartment of Electrical Engineering, Faculty of Engineering, Shahid Chamran University of AhvazDepartment of Electrical Engineering, Faculty of Engineering, Shahid Chamran University of AhvazDepartment of Electrical Engineering, Faculty of Engineering, Shahid Chamran University of AhvazAbstract The diverse types and sizes, proximity to non-nodule structures, identical shape characteristics, and varying sizes of nodules make them challenging for segmentation methods. Although many efforts have been made in automatic lung nodule segmentation, most of them have not sufficiently addressed the challenges related to the type and size of nodules, such as juxta-pleural and juxta-vascular nodules. The current research introduces a Squeeze-Excitation Dilated Attention-based Residual U-Net (SEDARU-Net) with a robust intensity normalization technique to address the challenges related to different types and sizes of lung nodules and to achieve an improved lung nodule segmentation. After preprocessing the images with the intensity normalization method and extracting the Regions of Interest by YOLOv3, they are fed into the SEDARU-Net with dilated convolutions in the encoder part. Then, the extracted features are given to the decoder part, which involves transposed convolutions, Squeeze-Excitation Dilated Residual blocks, and skip connections equipped with an Attention Gate, to decode the feature maps and construct the segmentation mask. The proposed model was evaluated using the publicly available Lung Nodule Analysis 2016 (LUNA16) dataset, achieving a Dice Similarity Coefficient of 97.86%, IoU of 96.40%, sensitivity of 96.54%, and precision of 98.84%. Finally, it was shown that each added component to the U-Net’s structure and the intensity normalization technique increased the Dice Similarity Coefficient by more than 2%. The proposed method suggests a potential clinical tool to address challenges related to the segmentation of lung nodules with different types located in the proximity of non-nodule structures.https://doi.org/10.1038/s41598-025-85199-5Lung noduleSegmentationDeep learningIntensity normalizationAttention |
| spellingShingle | Dhafer Alhajim Karim Ansari-Asl Gholamreza Akbarizadeh Mehdi Naderi Soorki Improved lung nodule segmentation with a squeeze excitation dilated attention based residual UNet Scientific Reports Lung nodule Segmentation Deep learning Intensity normalization Attention |
| title | Improved lung nodule segmentation with a squeeze excitation dilated attention based residual UNet |
| title_full | Improved lung nodule segmentation with a squeeze excitation dilated attention based residual UNet |
| title_fullStr | Improved lung nodule segmentation with a squeeze excitation dilated attention based residual UNet |
| title_full_unstemmed | Improved lung nodule segmentation with a squeeze excitation dilated attention based residual UNet |
| title_short | Improved lung nodule segmentation with a squeeze excitation dilated attention based residual UNet |
| title_sort | improved lung nodule segmentation with a squeeze excitation dilated attention based residual unet |
| topic | Lung nodule Segmentation Deep learning Intensity normalization Attention |
| url | https://doi.org/10.1038/s41598-025-85199-5 |
| work_keys_str_mv | AT dhaferalhajim improvedlungnodulesegmentationwithasqueezeexcitationdilatedattentionbasedresidualunet AT karimansariasl improvedlungnodulesegmentationwithasqueezeexcitationdilatedattentionbasedresidualunet AT gholamrezaakbarizadeh improvedlungnodulesegmentationwithasqueezeexcitationdilatedattentionbasedresidualunet AT mehdinaderisoorki improvedlungnodulesegmentationwithasqueezeexcitationdilatedattentionbasedresidualunet |