Lung_PAYNet: a pyramidal attention based deep learning network for lung nodule segmentation
Abstract Accurate and reliable lung nodule segmentation in computed tomography (CT) images is required for early diagnosis of lung cancer. Some of the difficulties in detecting lung nodules include the various types and shapes of lung nodules, lung nodules near other lung structures, and similar vis...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-11-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-022-24900-4 |
| _version_ | 1811210998327017472 |
|---|---|
| author | P. Malin Bruntha S. Immanuel Alex Pandian K. Martin Sagayam Shivargha Bandopadhyay Marc Pomplun Hien Dang |
| author_facet | P. Malin Bruntha S. Immanuel Alex Pandian K. Martin Sagayam Shivargha Bandopadhyay Marc Pomplun Hien Dang |
| author_sort | P. Malin Bruntha |
| collection | DOAJ |
| description | Abstract Accurate and reliable lung nodule segmentation in computed tomography (CT) images is required for early diagnosis of lung cancer. Some of the difficulties in detecting lung nodules include the various types and shapes of lung nodules, lung nodules near other lung structures, and similar visual aspects. This study proposes a new model named Lung_PAYNet, a pyramidal attention-based architecture, for improved lung nodule segmentation in low-dose CT images. In this architecture, the encoder and decoder are designed using an inverted residual block and swish activation function. It also employs a feature pyramid attention network between the encoder and decoder to extract exact dense features for pixel classification. The proposed architecture was compared to the existing UNet architecture, and the proposed methodology yielded significant results. The proposed model was comprehensively trained and validated using the LIDC-IDRI dataset available in the public domain. The experimental results revealed that the Lung_PAYNet delivered remarkable segmentation with a Dice similarity coefficient of 95.7%, mIOU of 91.75%, sensitivity of 92.57%, and precision of 96.75%. |
| first_indexed | 2024-04-12T05:05:30Z |
| format | Article |
| id | doaj.art-f66fba49c2554a57a01205705d2c8ee6 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-12T05:05:30Z |
| publishDate | 2022-11-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-f66fba49c2554a57a01205705d2c8ee62022-12-22T03:46:54ZengNature PortfolioScientific Reports2045-23222022-11-0112111110.1038/s41598-022-24900-4Lung_PAYNet: a pyramidal attention based deep learning network for lung nodule segmentationP. Malin Bruntha0S. Immanuel Alex Pandian1K. Martin Sagayam2Shivargha Bandopadhyay3Marc Pomplun4Hien Dang5Department of Electronics and Communication Engineering, Karunya Institute of Technology and SciencesDepartment of Electronics and Communication Engineering, Karunya Institute of Technology and SciencesDepartment of Electronics and Communication Engineering, Karunya Institute of Technology and SciencesDepartment of Computer Vision & Deep Learning, Orbo.AiDepartment of Computer Science, University of Massachusetts BostonDepartment of Computer Science, University of Massachusetts BostonAbstract Accurate and reliable lung nodule segmentation in computed tomography (CT) images is required for early diagnosis of lung cancer. Some of the difficulties in detecting lung nodules include the various types and shapes of lung nodules, lung nodules near other lung structures, and similar visual aspects. This study proposes a new model named Lung_PAYNet, a pyramidal attention-based architecture, for improved lung nodule segmentation in low-dose CT images. In this architecture, the encoder and decoder are designed using an inverted residual block and swish activation function. It also employs a feature pyramid attention network between the encoder and decoder to extract exact dense features for pixel classification. The proposed architecture was compared to the existing UNet architecture, and the proposed methodology yielded significant results. The proposed model was comprehensively trained and validated using the LIDC-IDRI dataset available in the public domain. The experimental results revealed that the Lung_PAYNet delivered remarkable segmentation with a Dice similarity coefficient of 95.7%, mIOU of 91.75%, sensitivity of 92.57%, and precision of 96.75%.https://doi.org/10.1038/s41598-022-24900-4 |
| spellingShingle | P. Malin Bruntha S. Immanuel Alex Pandian K. Martin Sagayam Shivargha Bandopadhyay Marc Pomplun Hien Dang Lung_PAYNet: a pyramidal attention based deep learning network for lung nodule segmentation Scientific Reports |
| title | Lung_PAYNet: a pyramidal attention based deep learning network for lung nodule segmentation |
| title_full | Lung_PAYNet: a pyramidal attention based deep learning network for lung nodule segmentation |
| title_fullStr | Lung_PAYNet: a pyramidal attention based deep learning network for lung nodule segmentation |
| title_full_unstemmed | Lung_PAYNet: a pyramidal attention based deep learning network for lung nodule segmentation |
| title_short | Lung_PAYNet: a pyramidal attention based deep learning network for lung nodule segmentation |
| title_sort | lung paynet a pyramidal attention based deep learning network for lung nodule segmentation |
| url | https://doi.org/10.1038/s41598-022-24900-4 |
| work_keys_str_mv | AT pmalinbruntha lungpaynetapyramidalattentionbaseddeeplearningnetworkforlungnodulesegmentation AT simmanuelalexpandian lungpaynetapyramidalattentionbaseddeeplearningnetworkforlungnodulesegmentation AT kmartinsagayam lungpaynetapyramidalattentionbaseddeeplearningnetworkforlungnodulesegmentation AT shivarghabandopadhyay lungpaynetapyramidalattentionbaseddeeplearningnetworkforlungnodulesegmentation AT marcpomplun lungpaynetapyramidalattentionbaseddeeplearningnetworkforlungnodulesegmentation AT hiendang lungpaynetapyramidalattentionbaseddeeplearningnetworkforlungnodulesegmentation |