A lung nodule segmentation model based on the transformer with multiple thresholds and coordinate attention
Abstract Accurate lung nodule segmentation is fundamental for the early detection of lung cancer. With the rapid development of deep learning, lung nodule segmentation models based on the encoder-decoder structure have become the mainstream research approach. However, during the encoding process, mo...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-12-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-024-82877-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559464896888832 |
|---|---|
| author | Tianjiao Hu Yihua Lan Yingqi Zhang Jiashu Xu Shuai Li Chih-Cheng Hung |
| author_facet | Tianjiao Hu Yihua Lan Yingqi Zhang Jiashu Xu Shuai Li Chih-Cheng Hung |
| author_sort | Tianjiao Hu |
| collection | DOAJ |
| description | Abstract Accurate lung nodule segmentation is fundamental for the early detection of lung cancer. With the rapid development of deep learning, lung nodule segmentation models based on the encoder-decoder structure have become the mainstream research approach. However, during the encoding process, most models have limitations in extracting edge and semantic information and in capturing long-range dependencies. To address these problems, we propose a new lung nodule segmentation model, abbreviated as MCAT-Net. In this model, we construct a multi-threshold feature separation module to capture edge and texture features from different levels and specified intensities of the input image. Secondly, we introduce the coordinate attention mechanism, which allows the model to better recognize and utilize spatial information when handling long-range dependencies, enabling the deep network to maintain its sensitivity to nodule positions. Thirdly, we use the transformer to fully capture the long-range dependencies, further enhancing the global information integration of the network. The proposed method was verified on the LIDC-IDRI and LNDb datasets. The Dice similarity coefficient (DSC) values achieved were 88.29% and 78.51%, and the sensitivities were 86.33% and 75.05%, respectively. The experimental results demonstrated its high practical value for the early diagnosis of lung cancer. |
| format | Article |
| id | doaj-art-c69ed6d751764ab0a1a38a02140ce29c |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-c69ed6d751764ab0a1a38a02140ce29c2025-01-05T12:29:50ZengNature PortfolioScientific Reports2045-23222024-12-0114111710.1038/s41598-024-82877-8A lung nodule segmentation model based on the transformer with multiple thresholds and coordinate attentionTianjiao Hu0Yihua Lan1Yingqi Zhang2Jiashu Xu3Shuai Li4Chih-Cheng Hung5School of Artificial Intelligence and Software Engineering, Nanyang Normal UniversitySchool of Artificial Intelligence and Software Engineering, Nanyang Normal UniversitySchool of Artificial Intelligence and Software Engineering, Nanyang Normal UniversitySchool of Artificial Intelligence and Software Engineering, Nanyang Normal UniversitySchool of Artificial Intelligence and Software Engineering, Nanyang Normal UniversityLaboratory for Machine Vision and Security Research, Kennesaw State University–Marietta CampusAbstract Accurate lung nodule segmentation is fundamental for the early detection of lung cancer. With the rapid development of deep learning, lung nodule segmentation models based on the encoder-decoder structure have become the mainstream research approach. However, during the encoding process, most models have limitations in extracting edge and semantic information and in capturing long-range dependencies. To address these problems, we propose a new lung nodule segmentation model, abbreviated as MCAT-Net. In this model, we construct a multi-threshold feature separation module to capture edge and texture features from different levels and specified intensities of the input image. Secondly, we introduce the coordinate attention mechanism, which allows the model to better recognize and utilize spatial information when handling long-range dependencies, enabling the deep network to maintain its sensitivity to nodule positions. Thirdly, we use the transformer to fully capture the long-range dependencies, further enhancing the global information integration of the network. The proposed method was verified on the LIDC-IDRI and LNDb datasets. The Dice similarity coefficient (DSC) values achieved were 88.29% and 78.51%, and the sensitivities were 86.33% and 75.05%, respectively. The experimental results demonstrated its high practical value for the early diagnosis of lung cancer.https://doi.org/10.1038/s41598-024-82877-8 |
| spellingShingle | Tianjiao Hu Yihua Lan Yingqi Zhang Jiashu Xu Shuai Li Chih-Cheng Hung A lung nodule segmentation model based on the transformer with multiple thresholds and coordinate attention Scientific Reports |
| title | A lung nodule segmentation model based on the transformer with multiple thresholds and coordinate attention |
| title_full | A lung nodule segmentation model based on the transformer with multiple thresholds and coordinate attention |
| title_fullStr | A lung nodule segmentation model based on the transformer with multiple thresholds and coordinate attention |
| title_full_unstemmed | A lung nodule segmentation model based on the transformer with multiple thresholds and coordinate attention |
| title_short | A lung nodule segmentation model based on the transformer with multiple thresholds and coordinate attention |
| title_sort | lung nodule segmentation model based on the transformer with multiple thresholds and coordinate attention |
| url | https://doi.org/10.1038/s41598-024-82877-8 |
| work_keys_str_mv | AT tianjiaohu alungnodulesegmentationmodelbasedonthetransformerwithmultiplethresholdsandcoordinateattention AT yihualan alungnodulesegmentationmodelbasedonthetransformerwithmultiplethresholdsandcoordinateattention AT yingqizhang alungnodulesegmentationmodelbasedonthetransformerwithmultiplethresholdsandcoordinateattention AT jiashuxu alungnodulesegmentationmodelbasedonthetransformerwithmultiplethresholdsandcoordinateattention AT shuaili alungnodulesegmentationmodelbasedonthetransformerwithmultiplethresholdsandcoordinateattention AT chihchenghung alungnodulesegmentationmodelbasedonthetransformerwithmultiplethresholdsandcoordinateattention AT tianjiaohu lungnodulesegmentationmodelbasedonthetransformerwithmultiplethresholdsandcoordinateattention AT yihualan lungnodulesegmentationmodelbasedonthetransformerwithmultiplethresholdsandcoordinateattention AT yingqizhang lungnodulesegmentationmodelbasedonthetransformerwithmultiplethresholdsandcoordinateattention AT jiashuxu lungnodulesegmentationmodelbasedonthetransformerwithmultiplethresholdsandcoordinateattention AT shuaili lungnodulesegmentationmodelbasedonthetransformerwithmultiplethresholdsandcoordinateattention AT chihchenghung lungnodulesegmentationmodelbasedonthetransformerwithmultiplethresholdsandcoordinateattention |