MSTD: A Multi-Scale Transformer-Based Method to Diagnose Benign and Malignant Lung Nodules
The identification of benign and malignant lung nodules is crucial for timely treatment to reduce the risk of the progression and metastasis of diseases. However, the varied sizes, diverse morphologies, non-fixed positions, and dynamic growth of lung nodules in computed tomography (CT) images make t...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10844082/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832583219913949184 |
|---|---|
| author | Xiaoyu Zhao Jiao Li Man Qi Xuxin Chen Wei Chen Yongqun Li Qi Liu Jiajia Tang Zhihai Han Chunyang Zhang |
| author_facet | Xiaoyu Zhao Jiao Li Man Qi Xuxin Chen Wei Chen Yongqun Li Qi Liu Jiajia Tang Zhihai Han Chunyang Zhang |
| author_sort | Xiaoyu Zhao |
| collection | DOAJ |
| description | The identification of benign and malignant lung nodules is crucial for timely treatment to reduce the risk of the progression and metastasis of diseases. However, the varied sizes, diverse morphologies, non-fixed positions, and dynamic growth of lung nodules in computed tomography (CT) images make their accurate identification challenging. To address these issues, we propose a multi-scale transformer-based diagnosis (MSTD) method for benign and malignant lung nodules. To handle significant variations in the shapes and sizes of the lung nodules, we first design a multi-scale module based on parallel branches to extract multi-scale features. To make full use of these features, we then introduce a multi-scale transformer fusion (MSTF) module to integrate the information obtained at different scales. Unlike conventional vision transformers, our MSTF can simultaneously extract attention-based features from the spatial dimensions at different scales to enhance the accuracy of classification of lung nodules. We conducted extensive ablation experiments on multi-scale structures and transformer-based methods of fusion to explore the impact of features obtained at different scales on the accuracy of classification of lung nodules. The results of verification on the LUNA16 dataset showed that the average F1Score, Specificity, and Sensitivity of the proposed MSTD exceeded 90% (94.5%, 96.5%, and 91.1%, respectively), where this shows that it can accurately identify both benign and malignant lung nodules. Its average performance was superior to the state-of-the-art method by about 1%, 3.4%, and 3.6% in terms of the area under the curve (AUC), Accuracy, and F1Score, respectively. |
| format | Article |
| id | doaj-art-43ba0d3fea8d4bffa00e50800d748775 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-43ba0d3fea8d4bffa00e50800d7487752025-01-29T00:01:14ZengIEEEIEEE Access2169-35362025-01-0113161821619510.1109/ACCESS.2025.353100110844082MSTD: A Multi-Scale Transformer-Based Method to Diagnose Benign and Malignant Lung NodulesXiaoyu Zhao0Jiao Li1Man Qi2Xuxin Chen3Wei Chen4Yongqun Li5Qi Liu6Jiajia Tang7Zhihai Han8Chunyang Zhang9https://orcid.org/0000-0002-4072-5511Department of Pulmonary and Critical Care Medicine, The Sixth Medical Center, Chinese PLA General Hospital, Beijing, ChinaDepartment of Pulmonary and Critical Care Medicine, The Sixth Medical Center, Chinese PLA General Hospital, Beijing, ChinaDepartment of Pulmonary and Critical Care Medicine, The Sixth Medical Center, Chinese PLA General Hospital, Beijing, ChinaDepartment of Pulmonary and Critical Care Medicine, The Sixth Medical Center, Chinese PLA General Hospital, Beijing, ChinaDepartment of Pulmonary and Critical Care Medicine, The Sixth Medical Center, Chinese PLA General Hospital, Beijing, ChinaDepartment of Pulmonary and Critical Care Medicine, The Sixth Medical Center, Chinese PLA General Hospital, Beijing, ChinaDepartment of Pulmonary and Critical Care Medicine, The Sixth Medical Center, Chinese PLA General Hospital, Beijing, ChinaDepartment of Pulmonary and Critical Care Medicine, The Sixth Medical Center, Chinese PLA General Hospital, Beijing, ChinaDepartment of Pulmonary and Critical Care Medicine, The Sixth Medical Center, Chinese PLA General Hospital, Beijing, ChinaDepartment of Pulmonary and Critical Care Medicine, The Sixth Medical Center, Chinese PLA General Hospital, Beijing, ChinaThe identification of benign and malignant lung nodules is crucial for timely treatment to reduce the risk of the progression and metastasis of diseases. However, the varied sizes, diverse morphologies, non-fixed positions, and dynamic growth of lung nodules in computed tomography (CT) images make their accurate identification challenging. To address these issues, we propose a multi-scale transformer-based diagnosis (MSTD) method for benign and malignant lung nodules. To handle significant variations in the shapes and sizes of the lung nodules, we first design a multi-scale module based on parallel branches to extract multi-scale features. To make full use of these features, we then introduce a multi-scale transformer fusion (MSTF) module to integrate the information obtained at different scales. Unlike conventional vision transformers, our MSTF can simultaneously extract attention-based features from the spatial dimensions at different scales to enhance the accuracy of classification of lung nodules. We conducted extensive ablation experiments on multi-scale structures and transformer-based methods of fusion to explore the impact of features obtained at different scales on the accuracy of classification of lung nodules. The results of verification on the LUNA16 dataset showed that the average F1Score, Specificity, and Sensitivity of the proposed MSTD exceeded 90% (94.5%, 96.5%, and 91.1%, respectively), where this shows that it can accurately identify both benign and malignant lung nodules. Its average performance was superior to the state-of-the-art method by about 1%, 3.4%, and 3.6% in terms of the area under the curve (AUC), Accuracy, and F1Score, respectively.https://ieeexplore.ieee.org/document/10844082/MSTDmulti-scale networkmulti-scale transformer fusionlung nodule diagnosis |
| spellingShingle | Xiaoyu Zhao Jiao Li Man Qi Xuxin Chen Wei Chen Yongqun Li Qi Liu Jiajia Tang Zhihai Han Chunyang Zhang MSTD: A Multi-Scale Transformer-Based Method to Diagnose Benign and Malignant Lung Nodules IEEE Access MSTD multi-scale network multi-scale transformer fusion lung nodule diagnosis |
| title | MSTD: A Multi-Scale Transformer-Based Method to Diagnose Benign and Malignant Lung Nodules |
| title_full | MSTD: A Multi-Scale Transformer-Based Method to Diagnose Benign and Malignant Lung Nodules |
| title_fullStr | MSTD: A Multi-Scale Transformer-Based Method to Diagnose Benign and Malignant Lung Nodules |
| title_full_unstemmed | MSTD: A Multi-Scale Transformer-Based Method to Diagnose Benign and Malignant Lung Nodules |
| title_short | MSTD: A Multi-Scale Transformer-Based Method to Diagnose Benign and Malignant Lung Nodules |
| title_sort | mstd a multi scale transformer based method to diagnose benign and malignant lung nodules |
| topic | MSTD multi-scale network multi-scale transformer fusion lung nodule diagnosis |
| url | https://ieeexplore.ieee.org/document/10844082/ |
| work_keys_str_mv | AT xiaoyuzhao mstdamultiscaletransformerbasedmethodtodiagnosebenignandmalignantlungnodules AT jiaoli mstdamultiscaletransformerbasedmethodtodiagnosebenignandmalignantlungnodules AT manqi mstdamultiscaletransformerbasedmethodtodiagnosebenignandmalignantlungnodules AT xuxinchen mstdamultiscaletransformerbasedmethodtodiagnosebenignandmalignantlungnodules AT weichen mstdamultiscaletransformerbasedmethodtodiagnosebenignandmalignantlungnodules AT yongqunli mstdamultiscaletransformerbasedmethodtodiagnosebenignandmalignantlungnodules AT qiliu mstdamultiscaletransformerbasedmethodtodiagnosebenignandmalignantlungnodules AT jiajiatang mstdamultiscaletransformerbasedmethodtodiagnosebenignandmalignantlungnodules AT zhihaihan mstdamultiscaletransformerbasedmethodtodiagnosebenignandmalignantlungnodules AT chunyangzhang mstdamultiscaletransformerbasedmethodtodiagnosebenignandmalignantlungnodules |