Pulmonary diseases accurate recognition using adaptive multiscale feature fusion in chest radiography
Abstract Pulmonary disease can severely impair respiratory function and be life-threatening. Accurately recognizing pulmonary diseases in chest X-ray images is challenging due to overlapping body structures and the complex anatomy of the chest. We propose an adaptive multiscale feature fusion model...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-08-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-13479-1 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849342363731755008 |
|---|---|
| author | Mengran Zhou Lipeng Gao Kai Bian Haonan Wang Ning Wang Yue Chen Siyi Liu |
| author_facet | Mengran Zhou Lipeng Gao Kai Bian Haonan Wang Ning Wang Yue Chen Siyi Liu |
| author_sort | Mengran Zhou |
| collection | DOAJ |
| description | Abstract Pulmonary disease can severely impair respiratory function and be life-threatening. Accurately recognizing pulmonary diseases in chest X-ray images is challenging due to overlapping body structures and the complex anatomy of the chest. We propose an adaptive multiscale feature fusion model for recognizing Chest X-ray images of pneumonia, tuberculosis, and COVID-19, which are common pulmonary diseases. We introduce an Adaptive Multiscale Fusion Network (AMFNet) for pulmonary disease classification in chest X-ray images. AMFNet consists of a lightweight Multiscale Fusion Network (MFNet) and ResNet50 as the secondary feature extraction network. MFNet employs Fusion Blocks with self-calibrated convolution (SCConv) and Attention Feature Fusion (AFF) to capture multiscale semantic features, and integrates a custom activation function, MFReLU, which is employed to reduce the model’s memory access time. A fusion module adaptively combines features from both networks. Experimental results show that AMFNet achieves 97.48% accuracy and an F1 score of 0.9781 on public datasets, outperforming models like ResNet50, DenseNet121, ConvNeXt-Tiny, and Vision Transformer while using fewer parameters. |
| format | Article |
| id | doaj-art-27915b7e4a234a6b95196502be752d48 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-27915b7e4a234a6b95196502be752d482025-08-20T03:43:26ZengNature PortfolioScientific Reports2045-23222025-08-0115112210.1038/s41598-025-13479-1Pulmonary diseases accurate recognition using adaptive multiscale feature fusion in chest radiographyMengran Zhou0Lipeng Gao1Kai Bian2Haonan Wang3Ning Wang4Yue Chen5Siyi Liu6School of Electrical and Information Engineering, Anhui University of Science and TechnologySchool of Electrical and Information Engineering, Anhui University of Science and TechnologySchool of Electrical and Information Engineering, Anhui University of Science and TechnologySchool of Electrical and Information Engineering, Anhui University of Science and TechnologySchool of Mechanics and Optoelectronic Physics, Anhui University of Science and TechnologySchool of Electrical and Information Engineering, Anhui University of Science and TechnologySchool of Electrical and Information Engineering, Anhui University of Science and TechnologyAbstract Pulmonary disease can severely impair respiratory function and be life-threatening. Accurately recognizing pulmonary diseases in chest X-ray images is challenging due to overlapping body structures and the complex anatomy of the chest. We propose an adaptive multiscale feature fusion model for recognizing Chest X-ray images of pneumonia, tuberculosis, and COVID-19, which are common pulmonary diseases. We introduce an Adaptive Multiscale Fusion Network (AMFNet) for pulmonary disease classification in chest X-ray images. AMFNet consists of a lightweight Multiscale Fusion Network (MFNet) and ResNet50 as the secondary feature extraction network. MFNet employs Fusion Blocks with self-calibrated convolution (SCConv) and Attention Feature Fusion (AFF) to capture multiscale semantic features, and integrates a custom activation function, MFReLU, which is employed to reduce the model’s memory access time. A fusion module adaptively combines features from both networks. Experimental results show that AMFNet achieves 97.48% accuracy and an F1 score of 0.9781 on public datasets, outperforming models like ResNet50, DenseNet121, ConvNeXt-Tiny, and Vision Transformer while using fewer parameters.https://doi.org/10.1038/s41598-025-13479-1Pulmonary diseasesComputer aided diagnosisDeep learningFeature fusion |
| spellingShingle | Mengran Zhou Lipeng Gao Kai Bian Haonan Wang Ning Wang Yue Chen Siyi Liu Pulmonary diseases accurate recognition using adaptive multiscale feature fusion in chest radiography Scientific Reports Pulmonary diseases Computer aided diagnosis Deep learning Feature fusion |
| title | Pulmonary diseases accurate recognition using adaptive multiscale feature fusion in chest radiography |
| title_full | Pulmonary diseases accurate recognition using adaptive multiscale feature fusion in chest radiography |
| title_fullStr | Pulmonary diseases accurate recognition using adaptive multiscale feature fusion in chest radiography |
| title_full_unstemmed | Pulmonary diseases accurate recognition using adaptive multiscale feature fusion in chest radiography |
| title_short | Pulmonary diseases accurate recognition using adaptive multiscale feature fusion in chest radiography |
| title_sort | pulmonary diseases accurate recognition using adaptive multiscale feature fusion in chest radiography |
| topic | Pulmonary diseases Computer aided diagnosis Deep learning Feature fusion |
| url | https://doi.org/10.1038/s41598-025-13479-1 |
| work_keys_str_mv | AT mengranzhou pulmonarydiseasesaccuraterecognitionusingadaptivemultiscalefeaturefusioninchestradiography AT lipenggao pulmonarydiseasesaccuraterecognitionusingadaptivemultiscalefeaturefusioninchestradiography AT kaibian pulmonarydiseasesaccuraterecognitionusingadaptivemultiscalefeaturefusioninchestradiography AT haonanwang pulmonarydiseasesaccuraterecognitionusingadaptivemultiscalefeaturefusioninchestradiography AT ningwang pulmonarydiseasesaccuraterecognitionusingadaptivemultiscalefeaturefusioninchestradiography AT yuechen pulmonarydiseasesaccuraterecognitionusingadaptivemultiscalefeaturefusioninchestradiography AT siyiliu pulmonarydiseasesaccuraterecognitionusingadaptivemultiscalefeaturefusioninchestradiography |